USRE37610E1 - Running guide apparatus for vehicle capable of keeping safety at passing through narrow path and the method thereof - Google Patents

Running guide apparatus for vehicle capable of keeping safety at passing through narrow path and the method thereof Download PDF

Info

Publication number
USRE37610E1
USRE37610E1 US09/102,880 US10288098A USRE37610E US RE37610 E1 USRE37610 E1 US RE37610E1 US 10288098 A US10288098 A US 10288098A US RE37610 E USRE37610 E US RE37610E
Authority
US
United States
Prior art keywords
distance
data
object
vehicle
side wall
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Lifetime
Application number
US09/102,880
Inventor
Hideaki Tsuchiya
Keiji Hanawa
Keiji Saneyoshi
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Subaru Corp
Original Assignee
Subaru Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority to JP5-330191 priority Critical
Priority to JP33019193A priority patent/JP3522317B2/en
Priority to US08/364,104 priority patent/US5530420A/en
Application filed by Subaru Corp filed Critical Subaru Corp
Priority to US09/102,880 priority patent/USRE37610E1/en
Application granted granted Critical
Publication of USRE37610E1 publication Critical patent/USRE37610E1/en
Assigned to FUJI JUKOGYO KABUSHIKI KAISHA reassignment FUJI JUKOGYO KABUSHIKI KAISHA CHANGE OF ADDRESS Assignors: FUJI JUKOGYO KABUSHIKI KAISHA
Anticipated expiration legal-status Critical
Application status is Expired - Lifetime legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
    • G06K9/00791Recognising scenes perceived from the perspective of a land vehicle, e.g. recognising lanes, obstacles or traffic signs on road scenes
    • G06K9/00805Detecting potential obstacles
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S11/00Systems for determining distance or velocity not using reflection or reradiation
    • G01S11/12Systems for determining distance or velocity not using reflection or reradiation using electromagnetic waves other than radio waves
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • G05D1/0251Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/50Depth or shape recovery
    • G06T7/55Depth or shape recovery from multiple images
    • G06T7/593Depth or shape recovery from multiple images from stereo images
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N13/20Image signal generators
    • H04N13/204Image signal generators using stereoscopic image cameras
    • H04N13/239Image signal generators using stereoscopic image cameras using two 2D image sensors having a relative position equal to or related to the interocular distance
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D2201/00Application
    • G05D2201/02Control of position of land vehicles
    • G05D2201/0213Road vehicle, e.g. car or truck
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00Indexing scheme for image data processing or generation, in general
    • G06T2200/28Indexing scheme for image data processing or generation, in general involving image processing hardware
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10004Still image; Photographic image
    • G06T2207/10012Stereo images
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30248Vehicle exterior or interior
    • G06T2207/30252Vehicle exterior; Vicinity of vehicle
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N13/10Processing, recording or transmission of stereoscopic or multi-view image signals
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N13/10Processing, recording or transmission of stereoscopic or multi-view image signals
    • H04N13/106Processing image signals
    • H04N13/167Synchronising or controlling image signals
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N13/10Processing, recording or transmission of stereoscopic or multi-view image signals
    • H04N13/189Recording image signals; Reproducing recorded image signals
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N2013/0074Stereoscopic image analysis
    • H04N2013/0081Depth or disparity estimation from stereoscopic image signals
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N2013/0074Stereoscopic image analysis
    • H04N2013/0092Image segmentation from stereoscopic image signals
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N2013/0074Stereoscopic image analysis
    • H04N2013/0096Synchronisation or controlling aspects

Abstract

A running guide apparatus for a vehicle includes stereoscopic picture processing element for processing a pair of stereoscopic pictures of an object outside a vehicle imaged by a imaging system mounted on the vehicle, construction detection element for detecting a plurality of various constructions by using three dimensional position data calculated with each portion of the object corresponding to the distance distribution data from the stereoscopic picture processing element; gap distance calculation element for respectively calculating the nearest distance as right and left gap distances each between an extended line of right or left side of the vehicle and each of ends on the vehicle side of the plurality of various constructions detected by the construction detection element; and information element for informing the driver of data related to the right and left gap data calculated by the gap distance calculation element; so as to obtain a distance distribution of an entire picture in dependency upon a discrepancy amount positions corresponding to of the pair of the stereoscopic pictures in accordance with a principle of a triangulation.

Description

BACKGROUND OF THE INVENTION

The present invention relates to a running guide apparatus for a vehicle capable of keeping a safety at passing through a narrow path, and of decreasing a burden of a driver when the vehicle is passing through the narrow path.

A vehicle such as an automobile conventionally has a sensor in which a touch switch is turned on when a corner pole or bar-shaped member touches an obstacle such as a wall, guardrail, pole and parked vehicle, as disclosed in an official gazette of Japanese Utility Model Laid-open No. 5-68742 (1993), in order to compensate a sense of a driver, thereby recognizing a gap between the vehicle and obstacles existing in right and left side of the vehicle.

Recently, a technology is developed for decreasing the burden of the driver when the vehicle passes through the narrow path in the manner that an ultrasonic sensor arranged on a side surface or four corners of the vehicle irradiates an ultrasonic wave, receives a reflected wave from the obstacle, and measures a distance of the gap, thereby informing the driver of the measured distance.

However, since the driver needs a lot of skill to operate the vehicle with the above-mentioned corner pole attached on an outside of the body of the vehicle as a sign, it is impossible to obtain an effect to decrease the burden of the driver. In a contact type such as a feeler sensor, the driver can not operate a steering wheel sufficiently after touching the obstacle because he can not recognize the position before touching the object.

Furthermore, a supersonic technology can not teach the driver a positional relationship of the obstacle because of a deterioration of a spatial resolving power, and has an object dependence in which a radiated ultrasonic does not return from clothes of walkers and slippery walls. Accordingly, it is quite difficult to correspond to various structures existing on a road.

SUMMARY OF THE INVENTION

In view of the above-mentioned condition, an object of the present invention is to provide to a running guide apparatus for a vehicle capable of keeping a safety at passing through a narrow path and decreasing a burden of a driver by informing the driver of a gap between the detected structure and own vehicle body in dependency upon a proper detection of various constructions existing in the advancing direction of the vehicle before the vehicle is passing through the narrow path.

The running guide apparatus according to the present invention comprises stereoscopic picture processing means for processing a pair of stereoscopic pictures of an object outside a vehicle imaged by a imaging system mounted on the vehicle so as to obtain a distance distribution of an entire picture in dependency upon a discrepancy amount positions corresponding to the pair of the stereoscopic pictures in accordance with a principle of a triangulation;

construction detection means for detecting a plurality of various constructions by using three dimensional position data calculated with each portion of the object corresponding to the distance distribution data from the stereoscopic picture processing means, gap distance calculation means for respectively calculating the nearest distance as right and left gap distances each between an extended line of right or left side of the vehicle and each of ends on the vehicle side of the plurality of various constructions detected by the construction detection means, and information means for informing the driver of data related to the right and left gap data calculated by the gap distance calculation means.

In the present invention, after the distance distribution data in the entire picture are obtained by the principle of the triangulation in dependency upon the discrepancy amount of the positions corresponding to the pair of the stereoscopic pictures which are stereoscopically imaged from the objects around the vehicle, the three-dimensional positions of respective portions corresponding to the distance distribution data, thereby detecting the construction by using the three-dimensional position data. The calculation means respectively calculates the nearest distance as the right and left gap distances between an extended line of right or left side of the vehicle and each of ends on the vehicle side of the plurality of various constructions which has been previously detected, in order to inform the driver of the right and left gap distance data.

As described above, the present invention obtains the distance distribution in the entire pictures in dependency on the discrepancy amount between the positions corresponding to the pair of the stereoscopic pictures imaging the objects around the vehicle, calculates the three-dimensional position of each portion of the object corresponding to the distance distribution data, and detects a plurality of the constructions by using the calculated three-dimensional position data. The apparatus of the present invention further calculates as the right and left gap distances of the nearest distance between the ends on the vehicle side of the detected plurality of the objects and the extended line of the sides of the vehicle, respectively, and informs the driver of the calculated right and left gap distance data. Accordingly, it is possible to properly inform the driver of the gap distance between own vehicle body and the various constructions existing in the advancing direction before the vehicle passes through the narrow path after precisely detecting, thereby obtaining extremely excellent effects such as a decrease of the burden of the driver and an insurance against the risk.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a view of entire constitution of a running guide apparatus;

FIG. 2 is a circuit block diagram showing the running guide apparatus;

FIG. 3 is an explanatory view showing a screen of a display;

FIG. 4 is a front view showing a vehicle;

FIG. 5 is an explanatory view showing a relationship between a camera and an object;

FIG. 6 is a detailed circuit diagram showing an image processor;

FIG. 7 is an explanatory view showing a city block distance calculation circuit;

FIG. 8 is a block diagram showing a minimum value detection circuit;

FIG. 9 is an explanatory view showing an example of a picture imaged by a CCD camera mounted on the vehicle;

FIG. 10 is an explanatory view showing an example of a distance picture;

FIG. 11 is a plan view of the vehicle;

FIG. 12 is a side view of the vehicle;

FIG. 13 is a function block diagram of a distance picture processing computer;

FIG. 14 is an explanatory view showing a classification method of a picture;

FIG. 15 is an explanatory view showing a relationship between a detected object and a histogram;

FIG. 16 is an explanatory view showing examples of a detected distance and a detected result of a region in which an object exists;

FIG. 17 is an explanatory view showing a shape of a three-dimensional window for detecting the object;

FIG. 18 is an explanatory view showing a shape of a two-dimensional window for detecting the object;

FIG. 19 is an explanatory view showing an example of data constituting a contour of the object;

FIG. 20 is an explanatory view showing an example of an external form size detected as a contour picture;

FIG. 21 an explanatory view showing a shape of a search region at detecting a side wall;

FIG. 22 is an explanatory view showing a side wall search region on a picture;

FIG. 23 is an explanatory view showing a distribution condition of construction data;

FIG. 24 is an explanatory view showing an idea of a straight line in Hough transformation;

FIG. 25 is an explanatory view showing a voting region of a parameter space;

FIG. 26 is an explanatory view showing a side wall candidate region;

FIG. 27 is an explanatory view showing a relationship between a histogram and a region in which a side wall existed;

FIG. 28 is an explanatory view showing a detected result of the side wall;

FIG. 29 is an explanatory view of a gap distance calculation;

FIG. 30 is a flow chart showing operation of an image processor;

FIG. 31 is an explanatory view showing a storing order in a shift register;

FIG. 32 is a timing chart showing operation of a city block distance calculation circuit;

FIG. 33 is a timing chart showing operation of a miss amount determiner;

FIG. 34 is a timing chart showing entire operation of the image processor;

FIGS. 35 and 36 are flow charts of object detection processing, respectively;

FIGS. 37 and 38 are flow charts of side wall detection processing, respectively; and

FIG. 39 is a flow chart of gap distance calculation processing.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

There will be described in detail a running guide apparatus for a vehicle according to preferred embodiments of the present invention in reference with the attached drawings.

In FIG. 1, numeral 1 denotes a vehicle such as an automobile, and the vehicle 1 has a running guide apparatus 2 having a function of an active drive assist (ADA) system to perform a high class assist control for a driver, thereby ensuring a risk by decreasing a burden of the driver when the vehicle passes through a narrow path in which wall, guardrails, electric (telephone) poles and parking cars exist.

The running guide apparatus 2 comprises a stereoscopic optical system 10 having a pair of cameras in right and left positions as an imaging system for imaging objects around the vehicle, stereoscopic picture processing means 15 for calculating a three-dimensional distance distribution in the entire picture by processing a pair of pictures imaged by the right and left cameras of the stereoscopic optical system 10, construction detection means 100 for detecting at a high speed a three-dimensional position of the continuous construction as a boundary of the road such as the wall and the guardrail and objects on the road such as .other vehicles, walkers and buildings in dependency on the distance distribution data supplied from the stereoscopic picture processing means 15, gap distance calculation means 110 for calculating as a gap distance a nearest distance in right and left sides of the vehicle between an extended line of the sides of the vehicle body and ends of the wall or construction detected by the construction detection means, and information means 115 for informing the driver of the gap distance data calculated by the gap distance calculation means 110 with respect to the right and left sides of the vehicle.

FIG. 2 is a circuit block diagram showing a hardware structure of the running guide apparatus 2. The stereoscopic optical system 10 uses CCD cameras including a charge coupled device (CCD) or the like, and comprises a pair of CCD cameras 11a and 11b on right and left sides for a short distance and a pair of CCD cameras 12a and 12b on right and left sides for a long distance. The stereoscopic optical system 10 is connected with the image processor 20 for realizing a function as the stereoscopic picture processing means 15.

Furthermore, the image processor 20 is connected with a distance picture processing computer 120 for realizing a function as the construction detection means 100 and the gap distance calculation means 110. The distance picture processing computer 120 is also connected with a display 3 as the information means 115.

The image processor 20 comprises a distance detection circuit 20a and a distance picture memory 20b. The distance detection circuit 20a searches portions imaging the same object in each fine regions against the pair of two stereoscopic pictures imaged by the stereoscopic optical system 10, and calculates a distance to the object in dependency on a discrepancy amount of positions corresponding to the portions searched. The distance picture memory 20b stores distance data which is an output of the distance detection circuit 20a.

The distance picture processing computer 120 comprises a multi-microprocessor system constitution in which a microprocessor 120a, microprocessor 120b and a microprocessor 120c are interconnected one another through a system bus 121. The microprocessor 120a mainly performs a processing of detecting respective object, the microprocessor 120b mainly performs a processing of detecting a side wall, and the microprocessor 120c mainly performs a processing of calculating a gap distance.

The system bus 121 is connected with an interface circuit 122 connected to the distance picture memory 20b, a read only memory (ROM) 123 storing a control program, a random access memory (RAM) 124 storing various parameters during calculation processing, an output memory 125 for storing parameters as processed results, a display controller (DISP. CONT.) 126 for controlling the display (DISP.) 3, and an interface circuit 127 for inputting signals from sensors and switches such as a vehicle speed sensor 4, a steering angle sensor 5 for detecting a steering angle, and a mode setting switch 6 for selecting a supporting mode of the ADA for the driver, which are mounted on the vehicle.

The distance picture processing computer 120 has divided memory regions respectively used by the microprocessors 120a, 120b and 120c, and parallel executes a object detection processing and side wall detection processing in dependency on the distance data from the image processor 20. The computer 120 displays a picture on the display 3 after a gap distance calculation processing in dependency on the detected object data when a standard signal inputs by a manipulation of the mode setting switch 6 by the driver.

As shown in FIG. 3, a monitor portion 3a is provided at the central portion in a screen of the display 3 in order to display a prospect (scene) in front of the vehicle by a condition of the distance picture mentioned below. A mode display portion 3b is provided on the side of the monitor portion 3a in order to display each mode (cruise, guide, assist and check) of the ADA, thereby lighting a relevant display of the monitor portion 3a corresponding to an operation input of the mode setting switch 6.

Furthermore, a data display portion 3c and a position display portion 3d displaying front, rear, right and left of the vehicle by the quadrisected oval shape are provided over the monitor portion 3a, and a mode data display portion 3e is provided under the monitor portion 3a in order to display characters of the distance between vehicles, speed, left gap distance and right gap distance with numerical values of a calculation.

In this invention, the driver selects the guide mode by operating the mode setting switch 6 when the vehicle should pass through the narrow path where a plurality of various obstacles exist. As a result, the display portion of “guide” in the mode display portion 3b is turned on, and at the same time the computer 120 calculates each distance on right and left sides between extending lines of the right and left sides of the body and ends of the obstacles around the vehicle on the road in dependency on the distance picture after processing a pair of the stereoscopic pictures imaged by the stereoscopic optical system 10.

As shown in FIG. 3, the numerical value of the gap distance is displayed under the characters of the right and left gap distances in the mode data display portion 3e, and the right and left portions of the position display portion 3d are turned on. The position display portion 3d is turned of and displayed by red on the corresponding side to alarm to contact wit the obstacle if going straight when the calculated gap distance is on or less than 0(zero). The position display portion 3d is turned on and displayed by yellow because of the danger to contact by carelessly handling the wheel by the driver when the gap distance is more than 0(zero) and on or less than 20 cm. The position display portion 3d is turned on and displayed by green to represent that the danger is sufficiently small if going straight when the gap distance is more than 20 cm.

Accordingly, the driver can make sure on the screen of the on the display that the vehicle safely passes through the narrow path by manipulating the mode setting switch 6 before passing through the narrow path where the side wall, the electric (telephone) pole and the parking car exist, thereby previously avoiding a contact accident by decreasing a burden of the driver. Furthermore, since the driver can grasp the gap distance quantitatively, it is possible for the driver to easily learn the vehicle position and to plan an advancement of a safe driving.

As a simplified construction, an indicator such as a bar graph may be provided in place of the display 3 for charging a light portion corresponding to the gap distance. Furthermore, a tone and a voice may be adopted as the information means 115 for informing the gap distance data to the driver, in place of the visual display.

There will be described an image processing function by the image processor 20, a construction detection function by the distance picture processing computer 120, and a gap distance calculation function when the guide mode is selected by the mode setting switch 6. The gap distance calculation by the picture processing computer 120 is executed only when the detected constructions do not block the way to the advancing direction as an obstacle.

A pair of cameras in the right and left sides constituting the stereoscopic optical system 10, as shown in FIG. 4, comprise two CCD cameras 11a and 11b (denoted by a CCD camera 11 as representation) and two CCD cameras 12a and 12b (denoted by a CCD camera 12 as representation). The CCD cameras 11a and 11b are arranged at the front portion on the ceiling in the room with a predetermined distance for imaging an obstacle in a short distance, and the CCD cameras 12a and 12b are also arranged at outer portions with each distance from the CCD cameras 11a and 11b for imaging an obstacle in a long distance, respectively.

In order to measure a distance from the nearest position to a position within 100 meters by the stereoscopic optical system 10, it is sufficient to measure positions from 2 to 100 meters front when the CCD cameras 11 and 12 in the room are 2 meters from a front end of the hood.

Accordingly, if the short distance CCD cameras 11a and 11b measure the positions within 2-20 meters and the long distance CCD cameras 12a and 12b measure positions within 10-100 meters, the cameras 11 and 12 can measure entire range with a security of the reliability by keeping a overlapped area in 10-20 meters front.

The distance calculation method by the image processor 20 will be described below with respect to the short distance CCD camera 11 as an example. The distance calculation with the long distance CCD camera 12 is the same processing as the camera 11. In the running guide device 2 according to the present embodiment, the short distance CCD camera 11 is used to detect construction just in front of the vehicle.

Accordingly, an image of a point P is taken on a projection plane of f distant from focal points of respective cameras, in which the point P is distant from set surfaces of two cameras 11a and 11b with a distance D, an arranged distance is r between two short distance cameras 11a and 11b, as shown in FIG. 5, and each of focal points is f of two cameras 11a and 11b.

At this time, if a discrepancy amount is x, “r+x” is obtained as the distance between the position of the image on the right CCD camera 11b and the position of the image on the left CCD camera 11a, and the distance D to the point P can be obtained by the following equation (1) from the discrepancy amount x:

D=r·f/x   (1)

The discrepancy amount x between the right and left pictures can be also detected after discover of the coincidence portion of the features such as edges, lines and specific shapes. However, in order to avoid a deterioration of the data amount, respective distance distribution in each small region is obtained with the entire screen by the image processor 20, in which the picture is divided into a plurality of small regions when finding the same object in the right and left pictures, and corresponding small regions in the right and left pictures are found out by comparing a pattern of luminance and color within the small regions.

An estimation of the coincidence of the right and left pictures, namely a stereoscopic matching, can be performed by a city block distance H represented by the following equation (2), for example, when the luminance (color can be used) in the i-th pixel in the right and left pictures are respectively Ai and Bi:

H=Σ|Ai−Bi|  (2)

The stereoscopic matching by the city block distance H has no deterioration of the data amount caused by the subtraction of a mean value, and can improve a calculation speed because of no multiplication. However, the matching method has a problem that the detected distance is uncertain because it is possible to grasp objects of longer distance and shorter distance in the same region when the size of the small region to be divided is too big. Accordingly, even though it is desired that the region is small to obtain the distance distribution of the picture, the data amount is insufficient to investigate the coincidence when the small region is too small. Therefore, when the apparatus of the present invention obtains an image with respect to the vehicle which is away 100 meters from the vehicle thereof in the manner of not including in the same region of a vehicle running in the adjacent lane, the obtained small regions are four pixels against the stereoscopic optical system 10 if the four pixels are the maximum value in the width direction. As the result that the optimum pixel number is obtained in the actual picture in dependency on the maximum value, respective four pixels can be obtained in dimensions.

In the following description, the image is divided into small regions of 4×4 to investigate the coincidence between the right and left pictures, and the stereoscopic optical system 10 is represented by the CCD cameras 11a and 11b.

A detailed circuit diagram of the image processor 20 is shown in FIG. 6. The circuit of the image processor 20 comprises the distance detection circuit 20a and the distance picture memory 20b. The distance detection circuit 20a comprises an picture converter 30 for converting an analog picture imaged by the stereoscopic optical system 10 into a digital picture, a city block distance calculator 40 for continuously calculating the city block distance H for determining the discrepancy amount x between the right and left pictures by means of shifting pixels one by one, a minimum and maximum values detector 50 for detecting the minimum value HMIN and maximum value HMAX of the city block distance H, and a discrepancy amount determiner 60 for determining the discrepancy amount x by checking whether the minimum value obtained by the minimum and maximum values detector 50 represents the coincidence between the right and left small regions or not. The distance picture memory 20b adopts a dual port memory 90.

The picture converter 30 comprises analog/digital (A/D) converter 31a and 31b respectively corresponding to the CCD cameras 11a and 11b for right and left pictures, and which are respectively connected with look up tables 32a and 32b as a data table, and picture memories 33a and 33b for each storing pictures respectively imaged by the CCD cameras 11a and 11b. Since the city block distance calculator 40, as mentioned later, repeatedly take out and process a part of the picture, the picture memories 33a and 33b can comprise a comparatively low speed memory, thereby decreasing a manufacturing cost.

Each of the A/D converters 31a and 31b has a resolving power of 8 bits, for example, and converts the analog picture from the right and left CCD cameras 11a and 11b into the digital picture having a predetermined luminance gradation. In other words, the converter converts the analog picture into a gray scale of 256 gradations, for example, because data are immediately lost for calculating the coincidence between the right and left pictures when a binary processing of the picture is performed for a high speed processing.

Furthermore, each of LUTs 32a and 32b is formed on the ROM to increase a contrast of a low luminance portion in the picture converted in the digital amount by the A/D converters 31a and 31b and to compensate the difference of characters between the right and left CCD cameras 11a and 11b. The signal converted by the LUTs 31a and 31b is once stored in the picture memories 33a and 33b, respectively.

In the city block distance calculator 40, a pair of input buffer memories 41a and 41b are connected through a common bus 80 to the picture memory 33a for the left picture in the picture converter 30, and a pair of input buffer memories 42a and 42b are connected through the common bus 80 to the picture memory 33b for the right picture.

A pair of the input buffer memories 41a and 41b for the left picture are connected to a pair of shift registers 43a and 43b each having a eight steps constitution, and a per of the input buffer memories 42a and 42b for the right picture are connected to a pair of shift registers 44a and 44b each having an eight step constitution. Two pairs of the shift registers 43a, 43b, 44a and 44b are connected with a city block distance calculation circuit 45 for calculating a city block distance.

Furthermore, the shift registers 44a and 44b for the right picture are a pair of shift registers 64a and 64b each having a ten step constitution and arranged in a discrepancy amount determiner 60 mentioned later. Old data after a calculation of the city block distance H are transferred to the shift registers 64a and 64b to be used for determining the discrepancy amount x when the data transfer starts with respect to the next small region.

The city block distance calculation circuit 45 is coupled with a high speed CMOS calculator 46 in which adders, subtracters and coupled input/output latches are formed in one chip, and instantaneously inputs and calculates the eight pixel components, for example, by a pipe line structure in which sixteen calculators 46 are connected with one another in a pyramid shape, as shown in FIG. 7. The pyramid structure has a first stage as an absolute value calculator, two through four stages as first, second and third adders, and a final stage as a total sum adder. FIG. 7 shows only a half structure of the absolute value calculator and the adders at first and second stages.

The input buffer memories 41a, 41b, 42a and 42b respectively have a comparatively small capacitance and a high speed type corresponding to a speed of the city block distance calculation, and each have a divided input and output for commonly receiving an address generated by a #1 address controller 86 according to a clock supplied from a clock generation circuit 85. A #2 address controller 87 controls a transfer of data between two pair of shift registers 43a, 43b, 44a and 44b.

The minimum and maximum values detector 50 comprises a minimum value detection circuit 51 for detecting a minimum value HMIN of the city block distance H and a maximum value detection circuit 52 for detecting a maximum value HMAX of the city block distance H, and has a constitution of two high speed CMOS calculators for respectively detecting the minimum and maximum values as the same as the city block distance calculation circuit 45 so as to maintain a synchronization with an output of the city block distance H.

As shown in FIG. 8, the minimum value detection circuit 51 comprises in detail a calculator 46 having an A register 46a, a B register 46b and an arithmetic logic unit (ALU) 46c, and a C latch 53, a latch 54 and a D latch which are connected with the calculator 46. An output of the city block distance calculation circuit 45 is supplied to the A register 46a and B register 46b through C latch 53 and the most significant bit (MSB) in the output of the ALU 46 is outputted to the latch 54. An output of the latch 54 is supplied to the B register 46b and D latch 55. The B register 46b stores an intermediate value of the minimum value calculation in the calculator 46. The D latch 55 stores the discrepancy amount δ in the minimum value calculation. The maximum value detection circuit 52 has the same constitution as the minimum value detection circuit 51 except an opposite logic and non-storage of the discrepancy amount δ.

As previously described, the city block distance H is calculated step by step with shifting pixels one by one of the left picture small region against one right picture small region. Accordingly, the maximum and minimum values HMAX and HMIN of the city block distance H in the small region can be obtained by a comparison and renewal of the previous maximum and minimum values HMAX and HMIN at each output of a value of the city block distance H, and at the same time, an output of the last city block distance H is obtained.

The discrepancy amount determiner 60 is constituted as a RISK processor having a comparatively small size. The determiner 60 comprises a calculator 61 as a main portion, 16 bit width data bus 62a and 62b, a latch 63a for holding the discrepancy amount x, a latch 63b for holding a threshold value HA as the first reference value, a latch 63c for holding a threshold value HB as a second reference value, a latch 63d for holding a threshold value HC as a third reference value, a switch circuit 65 for outputting the discrepancy amount x or an output of “0” after receiving an output of the calculator 61, output buffer memories 66a and 66b for temporarily storing an output of the switch circuit 65, and a ROM 67 of the sixteen bits width for storing a control program about an operation timing of the circuit and a function of the calculator 61.

The calculator 61 comprises an ALU 70 as a main portion, an A register 71, a B register 72, an F register 73 and a selector 74. The A register 71 is connected with the data bus 62a (called hereafter as an A bus 62a), and the. B register 72 is connected with the data bus 62b (called hereafter as an B bus 62b), thereby activating the switch 65 in dependency on the calculated result of the ALU 70, and storing the discrepancy amount x or the output “0” in the output buffer memories 66a and 66b.

The A bus 62a is connected with the maximum value detection circuit 52, the latches 63b, 63c and 63d holding each of the threshold value HA, HB and HC, and the B bus 62b is connected with the minimum value detection circuit 51. The A bus 62a and the B bus 62b are connected with the shift registers 64a and 64b, respectively.

The switch circuit 65 is connected with the calculator 61 and the minimum value detection circuit 51 through the latch 63a. The calculator 61 determines three checking conditions mentioned later to output a determined result to change the outputs to the output buffer memories 66a and 66b.

The discrepancy amount determiner 60 checks whether the obtained minimum value HMIN of the city block distance really represents the coincidence between the right and left small regions or not. The determiner 60 outputs the discrepancy amount x of the pixels corresponding to the buffer memories 66a and 66b only when the condition is satisfied.

Accordingly, the discrepancy amount is the discrepancy amount x to be obtained when the city block distance H is the minimum value HMIN. The discrepancy amount x is outputted when three checking conditions below are satisfied, and the “0” is outputted without adopting the data when the conditions are not satisfied:

(1) HMIN≦HA (The distance can not be obtained when HMIN>HA.)

(2) HMAX−HMIN≧HB (this is a condition for checking that the obtained minimum value HMIN clearly becomes low by flickering of noises, and the checking object is the difference between the minimum value HMIN and the maximum value HMAX without the difference between the minimum value HMIN and the nearest value thereof, thereby detecting the distance against an object such as a curved surface and the like slowly changing a luminance.)

(3) the luminance difference between adjacent pixels in the horizontal direction in the small region of the right picture>HC (even though the detection becomes an edge detection when the threshold value HC becomes large, the threshold value HC is set to be lower than the usual edge detection level because it is possible to correspond to the case where the luminance slowly changes. The condition is based on the fundamental principle in which the distance can not be detected in a portion without the luminance change. Since the detection in the portion is performed with each pixel in the small region, there is adopted only pixel of which the actual distance is detected in the small region, thereby obtaining a natural result.)

The distance distribution data, which are as the final result outputted from the discrepancy amount determiner 60, are written in a dual port memory 90 as a distance picture memory 20b through a common bus 80.

The distance distribution data from the image processor 20 have such a form as the picture (a distance picture), for example, the picture imaged by the CCD camera 11 as shown in FIG. 9. The picture for imaging the constitution such as parking cars 200 and 300 and guardrail 400 (showing the picture imaged by the one camera in FIG. 9) is processed by the image processor 20 to generate the image shown in FIG. 10.

In an example of the distance picture shown in FIG. 10, the picture has a size 400 by 200 pixels in dimensions, distance data are in a black portion in which a brightness change between two adjacent pixels in right and left direction is larger within respective pixels in the picture shown in FIG. 9. The coordinate axes on the picture is that the horizontal direction is an i coordinate axis at an original point in upper left corner, a vertical direction is a j coordinate axis, and a unit is pixels, as shown in FIG. 10.

The distance picture is read in the distance picture processing computer 120 to detect a plurality of objects such as other cars and obstacles existing in front of the vehicle, so as to calculate a position and size of the objects, thereby extracting an outline image of the detected objects. Furthermore, it is possible to calculate a correlative speed thereof caused by a time lag of the position.

In this case, the distance picture processing computer 120 uses a three dimensional data of the object, and performs a distinction of the road and background in dependency on the height from the road surface and a distinction of the object and background in dependency on a distance value. Therefore, the distance picture processing computer 120 first changes the coordinate axes of the distance picture from the image processor 20 to the coordinate axes of the actual space around the vehicle 1, and calculates the position and size corresponding to the detected construction.

Accordingly, as shown in FIGS. 11 and 12, when the coordinate axes of the actual space is fixed to the coordinate axes of the vehicle 1, in which an X axis is a right side of the vehicle 1, a Y axis is over the vehicle 1, a Z axis is in front of the vehicle 1, an original point is a road surface at the center and immediately under two CCD cameras 11a (12a) and 11b (12b), an X-Z plane (Y=0) coincides with the road surface in the case that the road is flat, and the three dimensional position of the object can be obtained in accordance with the following equations (3) and (4) in dependency on the distance data (i, j, Z) in the picture by a kind of the coordinate conversion:

Y=CH−Z×PW×(j−JV)   (3)

X=r/2+Z×PW×(i−IV)   (4)

where,

CH: an attached height of the CCD camera 11 (12),

PW: a visual angle per one pixel,

JV, IV: a coordinate on the picture of an infinite far point in the direct front of the vehicle 1.

Furthermore, the equations (3) and (4) can be changed to the following equations (5) and (6) in order to calculate the position (i, j) on the picture in dependency on the three dimensional axes (X, Y, Z) of the actual space:

j=(CH−Y)/(Z×PW)+JV   (5)

i=(X−r/2)/(Z×PW)+IV   (6)

If the attached position of the CCD camera 11 is shown in the XYZ coordinate axes of the actual space, the right CCD camera 11b is X=0.20 (m), Y=1.24 (m), and Z=0.0 (m), and the left CCD camera is X=−0.20 (m), Y=1.24 (m), and Z=0.0 (m), for example.

FIG. 13 shows a functional constitution of the distance picture processing computer 120 mainly comprising an object recognizer 130 for the microprocessor 120a, a side wall detector 140 for the microprocessor 120b, a gap distance calculator 160 for the microprocessor 120c. A processed result of the object recognizer 130 and side wall detector 140 is stored in a construction parameter storage portion 150 comprised of an output memory 125, and is read in other device (not shown) for the microprocessor 120c (the gap distance calculator 160) and ADA.

Furthermore, a function of the object recognizer 130 is divided into an object detector 131, a three dimensional window generator 132, and an object contour extractor 133. The object recognizer 131 divides the distance picture from the image processor 20 into a predetermined interval (for example, 8-20 pixel intervals) in the stripe shape, selects only constitution data having the danger as an obstacle for running, and calculates the detected distance.

FIG. 14 is an explanatory view for setting a stripe shape region of the bright picture imaged the front view from the vehicle 1. The distance picture shown in FIG. 10 is actually divided as shown in FIG. 14. In the embodiment, the picture is divided into thirty three small regions AR1-AR33 with twelve pixel intervals. Accordingly, since the object is searched by dividing the picture into a plurality of regions, it is possible to instantaneously detect a plurality of objects.

In the object in each region, the three dimensional position (X, Y, Z) of the actual space is calculated from the coordinate (i, j) on the picture and the distance data Z by using the above-mentioned equations (3) and (4), and the height H of the object at the distance Z from the road surface can be calculated by the following equation (7) when the height of the road surface is Yr:

H=Y−YR   (7)

Since the coordinate axes are set as shown in FIGS. 11 and 12, Yr can be set to Yr=0.0 (m) unless there are the specific inclination and a vertical shock on the vehicle 1. Since an object of the height H under 0.1 (m) such as a white line, stain or shadow on the road does not obstruct the vehicle running on the road, the data thereof is deserted. An object over the height of the vehicle is supposed to be a pedestrian overpass and a road sign, which is deserted, and the apparatus selects only data of the construction to be obstacles on the road. Therefore, if the object overlaps on the road on the two dimensional picture, the apparatus can detect after distinguishing data in accordance with the height over the road surface.

Next, with respect to the construction data extracted along the above-mentioned way, the apparatus counts a number of the data included predetermined section of the distance Z and makes a histogram using the distance Z as a horizontal axis. FIG. 15 is a histogram of the parking car 300 as the detected object in the right side in front of the vehicle in the picture example, and a number and length of the section of the distance Z are determined under the consideration of the detection limit and the precision of the distance Z and the shape of the construction as a detected object.

In the histogram, since an erroneously detected value exists in the distance data in the input distance picture, few data appear at a position in which an object does not exist actually. However, in the case where an object having a predetermined size exists, a frequency of the position shows a large value. On the other hand, in the case where no object exists, a frequency generated by the erroneous distance data becomes a small value.

Accordingly, if there is a section where a frequency of the generated histogram is more than the predetermined judge value and becomes the maximum value, the object exists in the judged section. To the contrary, when the maximum value of the frequency is less than the judge value, the object does not exist in the section. By this, even when the few noises are included in the picture data, a noise influence becomes within the minimum limit to detect the object.

When the object is judged to exist, a mean value of the distance data Z of the construction included in the detected section and sections before and after the detected section is calculated to treat as a distance to the object. After a distance detection ti the object is processed in entire regions, the apparatus investigates the detected distance of the object in each region, and judges that the object is the same when the difference of the detection distance to the object in the adjacent regions is less than the set value. To the contrary, when the difference is over the set value, the apparatus judges that the objects are different from each other.

In detail, a left end region AR1 is investigated. When the object is detected, this is set to the object S1 and to the distance Z1. Next, an adjacent right region AR2 is investigated. When the object is not detected, the object S1 exists within and around the region AR1 and the distance is judged to be Z1 so as to detect the object. When the detected distance is Z2, the difference between the distances Z1 and Z2 is investigated.

When the difference between the distances Z1 and Z2 is over the set value, the object detected in the region AR2 is determined to be different from the previously detected object S1, and to be new object S2 and new distance Z2. Then, the apparatus investigates further right adjacent region.

On the other hand, when the difference between the distances Z1 and Z2 is less than the set value, the object detected in the region AR2 is judged as the object S1 previously detected, and the distance is a mean value of Z1 and Z2. Then, further right regions will be investigated in the order, and the distance and existing regions are renewed when the object S1 is judged to continuously exist.

It has been conventionally difficult to extract only the object data when a background distance around the object is imaged on the two dimensional picture. However, since the above-mentioned processing is performed from the region AR1 of the left end to the region AR33 of the right end to sort the data by the distance values, it is possible to detect by dividing a plurality of the object and the background with respect to the distance and exist regions, thereby detecting a plurality of the objects overlapped one another on the two dimensional picture by dividing them in dependency on the distances of each object.

The set value is desired to be 4-6 meters at detecting the vehicle and to be 1-2 meters at detecting the walkers in dependency on an experimental result.

FIG. 16 shows by a block line an object existing region detected by the above processing. This embodiment detects two objects, namely, a vehicle 200 on the left side and a vehicle 300 on the right side. A numeral value shown at the bottom of the figure is a detection distance of each object.

The three dimension window generator 132 sets a three dimensional space region of a rectangular solid shape, namely, a three dimension window WD3 including the detected object (the parking car 300) in the three dimensional space shown in FIG. 17 with respect to each of the objects detected by the object detector 131, and calculates how to be shown the set three dimensional window WD3 on the two dimensional picture, so as to set the detection object with respect to only data within a window contour line as the two dimension window WD2.

The horizontal width of the three dimensional window WD3 is within an area extending each one region of the right and left sides of the object existing regions. Because the other objects are not detected when the right and left ends of the objects overlap on any regions. In this case, the object to be detected is not detected because the object can not become large value on the histogram and the other object is detected. Accordingly, the window area should be extended to avoid such the condition.

The length in the distance Z direction of the three dimensional window WD3 is within an area including the detected distance of the object and a section length of the histogram added with portions before and behind the detected distance. The lower end of the three dimensional window WD3 resides in the position of adding 0.1 meter with the height of the road surface, and the upper end coincides with the upper ends of each of the divided regions for detecting the object.

For the purpose of obtaining the two dimensional window WD2 in dependency on the three dimensional window WD3, the coordinate (in, jn) on the picture is first calculated by the above-mentioned equations (5) and (6) in dependency on each of the coordinate (Xn, Yn, Zn) of eight tops of the three dimensional window WD3, and a polygon enveloping eight tops is calculated. FIG. 18 shows an example in which the two dimensional window WD2 is set for one (the parked car 300) amongst the detected objects as has been shown in FIG. 16.

The object contour extractor 133 surveys one by one each of the data in the two dimensional window WD2, selects only data included in the three dimensional window WD3, extracts a contour image of the detected object, and detects a positional relationship between the detected object and vehicle own body.

Accordingly, the extractor 133 surveys one by one each of the data in the two dimensional window WD2 for each object, calculates the three dimensional position (X, Y, Z) by the above mentioned equations (3) and (4) with respect to pixels having the distance data, extracts only data which values of the distance and height are included in a range of the three dimensional window WD3, and deserts the other of data.

FIG. 19 shows the extracted data in the manner of projecting them on the two dimensional picture. Furthermore, a contour picture of the object is obtained by a connection of an outline of the data by lines as shown in FIG. 20. A coordinate (i, j) on the pictures on the right and left ends and the upper end of the contour picture is detected to calculate positions of the right and let ends and upper end in the three dimensional space by using the detection distance Z of the object and the above-mentioned equation (3) and (4). As a result, the width of the object can be obtained by the positions of the right and left ends, and the height of the object can be obtained from the upper end position. In FIG. 20, it is possible to judge the object having a width of 1.7 meters and a height of 1.3 meters.

On the other hand, a function of the side wall detector 140 by the microprocessor 120b is further divided into a construction data extractor 141, a side wall straight line detector 142, and a side wall area detector 143, in which a distinction of the side wall from the road is performed by the height from the road surface, and the distinction of the side wall from the distant background is performed by the distance before and after the vehicle and the adjacent distance. Accordingly, the detector 140 extracts only data around the side wall presumed to exist, and the extracted side wall data are detected by the Hough transformation in view of the characteristics arranged along the straight line in the horizontal direction to obtain the position of the construction.

Accordingly, the construction data extractor 141 extracts only the data over the predetermined road surface previously set from the distance distribution data, and the side wall straight line detector 142 extracts only the data within a side wall search region previously set, and the extracted data are processed by the Hough transformation, thereby detecting a linear equation showing presence or absence of the side wall and the position of the side wall. The side wall area detector 143 sets a side wall estimated region in which the side wall is estimated to exist on the basis of the straight line showing the position of the side wall, and detects the positions of before and after ends of the side wall in dependency on the distribution condition of the construction data in the side wall estimated region.

In detail, since the side wall is a portion of the construction, the construction data extractor 141 extracts the data of the construction over the road surface from the distance pictures. At this time, since the construction having the height under 0.1 meter is treated as the white line, stain and shadow on the road, such the data are deserted. Since the construction having a height over the vehicle roof is supposed as the pedestrian overpass and traffic sign, the data are also deserted. Accordingly, the extractor 141 selects only the data of the construction on the road.

Even though the construction data extractor 141 extracts the data of the construction with a wide area imaged in the screen, a limit is set for the side wall search area in the side wall straight line detector 142 because processing for the entire data in the wide area is not reasonable.

In this case, at overlooking an area in which the picture is measured, a visual field of the CCD camera 11 limits the bird eye's view to result FIG. 21. When the vehicle is normally running on the road, the side wall exists on the right and left sides of the vehicle 1 substantially along the vehicle. On the other hand, the side wall of the long distance is difficult to detect the distance data in view of the precision, and has little necessity of the detection. Accordingly, in view of these conditions, two search areas SL and SR are set on the left and right sides, and the side walls on the right side and the left side are particularly detected.

In other words, for detecting the side walls on the right and left sides, the side wall straight liner detector 142 set first the search area on the left side to perform the side wall straight line extraction processing and the side wall detection processing so as to detect the left side wall, and then, the side wall straight line detector 142 sets again the search area on the right side to perform the above mentioned processing so as to detect the right side wall.

In order to extract the construction data included in the search areas SL and SR, the three dimensional position (X and Z coordinates) of the object of each data extracted by the construction data extractor 141 is calculated to compare and judge the three dimensional position (X, Z) and each of search regions SR and SL.

For example, in the condition shown in FIG. 22, each of the search regions SR and SL can be shown by a dotted line on the picture, and various constructions exist in the search region in addition to the side wall as an object. Furthermore, since the pseudo data having noises are included in the distance picture, only distributed data exist in the space in which the object does not exist actually. In FIG. 23 showing these data as a model, the sidle wall has the characteristic in which the data are arranged in the straight line. Accordingly, the side wall is detected by calculating the linear equation of the data train by using a Hough transformation.

There is described a detection of the linear equation by the Hough transformation. A straight line Fi is assumed to pass through a construction data Pi at point (coordinate Xi, Zi) in FIG. 24. The linear equation is shown in an equation (8) as follows:

X=afi×Z+bfi   (8)

Next, as shown in FIG. 25, a parameter space is set to have a slant afi of the equation (8) as a vertical axis and a fragment bfi as a horizontal axis, and a voting is performed at the position corresponding to the parameters of afi and bfi in the equation.

Here, a value of the slant afi is practically sufficient to change in the range of ±20° (afi:±0.36) because the side wall is considered to be substantially parallel to the vehicle 1. A value of the fragment bfi is limited in a range of X=−1 to −10 meters as a left side of the vehicle when the left side wall is detected, and in a range of X=+1 to +10 meters as a right side when the right side wall is detected. In this manner, the reason why the limited range is within ±10 meters is that the detection of the side wall distant from the vehicle has little necessity for a practical use.

Such the limitation results in that the range of voting on the parameter space becomes a rectangular area as shown in FIG. 25, and the rectangular area is further divided into a plurality of gratings at each which a voting is performed. The slant afi in the equation (8) is within a predetermined change area (for example, ±10° to ±20°) and set at each interval Δaf of the gratings with a change one by one. The fragment bfi is calculated by substituting a set slant afi and a coordinate (Xi, Zi) of the construction data Pi for the equation (8), and the voting is performed for the grating corresponding to the parameter space if the calculated value is within the limit range.

The detected position of the side wall, namely, the detection accuracy of the slant and fragment in the linear equation is determined by the grating intervals Δaf and Δbf which are set by a requirement of the external apparatus using the side wall data. For example, the grating interval Δaf is desired to be 1°-2° and the grating interval Δbf 0.3-0.6 meters for using as a sensing means of such a dangerous condition as a collision when the vehicle is normally running on the road.

As described above, the voting of the parameter space is performed with entire construction data in the search region. At this time, as shown in FIG. 24, if the data arranged along the straight line exist, the grating corresponding to the straight line parameter afi and bfi which are set in the manner of coinciding with the data train, obtains many votes to appear locally maximum values at each left and right voting region SL and SR.

The locally maximum value become a large value when the side wall exists and clear construction data train exists, but the locally maximum values becomes a small value when the side wall does not exist and a plurality of objects are sporadical existing. Accordingly, the locally maximum values are detected at each of the left and right voting region SL and SR in the parameter space, thereby judging an existence of the side wall if the detected locally maximum values are more than a judge value. The judge value is set under the consideration of a size of the set search region and distance between the gratings.

When the side wall straight line detector 142 judges that the side wall exists, the side wall region detector 143 detects the positions of the front and rear ends of the side wall. When the parameters af and bf are read out corresponding gratings of the locally maximum values, the side wall is estimated to be along the linear equation (9) below, so as to be the straight line Ff as shown in FIG. 26 when the detected linear equation is shown from an example of FIG. 24.

X=af×Z+bf   (9)

When the region of width 0.3-1.0 meters at the center of the straight line Ff is supposed to be a side wall candidate region Tf, the region is divided in the Z direction as shown in FIG. 26. The width of the side wall candidate region Tf is set from the grating distance Δbf of the parameter space under the consideration of data errors and the like.

Next, the construction data in the search region are sequentially surveyed to extract only the data within the side wall candidate region Tf. After that, a number of the construction data is counted at each section to form the histogram. The histogram is shown in FIG. 27 as a model, in which a portion included by the side wall shows a large degree. Accordingly, it is possible to judge that the side wall exists in the region by detecting the section in which the degree is on or over the judge value, thereby setting the front and rear ends positions by calculating the three dimensional position of the side wall. In the example shown in FIG. 24, an upper end of the search region SR is regarded as the rear end position of the side wall (guardrail 400).

FIG. 28 shows the side wall detected by the above processing as a frame line. In this example, the guardrail 400 at the right side can be detected.

As described above, it is possible to obtain the parameters such as a position and shape of each object on the road in dependency on the distance picture to write in the construction parameter storage portion 150. Then, the gap distance calculator 160 formed by the microprocessor 120c calculates the gap distance of right and left between the vehicle 1 and the detected object.

In the example of the picture shown in FIG. 9, for example, when an X coordinate XL is a side of the parked car 200, an X coordinator XR is a side of the parked car 300, and an X coordinate XWR is an end of the guardrail 400 as shown in FIG. 29, a distance DL between the extending line of the left side of the vehicle 1 and the parked car 200 on the left side is calculated from an equation (10), a distance DR between the extending line of the right side of the vehicle 1 and the parked car 300 on the right side is calculated from an equation (11), and a distance DWR between the extending line of the right side of the vehicle 1 and the guardrail 400 on the right side is calculated from an equation (12) when a width of the vehicle 1 is W:

DL=|XL|−W/2   (10)

DR=|XR|−W/2   (11)

DWR=|XWR|−W/2   (12)

A calculation is performed at each edge by the equations (10), (11) and (12) to obtain the minimum values on the left and right sides. The minimum values become the nearest distance, namely, a gap distance. The gap distance is added with a little room for a rear view mirror of the object car to display the picture on the display 3, as shown in FIG. 3.

In the picture example shown in FIG. 9, since the distance DR between the parked car and the vehicle 1 is smaller than the distance DWR between the guardrail 400 and the vehicle 1, the distance DR is adopted as the right gap distance to output the display 3.

A threshold value such as 1 meter is provided for the numerical value of the gap distance for displaying on the display 3, and a numerical value over the threshold value is not displayed. Because it does not make sense to display the numerical value when the gap is sufficiently large.

Next, there will be described operation of the image processor 20 and the distance picture processing computer 120.

FIG. 30 is a flow chart showing a flow of operation of the image processor 20. In step S101, the pictures are imaged by the CCD cameras 11a and 11b on the left and right sides to input. In step S102, after the input analog pictures are converted by the A/D converter 31a and 31b into digital pictures having a predetermined luminance gradation, the LUTs 32a and 32b perform a characteristic compensation of the CCD camera 11a and 11b on the right and left sides and a contrast increase of the low luminance component so as to store the picture data in the picture memories 33a and 33b.

The pictures stored in the memories 33a and 33b are only lines necessary to the processing in the following steps within the entire lines of the CCD elements of the CCD cameras 11a and 11b, and are rewritten at a rate of one time per 0.1 second (a rate of one per three in the TV picture).

Next, in step S103, the right and left picture data having four lines are read from the picture memories 33a and 33b for the right and left pictures through the common bus 80 to input buffer memories 41a, 41b, 42a and 42b so as to estimate a matching, namely, a coincidence between the right and left pictures previously read in.

At that time, reading and writing operations are alternatively repeated, in which the reading operation is performed from the picture memories 33a and 33b to the input buffer memories 41a, 41b, 42a and 42b, and the write operation is performed to the shift register 43a, 43b, 44a and 44b. For example, in the left picture, while the picture data are read from the picture memory 33a to the buffer memory 41a on one side, the picture data are written from the input buffer on the other side into the shift register 43b. In the right picture, while the picture data are read from the picture memory 33b to the buffer memory 42a on one side, the picture data are written from the buffer memory 42b on the other side into the shift register 44b.

As shown in FIG. 31, the shift registers 43a, 43b, 44a and 44b store picture data (1, 1) through (4, 4) of the small regions of 4 by 4 pixels in the right and left, in which the shift register 43a(44a) stores data of first and second lines and the shift register 43b (44b) stores data of third and fourth lines respectively in the order of the odd numbered line and the even numbered line for each one pixel. Each of the shift registers 43a, 43b, 44a and 44b has: an independent transfer line, and the data of 4 by 4 pixels are transferred by 8 clocks, for example.

The contents of the even numbered stages in 8 stages are instantaneously outputted from the shift registers 43a, 43b, 44a and 44b to the city block distance calculation circuit 45. When the calculation of the city block distance H starts, the right picture data are stored in the shift register 44a and 44b, and the odd numbered line data and even numbered line data are alternatively outputted at each clock. On the other hand, the left picture data are continued to transfer to the shift registers 43a and 43b, and then the odd numbered line data and the even numbered line data are alternatively outputted and the data are shifted and replaced to the right one pixel per 2 clocks. This operation is repeated until the replacement of 100 pixels (200 clocks).

After that, when the transfer is completed with respect to one small region, the process in next small region starts by setting the contents (an initial address in the small region of 4 by 4 pixels) in the right picture address counter into the left picture address counter in a #2 address controller 87.

In the city block distance calculation circuit 45, as shown in the timing chart of FIG. 32, the data for the eight pixels are first inputted into an absolute value calculator at the first stage of the pyramid constitution to calculate an absolute value of the luminance difference between the right and left pictures, namely, the luminance of the left picture is subtracted from the luminance of the corresponding right picture. When the subtracted result is negative, the subtraction is performed again by changing the subtraction positions each other to calculate the absolute value. Accordingly, there is once an occasion in which two subtractions are performed in the initial stage.

Next, after the initial stage is completed, two instantaneous input data are added by the first through third adders in second through fourth stages to output added data. Then, a total sum adder in the final stage adds two continuous data each other to calculate a total sum, so as to output the city block distance H for necessary sixteen pixel components every two clocks to the minimum and maximum value detector 50.

Next, in step S104, the maximum value HMAX and the minimum value HMIN are detected for the city block distance H which is calculated in step S103. As mentioned above, the detections of the maximum value HMAX and the minimum value HMIN are the same each other except the opposite logic and a storage of the discrepancy amount. Accordingly, there will be later the detection of the minimum value HMIN as a representation.

First, the city block distance H (the discrepancy amount x=0) of the first output is supplied through the C latch 53 of the minimum value detection circuit 51 shown in FIG. 8 to the B register 46b of the calculator 46. The city block distance H (the discrepancy amount δ=1) which is outputted at the next clock, is supplied to the C latch 53 and the calculator 46. The calculator 46 starts the comparison calculation with the B register 46b at the same time of the input of the city block distance H.

As a result of the comparison calculation in the calculator 46, if the contents in the A register 46a are smaller than the contents in the B register 46b, the contents in the C latch 53 (namely, the contents in the A register 46a) are transferred to the B register 46b at the next clock, and the discrepancy amount δ at this time is stored in the D latch 55. At the same time of this clock, the next city block distance H (the discrepancy amount δ=2) is supplied to the A register 46a and the C latch 53 to start the comparison calculation again.

In this manner, while the minimum value in the middle of the calculation is usually stored in the B register 46b and the discrepancy amount δ at this time is stored in the D latch 55, the calculation is continued until the discrepancy amount becomes 100. When the calculation is completed (namely, 1 clock after the final city block distance H is outputted), the contents in the B register 46b and the D latch 55 are read in the discrepancy amount determiner 60.

During this processing, the above-mentioned city block distance calculation circuit 45 reads the initial value of the next small region not to generate a dead time. Even though four clocks are taken for the calculation of one city block distance H, since the circuit 45 has the pipe line constitution, new calculation results can be obtained at every two clocks.

When there are established the minimum value HMIN and the maximum value HMAX of the city block distance H in step S104, the discrepancy amount determiner 60 checks the above mentioned three conditions to determine the discrepancy amount x in step S105.

Accordingly, as shown in FIG. 33, the minimum value HMIN is latched through the B bus 62b in the B register 72, and the threshold value HA which is compared with the value in the B register 72 is latched through the A bus 62a in the A register 71. Then, the ALU 70 compares both values. When the minimum value HMIN is larger than the threshold value HA, the switch circuit 65 is reset to usually output “0” in spite of the any check later.

Next, the maximum value HMAX is latched by the A register 71, and the difference between the maximum value HMAX latched in the A register 71 and the minimum value HMIN latched in the B register 72 is calculated to output the calculation result to the F register 73. The A register 71 latches the threshold value HB at the next clock, and compares it with the value in the F register 73. The switch circuit 65 is reset in the same manner when the contents in the F register 73 are smaller than the threshold[ value HB latched by the A register 71.

From the next clock, it starts to calculate the luminance difference between the adjacent pixels. Two shift registers 64a and 64b respectively have ten stage constitution for storing the luminance data and connected to rear stages of the shift registers 44a and 44b of the city block distance calculator 40, in which the shift register 44a is for the first and second lines and the shift register 44b is for the third and fourth lines. Outputs of the shift registers 64a and 64b are taken from the final stage and two before the final stage to output to the A bus 62a and the B bus 62b, respectively.

When the calculation of the luminance difference starts, each stage in the shift registers 64a and 64b stores the luminance data of each plate in the small regions, and the A register 71 and the B register 72 in the calculator 61 first latch the luminance data at the fourth column in the first row of the previous small region and the luminance data at the first column in the first row of the present small region, respectively.

The calculator 61 calculates an absolute value of the difference between the content in the A register 71 and the content in the B register 72 to store the calculated result in the F register 73. The A register 71 latches the threshold value HC by the next clock to compare it with the value in the F register 73.

As a result in the calculator 61, if the content (the absolute value of the luminance difference) in the F register 73 is larger than the content (threshold value HC) of the A register 71, the switch circuit 65 outputs the discrepancy amount x or “0”. To the contrary, when the content in the F register 73 is smaller than the content in the A register 71, the switch circuit 65 outputs “0” to write it at the position in the first column in the first row in the small region corresponding to the output buffers 66a and 66b.

While the calculator 61 compares the luminance difference between the adjacent pixels with the threshold value HC, the shift registers 64a and 64b shift one stage, respectively. Then, the calculator 61 starts to calculate with respect to the luminance data at the fourth column in the second row in the previous small region and the luminance data at the first column in the second row in the present small region. In this manner, after the alternative calculation is performed with the first and second rows in the small region, the same calculation is performed with respect to the third and fourth rows.

During the calculation, a ring register is formed by connecting the final stage of the shift register 64a with the first stage of the shift register 64b. When two shift clocks are added after the calculation is performed with the entire small regions, the content in the register returns to the condition before the calculation. When the luminance data in the next small region are completed to transfer, the data in the fourth row in the present small region are maintained in the final and previous stages.

In this manner, since the next data are provided in and the calculation results are written in the A bus 62a and B bus 62b during the calculation for determining the discrepancy amount, one data is processed only by two clocks necessary to the calculation. As a result, entire calculation is completed within 43 clocks even though the initial check for the minimum value HMIN and the maximum value HMAX is included, and it is sufficient for a time to obtain the minimum value HMIN and the maximum value HMAX of the city block distance H against one small region, thereby adding further function.

When the discrepancy amount is determined, in step S106, the discrepancy amount x is outputted as the distance distribution information from the output buffer memories 66a and 66b to the dual port memory 90 so as to end the processing in the image processor 20.

The output buffer memories 66a and 66b have the capacity of four lines, for example, in the same manner of the above-mentioned input buffer memories 41a, 41b, 42a and 42b. While the distance distribution data are written into one pair of two pairs, the data are transferred from another pair of two pairs to the dual port memory 90.

It is possible to calculate the three dimensional position in the XYZ space of the object corresponding to each pixel from the distance distribution information which is written into the dual port memory 90 in dependency on the lens parameter such as an attached position and a focal point of the CCD cameras 11 and 12, thereby precisely detecting the distance the object outside the vehicle without deterioration of the data amount.

Here, entire timing of the image processor 20 will be described in accordance with the timing chart shown in FIG. 34.

At first, the picture memories 33a and 33b write in oneself the field signal from the left and right CCD cameras 11a and 11b synchronizing each other at the timing of each 0.1 second (a rate of one picture per three pictures).

Next, a block is transferred at each four lines after receiving a taking end signal. The transfer is performed by transferring three blocks of the right picture, the left picture and the distance distribution picture as a result in the order.

During this, a calculation is performed with respect to a discrepancy amount δ for one of the input and output buffer memories. After a predetermined time passes through under the consideration of the calculation time of the discrepancy amount 67 , a transfer is performed to the other of the input and output buffer memories.

A hundred of calculations is performed about the city block distance H against a small region of four by four pixels of one right picture because the calculation is performed by shifting a hundred pixels about the left picture. During the calculation is performed with respect to the city block distance H in one region, the discrepancy amount δ in the previous one region is outputted as the distance distribution after each checking.

When the line number to be processed is two hundreds, a processing for four lines is repeated in fifty times, thereby requiring a processing time eight lines of four lines to transfer the initial data when starting the calculation, and of four lines to transfer the final result to the picture recognizing portion after the calculation is completed.

A time is 0.076 second as a result of the actual circuit operation from the start of the transfer of the initial input picture line to the end of the transfer of the final distance distribution.

On the other hand, flow charts of FIGS. 35 and 36 show an object detection processing executing in the microprocessor 120a. In step S201, a position of the road surface is set. In step S202, the distance picture from the image processor 20 is divided into a grating shape regions. In step S203, the data are read for the initial region.

Next, the processing advances to step S204, and the initial data in the region are set. In step S205, the calculation is performed about the three dimensional position (X, Y, Z) of the object, namely, the distance and height. After the height of the road surface is calculated at the distance Z in step S206, the data over the road surface are selected in step S207.

In step S208, the data are checked as to whether the data are final data or not. When the data are not the final data, next data in the region are set in step S209 to return process to the above mentioned step S205 so as to continue the processing. When the data are the final data, the process advances from step S208 to step S210.

In step S210, a histogram is formed. In step S211, there is detected section in which a degree of the histogram is over the judge value and becomes the maximum value. When the section is detected in which the degree of the histogram is over the judge value and becomes the maximum value, the object exists in the section in step S212 so as to detect the distance to the object.

In step S213, there is studied as to whether the region is the final region or not. When the region is not final, the data in the next region are read in step S214 to return to the step S204 so as to continue the same processing. When the region is final, the process advances to step S215 to detect the distance and existing region of the object so as to end the detection to advance the process to step S216.

In Step S216, a parameter is set for the initial object. In step S217, the three dimensional window WD3 is set for the height of its lower end and the distance area. In step S218, the shape of the two dimensional window WD2 is calculated in dependency on the three dimensional window WD3 to advance the processing to step S219.

In step S219, the data are read from the two dimensional window WD2. After calculating the three dimensional position of the object in step S220, the data are selected and extracted from the three dimensional window WD3 in step S221.

After that, when the data extracted in step S221 are projected on the two dimensional picture in step S222, a contour image is formed by connecting each data by lines in step S223. Next, in step 224, the shape, size, position and speed of the object are calculated. In step S225, there is checked whether the object is final or not.

When the object is not final, a parameter of the next object is set in step S226 to return to step S217. When the object is final, in step S227, parameters such as a position, shape, speed, acceleration and possibility of collision of the object are read in the output memory 125 to complete the process.

Furthermore, the microprocessor 120b performs the side wall detection process shown in FIGS. 37 and 38 in parallel with the object detection process by the microprocessor 120a. In this side wall detection process, when the road surface position is set in step S301, the initial distance data are read from the distance picture in step S302.

Next, in step S303, the position (X, Z coordinates) and the height (Y coordinate) of the object are calculated. In step S304, the height H (Y coordinate) is calculated with respect to the road surface in the distance Z. In step S305, the data over the road surface and under the height of the vehicle are extracted as the construction data.

In step S306, the data are investigated to be final or not. When the data are not final, the next distant data are read in step S307 and the process returns to step S303 to repeat the process again. When the data is final, the process advances from step S306 to step S308.

In step S308, the initial construction data are read, and in step S309, the position (X, Z coordinates) of the object is calculated. In step S310, the calculated position (X, Z coordinates) is checked to be within the search region or not.

When the calculated position (X, Z coordinates) is without the search region, the process jumps from steps S310 to S312. When the position is in the search region, the process advances from step S310 to step S311 to vote into the parameter space to be in step S312.

In step S312, the processed construction data are checked as to be the final data or not. When the data are not final, the next construction data are read in step S313 to repeat the same process from step S309, when the data are final, the process advances to step S314 to detect the local maximum value in the parameter space.

Next, at advancing to the step S315, the detected local maximum value is checked to be over the judge value or not. When the value is under the judge value, the side wall is determined to be absent in step S316. When the value is over the judge value, the side wall is determined to be present in step S317. Then, the process advances to step S318.

In step S318, there is a reading process for a parameter corresponding to the grating of the local maximum value detected in step S314, namely, a parameter (af, bf) of the linear equation showing the local maximum point. Next, the side wall candidate region is set in step S319.

In step S320, the initial structure data are read from the search region. After the position (X, Z coordinates) of the object is calculated in step S321, the data including in the side wall estimated region are extracted in step S322. After that, in step S323, the processed data are investigated to be the final data within the search region or not.

When the data are not final, the process is divided from step S323 to step S324 to read the next structure data in the search region to return to step S321. When the data are final in the search region, the process advances from step S323 to step S325 to form the histogram by using the data in the side wall estimated region.

Next, in step S326, the degree of the formed histogram is detected to be the section over the judge value to be in step S327. In step S327, the three dimensional position of both ends of the section in which the degree of the histogram is over the judge value is calculated. In step S328, the program is completed by writing the parameters such as a presence or absence, position and direction of the side wall, and positions of front and rear ends into the output memory 125. The program is first executed on the left side wall, and then on the right side wall.

By the above process, it is possible to detect the position and size of the front wall and parked car from the own vehicle 1, and it is possible to prosecute the program for processing the gap distance calculation shown in FIG. 39 by the microprocessor 120c.

In the gap distance calculation processing, in step S401, there are inputted the position of the edge of the object on the vehicle side and the position of the end of the side wall. Then, in step S402, the right and left distances are respectively obtained in the X direction between the end of the side wall or each edge of the objects and the executed line of the side portion of the vehicle 1.

Next, in step S403, the right and left minimum values are respectively obtained from the each of distances obtained in the step S402. In step S404, a little clearance as the gap distance is added with each of the right and left minimum values to display the numerical value on the display 3 through the display controller 126.

Claims (24)

What is claimed is:
1. A running guide apparatus for a vehicle having a pair of cameras mounted on a front portion of said vehicle for taking a three-dimensional picture of objects in front of the vehicle and for generating a picture signal, said apparatus comprising:
stereoscopic picture processing means responsive to said picture signal for processing a pair of stereoscopic pictures of said object outside said vehicle and for producing a distance signal by obtaining a distance distribution of an entire picture in dependency upon a discrepancy amount positions corresponding to said pair of the stereoscopic pictures in accordance with a principle of a triangulation;
object detection means responsive to said distance signal for detecting a plurality of various objects by using three dimensional position data calculated with each portion of the object corresponding to the distance distribution and for generating a distance signal;
gap distance calculation means responsive to a distribution signal for respectively calculating a nearest distance of right and left gap distances each between an extended line of right or left side of the vehicle and each end of the vehicle side from the plurality of various objects and for producing a distance signal; and
information means responsive to said distance signal for informing a driver of data related to the right and left gap data so as to entirely and exactly display surrounding conditions of said vehicle and to largely decrease burdens of said driver when running on a narrow road.
2. The running guide apparatus for the vehicle according to claim 1, further comprising
two pairs of charge coupled device (CCD) cameras respectively arranged as said imaging system to a front surface of said vehicle with a predetermined interval, one pair provided for a long distance and the provided for a short distance, and each pair including a right and left cameras each other;
an image processor provided as said stereoscopic picture processing means, and including a distance detection circuit for searching a portion in which a same object is imaged in each small region of the stereoscopic picture pair from said CCD cameras and for calculating a distance to the object by obtaining a discrepancy amount of a position corresponding to said portion, and a distance picture memory for storing distance data outputted from said distance detection circuit;
a distance picture processing computer provided as said object detection means and said gap distance calculation means, and comprised of a multi-microprocessor system construction including a first microprocessor for mainly performing detection processing of individual object, a second microprocessor for mainly performing detection processing of a side wall, a third microprocessor for mainly performing calculation processing of a gap distance, and a system bus for connecting said first through third microprocessors in parallel; and
a discrepancy as said information means for displaying to a driver gap data by obtaining said calculation processing of said gap distance.
3. The running guide apparatus for the vehicle according to claim 2, further comprising
an object recognizer comprised of said first microprocessor;
a side wall detector comprised of said second microprocessor;
a gap distance calculator comprised of said third microprocessor;
a construction parameter memory for storing a processed result of said object recognizer and said side wall detector to output said result to said gap distance calculator.
4. The running guide apparatus for the vehicle according to claim 3, further comprising
object detector for dividing the distance picture from a distance picture memory comprised of said image processor into a predetermined interval in the stripe shape and for selecting only construction data having the danger as an object for running to calculate the detected distance;
a three dimension window generator for setting a three dimensional space region of a rectangular solid shape with respect to respective object detected by said object detector, and for calculating how to be shown set three dimension window on a two dimensional picture, so as to set the detection object with respect to only data within a window contour line as the two dimension window; and
an object contour extractor for surveying one by one each of the data in the two dimension window, for selecting only data included in said three dimension window, extracting a contour image of the detected object, and for detecting a positional relationship between the detected object and vehicle own body.
5. The running guide apparatus for the vehicle according to claim 4, further comprising:
an object data extractor for extracting only data over the predetermined road surface previously set from the distance distribution data supplied from a distance picture memory comprised of said image processor;
a side wall straight line detector for extracting only data within a side wall search region previously set, for processing the extracted data by the Hough transformation, thereby detecting a linear equation showing presence or absence of the side wall and the position of the side wall; and
a side wall area detector for setting the side wall candidate region in which the side wall is estimated to exist on the basis of the straight line showing the position of the side wall, and for detecting the positions of before and after ends of the side wall in dependency on the distribution condition of the construction data in the side wall candidate region.
6. A running guide method for a vehicle having a pair of cameras mounted on a front portion of said vehicle for taking a three-dimensional picture of objects in front of the vehicle and for generating a picture signal, said apparatus comprising:
a step of processing a pair of stereoscopic pictures of said object outside said vehicle to produce a distance signal by obtaining a distance distribution of an entire picture in dependency upon a discrepancy amount positions corresponding to said pair of the stereoscopic pictures in accordance with a principle of a triangulation;
a step of detecting a plurality of various objects by using three dimensional position data calculated with each portion of the object corresponding to the distance distribution and for generating a distance signal;
a step of respectively calculating a nearest distance of right and left gap distances each between an extended line of right or left side of the vehicle and each end of the vehicle side from the plurality of various objects; and
a step of informing a driver of data related to the right and left gap data so as to entirely and exactly display surrounding conditions of said vehicle and to largely decrease burdens of said driver when running on a narrow road.
7. The running guide method for the vehicle according to claim 6, further comprising
a step of obtaining long distance data of a picture in front of the vehicle;
a step of obtaining short distance data of a picture in front of the vehicle;
a step of searching a portion in which a same object is imaged in each small region of the stereoscopic picture pair from said CCD cameras;
a step of calculating a distance to the object by obtaining a discrepancy amount of a position corresponding to said portion, and a distance picture memory for storing distance data outputted from a distance detection circuit;
a step of performing detection processing of a side wall, a third microprocessor for mainly performing calculation processing of a gap distance, and a system bus for connecting said first through third microprocessors in parallel; and
a step of displaying to a driver gap data by obtaining said calculation processing of said gap distance.
8. The running guide apparatus for the vehicle according to claim 7, further comprising
a step of dividing the distance picture from a distance picture memory comprised of a image processor into a predetermined interval in the strip shape;
a step of selecting only construction data having the danger as an object for running to calculate the detected distance;
a step of setting a three dimensional space region of a rectangular solid shape with respect to respective object detected by said object detector;
a step of calculating how to be shown set three dimension window on a two dimensional picture, so as to set the detection object with respect to only data within a window contour line as the two dimension window;
a step of surveying one by one each of the data in the two dimension window;
a step of selecting only data included in said three dimension window;
a step of extracting a contour image of the detected object; and
a step of detecting a positional relationship between the detected object and vehicle own body.
9. The running guide apparatus for the vehicle according to claim 8, further comprising
a step extracting only data over the predetermined road surface previously set from the distance distribution data supplied from a distance picture memory comprised of said image processor;
a step of extracting only data within a side wall search region previously set;
a step of processing the extracted data by the Hough transformation, thereby detecting a linear equation showing presence or absence of the side wall and the position of the side wall;
a step of setting the side wall candidate region in which the side wall is estimated to exist on the basis of the straight line showing the position of the side wall; and
a step of detecting the positions of before and after ends of the side wall in dependency on the distribution condition of the construction data in the side wall candidate region.
10. A driving guide apparatus for a vehicle having a pair of cameras mounted on a front portion of said vehicle and arranged to take pairs of image pictures of a scene containing objects which may form obstacles in front of the vehicle and for generating picture signals, said apparatus comprising:
image picture processing means for processing a pair of image pictures of objects outside said vehicle for producing a distance distribution picture made up by the distribution of an object point distance from said pair of cameras in dependence upon a discrepancy amount between the imaged object points within said pair of image pictures in accordance with a principle of triangulation;
object detection means for detecting objects constituting a potential obstacle by calculating three dimensional positions for said object from the distance distribution picture;
gap distance calculation means for calculating a gap distance between an extended line of a side of the vehicle and one of said detected objects nearest said vehicle; and
information means for informing a driver of data related to the gap distance so as to decrease the burdens of said driver when driving on a narrow road.
11. The driving guide apparatus according to claim 10, wherein said gap distance calculation means calculates said gap distance on each side of said vehicle.
12. The driving guide apparatus according to claim 10, wherein said information means comprises a display provided to inform said driver of said gap distance so as to be entirely and precisely display lateral obstacles in the traveling direction of said vehicle to said driver.
13. The driving guide apparatus according to claim 10, wherein said object detection means comprises:
an object recognizer provided to recognize obstacles on a road as said objects; and
a side wall detector provided to detect a side wall on a side of said road as said object; and
wherein said gap distance calculation means calculates a distance to each of said obstacle and said side wall from said vehicle to detect said gap distance.
14. The driving guide apparatus according to claim 13, wherein said object recognizer comprises:
an object detector provided to divide said distance distribution picture in a stripe shape by a predetermined interval and select only obstacles as said objects;
a three dimension window generator provided to set a three dimension space region of a rectangular solid shape with respect to each obstacle detected by said object detector; and
an object contour extractor provided to select data existing within said three dimension window to extract a contour image of said detected obstacle, said contour image being used to calculate a distance between said detected obstacle and said vehicle.
15. The driving guide apparatus according to claim 13, wherein said wall detector comprises:
an object data extractor provided to extract data indicative of potential objects over a road surface from said distance distribution picture;
a side wall straight line detector provided to process the extracted data to determine a straight line with a linear equation representing the position of a side wall; and
a side wall area detector provided to determine positions of ends of said side wall in dependence on a volume of data within a side wall candidate region set around said straight line.
16. The driving apparatus for the vehicle according to claim 10, further comprising:
two pairs of charge coupled device (CCD) cameras respectively arranged as said imaging system to a front surface of said vehicle with a predetermined interval, one pair is provided for a long distance and the other provided for a short distance, and each pair including a right camera and a left camera;
an image processor provided as said image picture processing means, and including a distance detection circuit for searching a portion in which a same object is imaged in each small region of the image picture pair from said CCD cameras and for calculating a distance to the object by obtaining a discrepancy amount of a position corresponding to said portion, and a distance picture memory for storing distance data output from said distance detection circuit;
a distance picture processing computer provided as said object detection means and said gap distance calculation means, and comprised of a multi-microprocessor system construction, including a first microprocessor for mainly performing detection processing of an individual object, a second microprocessor for mainly performing detection processing of a side wall, a third microprocessor for mainly performing calculation processing of a gap distance, and a system bus for connecting said first through third microprocessors in parallel; and
a display as said information means for displaying to a driver gap data by obtaining said calculation processing of said gap distance.
17. The driving guide apparatus for a vehicle according to claim 16, further comprising:
an object recognizer comprised of said first microprocessor;
a side wall detector comprised of said second microprocessor;
a gap distance calculator comprised of said third microprocessor;
a construction parameter memory for storing a processed result of said object recognizer and said side wall detector to output said result to said gap distance calculator.
18. The driving guide apparatus for the vehicle according to claim 17, further comprising:
an object detector for dividing the distance picture from a distance picture memory comprised of said image processor into a predetermined interval in a stripe shape and for selecting only object data having the danger to be an obstacle to calculate the detected distance;
a three dimension window generator for setting a three dimensional space region of a rectangular solid shape with respect to a respective object detected by said object detector, and for calculating how to be shown a set three dimension window on a two dimensional picture, so as to set the detected object with respect only to data within a window contour line as the two dimension window; and
an object contour extractor for surveying one by one each of the data in the two dimension window, for selecting only data included in said three dimension window, extracting a contour image of the detected object, and for detecting a positional relationship between the detected object and the vehicle's own body.
19. The driving guide apparatus for the vehicle according to claim 16, further comprising:
an object data extractor for extracting only data over the predetermined road surface previously set from the distance distribution data supplied from a distance picture memory comprised of said image processor;
a side wall straight light detector for extracting only data within a side wall search region previously set, and for processing the extracted data by the Hough transformation, thereby detecting a linear equation showing the presence or absence of the side wall and the position of the side wall; and
a side wall area detector for setting the side wall candidate region in which the side wall is estimated to exist on the basis of the straight line showing the position of the side wall, and for detecting the positions of ends of the side wall in dependency on the distribution condition of the construction data in the side wall candidate region.
20. A driving guide method for a vehicle having a pair of cameras mounted on a front portion of said vehicle and provided to take a pair of image pictures of a scene in front of the vehicle containing objects which may form obstacles and for generating a picture signal, said method comprising the steps of:
processing a pair of image pictures of said objects outside said vehicle and producing a distance distribution picture made up by a distribution of object point distances from said cameras in dependency upon discrepancy amounts between imaged object points within said pair of image pictures using a principle of triangulation;
detecting a plurality of objects constituting a potential obstacle by using three dimensional positions for said objects from the distance distribution picture;
calculating a gap distance each between an extended line of a side of the vehicle and a detected object nearest to said vehicle; and
informing a driver of data related to said gap distance so as to largely decrease burdens of said driver when running on a narrow road.
21. The driving guide method for the vehicle according to claim 20, further comprising the steps of:
obtaining long distance data of a picture in front of the vehicle;
obtaining short distance data of a picture in front of the vehicle;
searching a position in which a same object is imaged in each small region of the image picture pair from CCD cameras;
calculating a distance to the object by obtaining a discrepancy amount of a position corresponding to said portion;
performing detection processing of a side wall; and
displaying to a driver gap data by obtaining said calculation of said gap distance.
22. The driving guide method for the vehicle according to claim 20, further comprising the steps of:
dividing the distance picture from a distance picture memory comprised of an image processor into a predetermined interval in the stripe shape;
selecting only construction data having the danger to be an obstacle for the vehicle to calculate the detected distance;
setting the dimensional space region of a rectangular solid shape with respect to a respective object detected by said object detector;
calculating how to show a set three dimension window on a two dimensional picture, so as to set the detected object with respect only to data within a window contour line as the two dimension window;
surveying one by one each of the data in the two dimension window;
selecting only data included in said three dimension window;
extracting a contour image of the detected object; and
detecting a positional relationship between the detected object and vehicle's own body.
23. The driving guide method for the vehicle according to claim 20, further comprising the steps of:
extracting only data over the predetermined road surface previously set from the distance distribution data supplied from a distance picture memory comprised of said image processor;
extracting only data within a side wall search region previously set;
processing the extracted data by the Hough transformation, thereby detecting a linear equation showing the presence or absence of the side wall and the position of the side wall;
setting the side wall candidate region in which the side wall is estimated to exist on the basis of the straight line showing the position of the side wall; and
detecting the positions of ends of the side wall in dependency on the distribution condition of the construction data in the side wall candidate region.
24. A driving apparatus for a vehicle, comprising:
imaging means mounted on a front portion of said vehicle and provided to generate image data of a scene in front of said vehicle, containing objects which may constitute potential obstacle;
object detection means for detecting objects constituting a potential obstacle by processing said image data;
gap distance calculation means for calculating a gap distance (D x , D y) between an extended line of a side of said vehicle and a side edge of one of said detected objects; and
information means for informing a driver of a status related to said gap distance so as to largely decrease burdens of the driver when driving on a narrow road.
US09/102,880 1993-12-27 1998-06-24 Running guide apparatus for vehicle capable of keeping safety at passing through narrow path and the method thereof Expired - Lifetime USRE37610E1 (en)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP5-330191 1993-12-27
JP33019193A JP3522317B2 (en) 1993-12-27 1993-12-27 Vehicle travel guidance system
US08/364,104 US5530420A (en) 1993-12-27 1994-12-27 Running guide apparatus for vehicle capable of keeping safety at passing through narrow path and the method thereof
US09/102,880 USRE37610E1 (en) 1993-12-27 1998-06-24 Running guide apparatus for vehicle capable of keeping safety at passing through narrow path and the method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US09/102,880 USRE37610E1 (en) 1993-12-27 1998-06-24 Running guide apparatus for vehicle capable of keeping safety at passing through narrow path and the method thereof

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US08/364,104 Reissue US5530420A (en) 1993-12-27 1994-12-27 Running guide apparatus for vehicle capable of keeping safety at passing through narrow path and the method thereof

Publications (1)

Publication Number Publication Date
USRE37610E1 true USRE37610E1 (en) 2002-03-26

Family

ID=18229856

Family Applications (2)

Application Number Title Priority Date Filing Date
US08/364,104 Expired - Lifetime US5530420A (en) 1993-12-27 1994-12-27 Running guide apparatus for vehicle capable of keeping safety at passing through narrow path and the method thereof
US09/102,880 Expired - Lifetime USRE37610E1 (en) 1993-12-27 1998-06-24 Running guide apparatus for vehicle capable of keeping safety at passing through narrow path and the method thereof

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US08/364,104 Expired - Lifetime US5530420A (en) 1993-12-27 1994-12-27 Running guide apparatus for vehicle capable of keeping safety at passing through narrow path and the method thereof

Country Status (4)

Country Link
US (2) US5530420A (en)
JP (1) JP3522317B2 (en)
DE (1) DE4446452B4 (en)
GB (1) GB2285719B (en)

Cited By (34)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6477260B1 (en) * 1998-11-02 2002-11-05 Nissan Motor Co., Ltd. Position measuring apparatus using a pair of electronic cameras
US6683969B1 (en) * 1999-05-27 2004-01-27 Honda Giken Kogyo Kabushiki Kaisha Object detection system
US20040080450A1 (en) * 2002-10-28 2004-04-29 Hyuck-Jin Cheong Method and apparatus for detecting vehicle distance
US6731332B1 (en) * 1998-01-29 2004-05-04 Matsushita Electric Industrial Co., Ltd. Image processing apparatus
US20040207515A1 (en) * 2003-04-21 2004-10-21 Chung Eui Yoon Method of controlling a distance between vehicles, and an apparatus thereof
US20050012603A1 (en) * 2003-05-08 2005-01-20 Frank Ewerhart Device for determining the passability of a vehicle
US6853738B1 (en) * 1999-06-16 2005-02-08 Honda Giken Kogyo Kabushiki Kaisha Optical object recognition system
US20050102070A1 (en) * 2003-11-11 2005-05-12 Nissan Motor Co., Ltd. Vehicle image processing device
US20050179875A1 (en) * 2004-02-13 2005-08-18 Nec Viewtechnology, Ltd. Projector with a plurality of cameras
US20050248503A1 (en) * 2002-08-19 2005-11-10 Koninklijke Phillips Electronics N.V. Display system for displaying images within a vehicle
US20060097858A1 (en) * 2004-10-27 2006-05-11 Denso Corporation Information presenting apparatus and method
US20060287825A1 (en) * 1999-06-25 2006-12-21 Fujitsu Ten Limited Vehicle drive assist system
US20070088469A1 (en) * 2005-10-04 2007-04-19 Oshkosh Truck Corporation Vehicle control system and method
US20070232448A1 (en) * 2003-10-25 2007-10-04 Daimler Chrysler Ag Method and Device for Controlling Distance
US20070291130A1 (en) * 2006-06-19 2007-12-20 Oshkosh Truck Corporation Vision system for an autonomous vehicle
US20080010018A1 (en) * 2005-01-12 2008-01-10 Toyota Jidosha Kabushiki Kaisha Parking support device
US20080181461A1 (en) * 2007-01-31 2008-07-31 Toru Saito Monitoring System
US20090010495A1 (en) * 2004-07-26 2009-01-08 Automotive Systems Laboratory, Inc. Vulnerable Road User Protection System
US20100060735A1 (en) * 2007-02-23 2010-03-11 Koji Sato Device and method of monitoring surroundings of a vehicle
US20100208060A1 (en) * 2009-02-16 2010-08-19 Masanori Kobayashi Liquid droplet recognition apparatus, raindrop recognition apparatus, and on-vehicle monitoring apparatus
US20100253784A1 (en) * 2009-04-06 2010-10-07 Samsung Electro-Mechanics Co., Ltd. Calibration method and apparatus for automotive camera system, and method and ecu for determining angular misalignments of automotive camera system
US20100290665A1 (en) * 2009-05-13 2010-11-18 Applied Vision Company, Llc System and method for dimensioning objects using stereoscopic imaging
US20110098892A1 (en) * 2008-06-25 2011-04-28 Astrid Lundmark Method of detecting object in the vicinity of a vehicle
US20110188741A1 (en) * 2009-05-13 2011-08-04 Applied Vision Corporation System and method for dimensioning objects using stereoscopic imaging
US20110193953A1 (en) * 2010-02-05 2011-08-11 Applied Vision Company, Llc System and method for estimating the height of an object using tomosynthesis-like techniques
WO2012084277A1 (en) * 2010-12-22 2012-06-28 Thomson Licensing Apparatus and method for determining a disparity estimate
US8459619B2 (en) 2010-10-24 2013-06-11 Oshkosh Corporation Gas spring control system and method
US20130147983A1 (en) * 2011-12-09 2013-06-13 Sl Corporation Apparatus and method for providing location information
US8725330B2 (en) 2010-06-02 2014-05-13 Bryan Marc Failing Increasing vehicle security
US8768007B2 (en) 2012-03-26 2014-07-01 Tk Holdings Inc. Method of filtering an image
US8824733B2 (en) 2012-03-26 2014-09-02 Tk Holdings Inc. Range-cued object segmentation system and method
US8947531B2 (en) 2006-06-19 2015-02-03 Oshkosh Corporation Vehicle diagnostics based on information communicated between vehicles
US9349058B2 (en) 2012-10-31 2016-05-24 Tk Holdings, Inc. Vehicular path sensing system and method
US10083361B2 (en) 2013-03-15 2018-09-25 Joyson Safety Systems Acquisition Llc Path sensing using structured lighting

Families Citing this family (249)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6891563B2 (en) 1996-05-22 2005-05-10 Donnelly Corporation Vehicular vision system
US7655894B2 (en) 1996-03-25 2010-02-02 Donnelly Corporation Vehicular image sensing system
US5877897A (en) 1993-02-26 1999-03-02 Donnelly Corporation Automatic rearview mirror, vehicle lighting control and vehicle interior monitoring system using a photosensor array
US6822563B2 (en) 1997-09-22 2004-11-23 Donnelly Corporation Vehicle imaging system with accessory control
US6396397B1 (en) * 1993-02-26 2002-05-28 Donnelly Corporation Vehicle imaging system with stereo imaging
US6498620B2 (en) 1993-02-26 2002-12-24 Donnelly Corporation Vision system for a vehicle including an image capture device and a display system having a long focal length
US5910854A (en) 1993-02-26 1999-06-08 Donnelly Corporation Electrochromic polymeric solid films, manufacturing electrochromic devices using such solid films, and processes for making such solid films and devices
US5670935A (en) * 1993-02-26 1997-09-23 Donnelly Corporation Rearview vision system for vehicle including panoramic view
JPH07189795A (en) * 1993-12-28 1995-07-28 Hitachi Ltd Controller and control method for automobile
US8294975B2 (en) 1997-08-25 2012-10-23 Donnelly Corporation Automotive rearview mirror assembly
US5668663A (en) 1994-05-05 1997-09-16 Donnelly Corporation Electrochromic mirrors and devices
JPH08167100A (en) * 1994-12-12 1996-06-25 Hisaji Nakamura Steering device
JP3246243B2 (en) * 1994-12-26 2002-01-15 いすゞ自動車株式会社 Lane departure warning device
JP3470453B2 (en) * 1995-04-06 2003-11-25 株式会社デンソー Vehicle-to-vehicle distance control device
JP3390289B2 (en) * 1995-06-16 2003-03-24 富士重工業株式会社 Alarm System
US5887268A (en) * 1995-10-31 1999-03-23 Honda Giken Kogyo Kabushiki Kaisha Automatically driven motor vehicle
US6053270A (en) * 1995-11-02 2000-04-25 Honda Giken Kogyo Kabushiki Kaisha Steering angle correcting system in vehicle
JP3866328B2 (en) * 1996-06-06 2007-01-10 富士重工業株式会社 Vehicle near the three-dimensional object recognition device
JP3577851B2 (en) * 1996-10-03 2004-10-20 トヨタ自動車株式会社 Travel control device
JP3468001B2 (en) * 1996-12-16 2003-11-17 日産自動車株式会社 Vehicle control system
JP3337197B2 (en) * 1997-04-04 2002-10-21 富士重工業株式会社 The outside of the vehicle monitoring system
JPH10320561A (en) * 1997-05-21 1998-12-04 Oki Data:Kk Image processing method and device therefor
US6757009B1 (en) 1997-06-11 2004-06-29 Eaton Corporation Apparatus for detecting the presence of an occupant in a motor vehicle
US6275231B1 (en) * 1997-08-01 2001-08-14 American Calcar Inc. Centralized control and management system for automobiles
US6124886A (en) 1997-08-25 2000-09-26 Donnelly Corporation Modular rearview mirror assembly
FR2770317B1 (en) * 1997-10-24 2000-12-08 Commissariat Energie Atomique A method for calibrating the position and orientation of the original one or more mobile cameras and its application to the three-dimensional position measurement stationary objects
US7370983B2 (en) 2000-03-02 2008-05-13 Donnelly Corporation Interior mirror assembly with display
US6326613B1 (en) 1998-01-07 2001-12-04 Donnelly Corporation Vehicle interior mirror assembly adapted for containing a rain sensor
US8288711B2 (en) 1998-01-07 2012-10-16 Donnelly Corporation Interior rearview mirror system with forwardly-viewing camera and a control
JP3516856B2 (en) * 1998-01-30 2004-04-05 富士重工業株式会社 The outside of the vehicle monitoring system
US6172613B1 (en) 1998-02-18 2001-01-09 Donnelly Corporation Rearview mirror assembly incorporating vehicle information display
US6278479B1 (en) 1998-02-24 2001-08-21 Wilson, Hewitt & Associates, Inc. Dual reality system
EP1408693A1 (en) * 1998-04-07 2004-04-14 Matsushita Electric Industrial Co., Ltd. On-vehicle image display apparatus, image transmission system, image transmission apparatus, and image capture apparatus
WO2000007373A1 (en) * 1998-07-31 2000-02-10 Matsushita Electric Industrial Co., Ltd. Method and apparatus for displaying image
EP1038734A4 (en) * 1998-10-08 2005-10-12 Matsushita Electric Ind Co Ltd Driving assisting device and recording medium
JP4114292B2 (en) * 1998-12-03 2008-07-09 アイシン・エィ・ダブリュ株式会社 Driving support system
US6445287B1 (en) 2000-02-28 2002-09-03 Donnelly Corporation Tire inflation assistance monitoring system
US6396535B1 (en) * 1999-02-16 2002-05-28 Mitsubishi Electric Research Laboratories, Inc. Situation awareness system
JP3807583B2 (en) * 1999-04-19 2006-08-09 本田技研工業株式会社 Road area determining device
JP3263931B2 (en) * 1999-09-22 2002-03-11 富士重工業株式会社 Stereo matching apparatus
JP3349121B2 (en) 1999-09-22 2002-11-20 富士重工業株式会社 Mounting structure of the stereo camera
JP3877475B2 (en) * 1999-09-22 2007-02-07 富士重工業株式会社 Mounting structure of the vehicle-mounted camera
US6411867B1 (en) 1999-10-27 2002-06-25 Fujitsu Ten Limited Vehicle driving support system, and steering angle detection device
US7167796B2 (en) 2000-03-09 2007-01-23 Donnelly Corporation Vehicle navigation system for use with a telematics system
US6329925B1 (en) 1999-11-24 2001-12-11 Donnelly Corporation Rearview mirror assembly with added feature modular display
GB2358975B (en) 2000-02-05 2004-05-05 Jaguar Cars Motor vehicle trajectory measurement
JP4233723B2 (en) * 2000-02-28 2009-03-04 本田技研工業株式会社 Obstacle detecting device, the obstacle detecting method, and a recording medium recording an obstacle detection program
US10144353B2 (en) 2002-08-21 2018-12-04 Magna Electronics Inc. Multi-camera vision system for a vehicle
AU4328501A (en) 2000-03-02 2001-09-12 Donnelly Corp Video mirror systems incorporating an accessory module
AU2002251807A1 (en) 2001-01-23 2002-08-19 Donnelly Corporation Improved vehicular lighting system for a mirror assembly
US6477464B2 (en) 2000-03-09 2002-11-05 Donnelly Corporation Complete mirror-based global-positioning system (GPS) navigation solution
US6396408B2 (en) 2000-03-31 2002-05-28 Donnelly Corporation Digital electrochromic circuit with a vehicle network
US6693517B2 (en) 2000-04-21 2004-02-17 Donnelly Corporation Vehicle mirror assembly communicating wirelessly with vehicle accessories and occupants
JP2001344597A (en) * 2000-05-30 2001-12-14 Fuji Heavy Ind Ltd Fused visual field device
US6535242B1 (en) * 2000-10-24 2003-03-18 Gary Steven Strumolo System and method for acquiring and displaying vehicular information
JP4823448B2 (en) * 2000-11-24 2011-11-24 アイシン精機株式会社 Alarm System
DE10103870B4 (en) * 2001-01-30 2004-02-05 Daimlerchrysler Ag The image recognition method in motor vehicles
DE20105340U1 (en) * 2001-03-26 2001-07-26 Daimler Chrysler Ag Dimensional environment detection
JP2002314989A (en) * 2001-04-10 2002-10-25 Yazaki Corp Peripheral monitor for vehicle
US6493620B2 (en) 2001-04-18 2002-12-10 Eaton Corporation Motor vehicle occupant detection system employing ellipse shape models and bayesian classification
JP3759429B2 (en) * 2001-05-23 2006-03-22 株式会社東芝 Obstacle detecting apparatus and method
JP4657495B2 (en) * 2001-05-29 2011-03-23 富士重工業株式会社 A vehicle driving support device
JP4802397B2 (en) * 2001-05-30 2011-10-26 コニカミノルタホールディングス株式会社 Imaging system, and the operating device
US6882287B2 (en) 2001-07-31 2005-04-19 Donnelly Corporation Automotive lane change aid
US7697027B2 (en) 2001-07-31 2010-04-13 Donnelly Corporation Vehicular video system
DE10162652A1 (en) * 2001-12-20 2003-07-03 Bosch Gmbh Robert Stereo camera arrangement in a motor vehicle
JP2003200755A (en) * 2001-12-28 2003-07-15 Yazaki Corp Displaying device for vehicle
US7038577B2 (en) 2002-05-03 2006-05-02 Donnelly Corporation Object detection system for vehicle
US6918674B2 (en) 2002-05-03 2005-07-19 Donnelly Corporation Vehicle rearview mirror system
US7329013B2 (en) 2002-06-06 2008-02-12 Donnelly Corporation Interior rearview mirror system with compass
EP1514246A4 (en) 2002-06-06 2008-04-16 Donnelly Corp Interior rearview mirror system with compass
DE10227221A1 (en) * 2002-06-18 2004-01-15 Daimlerchrysler Ag Method for monitoring the interior or exterior space of a vehicle and a vehicle with at least one surveillance camera
DE10234645B4 (en) * 2002-07-29 2004-07-22 Daimlerchrysler Ag Camera arrangement having a reflecting surface
US7255451B2 (en) 2002-09-20 2007-08-14 Donnelly Corporation Electro-optic mirror cell
US7310177B2 (en) 2002-09-20 2007-12-18 Donnelly Corporation Electro-optic reflective element assembly
EP1543358A2 (en) 2002-09-20 2005-06-22 Donnelly Corporation Mirror reflective element assembly
US8013889B1 (en) 2002-10-11 2011-09-06 Hong Brian Kwangshik Peripheral viewing system for a vehicle
TWI380080B (en) * 2003-03-07 2012-12-21 Semiconductor Energy Lab Liquid crystal display device and method for manufacturing the same
JP3879696B2 (en) * 2003-04-25 2007-02-14 日産自動車株式会社 Driving support system
DE10319700A1 (en) * 2003-05-02 2004-11-18 Ibeo Automobile Sensor Gmbh Method and apparatus for determining a probability of a collision of a vehicle with an object
US7289037B2 (en) 2003-05-19 2007-10-30 Donnelly Corporation Mirror assembly for vehicle
JP4043416B2 (en) 2003-07-30 2008-02-06 オリンパス株式会社 Safe movement support apparatus
DE10341128A1 (en) * 2003-09-06 2005-03-31 Daimlerchrysler Ag Apparatus and method for detecting an instantaneous distance of a motor vehicle from an obstacle
US7446924B2 (en) 2003-10-02 2008-11-04 Donnelly Corporation Mirror reflective element assembly including electronic component
US7308341B2 (en) 2003-10-14 2007-12-11 Donnelly Corporation Vehicle communication system
DE10351915A1 (en) * 2003-11-07 2005-06-09 Volkswagen Ag Monitoring device for a vehicle for detecting obstacles in front or behind it has a sensor device for which a monitoring surface of variable area can be defined dependent on the vehicle configuration
JP4332027B2 (en) * 2003-12-25 2009-09-16 キャタピラージャパン株式会社 Display control system
DE102004009924A1 (en) * 2004-02-23 2005-09-01 Valeo Schalter Und Sensoren Gmbh Picture processing method for motor vehicle, involves processing picture based on determination of real position of obstacle in vicinity of vehicle and determination of position from picture provided by camera device
US7526103B2 (en) 2004-04-15 2009-04-28 Donnelly Corporation Imaging system for vehicle
DE102004029985B4 (en) * 2004-06-21 2017-08-31 Harman Becker Automotive Systems Gmbh Method and apparatus for outputting a Anfahrsignals
US20050283062A1 (en) * 2004-06-22 2005-12-22 Cerner Innovation, Inc. Computerized method and system for associating a portion of a diagnostic image with an electronic record
JP4488804B2 (en) * 2004-06-23 2010-06-23 株式会社トプコン Stereo image association method and 3-dimensional data generation device
DE102004040558A1 (en) * 2004-08-21 2006-02-23 A.D.C. Automotive Distance Control Systems Gmbh An optical object detection system
US20060061008A1 (en) 2004-09-14 2006-03-23 Lee Karner Mounting assembly for vehicle interior mirror
US7881496B2 (en) 2004-09-30 2011-02-01 Donnelly Corporation Vision system for vehicle
US7639841B2 (en) * 2004-12-20 2009-12-29 Siemens Corporation System and method for on-road detection of a vehicle using knowledge fusion
US7720580B2 (en) 2004-12-23 2010-05-18 Donnelly Corporation Object detection system for vehicle
KR100630088B1 (en) * 2004-12-28 2006-09-27 삼성전자주식회사 Apparatus and method for supervising vehicle using optical flow
JP4693561B2 (en) * 2005-02-02 2011-06-01 住友電気工業株式会社 Vehicle environment monitoring device
JP4020128B2 (en) * 2005-04-22 2007-12-12 トヨタ自動車株式会社 Target position setting device and a parking assist device having the same
US7626749B2 (en) 2005-05-16 2009-12-01 Donnelly Corporation Vehicle mirror assembly with indicia at reflective element
JP4640011B2 (en) * 2005-07-19 2011-03-02 株式会社セガ The image processing apparatus, a distant view image display method, and a distant view image display program
JPWO2007015288A1 (en) * 2005-08-01 2009-02-12 三菱電機株式会社 Axial misalignment estimation method and the axial shift amount estimate device
US7581859B2 (en) 2005-09-14 2009-09-01 Donnelly Corp. Display device for exterior rearview mirror
JP4882324B2 (en) * 2005-09-20 2012-02-22 トヨタ自動車株式会社 The image processing apparatus for a vehicle
WO2007053710A2 (en) 2005-11-01 2007-05-10 Donnelly Corporation Interior rearview mirror with display
FR2893173B1 (en) * 2005-11-10 2008-01-18 Valeo Vision Sa Method for evaluation by a motor vehicle, the characteristics of a front element.
JP2007142765A (en) * 2005-11-17 2007-06-07 Auto Network Gijutsu Kenkyusho:Kk Vehicle periphery monitoring system
US20070150138A1 (en) 2005-12-08 2007-06-28 James Plante Memory management in event recording systems
US20070136078A1 (en) 2005-12-08 2007-06-14 Smartdrive Systems Inc. Vehicle event recorder systems
JP5058491B2 (en) * 2006-02-09 2012-10-24 日産自動車株式会社 Display apparatus and a video display control method for a vehicle for a vehicle
US9201842B2 (en) 2006-03-16 2015-12-01 Smartdrive Systems, Inc. Vehicle event recorder systems and networks having integrated cellular wireless communications systems
US8996240B2 (en) 2006-03-16 2015-03-31 Smartdrive Systems, Inc. Vehicle event recorders with integrated web server
JP4632987B2 (en) * 2006-03-28 2011-02-23 株式会社パスコ Road image analyzing apparatus and a road image analyzing method
US20070233361A1 (en) * 2006-03-30 2007-10-04 Ford Global Technologies, Llc Centralized Image Processing For An Automobile With A Navigation System
US7804426B2 (en) * 2006-05-08 2010-09-28 Drivecam, Inc. System and method for selective review of event data
US8373567B2 (en) * 2006-05-08 2013-02-12 Drivecam, Inc. System and method for identifying non-event profiles
US7659827B2 (en) * 2006-05-08 2010-02-09 Drivecam, Inc. System and method for taking risk out of driving
US7536457B2 (en) * 2006-05-08 2009-05-19 Drivecam, Inc. System and method for wireless delivery of event data
US8314708B2 (en) * 2006-05-08 2012-11-20 Drivecam, Inc. System and method for reducing driving risk with foresight
US20070257782A1 (en) * 2006-05-08 2007-11-08 Drivecam, Inc. System and Method for Multi-Event Capture
US9836716B2 (en) * 2006-05-09 2017-12-05 Lytx, Inc. System and method for reducing driving risk with hindsight
US20070268158A1 (en) * 2006-05-09 2007-11-22 Drivecam, Inc. System and Method for Reducing Driving Risk With Insight
US7972045B2 (en) 2006-08-11 2011-07-05 Donnelly Corporation Automatic headlamp control system
US20080043736A1 (en) * 2006-08-18 2008-02-21 Drivecam, Inc. Data Transfer System and Method
EP1892688B1 (en) * 2006-08-24 2010-09-01 Valeo Vision Method for determining the passing of a vehicle in a bottleneck
US8989959B2 (en) 2006-11-07 2015-03-24 Smartdrive Systems, Inc. Vehicle operator performance history recording, scoring and reporting systems
US8649933B2 (en) 2006-11-07 2014-02-11 Smartdrive Systems Inc. Power management systems for automotive video event recorders
US8868288B2 (en) 2006-11-09 2014-10-21 Smartdrive Systems, Inc. Vehicle exception event management systems
EP2110797B1 (en) * 2006-12-05 2015-10-07 Fujitsu Limited Traffic situation display method, traffic situation display system, vehicle-mounted device, and computer program
US8199975B2 (en) * 2006-12-12 2012-06-12 Cognex Corporation System and method for side vision detection of obstacles for vehicles
DE102006062061B4 (en) * 2006-12-29 2010-06-10 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. The device, method and computer program for determining a position based on a camera image from a camera
WO2008127752A2 (en) 2007-01-25 2008-10-23 Magna Electronics Radar sensing system for vehicle
JP2008225785A (en) * 2007-03-12 2008-09-25 Toyota Motor Corp Image recognition device
WO2008139530A1 (en) * 2007-04-27 2008-11-20 Honda Motor Co., Ltd. Vehicle periphery monitoring device, vehicle periphery monitoring program, and vehicle periphery monitoring method
US8239092B2 (en) 2007-05-08 2012-08-07 Smartdrive Systems Inc. Distributed vehicle event recorder systems having a portable memory data transfer system
DE102007027756A1 (en) * 2007-06-16 2008-12-18 Bayerische Motoren Werke Aktiengesellschaft A method for assisting a driver of a motor vehicle during the passage of the motor vehicle through a constriction and / or to keep a safety distance to the front vehicle
US7914187B2 (en) 2007-07-12 2011-03-29 Magna Electronics Inc. Automatic lighting system with adaptive alignment function
US8017898B2 (en) 2007-08-17 2011-09-13 Magna Electronics Inc. Vehicular imaging system in an automatic headlamp control system
EP2191457B1 (en) 2007-09-11 2014-12-10 Magna Electronics Imaging system for vehicle
EP2037408B1 (en) 2007-09-14 2012-03-28 Saab Ab Method, computer program and device for determining the risk of midair collision
US8446470B2 (en) 2007-10-04 2013-05-21 Magna Electronics, Inc. Combined RGB and IR imaging sensor
DE102008061749A1 (en) * 2007-12-17 2009-06-25 Continental Teves Ag & Co. Ohg Method and apparatus for optically detecting a vehicle environment
JP2009239390A (en) * 2008-03-26 2009-10-15 Fujifilm Corp Compound eye photographing apparatus, control method therefor, and program
US8154418B2 (en) 2008-03-31 2012-04-10 Magna Mirrors Of America, Inc. Interior rearview mirror system
DE102008001409A1 (en) * 2008-04-28 2009-11-05 Robert Bosch Gmbh A method for the determination of free areas in the, in particular for vehicle guidance relevant environment of a motor vehicle
JP4377439B1 (en) * 2008-06-12 2009-12-02 本田技研工業株式会社 Vehicle environment monitoring device
US20100020170A1 (en) 2008-07-24 2010-01-28 Higgins-Luthman Michael J Vehicle Imaging System
US20100076710A1 (en) * 2008-09-19 2010-03-25 Caterpillar Inc. Machine sensor calibration system
US9487144B2 (en) 2008-10-16 2016-11-08 Magna Mirrors Of America, Inc. Interior mirror assembly with display
WO2010099416A1 (en) 2009-02-27 2010-09-02 Magna Electronics Alert system for vehicle
TWI398372B (en) * 2009-03-11 2013-06-11 Lane departure warning system/device, ldws
US8376595B2 (en) 2009-05-15 2013-02-19 Magna Electronics, Inc. Automatic headlamp control
JP4858574B2 (en) * 2009-05-19 2012-01-18 トヨタ自動車株式会社 Object detecting device
JP5440903B2 (en) * 2009-05-20 2014-03-12 株式会社リコー The imaging device and the stereo camera apparatus and a vehicle surroundings monitoring apparatus
US9495876B2 (en) 2009-07-27 2016-11-15 Magna Electronics Inc. Vehicular camera with on-board microcontroller
KR101735134B1 (en) 2009-07-27 2017-05-24 마그나 일렉트로닉스 인크. Parking assist system
EP2473871B1 (en) 2009-09-01 2015-03-11 Magna Mirrors Of America, Inc. Imaging and display system for vehicle
US20110169957A1 (en) * 2010-01-14 2011-07-14 Ford Global Technologies, Llc Vehicle Image Processing Method
US8890955B2 (en) 2010-02-10 2014-11-18 Magna Mirrors Of America, Inc. Adaptable wireless vehicle vision system based on wireless communication error
US9117123B2 (en) 2010-07-05 2015-08-25 Magna Electronics Inc. Vehicular rear view camera display system with lifecheck function
DE102010040803A1 (en) * 2010-09-15 2012-03-15 Continental Teves Ag & Co. Ohg Visual driver information and warning system for a driver of a motor vehicle
JP5690539B2 (en) 2010-09-28 2015-03-25 株式会社トプコン Automatic takeoff and landing system
WO2012068331A1 (en) 2010-11-19 2012-05-24 Magna Electronics Inc. Lane keeping system and lane centering system
US9900522B2 (en) 2010-12-01 2018-02-20 Magna Electronics Inc. System and method of establishing a multi-camera image using pixel remapping
US9264672B2 (en) 2010-12-22 2016-02-16 Magna Mirrors Of America, Inc. Vision display system for vehicle
JP5618840B2 (en) 2011-01-04 2014-11-05 株式会社トプコン Aircraft flight control system of
DE102011002577A1 (en) 2011-01-12 2012-07-12 3Vi Gmbh Remote control device for controlling a device based on a mobile object, and interface module for communication between modules of such a remote control device, or between one of the modules and an external device
WO2012103193A1 (en) 2011-01-26 2012-08-02 Magna Electronics Inc. Rear vision system with trailer angle detection
US9194943B2 (en) 2011-04-12 2015-11-24 Magna Electronics Inc. Step filter for estimating distance in a time-of-flight ranging system
US9357208B2 (en) 2011-04-25 2016-05-31 Magna Electronics Inc. Method and system for dynamically calibrating vehicular cameras
WO2012145822A1 (en) 2011-04-25 2012-11-01 Magna International Inc. Method and system for dynamically calibrating vehicular cameras
WO2012145819A1 (en) 2011-04-25 2012-11-01 Magna International Inc. Image processing method for detecting objects using relative motion
JP5775354B2 (en) 2011-04-28 2015-09-09 株式会社トプコン Take-off and landing target device and automatic takeoff and landing system
JP5276140B2 (en) * 2011-05-19 2013-08-28 富士重工業株式会社 Environment recognition device and an environment recognition method
CN103635240B (en) 2011-07-01 2015-12-16 英派尔科技开发有限公司 The game based on the security posture of
US9491450B2 (en) 2011-08-01 2016-11-08 Magna Electronic Inc. Vehicle camera alignment system
DE102011080702B3 (en) * 2011-08-09 2012-12-13 3Vi Gmbh Object detecting apparatus for a vehicle, the vehicle having such a object detection apparatus
US9390318B2 (en) 2011-08-31 2016-07-12 Empire Technology Development Llc Position-setup for gesture-based game system
DE102011113077A1 (en) * 2011-09-07 2013-03-07 Conti Temic Microelectronic Gmbh A method for determining a through drivability of an object for a vehicle by means of a 3D camera
DE102011082475A1 (en) * 2011-09-12 2013-03-14 Robert Bosch Gmbh Driver assistance system for assisting a driver in collision-relevant situations
US20140218535A1 (en) 2011-09-21 2014-08-07 Magna Electronics Inc. Vehicle vision system using image data transmission and power supply via a coaxial cable
US9681062B2 (en) 2011-09-26 2017-06-13 Magna Electronics Inc. Vehicle camera image quality improvement in poor visibility conditions by contrast amplification
JP5787695B2 (en) 2011-09-28 2015-09-30 株式会社トプコン Image acquisition device
US9146898B2 (en) 2011-10-27 2015-09-29 Magna Electronics Inc. Driver assist system with algorithm switching
WO2013074604A2 (en) 2011-11-15 2013-05-23 Magna Electronics, Inc. Calibration system and method for vehicular surround vision system
TWI438729B (en) 2011-11-16 2014-05-21 Ind Tech Res Inst Method and system for lane departure warning
US10071687B2 (en) 2011-11-28 2018-09-11 Magna Electronics Inc. Vision system for vehicle
WO2013086249A2 (en) 2011-12-09 2013-06-13 Magna Electronics, Inc. Vehicle vision system with customized display
KR101438876B1 (en) * 2011-12-22 2014-09-05 현대자동차주식회사 Safety device and method for driving narrow road of vehicle
US9269263B2 (en) * 2012-02-24 2016-02-23 Magna Electronics Inc. Vehicle top clearance alert system
JP5807130B2 (en) * 2012-02-24 2015-11-10 エンパイア テクノロジー ディベロップメント エルエルシー Safe method for gesture-based game system
JP5982134B2 (en) * 2012-02-29 2016-08-31 富士通テン株式会社 Radar apparatus, and signal processing method
US8694224B2 (en) 2012-03-01 2014-04-08 Magna Electronics Inc. Vehicle yaw rate correction
JP6182866B2 (en) 2012-03-21 2017-08-23 株式会社リコー Calibration apparatus, the distance measuring apparatus and the vehicle
US9751465B2 (en) 2012-04-16 2017-09-05 Magna Electronics Inc. Vehicle vision system with reduced image color data processing by use of dithering
US10089537B2 (en) 2012-05-18 2018-10-02 Magna Electronics Inc. Vehicle vision system with front and rear camera integration
DE102012012501A1 (en) * 2012-06-21 2013-12-24 Volkswagen Aktiengesellschaft Camera system for a motor vehicle
EP2879113B1 (en) * 2012-07-27 2018-05-30 Nissan Motor Co., Ltd Three-dimensional object detection device, three-dimensional object detection method
MX341888B (en) * 2012-07-27 2016-09-07 Nissan Motor Three-dimensional object detection device.
US9728228B2 (en) 2012-08-10 2017-08-08 Smartdrive Systems, Inc. Vehicle event playback apparatus and methods
US9340227B2 (en) 2012-08-14 2016-05-17 Magna Electronics Inc. Vehicle lane keep assist system
DE102013217430A1 (en) 2012-09-04 2014-03-06 Magna Electronics, Inc. Driver assistance system for a motor vehicle
US9446713B2 (en) 2012-09-26 2016-09-20 Magna Electronics Inc. Trailer angle detection system
US9558409B2 (en) 2012-09-26 2017-01-31 Magna Electronics Inc. Vehicle vision system with trailer angle detection
US9723272B2 (en) 2012-10-05 2017-08-01 Magna Electronics Inc. Multi-camera image stitching calibration system
US9090234B2 (en) 2012-11-19 2015-07-28 Magna Electronics Inc. Braking control system for vehicle
US9743002B2 (en) 2012-11-19 2017-08-22 Magna Electronics Inc. Vehicle vision system with enhanced display functions
US10025994B2 (en) 2012-12-04 2018-07-17 Magna Electronics Inc. Vehicle vision system utilizing corner detection
US9481301B2 (en) 2012-12-05 2016-11-01 Magna Electronics Inc. Vehicle vision system utilizing camera synchronization
DE102012112164A1 (en) * 2012-12-12 2014-06-12 Continental Teves Ag & Co. Ohg Video-based detection of obstacles on a roadway
US9092986B2 (en) 2013-02-04 2015-07-28 Magna Electronics Inc. Vehicular vision system
US9667947B2 (en) * 2013-02-25 2017-05-30 The United States of America represented by the Secretary of the Air Force Stereoscopic 3-D presentation for air traffic control digital radar displays
US10179543B2 (en) 2013-02-27 2019-01-15 Magna Electronics Inc. Multi-camera dynamic top view vision system
US9688200B2 (en) 2013-03-04 2017-06-27 Magna Electronics Inc. Calibration system and method for multi-camera vision system
US10027930B2 (en) 2013-03-29 2018-07-17 Magna Electronics Inc. Spectral filtering for vehicular driver assistance systems
US9327693B2 (en) 2013-04-10 2016-05-03 Magna Electronics Inc. Rear collision avoidance system for vehicle
US10232797B2 (en) 2013-04-29 2019-03-19 Magna Electronics Inc. Rear vision system for vehicle with dual purpose signal lines
US9508014B2 (en) 2013-05-06 2016-11-29 Magna Electronics Inc. Vehicular multi-camera vision system
US9280202B2 (en) * 2013-05-10 2016-03-08 Magna Electronics Inc. Vehicle vision system
US9563951B2 (en) 2013-05-21 2017-02-07 Magna Electronics Inc. Vehicle vision system with targetless camera calibration
US9205776B2 (en) 2013-05-21 2015-12-08 Magna Electronics Inc. Vehicle vision system using kinematic model of vehicle motion
US9260095B2 (en) 2013-06-19 2016-02-16 Magna Electronics Inc. Vehicle vision system with collision mitigation
US20140375476A1 (en) 2013-06-24 2014-12-25 Magna Electronics Inc. Vehicle alert system
US9619716B2 (en) 2013-08-12 2017-04-11 Magna Electronics Inc. Vehicle vision system with image classification
JP2015060053A (en) * 2013-09-18 2015-03-30 株式会社東芝 Solid-state imaging device, control device, and control program
US9501878B2 (en) 2013-10-16 2016-11-22 Smartdrive Systems, Inc. Vehicle event playback apparatus and methods
US9610955B2 (en) 2013-11-11 2017-04-04 Smartdrive Systems, Inc. Vehicle fuel consumption monitor and feedback systems
JP6429466B2 (en) * 2013-11-19 2018-11-28 キヤノン株式会社 Image processing apparatus and control method thereof, an imaging apparatus, a program
US9499139B2 (en) 2013-12-05 2016-11-22 Magna Electronics Inc. Vehicle monitoring system
US9988047B2 (en) 2013-12-12 2018-06-05 Magna Electronics Inc. Vehicle control system with traffic driving control
US10160382B2 (en) 2014-02-04 2018-12-25 Magna Electronics Inc. Trailer backup assist system
US8892310B1 (en) 2014-02-21 2014-11-18 Smartdrive Systems, Inc. System and method to detect execution of driving maneuvers
US9623878B2 (en) 2014-04-02 2017-04-18 Magna Electronics Inc. Personalized driver assistance system for vehicle
US9487235B2 (en) 2014-04-10 2016-11-08 Magna Electronics Inc. Vehicle control system with adaptive wheel angle correction
JP2016019009A (en) * 2014-07-04 2016-02-01 日立オートモティブシステムズ株式会社 Information processing apparatus
US9663127B2 (en) 2014-10-28 2017-05-30 Smartdrive Systems, Inc. Rail vehicle event detection and recording system
DE102014222900A1 (en) 2014-11-10 2016-05-12 Bombardier Transportation Gmbh Operating a rail vehicle with an image forming system
US9916660B2 (en) 2015-01-16 2018-03-13 Magna Electronics Inc. Vehicle vision system with calibration algorithm
EP3315999A4 (en) * 2015-06-24 2018-06-20 Konica Minolta, Inc. Distance image processing device, distance image processing method, distance image processing program, and recording medium
US10214206B2 (en) 2015-07-13 2019-02-26 Magna Electronics Inc. Parking assist system for vehicle
US10078789B2 (en) 2015-07-17 2018-09-18 Magna Electronics Inc. Vehicle parking assist system with vision-based parking space detection
US10086870B2 (en) 2015-08-18 2018-10-02 Magna Electronics Inc. Trailer parking assist system for vehicle
JP2017058189A (en) * 2015-09-15 2017-03-23 株式会社デンソーアイティーラボラトリ Object detection device, object detection system, object detection method, and object detection program
US10160437B2 (en) 2016-02-29 2018-12-25 Magna Electronics Inc. Vehicle control system with reverse assist
US10132971B2 (en) 2016-03-04 2018-11-20 Magna Electronics Inc. Vehicle camera with multiple spectral filters
US10055651B2 (en) 2016-03-08 2018-08-21 Magna Electronics Inc. Vehicle vision system with enhanced lane tracking
CN107180067A (en) * 2016-03-11 2017-09-19 松下电器(美国)知识产权公司 Image processing method, image processing apparatus, and program
US10242575B1 (en) * 2017-12-05 2019-03-26 Industrial Technology Research Institute Marked parking space identification system and method thereof

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4257703A (en) * 1979-03-15 1981-03-24 The Bendix Corporation Collision avoidance using optical pattern growth rate
US4851901A (en) * 1986-09-03 1989-07-25 Kabushiki Kaisha Toshiba Stereoscopic television apparatus
US4942539A (en) * 1988-12-21 1990-07-17 Gmf Robotics Corporation Method and system for automatically determining the position and orientation of an object in 3-D space
US5283640A (en) * 1992-01-31 1994-02-01 Tilton Homer B Three dimensional television camera system based on a spatial depth signal and receiver system therefor
US5304980A (en) * 1991-01-24 1994-04-19 Mitsubishi Denki Kabushiki Kaisha Distance detecting apparatus for a vehicle
US5307136A (en) * 1991-10-22 1994-04-26 Fuji Jukogyo Kabushiki Kaisha Distance detection system for vehicles
US5410346A (en) * 1992-03-23 1995-04-25 Fuji Jukogyo Kabushiki Kaisha System for monitoring condition outside vehicle using imaged picture by a plurality of television cameras
US5461357A (en) * 1992-01-29 1995-10-24 Mazda Motor Corporation Obstacle detection device for vehicle

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS616349B2 (en) * 1979-01-19 1986-02-25 Nissan Motor
US4601053A (en) * 1983-11-21 1986-07-15 Grumman Aerospace Corporation Automatic TV ranging system
US4916302A (en) * 1985-02-09 1990-04-10 Canon Kabushiki Kaisha Apparatus for and method of measuring distances to objects present in a plurality of directions
EP0530307B1 (en) * 1990-04-11 1998-07-08 Auto-Sense, Ltd. Method of determining optimal detection beam locations using reflective feature mapping
JPH0690760B2 (en) * 1991-01-23 1994-11-14 株式会社カンセイ Preceding vehicle position detection device
JPH05265537A (en) * 1991-04-03 1993-10-15 Hitachi Metals Ltd Automatic teaching method for robot
JPH072314Y2 (en) * 1992-02-28 1995-01-25 株式会社ヨシコー Corner pole for automobiles

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4257703A (en) * 1979-03-15 1981-03-24 The Bendix Corporation Collision avoidance using optical pattern growth rate
US4851901A (en) * 1986-09-03 1989-07-25 Kabushiki Kaisha Toshiba Stereoscopic television apparatus
US4942539A (en) * 1988-12-21 1990-07-17 Gmf Robotics Corporation Method and system for automatically determining the position and orientation of an object in 3-D space
US5304980A (en) * 1991-01-24 1994-04-19 Mitsubishi Denki Kabushiki Kaisha Distance detecting apparatus for a vehicle
US5307136A (en) * 1991-10-22 1994-04-26 Fuji Jukogyo Kabushiki Kaisha Distance detection system for vehicles
US5461357A (en) * 1992-01-29 1995-10-24 Mazda Motor Corporation Obstacle detection device for vehicle
US5283640A (en) * 1992-01-31 1994-02-01 Tilton Homer B Three dimensional television camera system based on a spatial depth signal and receiver system therefor
US5410346A (en) * 1992-03-23 1995-04-25 Fuji Jukogyo Kabushiki Kaisha System for monitoring condition outside vehicle using imaged picture by a plurality of television cameras

Cited By (61)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6731332B1 (en) * 1998-01-29 2004-05-04 Matsushita Electric Industrial Co., Ltd. Image processing apparatus
US6477260B1 (en) * 1998-11-02 2002-11-05 Nissan Motor Co., Ltd. Position measuring apparatus using a pair of electronic cameras
US20040022417A1 (en) * 1999-05-27 2004-02-05 Honda Giken Kogyo Kabushiki Kaisha Object detection system
US6987864B2 (en) 1999-05-27 2006-01-17 Honda Giken Kogyo Kabushiki Kaisha Object detection system
US6683969B1 (en) * 1999-05-27 2004-01-27 Honda Giken Kogyo Kabushiki Kaisha Object detection system
US6853738B1 (en) * 1999-06-16 2005-02-08 Honda Giken Kogyo Kabushiki Kaisha Optical object recognition system
US7640107B2 (en) * 1999-06-25 2009-12-29 Fujitsu Ten Limited Vehicle drive assist system
US20060287825A1 (en) * 1999-06-25 2006-12-21 Fujitsu Ten Limited Vehicle drive assist system
US20050248503A1 (en) * 2002-08-19 2005-11-10 Koninklijke Phillips Electronics N.V. Display system for displaying images within a vehicle
US7365707B2 (en) * 2002-08-19 2008-04-29 Koninklijke Philips Electronics N.V. Display system for displaying images within a vehicle
US6795014B2 (en) * 2002-10-28 2004-09-21 Hyundai Motor Company Method and apparatus for detecting vehicle distance
US20040080450A1 (en) * 2002-10-28 2004-04-29 Hyuck-Jin Cheong Method and apparatus for detecting vehicle distance
US20040207515A1 (en) * 2003-04-21 2004-10-21 Chung Eui Yoon Method of controlling a distance between vehicles, and an apparatus thereof
US20050012603A1 (en) * 2003-05-08 2005-01-20 Frank Ewerhart Device for determining the passability of a vehicle
US7259660B2 (en) * 2003-05-08 2007-08-21 Robert Bosch Gmbh Device for determining the passability of a vehicle
US20070232448A1 (en) * 2003-10-25 2007-10-04 Daimler Chrysler Ag Method and Device for Controlling Distance
US20050102070A1 (en) * 2003-11-11 2005-05-12 Nissan Motor Co., Ltd. Vehicle image processing device
US7542835B2 (en) * 2003-11-11 2009-06-02 Nissan Motor Co., Ltd. Vehicle image processing device
US7226173B2 (en) * 2004-02-13 2007-06-05 Nec Viewtechnology, Ltd. Projector with a plurality of cameras
US20050179875A1 (en) * 2004-02-13 2005-08-18 Nec Viewtechnology, Ltd. Projector with a plurality of cameras
US20090010495A1 (en) * 2004-07-26 2009-01-08 Automotive Systems Laboratory, Inc. Vulnerable Road User Protection System
US8594370B2 (en) * 2004-07-26 2013-11-26 Automotive Systems Laboratory, Inc. Vulnerable road user protection system
US9330321B2 (en) 2004-07-26 2016-05-03 Tk Holdings, Inc. Method of processing an image of a visual scene
US7394356B2 (en) * 2004-10-27 2008-07-01 Denso Corporation Information presenting apparatus and method
US20060097858A1 (en) * 2004-10-27 2006-05-11 Denso Corporation Information presenting apparatus and method
US20080010018A1 (en) * 2005-01-12 2008-01-10 Toyota Jidosha Kabushiki Kaisha Parking support device
US7739046B2 (en) * 2005-01-12 2010-06-15 Toyota Jidosha Kabushiki Kaisha Parking support device
US20070088469A1 (en) * 2005-10-04 2007-04-19 Oshkosh Truck Corporation Vehicle control system and method
US8947531B2 (en) 2006-06-19 2015-02-03 Oshkosh Corporation Vehicle diagnostics based on information communicated between vehicles
US8139109B2 (en) 2006-06-19 2012-03-20 Oshkosh Corporation Vision system for an autonomous vehicle
WO2008073518A3 (en) * 2006-06-19 2008-08-14 Alberto Broggi Vision system for an autonomous vehicle
WO2008073518A2 (en) * 2006-06-19 2008-06-19 Oshkosh Corporation Vision system for an autonomous vehicle
US20070291130A1 (en) * 2006-06-19 2007-12-20 Oshkosh Truck Corporation Vision system for an autonomous vehicle
US9420203B2 (en) 2006-06-19 2016-08-16 Oshkosh Defense, Llc Vision system for a vehicle
US20080181461A1 (en) * 2007-01-31 2008-07-31 Toru Saito Monitoring System
US8055017B2 (en) * 2007-01-31 2011-11-08 Fuji Jukogyo Kabushiki Kaisha Headlamp monitoring apparatus for image exposure adjustment
US20100060735A1 (en) * 2007-02-23 2010-03-11 Koji Sato Device and method of monitoring surroundings of a vehicle
US8525728B2 (en) * 2008-06-25 2013-09-03 Autoliv Development Ab Method of detecting object in the vicinity of a vehicle
US20110098892A1 (en) * 2008-06-25 2011-04-28 Astrid Lundmark Method of detecting object in the vicinity of a vehicle
US20100208060A1 (en) * 2009-02-16 2010-08-19 Masanori Kobayashi Liquid droplet recognition apparatus, raindrop recognition apparatus, and on-vehicle monitoring apparatus
US8466960B2 (en) * 2009-02-16 2013-06-18 Ricoh Company, Ltd. Liquid droplet recognition apparatus, raindrop recognition apparatus, and on-vehicle monitoring apparatus
US20100253784A1 (en) * 2009-04-06 2010-10-07 Samsung Electro-Mechanics Co., Ltd. Calibration method and apparatus for automotive camera system, and method and ecu for determining angular misalignments of automotive camera system
US8284988B2 (en) 2009-05-13 2012-10-09 Applied Vision Corporation System and method for dimensioning objects using stereoscopic imaging
US20110188741A1 (en) * 2009-05-13 2011-08-04 Applied Vision Corporation System and method for dimensioning objects using stereoscopic imaging
US20100290665A1 (en) * 2009-05-13 2010-11-18 Applied Vision Company, Llc System and method for dimensioning objects using stereoscopic imaging
US8781159B2 (en) * 2009-05-13 2014-07-15 Applied Vision Corporation System and method for dimensioning objects using stereoscopic imaging
US20110193953A1 (en) * 2010-02-05 2011-08-11 Applied Vision Company, Llc System and method for estimating the height of an object using tomosynthesis-like techniques
US8508591B2 (en) 2010-02-05 2013-08-13 Applied Vision Corporation System and method for estimating the height of an object using tomosynthesis-like techniques
US9114719B1 (en) 2010-06-02 2015-08-25 Bryan Marc Failing Increasing vehicle security
US8725330B2 (en) 2010-06-02 2014-05-13 Bryan Marc Failing Increasing vehicle security
US9393878B1 (en) 2010-06-02 2016-07-19 Bryan Marc Failing Energy transfer with vehicles
US8841881B2 (en) 2010-06-02 2014-09-23 Bryan Marc Failing Energy transfer with vehicles
US10124691B1 (en) 2010-06-02 2018-11-13 Bryan Marc Failing Energy transfer with vehicles
US8459619B2 (en) 2010-10-24 2013-06-11 Oshkosh Corporation Gas spring control system and method
WO2012084277A1 (en) * 2010-12-22 2012-06-28 Thomson Licensing Apparatus and method for determining a disparity estimate
US9591281B2 (en) 2010-12-22 2017-03-07 Thomson Licensing Apparatus and method for determining a disparity estimate
US20130147983A1 (en) * 2011-12-09 2013-06-13 Sl Corporation Apparatus and method for providing location information
US8824733B2 (en) 2012-03-26 2014-09-02 Tk Holdings Inc. Range-cued object segmentation system and method
US8768007B2 (en) 2012-03-26 2014-07-01 Tk Holdings Inc. Method of filtering an image
US9349058B2 (en) 2012-10-31 2016-05-24 Tk Holdings, Inc. Vehicular path sensing system and method
US10083361B2 (en) 2013-03-15 2018-09-25 Joyson Safety Systems Acquisition Llc Path sensing using structured lighting

Also Published As

Publication number Publication date
JP3522317B2 (en) 2004-04-26
GB9426131D0 (en) 1995-02-22
GB2285719A (en) 1995-07-19
GB2285719B (en) 1998-07-01
JPH07192199A (en) 1995-07-28
DE4446452A1 (en) 1995-06-29
DE4446452B4 (en) 2006-11-16
US5530420A (en) 1996-06-25

Similar Documents

Publication Publication Date Title
US7176959B2 (en) Vehicle surroundings display device and image providing system
US7349582B2 (en) System and method for detecting obstacle
US5757287A (en) Object recognition system and abnormality detection system using image processing
US6122597A (en) Vehicle monitoring apparatus
JP2667924B2 (en) Aircraft docking guidance system
US6801244B2 (en) Obstacle detection apparatus and method
Vaudrey et al. Differences between stereo and motion behaviour on synthetic and real-world stereo sequences
US6546115B1 (en) Method of updating reference background image, method of detecting entering objects and system for detecting entering objects using the methods
US7151996B2 (en) System and method for generating a model of the path of a roadway from an image recorded by a camera
US6370261B1 (en) Vehicle surroundings monitoring apparatus
EP1780675B1 (en) Object detector
Zielke et al. Intensity and edge-based symmetry detection with an application to car-following
EP0686942A2 (en) Stereo matching method and disparity measuring method
EP0488828A2 (en) Control device of an autonomously moving body and evaluation method for data thereof
JP2570315B2 (en) Car on the distance detection device
CN1080911C (en) Object observing method and device
EP0738872B1 (en) Stereo matching method and disparity measuring method
US8340896B2 (en) Road shape recognition device
US7046822B1 (en) Method of detecting objects within a wide range of a road vehicle
US6172601B1 (en) Three-dimensional scope system with a single camera for vehicles
US6658150B2 (en) Image recognition system
US20090121899A1 (en) Parking assistance device
US20100246901A1 (en) Operation Support System, Vehicle, And Method For Estimating Three-Dimensional Object Area
US5475494A (en) Driving environment surveillance apparatus
US20030137593A1 (en) Infrared image-processing apparatus

Legal Events

Date Code Title Description
FPAY Fee payment

Year of fee payment: 8

FPAY Fee payment

Year of fee payment: 12

AS Assignment

Owner name: FUJI JUKOGYO KABUSHIKI KAISHA, JAPAN

Free format text: CHANGE OF ADDRESS;ASSIGNOR:FUJI JUKOGYO KABUSHIKI KAISHA;REEL/FRAME:033989/0220

Effective date: 20140818