JP2012208877A - Vehicle information acquisition device, vehicle information acquisition method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a vehicle information acquisition device, a vehicle information acquisition method and a program for highly accurately acquiring the self-vehicle position information of a vehicle, and for reducing a processing load.SOLUTION: A vehicle information acquisition device includes: imaging means for imaging the back part of a self-vehicle; acquisition means for acquiring the traveling azimuth and speed of the self-vehicle; extraction means for extracting a feature point from an image picked up by the imaging means; determination means for calculating the estimated position of the feature point in the image picked up by the imaging means on the basis of the traveling azimuth and speed, and for determining whether or not the feature point has been imaged at the estimated position in the image picked up after its image pickup by the imaging means; and self-vehicle position information acquisition means for, when it is determined that the feature point has not been imaged at the estimated position, acquiring the self-vehicle position information on the basis of the moving position and shape of the feature point in the image picked up by the imaging means and the image picked up after its image pickup by the imaging means.

Description

  The present invention relates to a vehicle information acquisition apparatus, a vehicle information acquisition method, and a program for acquiring own vehicle position information of a vehicle.

Conventionally, various techniques for acquiring vehicle position information of a vehicle have been proposed.
For example, based on outputs from a GPS receiver, an orientation sensor, and a distance sensor, information on the current position of the host vehicle (hereinafter referred to as “own vehicle position”) expressed in latitude and longitude, and the traveling direction of the host vehicle The vehicle position information including the information is acquired.

  Then, using the back camera that captures the road surface behind the host vehicle, the character string “rare” among the character signs “to rare” provided on the road surface in front of the stop line that is obliged to pause is displayed. When the image is recognized, the image recognition for the stop line is started. And when it determines with a stop line being included in image information, it determines with the position of the said stop line being a point with the obligation of temporary stop, and memorize | stores the own vehicle position information of this point as stop obligation point information There is an image recognition device configured as described above (see, for example, Patent Document 1).

JP 2009-99125 A

  In the image recognition apparatus described in Patent Document 1 described above, when it is determined that the position of the stop line that has been image-recognized based on the image information captured by the back camera is a point that is obliged to temporarily stop, The own vehicle position information is stored as stop duty point information.

  However, since the own vehicle position information acquired based on the output from the GPS receiver, the direction sensor, the distance sensor, etc. causes an accumulated error of the sensor output value due to a sudden handle, wheel slip, etc., the own vehicle position It is difficult to improve the accuracy of information. In addition, if a feature point in an image captured by a back camera at an interval of 10 msec to 50 msec is continuously recognized and the vehicle position information is acquired based on the movement position and shape of the feature point in the image, the processing load increases. Real-time processing is difficult.

  Accordingly, the present invention has been made to solve the above-described problems, and is a vehicle information acquisition device that can acquire the vehicle position information of the vehicle with high accuracy and reduce the processing load. An object of the present invention is to provide a vehicle information acquisition method and program.

  In order to achieve the above object, a vehicle information acquisition apparatus according to claim 1 includes an imaging unit that captures the rear of the host vehicle, an acquisition unit that acquires a traveling direction and a speed of the host vehicle, and an image captured by the imaging unit. After extracting the feature point from the image, the estimated position of the feature point in the image captured by the imaging unit is calculated based on the traveling direction and speed, and the feature point is captured by the imaging unit Based on the advancing azimuth and speed when it is determined that the determination unit determines whether or not the estimated position in the captured image is captured at the estimated position and that the feature point is captured at the estimated position. When the vehicle position information is acquired and it is determined that the feature point is not captured at the estimated position, the image is captured by the imaging unit and after being captured by the imaging unit. Characterized by comprising a vehicle position information acquisition means for acquiring vehicle position information based on the moving position and shape of the feature points of the image are within image.

  The vehicle information acquisition device according to claim 2 is the vehicle information acquisition device according to claim 1, wherein the extraction unit is configured to determine a traveling direction side end portion of the feature on the rear road surface imaged by the imaging unit. The feature points are extracted.

  Further, the vehicle information acquisition device according to claim 3 is the vehicle information acquisition device according to claim 2, wherein the extraction means is configured such that when the feature on the rear road surface is a circular feature, The feature is characterized in that the advancing direction side end of the feature is further extracted as the feature point.

  According to a fourth aspect of the present invention, there is provided a vehicle information acquisition method, an acquisition step of acquiring a traveling direction and speed of the host vehicle, an extraction step of extracting a feature point from an image captured by an imaging unit that captures the rear of the host vehicle, and The estimated position of the feature point in the image picked up by the image pickup means extracted in the extraction step is calculated based on the traveling direction and speed, and the feature point was picked up after being picked up by the image pickup means A determination step for determining whether or not the estimated position in the image is imaged, and if it is determined in the determination step that the feature point is imaged at the estimated position, based on the traveling direction and speed If the vehicle position information is acquired and it is determined in the determination step that the feature point is not imaged at the estimated position, the image is picked up by the image pickup means and the image pickup means. Characterized in that and a vehicle position information obtaining step of obtaining vehicle position information based on the moving position and shape of the feature points in the captured image after being captured Te.

  Further, the program according to claim 5 is an acquisition step of acquiring a traveling direction and speed of the host vehicle in a computer, and an extraction step of extracting a feature point from an image captured by an imaging unit that images the rear of the host vehicle. The estimated position of the feature point in the image picked up by the image pickup means extracted in the extraction step is calculated based on the traveling direction and speed, and the feature point was picked up after being picked up by the image pickup means A determination step for determining whether or not the estimated position in the image is imaged, and if it is determined in the determination step that the feature point is imaged at the estimated position, based on the traveling direction and speed If the vehicle position information is acquired and it is determined in the determination step that the feature point has not been imaged at the estimated position, Is a program for executing and a vehicle position information obtaining step of obtaining vehicle position information based on the moving position and shape of the feature points in the captured image after being captured by the means.

  In the vehicle information acquisition device according to claim 1, the vehicle information acquisition method according to claim 4, and the program according to claim 5, the feature point extracted from the image captured by the imaging unit that captures the rear of the host vehicle is captured. If the vehicle is captured at the estimated position in the captured image after being captured by the means, the vehicle position information is acquired quickly based on the traveling direction and speed of the vehicle. can do. Further, when the feature point is not captured at the estimated position in the image captured after being captured by the imaging unit, the feature point is captured in the captured image and the image captured after that. Since the vehicle position information is acquired based on the moving position and shape of the feature point, accumulation of errors in the sensor information can be prevented and highly accurate vehicle position information can be acquired. Furthermore, since the feature point only needs to be in the image where the feature point is captured and in the image captured thereafter, image recognition can be performed with a longer time interval for capturing each captured image. Thus, the processing load for acquiring the vehicle position information can be reduced.

  Further, in the vehicle information acquisition device according to claim 2, in order to extract the traveling direction side end portion of the feature on the rear road surface as a feature point, the traveling direction side end portion of the feature is extracted from the image captured later. It can be reliably extracted as a feature point.

  Furthermore, in the vehicle information acquisition device according to claim 3, in the case where the feature on the rear road surface is a circular feature, the traveling direction side end of another feature is further extracted as a feature point. It is possible to reliably extract at least the traveling direction side end of another feature from the captured image as a feature point.

It is a schematic block diagram of the vehicle by which the navigation apparatus concerning a present Example is mounted. It is a block diagram which shows typically the control system centering on the navigation apparatus mounted in a vehicle. It is a flowchart which shows the own vehicle position information acquisition process which acquires own vehicle position information from the image imaged with each sensor and the back camera. It is a figure which shows an example of the image recognition when turning rightward.

  Hereinafter, a vehicle information acquisition device, a vehicle information acquisition method, and a program according to the present invention will be described in detail with reference to the drawings based on an embodiment in which a navigation device is embodied.

  As shown in FIG. 1, a camera ECU (Electronic Control Unit) 51 for driving and controlling a CCD camera and the like is electrically connected to the navigation control unit 13 of the navigation apparatus 1 installed on the host vehicle 2. . Further, a back camera 53 that is configured by a CCD camera or the like and captures a stop line 55 on the rear road surface is installed at a substantially center in the vehicle width direction of the rear end portion of the host vehicle 2 and is connected to the camera ECU 51. .

  The navigation device 1 is provided on the center console or panel surface of the vehicle 2, displays a search route to a map or destination on a liquid crystal display (LCD) 15, and uses a speaker 16 to provide voice guidance regarding route guidance. Is output. In addition, the navigation device 1 can detect a stop line 55 on the road surface behind the vehicle 2 by transmitting a control signal to the camera ECU 51.

Next, the configuration related to the control system of the vehicle 2 according to the present embodiment will be described with reference to FIG. FIG. 2 is a block diagram schematically showing a control system centered on the navigation device 1 mounted on the vehicle 2.
As shown in FIG. 2, the control system of the vehicle 2 is configured based on a navigation device 1 and a camera ECU 51 that is electrically connected to the navigation device 1. The device is connected.

  The navigation device 1 includes a current position detection processing unit 11 that detects a current position of the host vehicle 2 (hereinafter referred to as “own vehicle position”), a data recording unit 12 that records various data, and the like. The navigation control unit 13 that performs various arithmetic processes based on the information, the operation unit 14 that receives operations from the operator, the liquid crystal display 15 that displays information such as a map to the operator, route guidance, and the like A speaker 16 that outputs voice guidance and a communication device 17 that communicates with a road traffic information center, a map information distribution center, and the like (not shown) via a mobile phone network or the like. The navigation control unit 13 is connected to a vehicle speed sensor 21 that detects the traveling speed of the host vehicle 2.

  Hereinafter, each component constituting the navigation device 1 will be described. The current location detection processing unit 11 includes a GPS 31, a distance sensor 32, a steering sensor 33, a gyro sensor 34, and the like, and represents the vehicle position and the direction of the vehicle. It is possible to detect the vehicle direction, travel distance, and the like.

  Specifically, the GPS 31 detects the current position and the current time of the host vehicle 2 on the earth by receiving radio waves generated by an artificial satellite, and the distance sensor 32 detects a predetermined position on the road. Detect the distance. Here, as the distance sensor 32, for example, the rotational speed of each of the left and right rear wheels WL, WR is measured, the distance is detected based on the measured rotational speed, the acceleration is measured, and the measured acceleration is measured twice. A sensor that integrates and detects the distance can be used.

  The steering sensor 33 detects the rudder angle of the host vehicle 2. Here, as the steering sensor 33, for example, an optical rotation sensor attached to a rotating portion of a steering wheel (not shown), a rotation resistance sensor, an angle sensor attached to a wheel, or the like is used.

  The gyro sensor 34 detects the turning angle of the host vehicle 2. Here, as the gyro sensor 34, for example, a gas rate gyro, a vibration gyro, or the like is used. Further, by integrating the turning angle detected by the gyro sensor 34, the vehicle direction can be detected.

  The data recording unit 12 includes an external storage device and a hard disk (not shown) as a recording medium, a map information database (map information DB) 25 stored in the hard disk, a template DB 27, a travel history DB 28, a predetermined program, and the like. And a driver (not shown) for writing predetermined data to the hard disk.

  The map information DB 25 stores navigation map information 26 used for travel guidance and route search of the navigation device 1. The template DB 27 stores various templates for pattern matching for recognizing images of features such as stop lines on the road when the host vehicle 2 turns due to a right or left turn. Further, as described later, the travel history DB 28 includes the own vehicle position (for example, latitude and longitude on the map), the own vehicle direction, the traveling direction of the own vehicle 2, the traveling speed, the time, the temperature, and the like. Vehicle position information 29 is stored in time series.

  Here, the navigation map information 26 is composed of various information necessary for route guidance and map display. For example, new road information for specifying each new road, map display data for displaying a map, Search for intersection data related to intersections, node data related to node points, link data related to roads (links), search data for searching routes, facility data related to POI (Point of Interest) such as stores that are a type of facility, and points. Search data and the like.

  The navigation map information 26 stores feature data related to features on the road. This feature is a display object that is installed or formed on the road in order to provide various driving information to the driver or to perform various driving guidance. (Paint), crosswalks, manholes, etc. This display line includes stop lines for stopping the vehicle, and lane markings such as “Chuo Road Center Line”, “Clane Border Line”, “Vehicle Road Outer Line”, “Train Zone”, etc. It is.

  Further, the road sign includes a pedestrian crossing, an arrow indicating the direction of travel in each lane, a character for notifying a temporary stop point such as “stop”, and the like. As feature data, a coordinate position (for example, latitude and longitude) representing the position of each feature, a type of each feature, image information representing each feature as an image, and the like are stored.

  The link data includes a link ID for specifying a link for each link constituting the road, a link length indicating the length of the link, a coordinate position (for example, latitude and longitude) of the start point and end point of the link, and the center. Data indicating presence / absence of separation zone, width of road to which link belongs, slope, gradient, cant, bank, road surface condition, number of road lanes, number of lanes decreasing, width narrowing, level crossing, etc. , For corners, curvature radius, intersections, T-junctions, corner entrances and exits, etc., for road attributes, data for downhills, uphills, etc., for road types, national roads, prefectural roads, narrow streets, etc. In addition to general roads, data representing toll roads such as highway automobile national roads, city highways, general toll roads, toll bridges and the like are recorded.

In addition, as facility data, names, addresses, telephone numbers, and coordinate positions on maps (for example, hotels, amusement parks, palaces, hospitals, gas stations, parking lots, stations, airports, ferry platforms, etc.) Latitude and longitude.), Data such as a facility icon for displaying the location of the facility on the map is stored together with an ID for identifying the POI.
In addition, the contents of the map information DB 25 and various templates for pattern matching stored in the template DB 27 are updated by downloading update information distributed via the communication device 17 from an information distribution center (not shown).

  As shown in FIG. 2, the navigation control unit 13 constituting the navigation device 1 is an arithmetic device that performs overall control of the navigation device 1, a CPU 41 as a control device, and working when the CPU 41 performs various arithmetic processes. An internal storage device such as a RAM 42 that is used as a memory and stores route data when a route is searched, a ROM 43 that stores a control program, and a flash memory 44 that stores a program read from the ROM 43 In addition, a timer 45 for measuring time is provided.

The ROM 43 stores a program such as a vehicle position information acquisition process (see FIG. 3) for acquiring the vehicle position information 29 from images captured by the sensors 21, 31 to 34 and the back camera 53 described later. ing.
Furthermore, the navigation control unit 13 is electrically connected to peripheral devices (actuators) of the operation unit 14, the liquid crystal display 15, the speaker 16, and the communication device 17.

  This operation unit 14 is operated when correcting the current position at the start of traveling, inputting a departure point as a guidance start point and a destination as a guidance end point, or searching for information about facilities, etc. Key and a plurality of operation switches. The navigation control unit 13 performs control to execute various corresponding operations based on switch signals output by pressing the switches.

  Further, the liquid crystal display 15 includes map information currently traveling, map information around the destination, operation guidance, operation menu, key guidance, recommended route from the current location to the destination, guidance information along the recommended route, traffic Information, news, weather forecast, time, mail, TV program, etc. are displayed.

  In addition, the speaker 16 outputs voice guidance or the like for guiding traveling along the recommended route based on an instruction from the navigation control unit 13. Here, the voice guidance to be guided includes, for example, “200m ahead, turn right at XX intersection”.

  The communication device 17 is a communication means such as a mobile phone network that communicates with an information distribution center (not shown), and is updated with the latest version of updated map information, display lines, road signs, etc. Send and receive update templates. In addition to the information distribution center, the communication device 17 receives traffic information including information such as traffic jam information transmitted from the road traffic information center and the service area congestion.

  Further, the camera ECU 51 includes a data receiving unit 51A that receives control information transmitted from the navigation control unit 13, and controls the back camera 53 based on the received control information and performs image recognition to output the image recognition. A part 51B is provided.

[Own vehicle location information acquisition processing]
Next, the vehicle that is the process executed by the CPU 41 of the navigation device 1 configured as described above, and that acquires the vehicle position information 29 from the images captured by the sensors 21, 31 to 34 and the back camera 53. The position information acquisition process will be described with reference to FIGS. Note that the program shown in the flowchart of FIG. 3 is executed by the CPU 41 at regular intervals (for example, every 10 msec).

As shown in FIG. 3, first, in step (hereinafter abbreviated as S) 11, the CPU 41 executes a determination process for determining whether or not the behavior of the host vehicle 2 has changed. Specifically, a determination process is executed to determine whether or not the steering angle of the host vehicle 2 has been changed by the steering sensor 33, that is, whether or not a steering wheel operation has been performed by the driver.
If it is determined that there is no change in the behavior of the host vehicle 2, that is, the steering operation by the driver is not performed (S11: NO), the CPU 41 ends the process.

  On the other hand, if it is determined that the behavior of the host vehicle 2 has changed, that is, that the driver has operated the steering wheel (S11: YES), the CPU 41 proceeds to the process of S12. In S <b> 12, the CPU 41 measures the traveling speed, rudder angle, turning angle, own vehicle position, own vehicle direction, time, and the like of the host vehicle 2 using the sensors 21, 31 to 34, and stores each measured value in the RAM 42.

  In S <b> 13, the CPU 41 outputs a control signal so as to output the first image data subjected to image recognition to the camera ECU 51 to the navigation device 1, and acquires the first image data on the rear road surface. Here, the camera ECU 51 performs binarization processing, edge detection processing, and the like on features such as lane markings and stop lines that divide the lane along the road imaged by the back camera 53, and outlines the features. The image data subjected to image recognition to be extracted is output.

  Thereafter, in S14, the CPU 41 performs pattern matching of the feature amount of the feature from the first image data on the contour information of the feature on the rear road surface and the template of each feature stored in the template DB 27, and on the rear road surface. Extract local features. And CPU41 reads the steering angle of the own vehicle 2 from RAM42, detects a turning direction, extracts the shape of the edge part of the advancing direction side of the own vehicle 2 of the various vehicles on a back road surface from 1st image data. The feature points of the feature are stored in the RAM 42. Further, the CPU 41 extracts position data (for example, X and Y coordinate positions) where the feature points of the feature are located in the captured image and stores them in the RAM 42.

  For example, as shown in the upper side of FIG. 4, the CPU 41 is characterized by the contour information of the features on the rear road surface 62 from the first image data 61, and the dividing line and stop line templates stored in the template DB 27. The pattern matching of the quantity is performed, and the partition lines 63L and 63R and the stop line 65 are extracted. And CPU41 reads the rudder angle of the own vehicle 2 from RAM42, and when turning to the right direction is detected, the lane marking 63R of the right advancing direction side is selected among each lane marking 63L, 63R.

  And CPU41 memorize | stores the edge part by the side of the own vehicle 2 of this right division line 63R, ie, the right advancing side edge part 64, in RAM42 as the feature point of the said division line 63R. Further, the CPU 41 stores the edge portion on the right traveling direction side of the stop line 65, that is, the right traveling side edge portion 66 as a feature point of the stop line 65 in the RAM 42. Further, the CPU 41 stores position data (for example, X and Y coordinate positions) in the first image data where the right advancing side edge portions 64 and 66 are located in the RAM 42.

  The CPU 41 stores one of the right advancing side edge portions 64 and 66 in the RAM 42 as a feature point of the feature on the rear road surface 62, and stores the position data in the first image data of the one. You may make it memorize | store in RAM42. In addition, when a round feature such as a manhole is extracted as a feature on the rear road surface 62 instead of the stop line 65, the edge of the round feature on the right traveling direction side is a feature point. And the edge of the right lane marking 63R on the own vehicle 2 side, that is, the right advancing side edge 64 may be stored as a feature point of the feature.

  Thereby, even if the edge on the right advancing direction side of a round shape feature such as a manhole is a feature point, the right advancing side edge 64 of the right partition line 63R is a feature point of the feature, The CPU 41 can also detect the turning angle as the vehicle position information.

  Subsequently, as shown in FIG. 3, in S15, the CPU 41 reads the traveling speed of the host vehicle 2 from the RAM 42, and sets the predetermined number of frames to be waited until the second image data is fetched corresponding to the traveling speed. Read from. Then, the CPU 41 outputs a control signal to the camera ECU 51 so that the second image data obtained by performing the image recognition for the predetermined number of frames from the first image data is output to the navigation device 1, and the second rear road surface is output. Get image data.

  The “predetermined number of frames” waiting until the second image data corresponding to each traveling speed is captured is stored in the data recording unit 12 in advance. For example, the number of frames to wait until the second image data is captured is “60 frames” when the running speed is 5 km / h or less, “30 frames” when the running speed is 10 km / h or less, and 15 km / h or less. The data recording unit 12 stores data such as “20 frames” for each of a plurality of traveling speeds.

  Further, the “predetermined number of frames” may be set so that the feature points of each feature extracted from the first image data are the maximum number of frames existing in the second image data at each traveling speed. Further, the back camera 53 images the rear road surface at a constant number of frames per second (for example, about 30 frames / second) and outputs the image to the camera ECU 51.

  In S16, the CPU 41 calculates the second frame number obtained in S15 from the data of the traveling speed, rudder angle, turning angle, own vehicle position, and own vehicle direction of the own vehicle 2 stored in the RAM 42 in S12. The vehicle position, vehicle direction, turning angle, etc. when waiting for the image data to be taken in are calculated.

  Then, the CPU 41 extracts the positional relationship between the calculated vehicle position and the imaging region based on the mounting position, the mounting angle, the angle of view, and the like of the back camera 53 to the host vehicle 2 and the above-described S14. Based on the position data and the shape of the feature points of each feature, the estimated position where the feature point of the feature in the captured image of the second image data is located and the estimated shape of the feature point of the feature are calculated. The estimated position where the feature point of each feature is located may be a circular or quadrangular area within a predetermined range.

  Subsequently, in S17, the CPU 41 performs pattern matching between the contour information of the feature on the rear road surface from the second image data and the template of the estimated shape of each feature stored in the template DB 27, and the various locations on the rear road surface. Extract feature points of objects. Thereafter, the CPU 41 extracts position data in which the feature points of the features of the estimated shape are located in the captured image, and executes a determination process for determining whether or not the estimated position is the estimated position calculated in S16. .

  If it is determined that the position data in the captured image of the feature point of each feature having the estimated shape is at the estimated position calculated in S16 (S17: YES), the CPU 41 performs the process of S18. Transition. For example, as shown in the upper side and the lower left side of FIG. 4, the CPU 41 turns the right advancing side edge portions 64 and 66 that are characteristic points of the features 63R and 65 of the first image data 61 in the right direction. If it is determined that it is within the estimated position 69 that is a circular area of the second image data 68 captured by the back camera 53 of the own vehicle 2 (S17: YES), the process proceeds to S18.

  In S <b> 18, the CPU 41 measures the traveling speed, rudder angle, turning angle, own vehicle position, own vehicle direction, time, and the like of the host vehicle 2 using the sensors 21, 31 to 34, and the temperature is measured with a thermometer (not shown). After the vehicle position information 29 including each measured value is created and stored in the RAM 42, the process proceeds to S20 described later.

  On the other hand, when it is determined that the position data in the captured image of the feature point of each feature having the estimated shape does not exist at the estimated position calculated in S16 (S17: NO), the CPU 41 performs the process of S19. Migrate to For example, as shown on the upper and lower right sides in FIG. 4, the CPU 41 determines that the right advancing side edge portions 64 and 66 that are characteristic points of the partition line 63R and the stop line 65 of the first image data 61 are in the right direction. When it is determined that the vehicle does not exist within the estimated position 69 that is the circular area of the second image data 70 captured by the back camera 53 of the host vehicle 2 turning to (NO at S17), the process of S19 is performed. Transition.

  In S <b> 19, the CPU 41 uses the positional relationship between the own vehicle position acquired in S <b> 12 and the imaging region based on the attachment position, attachment angle, angle of view, and the like of the back camera 53 to the own vehicle 2. The coordinate position on the map of the feature point of each feature in the image data is accurately calculated. And CPU41 is based on the position data in the 2nd image data of the imaging region and the feature point of each feature based on the attachment position of the back camera 53 to the own vehicle 2, the attachment angle, the angle of view, etc. The own vehicle position, own vehicle direction, turning angle, travel distance, etc. with respect to the coordinate position of the feature point on the map are calculated.

  For example, as shown in the upper side and lower right side of FIG. 4, the CPU 41 determines the vehicle position acquired in S <b> 12 based on the mounting position, mounting angle, field angle, and the like of the back camera 53 to the host vehicle 2. Using the positional relationship with the imaging region, the coordinate positions on the map of the right advancing side edge portions 64 and 66 in the first image data 61 are accurately calculated. And CPU41 is based on the attachment position of the back camera 53 to the own vehicle 2, an attachment angle, an angle of view, etc., The position data in the 2nd image data 70 of an imaging area and each right advancing side edge part 64 and 66 From the above, the vehicle position, the vehicle direction, the turning angle, the travel distance, and the like of the vehicle 2 with respect to the coordinate positions on the map of the right traveling side edge portions 64 and 66 are calculated.

  Then, the CPU 41 reads the time from the timer 45, measures the temperature with a thermometer (not shown), and calculates the own vehicle position, own vehicle direction, turning angle, and travel distance of the own vehicle 2 calculated from the second image data. The vehicle position information 29 including the time and temperature measurement values is created and stored in the RAM 42, and the process proceeds to S20.

In S20, the vehicle position information 29 stored in the RAM 42 in S18 or S19 is read again from the RAM 42 and stored in the travel history DB 28 in time series.
Subsequently, in S21, the CPU 41 executes a determination process for determining whether the acquisition of the behavior information of the host vehicle 2 has ended, that is, whether the steering operation by the driver has ended. Specifically, a determination process for determining whether or not the steering angle of the host vehicle 2 detected by the steering sensor 33 has become approximately 0 degrees is executed.

And when acquisition of the behavior information of the own vehicle 2 is not completed, that is, when it is determined that the rudder angle of the own vehicle 2 detected by the steering sensor 33 is not yet 0 degree (S21: NO), CPU41 performs the process after S12 again.
On the other hand, when the acquisition of the behavior information of the host vehicle 2 is completed, that is, when it is determined that the steering angle of the host vehicle 2 detected by the steering sensor 33 has become 0 degree (S21: YES), the CPU 41 performs the process Exit.

  As described above in detail, in the navigation device 1 according to the present embodiment, the CPU 41 detects the feature points of the features on the rear road surface extracted from the first image data captured by the back camera 53 from the first image data. When it is at the estimated position in the captured image of the second image data of the predetermined number of frames, the running speed, rudder angle, own vehicle position, own vehicle direction, etc. are determined from the measured values measured by the sensors 21, 31 to 34. The vehicle position information 29 including the vehicle information can be quickly created and stored in the travel history DB 28 in real time.

  Further, the CPU 41 estimates the feature points of the features on the rear road surface extracted from the first image data captured by the back camera 53 in the captured image of the second image data of a predetermined number of frames from the first image data. If not, the coordinate position on the map of the feature point of each feature in the first image data is accurately calculated. Then, the CPU 41 determines the own vehicle position, own vehicle direction, turning angle, travel distance, etc. of the own vehicle 2 with respect to the coordinate position of the feature point of each feature on the map from the position data of the feature point of each feature in the second image data. To calculate the vehicle position information 29. Thereby, CPU41 can prevent accumulation of the error of the measured value measured by each sensor 21,31-34, can create highly accurate own-vehicle position information 29, and can memorize it in run history DB28.

  Further, if the feature point of the feature extracted from the first image data is captured in the second image data of a predetermined number of frames from the first image data, the CPU 41 can create the vehicle position information 29. it can. As a result, the CPU 41 can increase the time interval of the timing for capturing the first image data and the second image data, recognize the feature points of the features in each image, and create the vehicle position information 29. Thus, the processing load for creating the vehicle position information 29 can be reduced, and real-time processing can be performed.

  Further, the CPU 41 extracts the shape of the traveling direction side edge of the host vehicle 2 of each feature on the rear road surface from the first image data and uses it as the feature point of the feature. It is possible to reliably extract the traveling direction side end of the feature as a feature point. In addition, when the feature on the rear road surface has a round shape, the CPU 41 extracts not only the traveling direction side edge of the feature but also the traveling direction side end of the other feature as a feature point. Thus, the turning angle can also be detected as the vehicle position information 29.

  In addition, this invention is not limited to the said Example, Of course, various improvement and deformation | transformation are possible within the range which does not deviate from the summary of this invention.

1 Navigation device 21 Vehicle speed sensor 25 Map information DB
27 Template DB
28 Travel history DB
31 GPS
32 Distance sensor 33 Steering sensor 34 Gyro sensor 41 CPU
42 RAM
43 ROM
51 Camera ECU
53 Back camera 61 First image data 62 Rear road surface 65 Stop line 63L, 63R Dividing line 64, 66 Right advancing side edge 68, 70 Second image data 69 Estimated position

Claims (5)

Imaging means for imaging the rear of the vehicle;
An acquisition means for acquiring the traveling direction and speed of the host vehicle;
Extraction means for extracting feature points from the image captured by the imaging means;
An estimated position of the feature point in the image captured by the imaging unit is calculated based on the traveling direction and speed, and the estimated position in the image captured after the feature point is captured by the imaging unit is calculated. Determination means for determining whether or not an image is captured;
If it is determined that the feature point is imaged at the estimated position, the vehicle position information is acquired based on the traveling direction and speed,
When it is determined that the feature point is not captured at the estimated position, the moving position of the feature point within the image captured by the imaging unit and the image captured after the imaging unit captures Vehicle position information acquisition means for acquiring vehicle position information based on the shape;
A vehicle information acquisition device comprising:   The vehicle information acquisition apparatus according to claim 1, wherein the extraction unit extracts, as the feature point, a traveling direction side end portion of a feature on a rear road surface imaged by the imaging unit.   3. The extraction unit according to claim 2, wherein when the feature on the rear road surface is a circular feature, the extraction unit further extracts a traveling direction side end of another feature as the feature point. The vehicle information acquisition device described. An acquisition step of acquiring the traveling direction and speed of the host vehicle;
An extraction step of extracting feature points from the image captured by the imaging means for capturing the rear of the host vehicle;
The estimated position of the feature point in the image picked up by the image pickup means extracted in the extraction step is calculated based on the traveling direction and the speed, and the image picked up after the feature point is picked up by the image pickup means A determination step of determining whether or not an image is picked up at the estimated position,
If it is determined in the determination step that the feature point is imaged at the estimated position, the vehicle position information is acquired based on the traveling direction and speed,
When it is determined in the determination step that the feature point is not captured at the estimated position, the feature point in the image captured by the imaging unit and in the image captured after being captured by the imaging unit A vehicle position information acquisition step of acquiring the vehicle position information based on the movement position and shape of
A vehicle information acquisition method comprising: On the computer,
An acquisition step of acquiring the traveling direction and speed of the host vehicle;
An extraction step of extracting feature points from the image captured by the imaging means for capturing the rear of the host vehicle;
The estimated position of the feature point in the image picked up by the image pickup means extracted in the extraction step is calculated based on the traveling direction and the speed, and the image picked up after the feature point is picked up by the image pickup means A determination step of determining whether or not an image is picked up at the estimated position,
If it is determined in the determination step that the feature point is imaged at the estimated position, the vehicle position information is acquired based on the traveling direction and speed,
When it is determined in the determination step that the feature point is not captured at the estimated position, the feature point in the image captured by the imaging unit and in the image captured after being captured by the imaging unit A vehicle position information acquisition step of acquiring the vehicle position information based on the movement position and shape of
A program for running

Images