WO2017056822A1 - 画像処理装置と画像処理方法および車両制御システム - Google Patents
画像処理装置と画像処理方法および車両制御システム Download PDFInfo
- Publication number
- WO2017056822A1 WO2017056822A1 PCT/JP2016/075295 JP2016075295W WO2017056822A1 WO 2017056822 A1 WO2017056822 A1 WO 2017056822A1 JP 2016075295 W JP2016075295 W JP 2016075295W WO 2017056822 A1 WO2017056822 A1 WO 2017056822A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- unit
- analysis
- polarized
- image analysis
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/174—Segmentation; Edge detection involving the use of two or more images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/147—Details of sensors, e.g. sensor lenses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
Definitions
- This technique relates to an image processing apparatus, an image processing method, and a vehicle control system, and enables the determination of the presence of an object from an image of a moving object peripheral region to be efficiently performed.
- the presence of an object in the real space is determined using a plurality of images obtained by photographing the real space.
- region is detected from each of the image obtained by image
- the area where the object exists may be limited to a specific area in the real space. In such a case, if the existence of the object is determined using the entire image obtained by photographing the real space, the existence of the object is determined even in an unnecessary area, and efficient processing cannot be performed. .
- an object of the present technology is to provide an image processing apparatus, an image processing method, and a vehicle control system that can efficiently determine the presence of an object from an image of a moving object peripheral area.
- the first aspect of this technology is A discrimination information generation unit that generates analysis target discrimination information using a polarization image indicating a peripheral area of the moving body; An image analysis unit for determining an object using an image of an image analysis region set based on the analysis target determination information generated by the determination information generation unit with respect to a non-polarized image indicating the moving object peripheral region. It is in the image processing apparatus having.
- the discrimination information generation unit generates analysis target discrimination information using a polarization image indicating a moving object peripheral region. For example, the discrimination information generation unit calculates a normal line based on the polarization image, and generates analysis target discrimination information indicating the road surface with a continuous image region whose normal direction is the vertical direction of the moving body as a road surface region. To do.
- the discrimination information generation unit generates information about the braking distance of the moving body as analysis target discrimination information.
- the information on the braking distance of the moving object is calculated by calculating the braking distance from the moving speed of the moving object, for example, an image generated by an imaging unit capable of detecting the distance or distance information and a polarization image capable of detecting the roughness of the moving surface.
- the image analysis unit discriminates an object using an image in the image analysis region set based on the analysis target discrimination information generated by the discrimination information generation unit with respect to the non-polarized image indicating the moving object peripheral region. For example, the image analysis unit discriminates an object using an image within a road surface area or a braking moving distance based on the analysis object discrimination information.
- the plurality of image analysis units share the non-polarized image with respect to the region divided based on the analysis target determination information, and perform target determination. For example, for an area within the braking distance, an object is determined using more image analysis units than other image areas.
- an image transfer unit that transfers the non-polarized image acquired by the image acquisition unit
- the image analysis unit is connected to the image transfer unit via a communication network
- the image transfer unit is generated by the discrimination information generation unit
- the non-polarized image transfer is controlled based on the analysis target determination information thus transferred, for example, the image selected from the images in the image analysis region or a plurality of images having different imaging directions and the analysis target determination information are transferred to the image analysis unit.
- an image analysis control unit and a plurality of image analysis units are provided, and the image analysis control unit is a non-polarized light that is transferred from the image transfer unit to the image analysis unit based on the analysis target determination information generated by the determination information generation unit.
- Image analysis control information for controlling how a plurality of image analysis units discriminate an object with respect to an image is generated and transmitted to the image analysis unit together with a non-polarized image.
- the second aspect of this technology is Generation of analysis target discrimination information using a polarization image indicating a moving object peripheral region in a discrimination information generation unit;
- the image analysis unit discriminates an object using an image in the image analysis region set based on the analysis target discrimination information generated by the discrimination information generation unit for the non-polarized image indicating the moving object peripheral region.
- an image processing method including:
- the third aspect of this technology is A discrimination information generating unit that generates analysis target discrimination information using a polarization image indicating a vehicle peripheral area;
- An image analysis unit for determining an object using an image of an image analysis region set based on the analysis target determination information generated by the determination information generation unit for a non-polarized image indicating the moving object peripheral region;
- the vehicle control system includes a drive system control unit that performs a vehicle travel control unit based on the determination result of the object in the image analysis unit.
- the analysis target discrimination information is generated by the discrimination information generation unit using the polarization image indicating the moving object peripheral region.
- the image analysis unit discriminates an object using an image in the image analysis region set based on the analysis target discrimination information generated by the discrimination information generation unit with respect to the non-polarized image indicating the moving object peripheral region. For this reason, it is possible to efficiently determine the presence of the object from the image of the peripheral area of the moving object. Note that the effects described in the present specification are merely examples and are not limited, and may have additional effects.
- FIG. 1 is a block diagram illustrating a schematic configuration of a vehicle control system. It is the figure which showed the example of installation of the image acquisition part. It is the figure which showed the structure of 1st Embodiment. It is a figure for demonstrating the polarization image acquired by a polarization image acquisition part. It is the figure which illustrated the composition of the discernment information generation part. It is explanatory drawing about a to-be-photographed object's shape and a polarization image. It is the figure which illustrated the relationship between a brightness
- a polarized image and a non-polarized image indicating the peripheral area of the moving body are acquired.
- analysis target discrimination information is generated using the acquired polarization image.
- the object is discriminated using the image in the image analysis region set based on the analysis object discrimination information for the non-polarized image.
- FIG. 1 is a block diagram illustrating a schematic configuration of a vehicle control system.
- the vehicle control system 10 includes a plurality of control units and detection units connected via the communication network 20.
- the vehicle control system 10 includes a drive system control unit 31, a body system control unit 32, a battery control unit 33, an outside information detection unit 34, and an integrated control unit 40.
- the communication network 20 may be an in-vehicle communication network that conforms to an arbitrary standard such as CAN (Controller Area Network), LIN (Local Interconnect Network), LAN (Local Area Network), or FlexRay (registered trademark).
- an input unit 51, an audio output unit 52, and a display unit 53 are connected to the integrated control unit 40.
- Each control unit includes a microcomputer that performs arithmetic processing according to various programs, a storage unit that stores a program executed by the microcomputer or parameters used for various operations, and a drive circuit that drives various devices to be controlled. Is provided.
- the drive system control part 31 controls the operation
- the drive system controller 31 includes a driving force generator for generating a driving force of the vehicle such as an internal combustion engine or a driving motor, a driving force transmission mechanism for transmitting the driving force to the wheels, and a steering angle of the vehicle. Functions as a steering mechanism to adjust.
- the drive system control unit 31 has a function as a control device such as a braking device that generates a braking force of the vehicle, and a function as a control device such as ABS (Antilock Brake System) or ESC (Electronic Stability Control). Also good.
- a vehicle state detection unit 311 is connected to the drive system control unit 31.
- the vehicle state detection unit 311 includes, for example, a gyro sensor that detects an angular velocity of the rotational movement of the vehicle body, an acceleration sensor that detects vehicle acceleration, or an accelerator pedal operation amount, a brake pedal operation amount, and steering wheel steering. At least one of sensors for detecting an angle, an engine speed, a traveling speed, or the like is included.
- the drive system control unit 31 performs arithmetic processing using the signal input from the vehicle state detection unit 311 to control the internal combustion engine, the drive motor, the electric power steering device, the brake device, or the like.
- the body system control unit 32 controls the operation of various devices mounted on the vehicle body according to various programs.
- the body control unit 32 functions as a keyless entry system, a smart key system, a power window device, or a control device for various lamps such as a headlamp, a back lamp, a brake lamp, a blinker, or a fog lamp.
- the body control unit 32 can be input with radio waves transmitted from a portable device that substitutes for a key or signals of various switches.
- the body system control unit 32 receives the input of these radio waves or signals, and controls the door lock device, power window device, lamp, and the like of the vehicle.
- the battery control unit 33 controls the secondary battery 331 that is a power supply source of the drive motor according to various programs. For example, information such as the battery temperature, the battery output voltage, or the remaining capacity of the battery is input to the battery control unit 33 from the battery device including the secondary battery 331.
- the battery control unit 33 performs arithmetic processing using these signals, and performs temperature adjustment control of the secondary battery 331 or control of a cooling device or the like provided in the battery device.
- the outside information detection unit 34 detects information outside the vehicle on which the vehicle control system 10 is mounted.
- the vehicle outside information detection unit 34 includes an image acquisition unit 341, a discrimination information generation unit 342, and an image analysis unit 344.
- the image acquisition unit 341 includes a camera that acquires a polarized image, a TOF (Time Of Flight) camera that can measure a distance, a stereo camera, and the like.
- FIG. 2 is a diagram showing an installation example of the image acquisition unit.
- the image acquisition unit 341 is provided, for example, at at least one of the front nose of the vehicle 80, the side mirror, the rear bumper, the back door, and the upper part of the windshield in the vehicle interior.
- the image acquisition unit 341A provided in the front nose and the image acquisition unit 341B provided in the upper part of the windshield in the vehicle interior mainly acquire an image in front of the vehicle 80.
- the image acquisition units 341 ⁇ / b> C and 341 ⁇ / b> D provided in the side mirror mainly acquire an image on the side of the vehicle 80.
- An image acquisition unit 341E provided in the rear bumper or the back door mainly acquires an image behind the vehicle 80.
- the imaging range ARa indicates the imaging range of the image acquisition unit 341A provided in the front nose
- the imaging range ARb indicates the imaging range of the image acquisition unit 341B provided on the upper part of the windshield in the vehicle interior.
- the imaging ranges ARc and ARd indicate the imaging ranges of the image acquisition units 341C and 341D provided in the side mirror, respectively
- the imaging range ARe indicates the imaging range of the image acquisition unit 341E provided in the rear bumper or the back door.
- the vehicle outside information detection unit 34 outputs an image obtained by imaging the surrounding area of the vehicle by the image acquisition unit 341 to the discrimination information generation unit 342 and the image analysis unit 344.
- the discrimination information generation unit 342 performs road surface detection, braking distance calculation, and the like based on the image obtained by the image acquisition unit 341, and generates analysis target discrimination information indicating a road surface detection result, a braking distance calculation result, and the like.
- the data is output to the image analysis unit 344.
- the image analysis unit 344 performs image analysis on the non-polarized image obtained by the image acquisition unit 341 using an image in the image analysis region set based on the analysis target discrimination information generated by the discrimination information generation unit 342. Then, an object such as an obstacle is determined.
- the determination result of the object is information that can be used for traveling of the vehicle, and the image analysis unit 344 outputs the determination result of the object to the integrated control unit 40.
- the image analysis unit 344 may be provided in the integrated control unit 40, and the vehicle outside information detection unit 34 may output an image or an image and analysis target determination information to the integrated control unit 40 via the communication network 20.
- An input unit 51, an audio output unit 52, and a display unit 53 are connected to the integrated control unit 40.
- the input unit 51 is realized by a device that can be input by a passenger, such as a touch panel, a button, a microphone, a switch, or a lever.
- the input unit 51 generates an input signal based on information input by a passenger or the like and outputs the input signal to the integrated control unit 40.
- the audio output unit 52 outputs information based on the audio signal from the integrated control unit 40 to audibly notify the passengers of the vehicle.
- the display unit 53 displays an image based on the image signal from the integrated control unit 40 and visually notifies the vehicle occupant of the information.
- the integrated control unit 40 has a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), and the like.
- ROM Read Only Memory stores various programs executed by CPU (Central Processing Unit).
- RAM Random Access Memory stores information such as various parameters, calculation results, or sensor values.
- the CPU executes various programs stored in the ROM, and stores the input signal from the input unit 51 and information acquired by communication with each control unit and detection unit via the communication network 20 and the RAM.
- the overall operation in the vehicle control system 10 is controlled in accordance with information and the like.
- the integrated control unit 40 generates an audio signal indicating information to be audibly notified to a vehicle occupant and outputs the audio signal to the audio output unit 52 to generate an image signal for visually notifying the information. And output to the display unit 53.
- the integrated control unit 40 includes a communication interface that performs communication with various devices and other vehicles existing in the external environment, a positioning unit that generates position information including the latitude, longitude, and altitude of the vehicle. It may be.
- At least two control units connected via the communication network 20 may be integrated as one control unit.
- each control unit may be configured by a plurality of control units.
- the vehicle control system 10 may include another control unit that is not illustrated.
- some or all of the functions of any of the control units may be provided to another control unit. That is, as long as information is transmitted and received via the communication network 20, a predetermined calculation process may be performed by any of the control units.
- FIG. 3 shows the configuration of the first embodiment.
- the vehicle exterior information detection unit 34 includes an image acquisition unit 341-1, a discrimination information generation unit 342-1, and an image analysis unit 344-1.
- the image acquisition unit 341-1 includes a polarization image acquisition unit 3411 that acquires a polarization image and a non-polarization image acquisition unit 3412 that acquires a non-polarization image.
- the polarization image acquisition unit 3411 acquires a plurality of polarization images having different polarization directions, for example, polarization images having three or more polarization directions.
- FIG. 4 is a diagram for explaining the polarization image acquired by the polarization image acquisition unit 3411.
- a polarization image is generated by arranging a polarization filter PLF having a pixel configuration of three or more polarization directions in the image sensor IMS and performing imaging.
- FIG. 4A illustrates an example in which a polarization filter PLF serving as a pixel in any of four different polarization directions (polarization directions are indicated by arrows) is arranged on the incident surface of the image sensor IMS. is doing. Further, as shown in FIG.
- polarized images are generated by providing polarizing plates PL1 to PL4 having different polarization directions in front of the cameras CM1 to CM4 and performing imaging with the cameras CM1 to CM4. Also good.
- a plurality of polarization images having different polarization directions may be generated using the configuration of the multi-lens array.
- a plurality (four in the figure) of lenses LZ are provided on the front surface of the image sensor IMS, and an optical image of a subject is formed on the imaging surface of the image sensor IMS by each lens LZ.
- a polarizing plate PL is provided in front of each lens LZ, and the polarizing direction of the polarizing plate PL is set to a different direction.
- the non-polarized image acquisition unit 3412 acquires a non-polarized image.
- the non-polarized image acquisition unit 3412 generates a non-polarized image by performing imaging without providing a polarizing plate or a polarizing filter on the incident surface of the image sensor.
- the non-polarized image acquisition unit 3412 may generate a non-polarized image from the polarized image acquired by the polarized image acquisition unit 3411.
- a luminance polarization image can be acquired.
- an image equivalent to a non-polarized normal luminance image can be obtained by averaging the luminances of four adjacent pixels having different polarization directions. it can.
- an image equivalent to the non-polarized normal luminance image can be acquired.
- the parallax can be ignored in a plurality of polarized images having different polarization directions as long as the distance between the lenses LZ is negligible with respect to the distance to the subject. Therefore, by averaging the luminance of polarized images having different polarization directions, an image equivalent to a non-polarized normal luminance image can be obtained.
- FIG. 5 illustrates the configuration of the discrimination information generation unit.
- the discrimination information generation unit 342-1 includes a normal detection unit 3421 and a road surface determination unit 3422.
- the normal line detection unit 3421 detects normal lines from a plurality of polarization images with different polarization directions acquired by the polarization image acquisition unit 3411.
- the shape of the subject and the polarization image will be described with reference to FIG.
- the light source LT is used to illuminate the subject OB
- the camera CM images the subject OB through the polarizing plate PL.
- the luminance of the subject OB changes according to the polarization direction of the polarizing plate PL.
- a plurality of polarization images are acquired by rotating the polarizing plate PL, for example, and the highest luminance is Imax and the lowest luminance is Imin.
- the angle in the y-axis direction with respect to the x-axis when the polarizing plate PL is rotated is a polarization angle ⁇ .
- the polarizing plate PL returns to the original polarization state when rotated 180 degrees and has a period of 180 degrees.
- the polarization angle ⁇ when the maximum luminance Imax is observed is defined as an azimuth angle ⁇ .
- the luminance I observed when the polarizing plate PL is rotated can be expressed as in Expression (1).
- FIG. 7 illustrates the relationship between the luminance and the polarization angle. This example shows a diffuse reflection model. In the case of specular reflection, the azimuth angle is shifted by 90 degrees from the polarization angle.
- Equation (1) the polarization angle ⁇ is clear when a polarization image is generated, and the maximum luminance Imax, the minimum luminance Imin, and the azimuth angle ⁇ are variables. Therefore, by performing the fitting to the model equation shown in the equation (1) using the luminance of the polarization image having three or more polarization directions, the polarization having the maximum luminance based on the model equation indicating the relationship between the luminance and the polarization angle.
- the azimuth angle ⁇ which is an angle, can be determined.
- the normal of the object surface is expressed in a polar coordinate system, and the normal is defined as an azimuth angle ⁇ and zenith angle ⁇ .
- the zenith angle ⁇ is an angle from the z axis toward the normal
- the azimuth angle ⁇ is an angle in the y axis direction with respect to the x axis as described above.
- the degree of polarization ⁇ can be calculated based on the equation (2).
- the relationship between the degree of polarization and the zenith angle is known to have the characteristics shown in FIG. 8, for example, from the Fresnel equation. Therefore, the zenith angle ⁇ can be determined based on the polarization degree ⁇ from the characteristics shown in FIG. Note that the characteristics shown in FIG. 8 are examples, and the characteristics change depending on the refractive index of the subject. For example, the degree of polarization increases as the refractive index increases.
- the normal line detection unit 3421 thus calculates the azimuth angle ⁇ and the zenith angle ⁇ for each pixel, and determines the road surface as a normal detection result using the normal line for each pixel indicating the calculated azimuth angle ⁇ and zenith angle ⁇ . Output to the unit 3422.
- the road surface determination unit 3422 Based on the normal detection result from the normal detection unit 3421, the road surface determination unit 3422 sets the road surface as a continuous region in which the normal direction is within a predetermined angle range in the left-right direction with respect to the vertical direction of the vehicle 80.
- the discrimination information generation unit 342 outputs analysis target discrimination information indicating the road surface detection result to the image analysis unit 344-1.
- the image analysis unit 344-1 performs image analysis of the image analysis region set based on the analysis target discrimination information generated by the discrimination information generation unit 342-1 for the non-polarized image obtained by the image acquisition unit 341-1. I do. That is, the image analysis unit 344-1 performs image analysis using the road surface and the detected area in the non-polarized image as an image analysis area, and determines an obstacle or the like. Note that the image analysis unit 344-1 may set the image analysis region widely in the left-right direction with reference to the road surface region in order to easily detect an obstacle located at the end of the road surface.
- FIG. 9 is a flowchart illustrating the operation of the first embodiment.
- the vehicle outside information detection unit 34 acquires a captured image.
- the image acquisition unit 341-1 of the vehicle exterior information detection unit 34 acquires a polarization image and a non-polarization image obtained by imaging the peripheral region of the vehicle 80, and proceeds to step ST ⁇ b> 2.
- step ST2 the vehicle exterior information detection unit 34 generates analysis target discrimination information.
- the discrimination information generation unit 342-1 of the outside information detection unit 34 generates, for example, analysis target discrimination information indicating a road surface detection result based on the polarization image acquired in step ST1, and proceeds to step ST3.
- step ST3 the vehicle exterior information detection unit 34 performs image analysis.
- the image analysis unit 344-1 of the vehicle outside information detection unit 34 performs image analysis of the image analysis region set based on the analysis target determination information generated in step ST2 on the non-polarized image acquired in step ST1. That is, the image analysis unit 344-1 performs image analysis using the road surface and the detected area in the non-polarized image as the image analysis area.
- FIG. 10 illustrates the operation of the first embodiment.
- FIG. 10A illustrates a non-polarized image acquired by the image acquisition unit 341-1.
- FIG. 10B shows the normal direction detected by the discrimination information generation unit 342-1 by arrows.
- the discrimination information generation unit 342-1 generates analysis target discrimination information indicating the detection result of the road surface using a continuous region whose normal direction is substantially vertical to the vehicle 80 as a road surface.
- FIG. 10C illustrates an image analysis region in which image analysis is performed by the image analysis unit 344-1.
- the image analysis unit 344-1 expands the road surface and the detected area based on the analysis target determination information to the left and right to form an image analysis area AN.
- the road surface can be detected with high accuracy, obstacles and the like can be detected efficiently if the image analysis area is set based on the detected road surface.
- FIG. 11 shows the configuration of the second embodiment.
- the vehicle exterior information detection unit 34 includes an image acquisition unit 341-2, a discrimination information generation unit 342-2, and an image analysis unit 344-2.
- the image acquisition unit 341-2 includes a polarization image acquisition unit 3411 that acquires a polarization image, a non-polarization image acquisition unit 3412 that acquires a non-polarization image, and a distance detection image acquisition unit 3413.
- the polarization image acquisition unit 3411 generates a polarization image and outputs the polarization image to the discrimination information generation unit 342 as in the first embodiment.
- the non-polarized image acquisition unit 3412 generates a non-polarized image and outputs the non-polarized image to the image analysis unit 344-2 as in the first embodiment.
- the distance detection image acquisition unit 3413 acquires an image that can be used for distance detection and outputs the acquired image to the discrimination information generation unit 342-2.
- the distance detection image acquisition unit 3413 includes, for example, a stereo camera, and outputs the right viewpoint image and the left viewpoint image acquired by the distance detection image acquisition unit 3413 to the discrimination information generation unit 342.
- FIG. 12 illustrates the configuration of the discrimination information generation unit.
- the discrimination information generation unit 342-2 includes a road surface roughness detection unit 3423, a distance detection unit 3424, a travel speed detection unit 3425, and a braking distance information generation unit 3426.
- the road surface roughness detection unit 3423 detects road surface roughness using the polarization image generated by the polarization image acquisition unit 3411.
- the road surface roughness detection unit 3423 uses, for example, the horizontal polarization image and the vertical polarization image generated by the polarization image acquisition unit 3411 to calculate the road surface roughness from the intensity distribution of the horizontal and vertical polarization components as disclosed in Japanese Patent Laid-Open No. 11-230898. To detect.
- the road surface roughness detection unit 3423 outputs the road surface roughness detection result to the braking distance information generation unit 3426.
- the distance detection unit 3424 detects the distance from the image acquired by the distance detection image acquisition unit 3413, for example, the right viewpoint image and the left viewpoint image to the subject located in the imaging direction, and sets the distance information indicating the detection result as the braking distance.
- the information is output to the information generation unit 3426.
- the traveling speed detection unit 3425 detects the traveling speed of the vehicle 80 and outputs speed information indicating the detection result to the braking distance information generation unit 3426.
- the travel information may be acquired from the vehicle state detection unit 311 connected to the drive system control unit 31.
- the braking distance information generation unit 3426 calculates the braking distance of the vehicle 80 based on the road surface roughness detected by the road surface roughness detection unit 3423 and the traveling speed detected by the traveling speed detection unit 3425. Also, the braking distance information generation unit 3426 discriminates the position that is ahead by the braking distance based on the distance detection result of the distance detection unit 3424, and outputs the braking distance information indicating the discrimination result to the image analysis unit 344-2. To do.
- the image analysis unit 344-2 performs image analysis of the image analysis region set based on the analysis target discrimination information generated by the discrimination information generation unit 342-2 for the non-polarized image obtained by the image acquisition unit 341-2. I do. That is, the image analysis unit 344-2 performs image analysis using a region up to a position separated by a braking distance forward in the non-polarized image as an image analysis region, and determines an obstacle or the like.
- the discrimination information generation unit 342-2 is configured as shown in FIG.
- the braking distance information generation unit 3426 calculates the braking distance of the vehicle 80 based on the road surface roughness detected by the road surface roughness detection unit 3423 and the traveling speed detected by the traveling speed detection unit 3425. Also, the braking distance information generation unit 3426 discriminates a position that is ahead by the braking distance based on the distance information acquired by the TOF camera, and outputs the braking distance information indicating the discrimination result to the image analysis unit 344-2. To do.
- processing is performed in the same manner as in the flowchart shown in FIG. 9, and in the generation of analysis target determination information, analysis target determination information indicating positions separated by the braking distance is generated.
- image analysis an area up to a position separated by a braking distance forward in the non-polarized image is set as an image analysis area.
- FIG. 14 illustrates the operation of the second embodiment.
- FIG. 14A illustrates a non-polarized image acquired by the image acquisition unit 341-2.
- FIG. 14B illustrates an image analysis region in which image analysis is performed by the image analysis unit 344-2.
- the image analysis unit 344-2 sets, as the image analysis region AN, a region up to a position separated by a braking distance forward based on the analysis target determination information.
- the image analysis area can be set according to the braking distance, it is possible to efficiently detect an obstacle or the like that needs to be detected quickly.
- the third embodiment is a case where the first and second embodiments are combined.
- FIG. 15 shows the configuration of the third embodiment.
- the vehicle outside information detection unit 34 includes an image acquisition unit 341-3, a discrimination information generation unit 342-3, and an image analysis unit 344-3.
- the image acquisition unit 341-3 includes a polarization image acquisition unit 3411 that acquires a polarization image, a non-polarization image acquisition unit 3412 that acquires a non-polarization image, and a distance detection image acquisition unit 3413.
- FIG. 16 illustrates the configuration of the discrimination information generation unit.
- the discrimination information generation unit 342-3 includes a normal detection unit 3421, a road surface determination unit 3422, a road surface roughness detection unit 3423, a distance detection unit 3424, a travel speed detection unit 3425, and a braking distance information generation unit 3426.
- the normal detection unit 3421 detects a normal from a plurality of polarization images having different polarization directions acquired by the polarization image acquisition unit 3411.
- the road surface determination unit 3422 detects the road surface based on the normal line detection result from the normal line detection unit 3421, and outputs the road surface detection result to the image analysis unit 344-3 as analysis target determination information.
- the road surface roughness detection unit 3423 detects the road surface roughness using the polarization image generated by the polarization image acquisition unit 3411 and outputs the detection result to the braking distance information generation unit 3426.
- the distance detection unit 3424 detects the distance using the image acquired by the distance detection image acquisition unit 3413, and outputs distance information indicating the detection result to the braking distance information generation unit 3426.
- Traveling speed detection unit 3425 detects the traveling speed of vehicle 80 and outputs speed information indicating the detection result to braking distance information generation unit 3426.
- the braking distance information generation unit 3426 calculates the braking distance of the vehicle 80 based on the road surface roughness detected by the road surface roughness detection unit 3423 and the traveling speed detected by the traveling speed detection unit 3425. Also, the braking distance information generation unit 3426 generates braking distance information indicating a position away from the front by the braking distance based on the calculated braking distance and the distance information generated by the distance detection unit 3424 or the TOF camera. Output to.
- the image analysis unit 344-3 performs image analysis of the image analysis region set based on the analysis target discrimination information generated by the discrimination information generation unit 342-3 for the non-polarized image obtained by the image acquisition unit 341-3. I do. That is, the image analysis unit 344-3 performs image analysis using the non-polarized image as an image analysis region up to a position detected from the road surface and separated from the front by a braking distance, and determines an obstacle or the like. . Note that the image analysis unit 344-3 may set the image analysis region widely in the left-right direction with reference to the road surface and the detected region in order to easily detect an obstacle located at the end of the road surface.
- processing is performed in the same manner as the flowchart shown in FIG. 9, and in the generation of analysis target determination information, analysis target determination information indicating a position separated from the road surface detection result by the braking distance is used.
- analysis target determination information indicating a position separated from the road surface detection result by the braking distance is used.
- image analysis an area that is detected as a road surface in a non-polarized image and that is a distance away from the front by a braking distance is set as an image analysis area.
- FIG. 17 illustrates the operation of the third embodiment.
- FIG. 17A illustrates a non-polarized image acquired by the image acquisition unit 341-3.
- FIG. 17B illustrates an image analysis region in which image analysis is performed by the image analysis unit 344-3. Based on the analysis target determination information, the image analysis unit 344-3 sets a region detected from the road surface to a position separated forward by a braking distance as an image analysis region AN.
- the image analysis area can be set on the road surface in accordance with the braking distance, so that an obstacle on the road surface that needs to be detected quickly can be detected efficiently.
- FIG. 18 is a diagram illustrating the configuration of the fourth embodiment, and three image analysis units are provided.
- the vehicle exterior information detection unit 34 includes an image acquisition unit 341-a, a discrimination information generation unit 342-a, and image analysis units 344-a, 344-b, and 344-c.
- the image acquisition unit 341-a and the discrimination information generation unit 342-a are configured in the same manner as in any of the first to third embodiments described above.
- the image analysis units 344-a, 344-b, and 344-c are regions based on the analysis target discrimination information generated by the discrimination information generation unit 342-a for the non-polarized image acquired by the non-polarization image acquisition unit. Division is performed, and a plurality of image analysis units share the image analysis of the divided areas.
- processing is performed in the same manner as the flowchart shown in FIG. 9, and in image analysis, a non-polarized image is divided based on analysis target determination information, and a plurality of image analysis units The image analysis of the divided area is performed by sharing.
- FIG. 19 illustrates the operation of the fourth embodiment.
- FIG. 19A illustrates a non-polarized image acquired by the image acquisition unit 341-a.
- FIG. 19B illustrates an image analysis region in which image analysis is performed by the image analysis units 344-a to 344-c.
- the image analysis units 344-a and 344-b perform image analysis of the image analysis area ANab in the area AS-ab up to a position separated by the braking distance forward based on the analysis target determination information.
- the image analysis unit 344-c performs image analysis of the image analysis area ANc in the remaining area AS-c different from the area AS-ab.
- the vehicle exterior information detection unit 34 outputs a non-polarized image to another control unit via the communication network 20.
- the communication speed of the communication network 20 is determined by the standard, if the amount of image data transferred from the vehicle outside information detection unit 34 to another control unit that performs image analysis increases, it takes time to transfer. There is a possibility that communication between the control units cannot be performed promptly. Therefore, the vehicle exterior information detection unit 34 outputs only the image of the region to be image analyzed in the captured image to the other control unit.
- the integrated control unit 40 performs image analysis will be described.
- FIG. 20 illustrates the configuration of the fifth embodiment.
- the vehicle outside information detection unit 34 includes an image acquisition unit 341-a, a discrimination information generation unit 342-a, and an image transfer unit 346-1.
- the image acquisition unit 341-a and the discrimination information generation unit 342-a are configured in the same manner as in any of the first to third embodiments described above.
- the image acquisition unit 341-a generates a polarization image or the like and outputs it to the discrimination information generation unit 342-a.
- the image acquisition unit 341-a generates a non-polarized image and outputs it to the image transfer unit 346-1.
- the discrimination information generation unit 342-a generates analysis target discrimination information using the polarization image supplied from the image acquisition unit 341-a and outputs the analysis target discrimination information to the image transfer unit 346-1.
- the image transfer unit 346-1 sets an image analysis region for performing image analysis on the non-polarized image supplied from the image acquisition unit 341-a based on the analysis target determination information supplied from the determination information generation unit 342-a. . Further, the image transfer unit 346-1 transfers the set image analysis region image to the integrated control unit 40 via the communication network 20.
- the integrated control unit 40 performs image analysis using the image supplied from the vehicle outside information detection unit 34 and detects an obstacle or the like. When image transfer is performed in units of lines, an image of a line including the image analysis area is transferred.
- the image transfer unit 346-1 uses the area detected as a road surface as an image analysis area, The image in the analysis area is transferred to the integrated control unit 40.
- the image transfer unit 346-1 sets an area within the braking distance as an image analysis area, and The image in the analysis area is transferred to the integrated control unit 40 via the communication network 20.
- the image transfer unit 346-1 is detected as a road surface within the braking distance, for example.
- the image area is the image analysis area.
- the image transfer unit 346-1 transfers the image in the image analysis area to the integrated control unit 40 via the communication network 20.
- FIG. 21 is a flowchart illustrating the operation of the fifth embodiment.
- the vehicle outside information detection unit 34 acquires a captured image.
- the image acquisition unit 341-a of the vehicle exterior information detection unit 34 acquires a polarized image and a non-polarized image obtained by imaging the peripheral region of the vehicle 80, and proceeds to step ST12.
- step ST12 the vehicle exterior information detection unit 34 generates analysis target discrimination information.
- the discrimination information generation unit 342-a of the vehicle exterior information detection unit 34 generates analysis target discrimination information based on the polarization image acquired in step ST11, and proceeds to step ST13.
- step ST13 the vehicle outside information detection unit 34 transfers the image.
- the image transfer unit 346-1 of the outside information detection unit 34 uses the communication network 20 to display an image in the image analysis region set based on the analysis target determination information generated in step ST12 for the non-polarized image acquired in step ST11. Then, the process proceeds to step ST14.
- step ST14 the integrated control unit 40 performs image analysis.
- the image analysis unit of the integrated control unit 40 performs image analysis using the non-polarized image transmitted from the vehicle exterior information detection unit 34 in step ST13.
- the image of the region in which the image analysis is performed is included in the communication network 20. Sent through. Therefore, the amount of data to be transferred can be reduced as compared with the case of transferring the entire non-polarized image.
- the sixth embodiment exemplifies a case where an image acquisition unit that images different peripheral areas is provided.
- an image acquisition unit 341A, 341C, 341D, and 341E illustrated in FIG. 2 will be described.
- FIG. 22 illustrates the configuration of the sixth embodiment.
- the vehicle exterior information detection unit 34 includes image acquisition units 341A, 341C, 341D, and 341E, a discrimination information generation unit 342-b, and an image transfer unit 346-2.
- Image acquisition units 341A, 341C, 341D, and 341E correspond to the image acquisition unit 341-a in the fifth embodiment described with reference to FIG.
- the discrimination information generation unit 342-b has the function of the discrimination information generation unit 342-a in the fifth embodiment for each of the image acquisition units 341A, 341C, 341D, and 341E.
- the image acquisition units 341A, 341C, 341D, and 341E generate polarized images and the like and output them to the discrimination information generation unit 342-b. In addition, the image acquisition units 341A, 341C, 341D, and 341E generate a non-polarized image and output it to the image transfer unit 346-2.
- the discrimination information generation unit 342-b generates analysis target discrimination information for each of the image acquisition units 341A, 341C, 341D, and 341E using the polarization image supplied from the image acquisition unit and sends the analysis target discrimination information to the image transfer unit 346-2. Output.
- the image transfer unit 346-2 determines a non-polarized image to be subjected to image analysis as a transfer target image based on the analysis target determination information supplied from the determination information generation unit 342-b. For example, the image transfer unit 346-2 sets a non-polarized image in which the road surface is detected as the transfer target image based on the analysis target determination information. In addition, when the braking distance is longer than the predetermined distance, the image transfer unit 346-2 may use the non-polarized images before and after the traveling direction as the images to be transferred. The image transfer unit 346-2 transfers the determined transfer target image together with the analysis target determination information to the integrated control unit 40 via the communication network 20. In addition, the image analysis unit of the integrated control unit 40 performs image analysis using the image in the image analysis region based on the received image and analysis target determination information.
- processing is performed in the same manner as in the flowchart shown in FIG. 21, and in image transfer, a non-polarized image including an image analysis region based on analysis target determination information is determined as analysis region determination. Transfer with information.
- FIG. 23 illustrates the operation of the sixth embodiment.
- FIG. 23A illustrates a non-polarized image acquired by the image acquisition unit 341A.
- (b), (c), and (d) of FIG. 23 illustrate the non-polarized images acquired by the image acquisition units 341C, 341D, and 341E, respectively.
- the road surface is detected from the images acquired by the image acquisition units 341A and 341E and the braking distance is calculated. Further, it is assumed that the road surface is not detected in the images acquired by the image acquisition units 341C and 341D.
- the image transfer unit 346 uses the image indicating the position of the road surface and the braking distance, that is, the non-polarized image acquired by the image acquisition units 341A and 341E as the transfer target image along with the analysis target determination information via the communication network 20.
- the image analysis unit of the integrated control unit 40 performs image analysis of the image analysis areas AN and ANB as shown in (e) and (f) of FIG. 23 based on the received image and analysis target determination information. By performing such processing, it becomes possible to detect an obstacle on the road surface closer to the braking distance and a succeeding vehicle having an inter-vehicle distance closer than the braking distance by image analysis.
- the non-polarized light generated by the plurality of image acquisition units Only an image to be analyzed from the image is transmitted via the communication network 20. Therefore, it is possible to reduce the amount of data to be transferred as compared with the case where all the non-polarized images generated by the image acquisition units are transferred.
- the transfer target image determined based on the analysis target determination information is transferred to the integrated control unit 40 via the communication network 20, but is the same as in the above-described fifth embodiment.
- the image in the image analysis area in the transfer target image may be transferred.
- a case will be described in which an image in the image analysis region in the transfer target image is transferred to the integrated control unit 40 via the communication network 20.
- the vehicle exterior information detection unit 34 is configured in the same manner as in the sixth embodiment.
- the image transfer unit 346-2 determines, as the transfer target image, a non-polarized image to be subjected to image analysis based on the analysis target determination information supplied from the determination information generation unit 342-b. For example, the image transfer unit 346-2 sets the non-polarized image from which the road surface is detected as the transfer target image based on the analysis target determination information.
- the image transfer unit 346-2 may use the non-polarized images before and after the traveling direction as the images to be transferred.
- the image transfer unit 346-2 sets a transfer area for the transfer target image based on the analysis target determination information, and the image of the transfer area is combined with the analysis target determination information via the communication network 20 to the integrated control unit 40. Forward to.
- a transfer area is set in units of lines.
- processing is performed in the same manner as in the flowchart shown in FIG. 21, and in image transfer, a non-polarized image in the transfer region determined based on the analysis target determination information is used as analysis target determination information. Forward with.
- FIG. 24 illustrates the operation of the seventh embodiment.
- FIG. 24A illustrates a non-polarized image acquired by the image acquisition unit 341A.
- (b), (c), and (d) of FIG. 24 illustrate non-polarized images acquired by the image acquisition units 341C, 341D, and 341E, respectively.
- the road surface is detected from the images acquired by the image acquisition units 341A and 341E and the braking distance is calculated. Further, it is assumed that the road surface is not detected in the images acquired by the image acquisition units 341C and 341D.
- the image transfer unit 346 sets the image indicating the position of the road surface and the braking distance, that is, the non-polarized image acquired by the image acquisition units 341A and 341E as the transfer target image. Further, when image transfer is performed in units of lines, a transfer area is set in units of lines. For example, the line of the area up to the position of the braking distance is used as the transfer area, that is, the image of the transfer area up to the position of the braking distance in the non-polarized images acquired by the image acquisition units 341A and 341E is combined with the analysis target determination information. 20 to the integrated control unit 40.
- the image analysis unit of the integrated control unit 40 is based on the received image and analysis target determination information, and is an image analysis region that is a road surface region in the transfer regions ATA and ATE images shown in FIGS. Image analysis is performed using images of AN and ANB.
- the seventh embodiment when image analysis is performed by another control unit or the like connected to the outside information detection unit via the communication network, the non-polarized light generated by the plurality of image acquisition units From the image, the image of the transfer area set based on the analysis target determination information is transmitted via the communication network 20. Therefore, the amount of data to be transferred can be further reduced as compared with the case where all non-polarized images generated by each image acquisition unit are transferred or when the entire image including the image analysis area is transferred.
- the configuration of the vehicle exterior information detection unit 34 is not limited to the above-described embodiment.
- the discrimination information generation unit performs road surface detection and road surface roughness detection using the polarization image.
- the image analysis unit or the image transfer unit may set the image analysis region based on the detection result of the road surface and the detection result of the road surface roughness, and perform image analysis of the image analysis region or transfer of the image of the image analysis region. Good.
- an image analysis control unit 348 may be provided in the vehicle exterior information detection unit 34.
- the image analysis control unit 348 generates image analysis control information based on the analysis target determination information, and transfers it to the integrated control unit 40 together with the image.
- the image analysis control information is information for controlling distribution of images to a plurality of image analysis units, for example, when image analysis is performed using a plurality of image analysis units.
- the integrated control unit 40 distributes the images to the plurality of image analysis units and shares the images among the plurality of analysis units in the same manner as in the fourth embodiment described above. Perform analysis.
- the analysis target determination information is generated from the polarization image indicating the moving object peripheral area.
- recognition processing or the like is performed using the non-polarized image indicating the moving object peripheral area, and the analysis target determination information is obtained. It may be generated.
- the distance detection result can also be used as analysis target discrimination information.
- the moving body is a vehicle
- the moving body is not limited to a vehicle.
- the above-described image processing apparatus may be provided in the robot, and the movement control of the robot may be performed based on the image analysis result.
- the above-described image processing device may be provided in the ship so that the land and the water surface are discriminated based on the polarization image, and the ship is steered based on the image analysis result of the water surface.
- the series of processes described in the specification can be executed by hardware, software, or a combined configuration of both.
- a program in which a processing sequence is recorded is installed and executed in a memory in a computer incorporated in dedicated hardware.
- the program can be installed and executed on a general-purpose computer capable of executing various processes.
- the program can be recorded in advance on a hard disk, SSD (Solid State Drive), or ROM (Read Only Memory) as a recording medium.
- the program is a flexible disk, a CD-ROM (Compact Disc Read Only Memory), an MO (Magneto optical disc), a DVD (Digital Versatile Disc), a BD (Blu-Ray Disc (registered trademark)), a magnetic disk, or a semiconductor memory card. It can be stored (recorded) in a removable recording medium such as temporarily or permanently. Such a removable recording medium can be provided as so-called package software.
- the program may be transferred from the download site to the computer wirelessly or by wire via a network such as a LAN (Local Area Network) or the Internet.
- the computer can receive the program transferred in this way and install it on a recording medium such as a built-in hard disk.
- the image processing apparatus may have the following configuration.
- a discrimination information generation unit that generates analysis target discrimination information using a polarization image indicating a moving object peripheral region;
- An image analysis unit for determining an object using an image of an image analysis region set based on the analysis target determination information generated by the determination information generation unit with respect to a non-polarized image indicating the moving object peripheral region.
- the discrimination information generation unit generates analysis target discrimination information indicating a road surface in the moving object peripheral region based on the polarization image, The image processing apparatus according to (1), wherein the image analysis unit sets the image analysis region in accordance with the road surface region.
- the image processing device sets a continuous image region in which a normal direction calculated from the polarization image is a vertical direction of the moving body as the road surface region. .
- the discrimination information generation unit generates information about the braking distance of the moving body in the peripheral area of the moving body as analysis target discrimination information using the polarization image,
- the image processing device according to any one of (1) to (3), wherein the image analysis unit sets an area within the braking distance as the image analysis area.
- the discrimination information generation unit is configured to display information indicating a region within the braking distance in the non-polarized image based on the braking distance calculated from the roughness and movement speed of the traveling surface and the distance on the non-polarized image.
- the image processing apparatus which is generated as the analysis target determination information.
- a plurality of the image analysis units are provided, The plurality of image analysis units share the non-polarized image with respect to a region divided based on the analysis target determination information, and perform determination of the target object according to any one of (1) to (5).
- Image processing device (7)
- the analysis target determination information is information about a braking distance of the moving body in the moving body peripheral area and information indicating a road surface in the moving body surrounding area,
- the image processing apparatus according to (6), wherein the plurality of image analysis units determine the object with respect to the region within the braking distance by using more image analysis units than other image regions.
- An image transfer unit that transfers the non-polarized image is provided,
- the image analysis unit is connected to the image transfer unit via a communication network,
- the image processing apparatus according to (1) wherein the image transfer unit controls transfer of the non-polarized image to the image analysis unit based on the analysis target determination information generated by the determination information generation unit.
- the image processing device according to (8) wherein the image transfer unit transfers an image in the image analysis region.
- the discrimination information generation unit generates analysis target discrimination information using the polarization image for each imaging direction,
- the image transfer unit selects the non-polarized image to be transferred to the image analysis unit based on the analysis target determination information generated by the determination information generation unit, and determines the selected non-polarized image as the analysis target determination
- the image processing apparatus according to (8), which is transferred together with information.
- the determination information generation unit generates analysis target determination information using the polarization image for each imaging direction
- the image transfer unit selects the non-polarized image to be transferred to the image analysis unit based on the analysis target determination information generated by the determination information generation unit, and the image analysis region in the selected non-polarized image
- the image processing apparatus according to (8), wherein the image is transferred together with the analysis target determination information.
- An image analysis control unit and a plurality of the image analysis units are provided,
- the image analysis control unit is configured to determine the object with respect to the non-polarized image transferred from the image transfer unit to the image analysis unit based on the analysis target determination information generated by the determination information generation unit.
- the image processing apparatus according to (8), wherein image analysis control information for controlling how the image analysis unit performs is generated and transmitted to the image analysis unit together with the non-polarized image.
- the analysis target determination information is generated by the determination information generation unit using, for example, a polarized image indicating a vehicle peripheral region.
- the image analysis unit uses an image in the image analysis region set based on the analysis target determination information generated by the determination information generation unit for the non-polarized image indicating the vehicle peripheral region, and the target object such as an obstacle on the road surface Is determined. For this reason, it is possible to efficiently determine the presence of the object from the image of the peripheral area of the moving object. Therefore, it is suitable for a control system for performing safe driving in, for example, an automobile.
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Vascular Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Closed-Circuit Television Systems (AREA)
- Image Processing (AREA)
Abstract
Description
移動体周辺領域を示す偏光画像を用いて解析対象判別情報を生成する判別情報生成部と、
前記移動体周辺領域を示す無偏光画像に対して前記判別情報生成部で生成された解析対象判別情報に基づいて設定した画像解析領域の画像を用いて対象物の判別を行う画像解析部と
を有する画像処理装置にある。
移動体周辺領域を示す偏光画像を用いて解析対象判別情報を判別情報生成部で生成すること、
前記移動体周辺領域を示す無偏光画像に対して前記判別情報生成部で生成された解析対象判別情報に基づいて設定した画像解析領域の画像を用いて対象物の判別を画像解析部で行うことと
を含む画像処理方法にある。
車両周辺領域を示す偏光画像を用いて解析対象判別情報を生成する判別情報生成部と、
前記移動体周辺領域を示す無偏光画像に対して前記判別情報生成部で生成された解析対象判別情報に基づいて設定した画像解析領域の画像を用いて対象物の判別を行う画像解析部と、
前記画像解析部における前記対象物の判別結果に基づき車両走行制御部を行う駆動系制御部と
を有する車両制御システムにある。
1.車両制御システムについて
2.画像処理装置について
3.第1の実施の形態
4.第2の実施の形態
5.第3の実施の形態
6.第4の実施の形態
7.第5の実施の形態
8.第6の実施の形態
9.第7の実施の形態
10.他の実施の形態
図1は、車両制御システムの概略構成を例示したブロック図である。車両制御システム10は、通信ネットワーク20を介して接続された複数の制御部や検出部を備える。図1に示した例では、車両制御システム10は、駆動系制御部31、ボディ系制御部32、バッテリ制御部33、車外情報検出部34、および統合制御部40を備える。通信ネットワーク20は、例えば、CAN(Controller Area Network)、LIN(Local Interconnect Network)、LAN(Local Area Network)又はFlexRay(登録商標)等の任意の規格に準拠した車載通信ネットワークであってよい。また、統合制御部40には、入力部51、音声出力部52、表示部53が接続されている。
入力部51は、例えば、タッチパネル、ボタン、マイクロフォン、スイッチ又はレバー等、搭乗者によって入力操作され得る装置によって実現される。入力部51は、搭乗者等により入力された情報に基づいて入力信号を生成し、統合制御部40に出力する。
次に、本技術の画像処理装置を、上述のように図1に示す車両制御システムの車外情報検出部として適用した場合の実施の形態について説明する。
図3は第1の実施の形態の構成を示している。車外情報検出部34は、画像取得部341-1と判別情報生成部342-1と画像解析部344-1を有している。また、画像取得部341-1は、偏光画像を取得する偏光画像取得部3411と無偏光画像を取得する無偏光画像取得部3412を有している。
図11は第2の実施の形態の構成を示している。車外情報検出部34は、画像取得部341-2と判別情報生成部342-2と画像解析部344-2を有している。また、画像取得部341-2は、偏光画像を取得する偏光画像取得部3411と無偏光画像を取得する無偏光画像取得部3412および距離検出画像取得部3413を有している。
第3の実施の形態は、第1と第2の実施の形態を組み合わせた場合である。
ところで、画像解析部で行われる処理に時間を要すると、車両の走行中に路面上の障害物等をリアルタイムで検出できないおそれがある。また、路面上に限らず他の位置でも障害物等の検出を行えば、より安全に走行が可能となる。そこで、第4の実施の形態では、画像解析部を複数設けた場合について説明する。
上述の第1乃至第4の実施の形態では、車外情報検出部34に画像解析部が設けられている場合を例示したが、画像解析は、車外情報検出部34に限らず他の制御部で行うようにしてもよい。この場合、車外情報検出部34は、通信ネットワーク20を介して他の制御部に無偏光画像を出力する。また、通信ネットワーク20の通信速度は規格で定められているため、車外情報検出部34から画像解析を行う他の制御部に転送する画像のデータ量が多くなると、転送に時間を要することから他の制御部間等の通信を速やかに行うことができないおそれがある。したがって、車外情報検出部34は、撮像画像において画像解析の対象となる領域の画像のみを他の制御部へ出力する。以下、統合制御部40で画像解析を行う場合について説明する。
第6の実施の形態では、異なる周辺領域を撮像する画像取得部が設けられている場合を例示している。例えば図2に示す画像取得部341A,341C,341D,341Eが設けられている場合について説明する。
上述の第6の実施の形態では、解析対象判別情報に基づいて判別した転送対象の画像を、通信ネットワーク20を介して統合制御部40へ転送したが、上述の第5の実施の形態と同様に、転送対象の画像における画像解析領域の画像を転送するようにしてもよい。第7の実施の形態では、転送対象の画像における画像解析領域の画像を、通信ネットワーク20を介して統合制御部40へ転送する場合について説明する。
また、車外情報検出部34の構成は上述の実施の形態に限られない。例えば、判別情報生成部では偏光画像を用いて路面検出と路面粗さ検出を行う。画像解析部または画像転送部は、路面の検出結果と路面粗さの検出結果に基づき画像解析領域を設定して、画像解析領域の画像解析または画像解析領域の画像の転送を行うようにしてもよい。
(1) 移動体周辺領域を示す偏光画像を用いて解析対象判別情報を生成する判別情報生成部と、
前記移動体周辺領域を示す無偏光画像に対して前記判別情報生成部で生成された解析対象判別情報に基づいて設定した画像解析領域の画像を用いて対象物の判別を行う画像解析部と
を有する画像処理装置。
(2) 前記判別情報生成部は、前記偏光画像に基づき前記移動体周辺領域における路面を示す解析対象判別情報を生成して、
前記画像解析部は、前記路面の領域に応じて前記画像解析領域を設定する(1)に記載の画像処理装置。
(3) 前記判別情報生成部は、前記偏光画像から算出された法線の方向が前記移動体の鉛直方向となる連続した画像領域を前記路面の領域とする(2)に記載の画像処理装置。
(4) 前記判別情報生成部は、前記偏光画像を用いて前記移動体周辺領域における前記移動体の制動距離に関する情報を解析対象判別情報として生成して、
前記画像解析部は、前記制動距離内の領域を前記画像解析領域として設定する(1)乃至(3)の何れかに記載の画像処理装置。
(5) 前記判別情報生成部は、走行面の粗さおよび移動速度から算出された制動距離と前記無偏光画像上の距離に基づき、前記無偏光画像における前記制動距離内の領域を示す情報を前記解析対象判別情報として生成する(4)に記載の画像処理装置。
(6) 前記画像解析部を複数設け、
前記複数の画像解析部は、前記無偏光画像を前記解析対象判別情報に基づいて分割した領域に対して分担して前記対象物の判別を行う(1)乃至(5)の何れかに記載の画像処理装置。
(7) 前記解析対象判別情報は前記移動体周辺領域における前記移動体の制動距離に関する情報と前記移動体周辺領域における路面を示す情報であり、
前記複数の画像解析部は、前記制動距離内の領域についての前記対象物の判別を、他の画像領域よりも多くの前記画像解析部を用いて行う(6)に記載の画像処理装置。
(8) 前記無偏光画像の転送を行う画像転送部を設け、
前記画像解析部は通信ネットワークを介して前記画像転送部と接続して、
前記画像転送部は、前記判別情報生成部で生成された解析対象判別情報に基づいて、前記画像解析部への前記無偏光画像の転送を制御する(1)に記載の画像処理装置。
(9) 前記画像転送部は、前記画像解析領域の画像を転送する(8)に記載の画像処理装置。
(10) 前記判別情報生成部は、撮像方向毎に前記偏光画像を用いて解析対象判別情報を生成し、
前記画像転送部は、前記判別情報生成部で生成された解析対象判別情報に基づいて、前記画像解析部に転送する前記無偏光画像を選択して、選択した前記無偏光画像を前記解析対象判別情報とともに転送する(8)に記載の画像処理装置。
(11) 前記判別情報生成部は、撮像方向毎に前記偏光画像を用いて解析対象判別情報を生成し、
前記画像転送部は、前記判別情報生成部で生成された解析対象判別情報に基づいて、前記画像解析部に転送する前記無偏光画像を選択して、選択した前記無偏光画像における前記画像解析領域の画像を前記解析対象判別情報とともに転送する(8)に記載の画像処理装置。
(12) 画像解析制御部と複数の前記画像解析部を設け、
前記画像解析制御部は、前記判別情報生成部で生成された解析対象判別情報に基づき、前記画像転送部から前記画像解析部へ転送される前記無偏光画像に対する前記対象物の判別を前記複数の画像解析部でどのように行うか制御する画像解析制御情報を生成して、前記無偏光画像と共に前記画像解析部へ送信する(8)に記載の画像処理装置。
20・・・通信ネットワーク
31・・・駆動系制御部
32・・・ボディ系制御部
33・・・バッテリ制御部
34・・・車外情報検出部
40・・・統合制御部
51・・・入力部
52・・・音声出力部
53・・・表示部
80・・・車両
311・・・車両状態検出部
331・・・二次電池
341・・・画像取得部
3411・・・偏光画像取得部
3412・・・無偏光画像取得部
3413・・・距離検出画像取得部
342・・・判別情報生成部
3421・・・法線検出部
3422・・・路面判定部
3423・・・路面粗さ検出部
3424・・・距離検出部
3425・・・走行速度検出部
3426・・・制動距離情報生成部
344・・・画像解析部
346・・・画像転送部
348・・・画像解析制御部
Claims (14)
- 移動体周辺領域を示す偏光画像を用いて解析対象判別情報を生成する判別情報生成部と、
前記移動体周辺領域を示す無偏光画像に対して前記判別情報生成部で生成された解析対象判別情報に基づいて設定した画像解析領域の画像を用いて対象物の判別を行う画像解析部と
を有する画像処理装置。 - 前記判別情報生成部は、前記偏光画像に基づき前記移動体周辺領域における路面を示す解析対象判別情報を生成して、
前記画像解析部は、前記路面の領域に応じて前記画像解析領域を設定する
請求項1に記載の画像処理装置。 - 前記判別情報生成部は、前記偏光画像から算出された法線の方向が前記移動体の鉛直方向となる連続した画像領域を前記路面の領域とする
請求項2に記載の画像処理装置。 - 前記判別情報生成部は、前記偏光画像を用いて前記移動体周辺領域における前記移動体の制動距離に関する情報を解析対象判別情報として生成して、
前記画像解析部は、前記制動距離内の領域を前記画像解析領域として設定する
請求項1に記載の画像処理装置。 - 前記判別情報生成部は、走行面の粗さおよび移動速度から算出された制動距離と前記無偏光画像上の距離に基づき、前記無偏光画像における前記制動距離内の領域を示す情報を前記解析対象判別情報として生成する
請求項4に記載の画像処理装置。 - 前記画像解析部を複数設け、
前記複数の画像解析部は、前記無偏光画像を前記解析対象判別情報に基づいて分割した領域に対して分担して前記対象物の判別を行う
請求項1に記載の画像処理装置。 - 前記解析対象判別情報は前記移動体周辺領域における前記移動体の制動距離に関する情報と前記移動体周辺領域における路面を示す情報であり、
前記複数の画像解析部は、前記制動距離内の領域についての前記対象物の判別を、他の画像領域よりも多くの前記画像解析部を用いて行う
請求項6に記載の画像処理装置。 - 前記無偏光画像の転送を行う画像転送部を設け、
前記画像解析部は通信ネットワークを介して前記画像転送部と接続して、
前記画像転送部は、前記判別情報生成部で生成された解析対象判別情報に基づいて、前記画像解析部への前記無偏光画像の転送を制御する
請求項1に記載の画像処理装置。 - 前記画像転送部は、前記画像解析領域の画像を転送する
請求項8に記載の画像処理装置。 - 前記判別情報生成部は、撮像方向毎に前記偏光画像を用いて解析対象判別情報を生成し、
前記画像転送部は、前記判別情報生成部で生成された解析対象判別情報に基づいて、前記画像解析部に転送する前記無偏光画像を選択して、選択した前記無偏光画像を前記解析対象判別情報とともに転送する
請求項8に記載の画像処理装置。 - 前記判別情報生成部は、撮像方向毎に前記偏光画像を用いて解析対象判別情報を生成し、
前記画像転送部は、前記判別情報生成部で生成された解析対象判別情報に基づいて、前記画像解析部に転送する前記無偏光画像を選択して、選択した前記無偏光画像における前記画像解析領域の画像を前記解析対象判別情報とともに転送する
請求項8に記載の画像処理装置。 - 画像解析制御部と複数の前記画像解析部を設け、
前記画像解析制御部は、前記判別情報生成部で生成された解析対象判別情報に基づき、前記画像転送部から前記画像解析部へ転送される前記無偏光画像に対する前記対象物の判別を前記複数の画像解析部でどのように行うか制御する画像解析制御情報を生成して、前記無偏光画像と共に前記画像解析部へ送信する
請求項8に記載の画像処理装置。 - 移動体周辺領域を示す偏光画像を用いて解析対象判別情報を判別情報生成部で生成すること、
前記移動体周辺領域を示す無偏光画像に対して前記判別情報生成部で生成された解析対象判別情報に基づいて設定した画像解析領域の画像を用いて対象物の判別を画像解析部で行うことと
を含む画像処理方法。 - 車両周辺領域を示す偏光画像を用いて解析対象判別情報を生成する判別情報生成部と、
前記移動体周辺領域を示す無偏光画像に対して前記判別情報生成部で生成された解析対象判別情報に基づいて設定した画像解析領域の画像を用いて対象物の判別を行う画像解析部と、
前記画像解析部における前記対象物の判別結果に基づき車両走行制御部を行う駆動系制御部と
を有する車両制御システム。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201680055410.3A CN108028022B (zh) | 2015-09-30 | 2016-08-30 | 图像处理装置、图像处理方法和车辆控制系统 |
JP2017543033A JP6801666B2 (ja) | 2015-09-30 | 2016-08-30 | 画像処理装置と画像処理方法および車両制御システム |
US15/761,878 US10769951B2 (en) | 2015-09-30 | 2016-08-30 | Image processing apparatus, image processing method, and vehicle control system to determine the presence of an object from an image of a peripheral area of a moving body |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2015-193300 | 2015-09-30 | ||
JP2015193300 | 2015-09-30 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017056822A1 true WO2017056822A1 (ja) | 2017-04-06 |
Family
ID=58423195
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2016/075295 WO2017056822A1 (ja) | 2015-09-30 | 2016-08-30 | 画像処理装置と画像処理方法および車両制御システム |
Country Status (4)
Country | Link |
---|---|
US (1) | US10769951B2 (ja) |
JP (1) | JP6801666B2 (ja) |
CN (1) | CN108028022B (ja) |
WO (1) | WO2017056822A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020049638A1 (ja) * | 2018-09-04 | 2020-03-12 | 株式会社ソニー・インタラクティブエンタテインメント | 情報処理装置およびプレイフィールド逸脱検知方法 |
EP3663882A4 (en) * | 2017-08-04 | 2020-08-12 | Sony Corporation | INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING PROCESS, PROGRAM AND MOBILE UNIT |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102018216983B3 (de) * | 2018-10-04 | 2019-11-28 | Audi Ag | Verfahren zum Unterdrücken von Abbildungen von Reflexionen in zumindest einem Kamerabild einer Kamera einer Umfeldsensorvorrichtung eines Kraftfahrzeugs sowie entsprechende Umfeldsensorvorrichtung |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06293236A (ja) * | 1992-12-22 | 1994-10-21 | Mitsubishi Electric Corp | 走行環境監視装置 |
JP2000353231A (ja) * | 1999-06-10 | 2000-12-19 | Mitsubishi Electric Corp | 画像処理装置 |
JP2012142903A (ja) * | 2011-01-06 | 2012-07-26 | Ricoh Co Ltd | 撮像装置 |
WO2015045501A1 (ja) * | 2013-09-27 | 2015-04-02 | 日立オートモティブシステムズ株式会社 | 外界認識装置 |
JP2015133078A (ja) * | 2014-01-15 | 2015-07-23 | 株式会社リコー | 制御用対象物認識装置、移動体機器制御システム及び制御用対象物認識用プログラム |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7979172B2 (en) * | 1997-10-22 | 2011-07-12 | Intelligent Technologies International, Inc. | Autonomous vehicle travel control systems and methods |
WO2006077710A1 (ja) * | 2005-01-19 | 2006-07-27 | Matsushita Electric Industrial Co., Ltd. | 画像変換方法、テクスチャマッピング方法、画像変換装置、サーバークライアントシステム、および画像変換プログラム |
JP4785044B2 (ja) * | 2006-01-13 | 2011-10-05 | スタンレー電気株式会社 | 反射型光学センサ及び測定面の表面粗さ検出方法 |
JP2008015573A (ja) | 2006-07-03 | 2008-01-24 | Sony Corp | 画像処理装置、画像処理方法および画像監視システム |
WO2009019886A1 (ja) * | 2007-08-07 | 2009-02-12 | Panasonic Corporation | 法線情報生成装置および法線情報生成方法 |
CN102113021B (zh) * | 2008-12-25 | 2013-11-27 | 松下电器产业株式会社 | 图像处理装置和模拟立体图像生成装置 |
EP2439716B1 (en) * | 2010-09-16 | 2013-11-13 | Ricoh Company, Ltd. | Object identification device, moving object controlling apparatus having object identification device and information presenting apparatus having object identification device |
JP5986206B2 (ja) * | 2012-07-27 | 2016-09-06 | 京セラ株式会社 | 画像処理装置、撮像装置、移動体、プログラム、および領域設定方法 |
JP5944781B2 (ja) * | 2012-07-31 | 2016-07-05 | 株式会社デンソーアイティーラボラトリ | 移動体認識システム、移動体認識プログラム、及び移動体認識方法 |
JP6380843B2 (ja) * | 2013-12-19 | 2018-08-29 | 株式会社リコー | 物体検出装置及びこれを備えた移動体機器制御システム並びに物体検出用プログラム |
CN104008645B (zh) * | 2014-06-12 | 2015-12-09 | 湖南大学 | 一种适用于城市道路车道线预测及预警方法 |
CN104129387B (zh) * | 2014-07-25 | 2016-10-05 | 杭州电子科技大学 | 安全距离与碰撞时间权衡风险的单摄像头汽车防撞方法 |
MX364878B (es) * | 2015-02-25 | 2019-05-09 | Facebook Inc | Identificación de un objeto en un volumen con base en las características de la luz reflejada por el objeto. |
-
2016
- 2016-08-30 JP JP2017543033A patent/JP6801666B2/ja active Active
- 2016-08-30 WO PCT/JP2016/075295 patent/WO2017056822A1/ja active Application Filing
- 2016-08-30 CN CN201680055410.3A patent/CN108028022B/zh active Active
- 2016-08-30 US US15/761,878 patent/US10769951B2/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH06293236A (ja) * | 1992-12-22 | 1994-10-21 | Mitsubishi Electric Corp | 走行環境監視装置 |
JP2000353231A (ja) * | 1999-06-10 | 2000-12-19 | Mitsubishi Electric Corp | 画像処理装置 |
JP2012142903A (ja) * | 2011-01-06 | 2012-07-26 | Ricoh Co Ltd | 撮像装置 |
WO2015045501A1 (ja) * | 2013-09-27 | 2015-04-02 | 日立オートモティブシステムズ株式会社 | 外界認識装置 |
JP2015133078A (ja) * | 2014-01-15 | 2015-07-23 | 株式会社リコー | 制御用対象物認識装置、移動体機器制御システム及び制御用対象物認識用プログラム |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3663882A4 (en) * | 2017-08-04 | 2020-08-12 | Sony Corporation | INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING PROCESS, PROGRAM AND MOBILE UNIT |
JPWO2019026714A1 (ja) * | 2017-08-04 | 2020-08-27 | ソニー株式会社 | 情報処理装置、および情報処理方法、プログラム、並びに移動体 |
US11373418B2 (en) | 2017-08-04 | 2022-06-28 | Sony Corporation | Information processing apparatus, information processing method, program, and mobile object |
JP7259749B2 (ja) | 2017-08-04 | 2023-04-18 | ソニーグループ株式会社 | 情報処理装置、および情報処理方法、プログラム、並びに移動体 |
WO2020049638A1 (ja) * | 2018-09-04 | 2020-03-12 | 株式会社ソニー・インタラクティブエンタテインメント | 情報処理装置およびプレイフィールド逸脱検知方法 |
JPWO2020049638A1 (ja) * | 2018-09-04 | 2021-08-12 | 株式会社ソニー・インタラクティブエンタテインメント | 情報処理装置およびプレイフィールド逸脱検知方法 |
JP7101250B2 (ja) | 2018-09-04 | 2022-07-14 | 株式会社ソニー・インタラクティブエンタテインメント | 情報処理装置およびプレイフィールド逸脱検知方法 |
Also Published As
Publication number | Publication date |
---|---|
US10769951B2 (en) | 2020-09-08 |
JP6801666B2 (ja) | 2020-12-16 |
CN108028022A (zh) | 2018-05-11 |
JPWO2017056822A1 (ja) | 2018-08-30 |
CN108028022B (zh) | 2021-06-15 |
US20180301032A1 (en) | 2018-10-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6760298B2 (ja) | 情報取得装置と情報取得方法 | |
US20230359213A1 (en) | Guiding vehicles through vehicle maneuvers using machine learning models | |
US10850680B2 (en) | Vehicle display apparatus and vehicle having the same | |
US11206388B2 (en) | Image processing apparatus and image processing method for aligning polarized images based on a depth map and acquiring a polarization characteristic using the aligned polarized images | |
JPWO2017159382A1 (ja) | 信号処理装置および信号処理方法 | |
JP6350383B2 (ja) | 車両走行制御装置 | |
WO2017212928A1 (ja) | 画像処理装置、画像処理方法、および車両 | |
US11908104B2 (en) | Weighted normalized automatic white balancing | |
US11891036B2 (en) | Leveraging rear-view sensors for automatic emergency braking in autonomous machine applications | |
US11948315B2 (en) | Image composition in multiview automotive and robotics systems | |
US11694408B2 (en) | Information processing device, information processing method, program, and movable object | |
JPWO2017057057A1 (ja) | 画像処理装置、画像処理方法、およびプログラム | |
US20240059295A1 (en) | Multi-view geometry-based hazard detection for autonomous systems and applications | |
WO2017056822A1 (ja) | 画像処理装置と画像処理方法および車両制御システム | |
US11954914B2 (en) | Belief propagation for range image mapping in autonomous machine applications | |
JP2018032986A (ja) | 情報処理装置および方法、車両、並びに情報処理システム | |
US11017671B2 (en) | Precautionary visual perception by detection of rear stop light of vehicle that is two vehicles ahead | |
JP2019145021A (ja) | 情報処理装置、撮像装置、及び撮像システム | |
WO2022061289A1 (en) | Simulating viewpoint transformations for sensor independent scene understanding in autonomous systems | |
US20230142299A1 (en) | Particle-Based Hazard Detection for Autonomous Machine Applications | |
JP2024007722A (ja) | 運転支援装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16850998 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2017543033 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15761878 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 16850998 Country of ref document: EP Kind code of ref document: A1 |