JP2006178652A - Vehicle environment recognition system and image processor - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a vehicle environment recognition system capable of recognizing a vehicle environment by specifying an image region in a necessary range according to the driving condition of a vehicle, and an image processor that constitutes the vehicle environment recognition system. <P>SOLUTION: An image processing part 26 reads from an image memory 23 an image picked up in one frame unit, and reads vehicle velocity v, steering angle α, and inclination angle β from a storage part 24 in synchronism with frame rates. Based on the vehicle velocity v, the steering angle α, and the inclination angle β read, the image processing part 26 refers to an LUT 261 to obtain a parameter for specifying a partial image. The partial image specified is temporarily stored in a frame memory 262. A walker recognition processing part 263 reads the partial image stored in the frame memory 262 and determines the similarities between the partial image read and standard patterns H1, H2 and so forth that are read from a standard pattern part 241. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention specifies an image area in a necessary range from a captured image obtained by imaging with an imaging device having a wide-angle or standard lens unit according to the running state of the vehicle, and The present invention relates to a vehicle periphery recognition system that recognizes a vehicle periphery by processing with an image processing device, and an image processing device that constitutes the vehicle periphery recognition system.

  A video camera is installed in the front of a vehicle (for example, an automobile) to capture pedestrians in front of the vehicle, and the captured images are displayed on a display device such as a head-up display to prompt the driver to pay attention. A system has been proposed.

  The video camera used in such a system can recognize a pedestrian far in front of the vehicle (for example, 30 to 150 m) with a required size on the display even when the vehicle travels at a high speed. And a narrow-angle lens (telephoto lens) having a viewing angle of about 10 to 15 °. However, in a video camera using a narrow-angle lens, when a vehicle turns a curve or the like, a pedestrian that exists in the vehicle's turning direction may not be fully recognized. There is a system that drives left and right (see Patent Document 1).

Also, with a video camera using a narrow-angle lens, when the vehicle travels at a low speed, the field of view in the left-right direction of the vehicle cannot be sufficiently secured, and pedestrians around the vehicle may not be sufficiently recognized. A system has also been proposed in which a video camera having a zoom lens and a zoom mechanism is arranged around the front grille of a vehicle and the angle of view is changed by driving the zoom lens according to the speed of the vehicle (see Patent Document 2). .
JP 2002-31898 A JP-A-7-105481

  However, in the system of Patent Document 1, since the narrow-angle lens has a large aperture, the shape of the video camera must be large. For this reason, the drive device for driving the video camera to the left and right according to the steering angle is enlarged, and it is difficult to attach the video camera and the drive device to a limited storage location in the front part of the vehicle such as the front grille. In some cases, the vehicle design could be adversely affected.

  Further, the system of Patent Document 2 has a movable part for driving a zoom lens by a stepping motor. Such moving parts may cause a decrease in the reliability of the vehicle against external factors peculiar to the vehicle, such as vibration applied during vehicle travel, temperature change of the outside air, dust from the outside air, and rain. It was. For this reason, the use of the zoom mechanism in a vehicle tends to be avoided, and a mechanism that replaces the zoom mechanism has been desired in order to improve the reliability of the vehicular image recognition apparatus.

  Furthermore, since the optical axis of the video camera lens is fixed in a predetermined direction in front of the vehicle, when the vehicle is traveling on a rough road, the optical axis of the lens also fluctuates up and down when the vehicle tilts back and forth. Therefore, there is a possibility that a pedestrian in front of the vehicle cannot be recognized.

  The present invention has been made in view of such circumstances, and includes a specifying unit that specifies, as a partial image, a part of a captured image obtained by imaging based on the running state of the vehicle, By recognizing the periphery of the vehicle based on the specified partial image, it is possible to recognize the periphery of the vehicle according to the traveling state of the vehicle without using a drive device that drives the video camera or a zoom mechanism. It is an object of the present invention to provide a vehicle periphery recognition system and an image processing apparatus constituting the vehicle periphery recognition system.

  Another object of the present invention is to change the size of the partial image in the captured image according to the speed of the vehicle, so that the vehicle periphery can be changed even when the speed of the vehicle changes. The object is to provide a vehicle periphery recognition system capable of recognizing.

  Another object of the present invention is to change the position of the partial image in the captured image to the left and right according to the steering angle, so that the vehicle periphery can be recognized even when the vehicle is turning a curve. An object of the present invention is to provide a vehicle periphery recognition system.

  Another object of the present invention is when the vehicle travels on a rough road by changing the position of the partial image in the captured image up and down according to the front and rear inclination angles of the vehicle. Another object of the present invention is to provide a vehicle periphery recognition system capable of recognizing the vehicle periphery.

  A vehicle periphery recognition system according to a first aspect of the present invention is the vehicle periphery recognition system in which the periphery of the vehicle is imaged by an imaging device, and the captured image obtained by imaging is processed by the image processing device to recognize the vehicle periphery. The apparatus includes a lens unit having a wide angle or a standard angle of view, and the image processing apparatus acquires the information related to the traveling state of the vehicle, the imaging unit based on the information acquired by the acquisition unit A specifying unit that specifies a part of the image as a partial image, and the vehicle periphery is recognized based on the partial image specified by the specifying unit.

  In the vehicle periphery recognition system according to a second aspect of the present invention, in the first aspect, the acquisition unit acquires a vehicle speed, and the specifying unit includes a changing unit that changes the size of the partial image. The changing means is characterized in that the size of the partial image in the captured image is changed according to the level of the acquired vehicle speed.

  In the vehicle periphery recognition system according to a third aspect, in the first aspect, the acquisition unit acquires a steering angle, and the specifying unit includes a changing unit that changes a position of the partial image in the captured image. And the changing means is configured to change the position of the partial image in the captured image to the left or right according to the magnitude of the acquired steering angle.

  In the vehicle periphery recognition system according to a fourth aspect of the present invention, in the first aspect, the acquisition unit acquires a front and rear inclination angle of the vehicle, and the specifying unit changes a position of the partial image in the captured image. The changing unit is configured to change the position of the partial image in the captured image up and down according to the acquired inclination angle.

  An image processing apparatus according to a fifth aspect of the present invention is an image processing apparatus that processes captured images and recognizes the periphery of the vehicle, an acquisition unit that acquires information related to the running state of the vehicle, and information acquired by the acquisition unit And a specifying means for specifying a part of the captured image as a partial image, and the vehicle periphery is recognized based on the partial image specified by the specifying means.

  In the first invention and the fifth invention, the periphery of the vehicle is imaged by an imaging device having a wide angle or standard lens portion. The acquisition unit of the image processing apparatus acquires information related to the running state of the vehicle. The specifying unit specifies, as a partial image, a part of the captured image obtained by imaging with the imaging device based on the information acquired by the acquiring unit. Accordingly, the image processing apparatus recognizes the periphery of the vehicle by processing a partial image having a required imaging region in accordance with the traveling state of the vehicle.

  In the second invention, the acquisition means acquires the vehicle speed. The changing means changes the size of the partial image in the captured image according to the level of the vehicle speed. For example, as the vehicle speed increases, the partial image is reduced and the apparent angle of view of the lens unit is reduced. Further, as the vehicle speed becomes lower, the partial image is enlarged and the apparent angle of view of the lens unit is increased.

  In the third invention, the acquisition means acquires a steering angle. The changing unit changes the position of the partial image in the captured image to the left and right according to the magnitude of the steering angle. For example, when the vehicle turns a right curve, the position of the partial image in the captured image is changed to the right. When the vehicle turns a left curve, the position of the partial image in the captured image is changed to the left.

  In the fourth invention, the acquisition means acquires the front and rear inclination angles of the vehicle. The changing unit changes the position of the partial image in the captured image up and down according to the inclination angle. For example, when the vehicle is tilted forward and upward, the position of the partial image in the captured image is changed downward. Further, when the vehicle is inclined forward and downward, the position of the partial image in the captured image is changed upward.

  In the first invention and the fifth invention, a part of the captured image obtained by imaging with the imaging device is specified as a partial image according to the traveling state of the vehicle, and the periphery of the vehicle is identified using the partial image. By recognizing, it is possible to recognize a pedestrian, an obstacle, and the like in a required imaging region according to the running state of the vehicle without using a video camera driving device or a zoom mechanism. Further, since a part of the captured image is processed, the processing time can be shortened and the processing capability can be reduced as compared with the case where all the captured images are processed.

  In the second invention, by changing the size of the partial image according to the speed of the vehicle, for example, when the vehicle is traveling at a high speed, the partial image is reduced and the apparent angle of view is reduced. It can be made small and the visibility of the long distance ahead of the vehicle can be enhanced. In addition, when the vehicle is traveling at a low speed, the partial image can be enlarged and the apparent angle of view can be increased to improve the visibility of the front left and right periphery of the vehicle.

  In the third aspect of the invention, by changing the position of the partial image in the captured image to the left or right according to the steering angle, for example, when the vehicle turns a right curve, the position of the partial image is changed to the right. Thus, the visibility of the vehicle turning direction can be improved. In addition, when the vehicle turns a left curve, the position of the partial image can be changed to the left to improve the visibility of the vehicle turning direction.

  In the fourth aspect of the invention, the position of the partial image in the captured image is changed up and down according to the front and rear inclination angles of the vehicle, for example, the vehicle travels on a rough road and is inclined upward in the front direction of the vehicle. In that case, the position of the partial image can be changed downward to improve the visibility in front of the vehicle. Further, when the vehicle is tilted downward in the front direction of the vehicle, the position of the partial image can be changed in the upward direction to improve the visibility in front of the vehicle.

  Hereinafter, the present invention will be described with reference to the drawings illustrating embodiments. FIG. 1 is a schematic diagram showing an outline of a vehicle periphery recognition system according to the present invention. In the figure, reference numeral 1 denotes a video camera that is mounted on a vehicle and images a pedestrian or the like. The video camera 1 is installed on the front grille and is connected to the image processing apparatus 2 via a communication line 7 for in-vehicle LAN conforming to IEEE1394.

  The image processing apparatus 2 includes a display device 3 having an operation unit and an alarm unit via a communication line 7, a steering angle sensor 4 for detecting a steering angle of a steering wheel, a lower surface of a vehicle body, and a front part and a rear part of the vehicle Distance sensors 5a and 5b that detect the distance from the ground (road surface) and a speed sensor 6 that detects the speed of the vehicle are connected to each other. The inclination angle indicating the inclination of the vehicle is calculated from the difference in distance from the ground detected by the distance sensors 5a and 5b and the distance between the distance sensors 5a and 5b.

  FIG. 2 is a block diagram showing the configuration of the video camera 1. Reference numeral 11 denotes an imaging unit. The imaging unit 11 includes glass lenses 111 and 112 having a standard angle of view (for example, 30 ° to 50 °), and a CCD or the like arranged so that the optical axes of the lenses 111 and 112 are positioned at the center of the imaging surface. An image sensor 113. The size of the captured image captured by the image sensor 113 has, for example, 1280 × 960 pixels. The light transmitted through the lenses 111 and 112 is input to the image sensor 113. The image sensor 113 converts the input light into RGB (R: red, G: green, B: blue) analog signals and outputs them to the signal processing unit 12.

  The signal processing unit 12 converts an analog signal input from the image sensor 113 into a digital signal, a process for removing various distortions generated in the optical system, a low-frequency noise removal process, and a correction process for correcting gamma characteristics. And so on. Further, the RGB signal is converted into a YUV (Y: luminance, U, V: color difference) signal, and a captured image having the converted YUV signal for each pixel is temporarily stored in the image memory 14.

  The interface unit 13 performs control for outputting a captured image stored in the image memory 14 to the image processing device 2 according to a command transmitted from the image processing device 2, and a transfer rate according to the resolution of the image captured by the video camera 1. Conversion, creation of packet data from image data of the captured image, and the like are performed. Further, the interface unit 13 outputs the captured image stored in the image memory 14 to the image processing device 2 under the control of the control unit 15.

  The control unit 15 controls processing of the imaging unit 11, the signal processing unit 12, and the interface unit 13 via the bus 16. For example, a command from the image processing device 2 is interpreted, and a captured image captured by the imaging unit 11 is stored in the image memory 14. Further, the stored captured image is read and output to the image processing apparatus 2 via the interface unit 13.

  FIG. 3 is a block diagram illustrating a configuration of the image processing apparatus 2. In the figure, reference numeral 21 denotes an interface unit that transfers instructions to the video camera 1 and transfers image data of a captured image from the video camera 1.

  The input unit 22 receives data such as the steering angle α detected by the steering angle sensor 4 and the vehicle speed v detected by the speed sensor 6, and stores the received data in the storage unit 24 described later. The input unit 22 receives distance data detected by the distance sensors 5a and 5b, calculates an inclination angle β indicating the inclination of the vehicle based on the received distance data, and stores the calculated inclination angle β. To remember.

  The storage unit 24 stores a standard pattern unit 241 for storing standard patterns H1, H2,... For recognizing pedestrians, a vehicle speed v, a steering angle α, and a vehicle inclination angle β input via the input unit 22. And a vehicle information unit 242 for storing. The standard patterns H1, H2,... Have a luminance distribution corresponding to the human luminance distribution, and have a plurality of patterns according to the human body shape, the distinction between children and adults, clothes, postures, and the like.

  The control unit 27 stores the captured image input from the video camera 1 via the interface unit 21 in the image memory 23 in units of one frame in synchronization with the frame rate of the video camera 1. Further, the control unit 27 outputs the captured image stored in the image memory 23 to the image processing unit 26 in units of frames. The control unit 27 has a built-in timer (not shown), and reads the vehicle speed v, the steering angle α, and the inclination angle β stored in the storage unit 24 in synchronization with the frame rate of the video camera 1. To the image processing unit 26.

  The image processing unit 26 corresponds to information related to the running state of the vehicle (vehicle speed v, steering angle α, inclination angle β), and stores an LUT (Look Up Table) that stores parameters for specifying a partial image to be described later. 261, a frame memory 262 for storing a partial image in which a part of a captured image read from the image memory 23 in units of one frame is specified, and a pedestrian recognition process based on the partial image stored in the frame memory 262 A pedestrian recognition processing unit 263.

  The image processing unit 26 reads a captured image in units of one frame from the image memory 23, and reads the vehicle speed v, the steering angle α, and the inclination angle β from the storage unit 24 in synchronization with the frame rate. The image processing unit 26 refers to the LUT 261 based on the read vehicle speed v, steering angle α, and inclination angle β, acquires parameters for specifying the partial image, and temporarily stores the specified partial image in the frame memory 262. Remember.

  The pedestrian recognition processing unit 263 reads the partial image stored in the frame memory 262, and determines the degree of similarity between the read partial image and the standard patterns H1, H2,... Read from the standard pattern unit 241. That is, the pedestrian recognition processing unit 263 calculates a predetermined correlation value between the partial image and the standard patterns H1, H2,..., And the calculated correlation value is stored in the pedestrian recognition processing unit 263 in advance as the threshold value TH. In the case where it is larger, it is assumed that there is a pedestrian, and processing for attaching a rectangular frame surrounding the pedestrian is performed to highlight the recognized pedestrian, and the processed image data is output to the output unit 25 To do.

  The image processing unit 26 performs the above-described processing in units of one frame, and when the processing for the captured image for one frame is completed, the image processing unit 26 continues the same processing for the next frame and outputs the processed image data to the output unit. To 25.

  The output unit 25 outputs the input image data to the display device 3.

  Based on the image data output from the image processing device 2, the display device 3 displays the presence of the recognized pedestrian on the display along with the external environment. When a pedestrian is recognized, a warning sound is emitted according to the position, distance, etc. of the pedestrian.

  FIG. 4 is a record layout showing the configuration of the LUT 261. The LUT 261 determines the size and position of a partial image indicating a partial range of a captured image captured by the video camera 1 according to the vehicle speed v, the steering angle α, and the vehicle inclination angle β. As shown in the figure, the LUT 261 corresponds to the vehicle speed v, the x and y coordinates of the start point pixel (upper left pixel) of the partial image in the captured image (the number of pixels in the x and y directions with the upper left pixel of the captured image as the origin). ), The number of pixels in the horizontal direction of the partial image, and the number of pixels in the vertical direction, and the same applies to the steering angle α and the inclination angle β. The steering angle when the vehicle is steered to the left is positive, the steering angle when the vehicle is steered to the right is negative, the tilt angle when the vehicle is tilted forward and upward is positive, and the tilt angle is tilted downward and forward The tilt angle is negative.

  For example, when the vehicle speed is v1, the x and y coordinates of the start point pixel are x1 and y1, respectively, and the number of pixels in the horizontal and vertical directions of the partial image is a1 and b1, respectively. When the vehicle speed is v2 (v2> v1), the x and y coordinates of the start pixel are x2 (x2> x1) and y2 (y2> y1), respectively, and the horizontal and vertical pixels of the partial image The numbers are a2 (a2 <a1) and b2 (b2 <b1), respectively. As a result, the partial image becomes smaller as the vehicle speed v increases.

  The size of the partial image with respect to the angle of view of the video camera 1 is 40 ° x 30 ° (horizontal x vertical) and the size of the captured image (1280 x 960 pixels) is, for example, 940 x 705 pixels and vehicle speed 50 km / h can be set to 750 × 562 pixels, and the vehicle speed can be set to 460 × 345 pixels when the vehicle speed is 80 km / h. As a result, the apparent angle of view of the video camera 1 is 30 ° x 23 ° (horizontal x vertical), 24 ° x 18 °, and 15 ° x 11 °, respectively. In addition, when traveling at high speed, it is possible to capture a pedestrian or the like existing far in front of the vehicle with a sufficient size.

  When the steering angle is α1, the x and y coordinates of the start pixel are x31 and y3, respectively, and the number of pixels in the horizontal and vertical directions of the partial image is a3 and b3, respectively. When the steering angle is 0, the x and y coordinates of the start pixel are x32 (x32> x31) and y3, respectively, and the number of pixels in the horizontal and vertical directions of the partial image are a3 and b3, respectively. . When the steering angle is −α1, the x and y coordinates of the start pixel are x33 (x33> x32) and y3, respectively, and the number of pixels in the horizontal and vertical directions of the partial image is a3 and b3, respectively. is there. As a result, when the vehicle turns a left curve, the position of the partial image moves to the left in the captured image, and when the vehicle turns the right curve, the position of the partial image moves to the right in the captured image. When the vehicle goes straight, the position of the partial image is symmetrical with respect to the vertical line passing through the center of the captured image. When the partial image is specified by simultaneously detecting the vehicle speed v and the steering angle α, the number of pixels in the horizontal and vertical directions of the partial image can be determined according to the vehicle speed v.

  When the inclination angle is β1, the x and y coordinates of the start pixel are x4 and y41, respectively, and the number of pixels in the horizontal and vertical directions of the partial image is a4 and b4, respectively. When the tilt angle is 0, the x and y coordinates of the start pixel are x4 and y42 (y42 <y41), respectively, and the number of pixels in the horizontal and vertical directions of the partial image is a4 and b4, respectively. . When the steering angle is −β1, the x and y coordinates of the start pixel are x4 and y43 (y43 <y42), respectively, and the number of pixels in the horizontal and vertical directions of the partial image is a4 and b4, respectively. is there. As a result, when the vehicle is tilted forward and upward, the position of the partial image moves downward in the captured image, and when the vehicle is tilted forward and downward, the position of the partial image is upward in the captured image. When the vehicle moves in the direction and the vehicle is not inclined, the position of the partial image is vertically symmetrical with respect to a horizontal line passing through the center of the captured image. Note that when the partial image is specified by simultaneously detecting the vehicle speed v and the inclination angle β, the number of pixels in the horizontal and vertical directions of the partial image can be determined according to the vehicle speed v.

  Next, the operation of the vehicle periphery recognition system according to the present invention will be described. When the driver operates the operation unit provided in the display device 3 to turn on the operation switch of the video camera 1, the image processing device 2 that has received the operation signal from the operation unit receives the operation signal via the interface unit 21. An initial command is sent to the video camera 1.

  The video camera 1 that has received the initial command starts imaging around the vehicle from the imaging unit 11. The signal processing unit 12 once records a captured image obtained by imaging in the image memory 14, and then transmits the captured image for one frame in synchronization with the frame rate of the video camera 1 via the interface unit 13. The data is sent to the processing device 2.

  The image processing apparatus 2 temporarily stores the captured image for one frame in the image memory 23. The image processing unit 26 reads the captured image stored in the image memory 23 and reads the vehicle speed v, the steering angle α, and the inclination angle β from the storage unit 24 in synchronization with the frame rate.

  The image processing unit 26 reads parameters for specifying the range of the partial image from the LUT 261 based on the read vehicle speed v, steering angle α, and inclination angle β, and specifies the range of the partial image from the captured image read from the image memory 23. The specified partial image is stored in the frame memory 262. In this case, the image processing unit 26 sequentially scans from the upper left pixel to the lower right pixel of the captured image for one frame, and extracts the corner pixels constituting the partial image according to the read parameters.

  The pedestrian recognition processing unit 263 reads the partial image stored in the frame memory 262, determines the similarity between the read partial image and the standard patterns H1, H2,. Is present, a process of applying a rectangular frame surrounding the pedestrian is performed to highlight the recognized pedestrian, and the processed image data is output to the output unit 25.

  Based on the image data output via the output unit 25, the display device 3 displays the presence of the recognized pedestrian on the display along with the external environment. When a pedestrian is recognized, a warning sound is emitted according to the position, distance, etc. of the pedestrian.

  5 to 7 are explanatory diagrams showing the positional relationship of the partial images in the captured image. As shown in the figure, when the vehicle speed increases from v1 to v2 (v2> v1), the size of the partial image 50 is reduced to the size of the partial image 51 in the captured image 100. Since the number of pixels of the partial image 51 is smaller than the number of pixels of the partial image 50, when an image is displayed on a display device of a predetermined size, the pedestrian recognized in the partial image 51 is displayed large. The

  Further, when the vehicle is steered leftward, the position of the partial image 52 moves leftward in the captured image 50, and when the vehicle is moved straight, the position of the partial image 53 is centered on the captured image 50. When the vehicle is steered rightward with respect to the passing vertical line, the position of the partial image 54 moves rightward in the captured image 50.

  When the vehicle is tilted forward and upward, the position of the partial image 55 moves downward in the captured image 50. When the vehicle is not tilted, the position of the partial image 56 is the position of the captured image 50. When the vehicle is vertically symmetrical with respect to a horizontal line passing through the center and the vehicle is inclined forward and downward, the position of the partial image 57 moves upward in the captured image 50.

  As described above, according to the present invention, from a high-resolution captured image captured by a video camera having a standard angle of view, one of the captured images according to the vehicle speed v, the steering angle α, and the tilt angle β. Even if the driving state of the vehicle changes by specifying the partial image that is a part and changing the size of the partial image and the position of the partial image in the captured image, the video camera drive device or zoom mechanism is used. Therefore, an imaging region necessary for pedestrian recognition can be cut out, and pedestrian recognition can be performed.

  In the above-described embodiment, the video camera has a CCD. However, the video camera is not limited to this and may have a CMOS. Further, the video camera is not limited to a visible light video camera, and may be a far infrared light video camera using a far infrared imaging device such as a bolometer type, a thermopile type, a pyroelectric type, or an SOI diode. Alternatively, a configuration using a video camera for mid-infrared light or a video camera for near-infrared light may be used. In this case, a wide-angle lens made of germanium, zinc sulfide, or the like can be used.

  In the above-described embodiment, the parameters of the partial image are stored in the LUT. However, the present invention is not limited to this, and the vehicle speed v, the steering angle α, the inclination detected in synchronization with the frame rate are not limited thereto. The configuration may be such that the parameter is calculated based on the angle β.

  In the above-described embodiment, the size of the image sensor (number of pixels) and the size of the partial image are examples, and are not limited thereto.

  In the above-described embodiment, the case of recognizing a pedestrian as recognizing the periphery of the vehicle has been described, but this is an example, and the present invention is not limited to this. That is, in addition to pedestrians, obstacles on the road, nearby vehicles, road surface displays, road signs, and other objects around the vehicle can be recognized.

  In the above-described embodiment, the configuration uses the x and y coordinates of the start pixel and the number of pixels in the horizontal and vertical directions as the parameters of the partial image. However, the present invention is not limited to this. Any parameter may be used as long as it can specify the size and position of the partial image.

  In the above-described embodiment, a lens having a standard angle of view is used. However, a lens having a wide angle of view (50 ° or more) may be used.

  In the above-described embodiment, the specific image specified based on the parameters read from the LUT 261 is stored in the frame memory 262. However, the specification of the specific image is not limited to this, and the partial image is not limited to this. The configuration may be such that the coordinates of each pixel on the boundary that identifies the pedestrian are stored, and the pedestrian recognition process is performed in the area surrounded by each pixel based on the stored coordinates of each pixel.

It is a schematic diagram which shows the outline | summary of the vehicle periphery recognition system which concerns on this invention. It is a block diagram which shows the structure of a video camera. It is a block diagram which shows the structure of an image processing apparatus. It is a record layout which shows the structure of LUT. It is explanatory drawing which shows the positional relationship of the partial image in a captured image. It is explanatory drawing which shows the positional relationship of the partial image in a captured image. It is explanatory drawing which shows the positional relationship of the partial image in a captured image.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Video camera 2 Image processing apparatus 3 Display apparatus 4 Steering angle sensor 5a, 5b Distance sensor 6 Speed sensor 11 Imaging part 110 Transmission window 111, 112 Wide angle lens 113 Imaging element 12 Signal processing part 13 Interface part 14 Image memory 15 Control part 21 Interface unit 22 Input unit 23 Image memory 24 Storage unit 25 Output unit 26 Image processing unit 242 Vehicle information unit 261 LUT
262 Frame memory 263 Pedestrian recognition processing unit

Claims (5)

In a vehicle periphery recognition system that captures the periphery of a vehicle with an imaging device, processes the captured image obtained by imaging with the image processing device and recognizes the periphery of the vehicle,
The imaging device
The angle of view has a wide angle or standard lens part,
The image processing apparatus includes:
Obtaining means for obtaining information relating to the running state of the vehicle;
A specifying unit that specifies a part of the captured image as a partial image based on the information acquired by the acquiring unit;
A vehicle periphery recognition system characterized in that the periphery of the vehicle is recognized based on the partial image specified by the specifying means. The acquisition means includes
To get the vehicle speed,
The specifying means is:
Changing means for changing the size of the partial image;
The changing means is
The vehicle periphery recognition system according to claim 1, wherein the size of the partial image in the captured image is changed according to the acquired vehicle speed. The acquisition means includes
The steering angle is acquired,
The specifying means is:
Changing means for changing the position of the partial image in the captured image;
The changing means is
2. The vehicle periphery recognition system according to claim 1, wherein the position of the partial image in the captured image is changed to the right and left in accordance with the acquired steering angle. The acquisition means includes
The vehicle's front and rear tilt angles are obtained,
The specifying means is:
Changing means for changing the position of the partial image in the captured image;
The changing means is
The vehicle periphery recognition system according to claim 1, wherein the position of the partial image in the captured image is changed up and down in accordance with the acquired inclination angle. In the image processing apparatus that recognizes the vehicle periphery by processing the captured image,
Obtaining means for obtaining information relating to the running state of the vehicle;
A specifying unit that specifies a part of the captured image as a partial image based on the information acquired by the acquiring unit;
An image processing apparatus characterized in that a vehicle periphery is recognized based on a partial image specified by the specifying means.

Images