JP2006331217A - Image processing system and image processing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To accurately recognize a recognition object. <P>SOLUTION: This image processing system is provided with a vehicle speed detection part for detecting a vehicle speed, an imaging device which is mounted on the predetermined part of a vehicle and photographs an object to be photographed to generate image data, a recognition area setting processing means for setting a recognition area in an image region where an image constituted of the image data is formed, a recognition area movement processing means for moving the recognition area according to the speed and a recognition object recognition processing means for recognizing the recognition object in the recognition area. In this case, the recognition area set in the image region is moved according to the speed, so that it is possible to increase the recognition rate of the recognition object, and to increase the recognition precision. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to an image processing system and an image processing method.

  Conventionally, in a navigation apparatus, for example, the current position of a vehicle, that is, the current position is detected by GPS (Global Positioning System), and the direction of the vehicle, that is, based on the turning angle of the vehicle detected by a gyro sensor, that is, The vehicle direction is detected, map data is read from the data recording unit, a map screen is formed on the display unit, the vehicle position indicating the current location, a map around the vehicle position, and the vehicle The direction is displayed. Therefore, the driver who is an operator can drive the vehicle according to the own vehicle position displayed on the map screen, the map around the own vehicle position, and the own vehicle direction.

  When the driver inputs a destination and sets search conditions, a route search process is performed based on the search conditions, and a route from the starting point represented by the current location to the destination is searched according to the map data. Is done. Then, the searched route, that is, the searched route is displayed on the map screen together with the vehicle position, and guidance for the searched route, that is, route guidance is performed. Therefore, the driver can drive the vehicle along the displayed search route.

By the way, a camera is mounted on the front end of the vehicle, a vehicle lane boundary line of a traveling lane representing a lane in which the vehicle is traveling is photographed as an object to be photographed by the camera, image data is generated, and the image data A travel support system is provided that recognizes the object to be recognized as a recognition object by performing image processing on the object, and performs travel support based on the recognized recognition object (see, for example, Patent Document 1). .)
JP-A-9-264554

  However, in the conventional driving support system, only the lower portion where the road in the image exists is set as an area for recognizing the recognition object, that is, a recognition area. When the portion where the road is present becomes large, the entire road becomes the recognition area, and the load of image processing increases.

  Therefore, it is conceivable that a portion smaller than the portion where the road exists is set as a recognition area, and the recognition object is recognized in the recognition area. In that case, if the recognition area is set near the camera, the distance on the actual road in the recognition area is shortened, so that the recognition accuracy can be improved. However, since the recognition object in the image moves relative to the vehicle, when the vehicle speed is high, the number of frames (hereinafter referred to as “frame number”) corresponding to the number of shutters at the time of shooting for the recognition object. The recognition rate is reduced accordingly.

  On the other hand, if a recognition area is set in a part away from the camera, the number of frames for the recognition object increases even when the vehicle speed is high, so that the recognition rate can be increased, but on the actual road in the recognition area. Since the distance becomes longer, the recognition accuracy is lowered accordingly.

  As described above, since the recognition rate is lowered and the recognition accuracy is lowered, the recognition target cannot be accurately recognized.

  It is an object of the present invention to provide an image processing system and an image processing method capable of solving the problems of the conventional driving support system and accurately recognizing an object to be recognized.

  Therefore, in the image processing system of the present invention, a vehicle speed detection unit that detects a vehicle speed, an imaging device that is attached to a predetermined portion of the vehicle and shoots an object to generate image data, and the image data A recognition area setting processing means for setting a recognition area in an image area where an image is formed, a recognition area movement processing means for moving the recognition area according to a vehicle speed, and a recognition object in the recognition area is recognized. Recognition object recognition processing means.

  According to the present invention, since the recognition area set in the image region is moved according to the vehicle speed, it is possible to increase the recognition rate of the recognition target object or increase the recognition accuracy. Therefore, the recognition object can be accurately recognized.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a diagram showing a navigation system according to an embodiment of the present invention.

  In the figure, reference numeral 10 denotes an automatic transmission control unit as a power train control unit. The automatic transmission control unit 10 is a power train that performs a shift at a predetermined gear ratio, for example, a continuously variable transmission as an automatic transmission. (CVT), stepped transmission (automatic transmission), electric drive device, etc. are controlled.

  Reference numeral 14 is an information terminal, for example, a navigation device as an in-vehicle device mounted on a vehicle, 63 is a network, 51 is an information center as an information provider, and the automatic transmission control unit 10, the navigation device 14, the network 63, the information center 51 and the like constitute a navigation system.

  The navigation device 14 includes a GPS sensor 15 as a current location detection unit for detecting a current location, a data recording unit 16 as an information recording unit in which various information is recorded in addition to map data, and navigation based on the input information. A navigation processing unit 17 that performs various arithmetic processing such as processing, a direction sensor 18 that serves as a direction detection unit that detects the vehicle direction, and a first input for performing predetermined input when operated by a driver as an operator. An operation unit 34 as an input unit, various displays by an image displayed on a screen (not shown), a display unit 35 as a first output unit for notifying the driver, and a predetermined input by voice A voice input unit 36 as a second input unit, a voice output unit 3 as a second output unit for performing various displays by voice and notifying the driver , And a communication unit 38 as a transmission / reception unit functioning as a communication terminal. The navigation processing unit 17 includes a GPS sensor 15, a data recording unit 16, an orientation sensor 18, an operation unit 34, a display unit 35, a voice input unit 36, An audio output unit 37 and a communication unit 38 are connected.

  The navigation processing unit 17 is attached to the automatic transmission control unit 10, a predetermined position at the front end of the vehicle, and a front monitoring device 48 for monitoring the front of the vehicle, and a predetermined position at the rear end of the vehicle. The rear camera (rear monitoring camera) 49 as an imaging device that captures the rear of the vehicle and an accelerator as an engine load detection unit that detects the operation of the accelerator pedal by the driver based on the accelerator opening A sensor 42, a brake sensor 43 as a braking detection unit that detects the operation of the brake pedal by the driver by a brake depression amount, a vehicle speed sensor 44 as a vehicle speed detection unit that detects the vehicle speed S, and the like are connected. The accelerator sensor 42, the brake sensor 43, and the like constitute an operation information detection unit for detecting vehicle operation information by the driver.

  The GPS sensor 15 detects the current location on the earth by receiving radio waves generated by an artificial satellite, and also detects the time. In the present embodiment, the GPS sensor 15 is used as the current position detection unit, but a distance sensor, a steering sensor, an altimeter, etc. (not shown) are used alone or in combination instead of the GPS sensor 15. You can also Further, a gyro sensor, a geomagnetic sensor, or the like can be used as the direction sensor 18.

  The data recording unit 16 includes a map database including map data files, and map data is recorded in the map database. The map data includes intersection data related to intersections, node data related to nodes, road data related to road links, search data processed for searching, facility data related to facilities, and feature data related to features. .

  The feature is a display object that is installed or formed on a road in order to provide various driving information to the driver or to perform various driving guidance. , Crosswalks, manholes, traffic lights, etc. The display line includes a stop line for stopping the vehicle, a vehicle lane boundary line that divides each lane, a partition line that indicates a parking space, and the road sign indicates an advancing direction in each lane. , A guidance sign for notifying a stop point such as “stop”, and the like. The feature data includes position information that represents the position of each feature by coordinates, image information that represents each feature by image, and the like. The temporary stop points include an entry point from a non-priority road to a priority road, a railroad crossing, an intersection where a red light flashes, and the like.

  The road data related to the lane includes lane data including a lane number assigned to each lane on the road, lane position information, and the like. Data for outputting predetermined information by the audio output unit 37 is also recorded in the data recording unit 16.

  Further, the data recording unit 16 includes a statistical database composed of statistical data files, a travel history database composed of travel history data files, and the like. Statistical data is stored in the statistical data file, and travel history data is stored in the travel history data file. However, both are recorded as performance data.

  The statistical data is a history of traffic information provided in the past, that is, history information representing a history, and a road traffic information center (not shown) such as a VICS (registered trademark: Vehicle Information and Communication System) center as an information provider. The road traffic census information that is the traffic information provided in the past by the Ministry of Land, Infrastructure, Transport and Tourism, the road traffic census information that is the data showing the traffic volume by the Road Traffic Census, the road timetable information provided by the Ministry of Land, Infrastructure, Transport and Tourism, etc. Alternatively, they are used in combination, processed as necessary, and subjected to statistical processing. It is possible to add traffic jam prediction information for predicting traffic jams to the statistical data. In that case, in creating the statistical data, detailed conditions such as date and time, day of the week, weather, various events, seasons, facility information (presence / absence of large facilities such as department stores and supermarkets) are added to the history information.

  The data items of the statistical data include a link number for each road link, a direction flag indicating a traveling direction, an information type indicating a type of information, a congestion level at each predetermined timing, and when traveling on each road link. It consists of a link required time representing a required time for each predetermined timing, average data for each day of the link required time (for example, day average data), and the like.

  Further, the travel history data is collected from a plurality of vehicles, that is, the own vehicle or other vehicles by the information center 51, and is a record of the travel of the vehicle on the road on which each vehicle travels, that is, the track record information representing the track record. It is calculated and accumulated as probe data based on the running data.

  The data items of the travel history data include a link required time at each predetermined timing when traveling on each road link, a degree of congestion at each predetermined timing when traveling on each road link, and the like. Note that travel history data can be added to the statistical data. Further, in the present embodiment, the congestion level is used as a congestion index that represents the degree of congestion, and is represented separately for congestion, congestion, and non-congestion.

  The data recording unit 16 includes a disk (not shown) such as a hard disk, a CD, a DVD, and an optical disk in order to record the various data, and also reads / writes for reading and writing various data. A head (not shown) such as a head is provided. A memory card or the like can be used for the data recording unit 16.

  In the present embodiment, the data recording unit 16 is provided with the map database, statistical database, travel history database, and the like. However, in the information center 51, the map database, statistical database, travel history, etc. A history database or the like can also be provided.

  The navigation processing unit 17 is a control device that performs overall control of the navigation device 14 and a CPU 31 as an arithmetic device, a RAM 32 that is used as a working memory when the CPU 31 performs various arithmetic processes, In addition to the above program, a ROM 33 in which various programs for searching for a route to the destination, route guidance and the like are recorded, and a flash memory (not shown) used for recording various data, programs and the like are provided. .

  In the present embodiment, various programs can be recorded in the ROM 33 and various data can be recorded in the data recording unit 16, but the programs, data, and the like can also be recorded on a disk or the like. In this case, the program, data, etc. can be read from a disk or the like and written to the flash memory. Therefore, the program, data, etc. can be updated by exchanging the disk or the like. Further, the control program, data, and the like of the automatic transmission control unit 10 can be recorded on the disk or the like. Further, the program, data, and the like can be received via the communication unit 38 and written into the flash memory of the navigation processing unit 17.

  The operation unit 34 is operated by the driver to correct the current location at the start of traveling, to input a departure point and a destination, to input a passing point, and to activate the communication unit 38. As the operation unit 34, a keyboard, a mouse, or the like disposed independently of the display unit 35 can be used. Further, as the operation unit 34, a predetermined input operation is performed by touching or clicking an image operation unit such as various keys, switches, and buttons displayed as images on the screen formed in the display unit 35. It is possible to use a touch panel that can be used.

  A display is used as the display unit 35. Then, on various screens formed on the display unit 35, the current position of the vehicle is displayed as the vehicle position, the vehicle direction is displayed as the vehicle direction, a map, a search route, guidance information along the search route, traffic In addition to displaying information and the like, displaying the distance to the next intersection on the searched route, and the traveling direction at the next intersection, the operation of the image operation unit, operation unit 34, voice input unit 36, etc. It is possible to display guidance, operation menus, key guidance, FM multiplex broadcast programs, and the like.

  The voice input unit 36 includes a microphone (not shown) and the like, and can input necessary information by voice. Further, the voice output unit 37 includes a voice synthesizer and a speaker (not shown), and the search route, guidance information, traffic information, and the like are output from the voice output unit 37, for example, as voice synthesized by the voice synthesizer. .

  The communication unit 38 transmits various information such as current traffic information and general information transmitted from the road traffic information center to radio wave beacons via radio wave beacon devices, optical beacon devices and the like arranged along the road. A beacon receiver for receiving as an optical beacon, an FM receiver for receiving as an FM multiplex broadcast via an FM broadcast station, and the like. The traffic information includes traffic jam information, regulation information, parking lot information, traffic accident information, service area congestion status information, and the like, and general information includes news, weather forecasts, and the like. Further, the beacon receiver and the FM receiver are unitized and arranged as a VICS receiver, but can be arranged separately.

  The traffic information includes an information type that indicates the type of information, a mesh number for specifying a mesh, a road link that connects two points (for example, intersections), and a link that indicates whether it is up / down. Number, including link information representing the content of information provided corresponding to the link number. For example, when the traffic information is traffic jam information, the link information is a distance from the start point of the road link to the head of the traffic jam Congestion head data representing traffic congestion degree, congestion section, traffic jam length representing the distance from the beginning of the traffic jam to the end of the traffic jam, link required time representing the time required to travel on the road link, and the like.

  And the communication part 38 can receive various information, such as traffic information and general information other than data, such as the said map data, statistical data, and driving history data, from the said information center 51 via the network 63. .

  For this purpose, the information center 51 includes a server 53, a communication unit 57 connected to the server 53, a database (DB) 58 as an information recording unit, and the like. A CPU 54, a RAM 55, a ROM 56, etc. are provided as devices. The database 58 records data similar to the various data recorded in the data recording unit 16, for example, the map data, statistical data, travel history data, and the like. Further, the information center 51 provides various information such as current traffic information and general information transmitted from the road traffic information center, and travel history data collected from a plurality of vehicles (own vehicle or other vehicles) in real time. can do.

  The forward monitoring device 48 is composed of a radar such as a laser radar or a millimeter wave radar, an ultrasonic sensor, or a combination thereof, and monitors or temporarily stops a preceding vehicle, which is a preceding traveling vehicle. Monitor places and obstacles. In addition, the front monitoring device 48 detects the relative speed indicating the relative vehicle speed with respect to the preceding vehicle, the approach speed with respect to the temporary stop point, the approach speed with respect to the obstacle, etc. Or calculate.

  The back camera 49 is composed of a CCD element and is mounted with the optical axis obliquely downward to monitor the rear of the own vehicle. In addition to the features, the rear camera 49 is traveling behind the own vehicle. A rear vehicle, a roadside structure, a structure, or the like is photographed as an object to be photographed, and image data of the photographed object is generated and sent to the CPU 31. The CPU 31 reads the image data and performs image processing on the image data, thereby recognizing each object to be photographed in the image as a recognition object. In the present embodiment, a CCD element is used as the back camera 49, but a C-MOS element or the like can be used.

  The navigation system, the navigation processing unit 17, the CPUs 31, 54, the server 53, and the like function as a computer singly or in combination of two or more, and perform arithmetic processing based on various programs, data, and the like. The data recording unit 16, RAMs 32 and 55, ROMs 33 and 56, database 58, flash memory, and the like constitute a recording medium. An MPU or the like can be used instead of the CPUs 31 and 54 as the arithmetic unit.

  Next, a basic operation of the navigation system having the above configuration will be described.

  First, when the operation unit 34 is operated by the driver and the navigation device 14 is activated, a navigation initialization processing unit (not shown) of the CPU 31 performs a navigation initialization process and detects the current location of the vehicle detected by the GPS sensor 15. The vehicle direction detected by the direction sensor 18 is read, and various data are initialized. Next, the matching processing means (not shown) of the CPU 31 performs matching processing, and based on the trajectory of the read current location and the shape, arrangement, etc. of each road link constituting the road around the current location, The current location is identified by determining whether it is located on the road link.

  In the present embodiment, the matching processing unit further specifies the current location based on the position of each feature that is the subject to be photographed by the back camera 49.

  For this purpose, image recognition processing means (not shown) of the CPU 31 performs image recognition processing, reads image data from the back camera 49, and recognizes a feature in the image composed of the image data. A distance calculation processing unit (not shown) of the CPU 31 performs a distance calculation process, and calculates a distance La from the camera 49 to the actual feature based on the position of the feature in the image. The current location specifying processing means of the matching processing means performs current location specifying processing, reads the distance La, reads the feature data from the data recording unit 16 to obtain the coordinates of the feature, and the coordinates and the coordinates The current location is specified based on the distance La.

  A lane detection processing unit (not shown) of the CPU 31 performs a lane detection process, and similarly collates the feature recognized based on the image data with the feature data read from the data recording unit 16. Thus, the lane in which the vehicle is traveling, that is, the traveling lane is detected.

  The lane detection processing means reads the sensor output of the geomagnetic sensor, and based on the sensor output, determines whether or not there is a detected object made of a ferromagnetic material such as a manhole in a predetermined lane on the road. The traveling lane can also be detected based on the determination result. Furthermore, it is possible to detect the current location with high accuracy using the highly accurate GPS sensor 15 and to detect the traveling lane based on the detection result. Further, if necessary, image processing can be performed on the display line image data, and at the same time, the traveling lane can be detected by combining the sensor output of the geomagnetic sensor, the current location, and the like.

  Subsequently, a basic information acquisition processing unit (not shown) of the CPU 31 performs a basic information acquisition process and acquires the map data by reading it from the data recording unit 16 or receiving it from the information center 51 or the like via the communication unit 38. And get. In addition, when acquiring map data from the information center 51 etc., the said basic information acquisition process means downloads the received map data to flash memory.

  A display processing unit (not shown) of the CPU 31 performs a display process and forms various screens on the display unit 35. For example, the map display processing means of the display processing means performs a map display process, forms a map screen on the display unit 35, displays a surrounding map on the map screen, and sets the current position as the vehicle position and the direction of the vehicle. Is displayed as the vehicle direction.

  Accordingly, the driver can drive the vehicle according to the map, the vehicle position, and the vehicle direction.

  Further, when the driver operates the operation unit 34 to input a destination, a destination setting processing unit (not shown) of the CPU 31 performs a destination setting process to set the destination. Note that the departure place can be input and set as necessary. Moreover, a predetermined point can be registered in advance, and the registered point can be set as a destination. Subsequently, when the driver operates the operation unit 34 to input a search condition, a search condition setting processing unit (not shown) of the CPU 31 performs a search condition setting process to set the search condition.

  When the destination and the search condition are set in this way, the route search processing unit (not shown) of the CPU 31 performs the route search process, reads the current location, the destination, the search condition, and the like from the data recording unit 16. Based on the current location, the destination, and the search data, a route from the departure point to the destination represented by the current location is searched based on the search condition, and route data representing the searched route is output. At this time, the route with the smallest total link cost assigned to each road link is set as the searched route.

  When a plurality of lanes are formed on the road and a traveling lane is detected, the route search processing means searches for a search route for each lane. In this case, the route data includes the lane number of the traveling lane.

  Subsequently, a guidance processing means (not shown) of the CPU 31 performs guidance processing and provides route guidance. For this purpose, the route display processing means of the guidance processing means performs route display processing, reads the route data, and displays the searched route on the map screen according to the route data. When a search route for each lane is searched, route guidance for each lane is performed at a predetermined point, for example, a guidance intersection, and a travel lane for which route guidance is being performed is displayed in the enlarged intersection view. If necessary, the voice output processing means of the guidance processing means performs voice output processing, and outputs a search route by voice from the voice output unit 37 to provide route guidance.

  The information center 51 can perform a route search process. In that case, the CPU 31 transmits the current location, the destination, search conditions, and the like to the information center 51. When the information center 51 receives the current location, destination, search conditions, etc., the route search processing means (not shown) of the CPU 54 performs route search processing similar to that of the CPU 31 and reads the search data from the database 58 to obtain the current location, destination. Based on the location and the search data, a route from the departure point to the destination is searched under the search conditions, and route data representing the searched route is output. Subsequently, a transmission processing unit (not shown) of the CPU 54 performs transmission processing and transmits the route data to the navigation device 14. Therefore, in the navigation device 14, when the basic information acquisition processing means receives the route data from the information center 51, the guidance processing means performs route guidance as described above.

  And when a guidance intersection exists on the searched route, when the vehicle reaches a route guidance point in front of the guidance intersection by a predetermined distance (for example, X [m]), the intersection enlarged map display processing means of the guidance processing means Performs an enlarged intersection map display process, forms an enlarged intersection map as described above in a predetermined area of the map screen, provides route guidance by the enlarged intersection map, and displays the map around the guided intersection in the enlarged intersection map. When the route guidance for the lane unit is being performed, the travel lane or the like is displayed. Further, if necessary, the voice output processing means outputs a voice such as “This is X [m] to the left” from the voice output unit 37 and performs route guidance.

  Next, the operation of the image recognition processing means will be described.

  FIG. 2 is a flowchart showing the operation of the image recognition processing means in the embodiment of the present invention, FIG. 3 is a diagram showing a mounting state of the back camera in the embodiment of the present invention, and FIG. 4 is an image in the embodiment of the present invention. FIG. 5 is a diagram showing the relationship between the area and the recognition area, FIG. 5 is a diagram showing the relationship between the vehicle speed and the number of recognition target frames in the embodiment of the present invention, and FIG. 6 is a change in the position of the recognition area in the embodiment of the present invention. FIG. 7 is a second diagram showing an example of changing the position of the recognition area in the embodiment of the present invention, and FIG. 8 is a diagram showing the position and distance on the image area in the embodiment of the present invention. FIG. 9 is a diagram showing the relationship with the weights, and FIG. 9 is a diagram showing details of the attached state of the back camera in the embodiment of the present invention. In FIG. 8, the horizontal axis represents the position, and the vertical axis represents the distance weight w.

  In the figure, f is the focal point of the back camera 49 (FIG. 1), Ra is the road surface, h is the height of the back camera 49 represented by the distance from the road surface Ra to the focal point f (strictly, the height of the focal point f). But substantially represents the height of the back camera 49). E1 is a line extending directly from the focal point f, E2 is a line indicating the lower edge of the photographing range, E3 is an optical axis of the back camera 49, E4 is a line extending from the focal point f toward the feature, and E5 is a focal point. A line E6 extending from f toward the vanishing point is a line indicating the upper edge of the photographing range.

  P1 is a point immediately below where the line E1 and the road surface intersect, P2 is a lower edge point where the line E2 and the road surface intersect, P3 is an optical axis point where the optical axis E3 and the road surface Ra intersect, and P4 is the line E4. A feature point that intersects the road surface, L1 is a distance from the direct point P1 to the lower edge point P2, L2 is a distance from the direct point P1 to the optical axis point P3, and La is a distance from the direct point P1 to the feature point P4. It is. Since the distance from the CCD element constituting the back camera 49 to the focal point f can be ignored, the distance La substantially represents the distance in the horizontal direction from the back camera 49 to the feature.

In addition, θ1 is a vertical field angle that represents the vertical shooting range of the back camera 49 as an angle, θ2 is a half field angle that represents a range from the optical axis E3 to the line E2, and the half field angle θ2 is
θ2 = θ1 / 2
It is. Θ3 is a depression angle of the back camera 49, and θ4 is an angle formed by the optical axis E3 and the line E4.

  AR1 is an area where an image composed of image data read from the back camera 49 is formed, that is, an image area. The image area AR1 is formed by a lower edge a1 formed by a line E2 and a line E6. The upper edge a2, the left side edge a3, and the right side edge a4 are surrounded and formed. A plurality of pixels are arranged in a matrix in the image area AR1. AR2 is a recognition area that is variably set in the image area AR1, and is movable in the vertical direction in the present embodiment. The recognition area AR2 includes a lower edge a5, an upper edge a6, It is formed by being surrounded by a left side edge a7 and a right side edge a8, and is composed of pixels that are targets of image recognition among the pixels. The side edge a7 is set slightly inside the side edge a3, and the side edge a8 is set slightly inside the side edge a4. M is a center line serving as an index indicating the position of the recognition area AR2 in the image area AR1, and is set to extend in the left-right direction.

  The size of the image area AR1 is defined by the specification of the back camera 49, and the distance Lr1 on the actual road corresponding to the vertical length Lf1 is constant. Further, although the size of the recognition area AR2 in the image area AR1 is made constant, the actual distance Lr2 on the road corresponding to the vertical length Lf2 of the recognition area AR2 is as shown in FIG. The shorter the recognition area AR2 is, the shorter it is, and the longer the recognition area AR2 is, the longer it is, as shown in FIG. This is because, in the image area AR1, the distance on the actual road indicated by one pixel is long in the lower part and the distance on the actual road indicated by one pixel is short in the upper part. The vertical range index for setting the size of the recognition area AR2 is configured by the length Lf2. In this case, the position of the center line M and the distance Lr2 are recorded in the ROM 33 in association with each other, and a center line position map is formed.

  In the present embodiment, the size of the recognition area AR2 in the image area AR1 is made constant, but in other embodiments, the size of the recognition area AR2 is set to the position of the recognition area AR2 in the image area AR1. Correspondingly, that is, corresponding to the position of the center line M on the image area AR1, for example, it can be made larger as the recognition area AR2 is placed below and smaller as it is placed above. In this case, the position of the center line M, the length Lf2, and the distance Lr2 on the actual road corresponding to the length Lf2 are recorded in the ROM 33 so as to form a centerline position map. . Note that the length Lf2 can be changed as needed regardless of the position of the center line M.

  By the way, as the vehicle travels, the feature moves rearward relative to the vehicle, so that the feature moves upward from below in the image area AR1. Therefore, when trying to recognize a feature in the recognition area AR2, the number of frames (hereinafter referred to as “recognition target frame number N”) corresponding to the number of shutters at the time of shooting and representing the number of acquired images increases. The amount of usable image data increases, and the recognition rate representing the possibility of recognizing a feature increases. On the other hand, the smaller the number N of recognition target frames, the smaller the available image data and the lower the recognition rate.

  Accordingly, the larger the number N of recognition target frames, the better. However, the higher the vehicle speed S changes, the smaller the number N of recognition target frames.

  Therefore, in the present embodiment, the recognition area AR2 is moved in accordance with the vehicle speed S in the image area AR1.

  For this purpose, first, the recognition area setting processing means of the image recognition processing means performs a recognition area setting process to set a recognition area AR2 in the image area AR1. That is, the recognition area setting processing means sets the center line M at the center position in the image area AR1, and sets the length Lf2 so that the distance Lr2 becomes a predetermined initial value, for example, 150 [cm]. Set.

Next, the frame number calculation processing means of the image recognition processing means performs frame number calculation processing, and sets a frame rate F, which is defined by the specification of the back camera 49 and represents the number of images acquired per unit time, as an image recognition parameter. And the vehicle speed S detected by the vehicle speed sensor 44 is read. In this case, if q is the amount of movement of the feature per frame accompanying the traveling of the vehicle,
q = S / F
It is. Therefore, the recognition target frame number N can be expressed by the number of frames while the feature moves in the recognition area AR2.
N = Lr2 / q
= Lr2 · F / S
become. Thus, the frame number calculation processing means calculates the recognition target frame number N corresponding to the vehicle speed S.

  When the frame rate F is 30 [f / s], as shown in FIG. 5, when the vehicle speed S [km / h], [cm / s] changes, the movement amount q and the number of recognition target frames N is changed corresponding to the vehicle speed S.

  Subsequently, the position calculation processing means of the image recognition processing means performs position calculation processing, reads the calculated number N of recognition target frames, refers to the centerline position map, and changes the distance Lr2 when the distance Lr2 changes. The position of the center line M at which the recognition target frame number N is the most preferable reference frame number Nr for recognizing the feature image is calculated.

  Next, the recognition area movement processing means of the image recognition processing means performs a recognition area movement process, and moves the recognition area AR2 in the vertical direction in the image area AR1 toward the calculated center line M.

  In this case, when the vehicle speed S is high, the recognition area movement processing means directs the recognition area AR2 in the direction away from the back camera 49 in the image area AR1, that is, toward the upper edge a2. When the vehicle speed S is low, the recognition area AR2 is moved toward the back camera 49 in the image area AR1, that is, toward the lower edge a1, as shown in FIG.

  By the way, since the moving amount per unit time of the feature in the image area AR1 when the vehicle is traveling is larger as the position of the feature is closer to the lower edge a1, the moving amount q is larger. As a result, the number N of recognition target frames is reduced. On the other hand, the amount of movement of the feature in the image area AR1 per unit time is smaller as the position of the feature is closer to the upper edge a2, so the amount of movement q becomes smaller. The recognition target frame number N increases.

  Therefore, when the vehicle speed S is high, by moving the recognition area AR2 toward the upper edge a2 of the image area AR1, the number N of recognition target frames can be increased, and the feature recognition rate can be increased. it can.

  On the other hand, when the vehicle speed S is low, if the recognition area AR2 is moved toward the lower edge a1 of the image area AR1, the number N of recognition target frames is reduced, so that the feature recognition rate is lowered. However, the recognition accuracy representing the accuracy of recognizing a feature can be increased.

That is, when the angle formed by the lines E1 and E4 is the shooting depression angle α, the shooting depression angle α
α = θ3 + θ4
The feature position is smaller as it is closer to the back camera 49, and the feature is photographed from the front. The feature is larger as it is away from the back camera 49, and the feature is photographed from an oblique side. It will be.

  Accordingly, when the distance on the actual road corresponding to the vertical dimension of each pixel (hereinafter referred to as “unit size ρ”) on the image area AR1 is set as a weight w, as shown in FIG. In addition, as the position of the feature in the image area AR1 is closer to the lower edge a1 (back camera 49), the distance weight w becomes smaller and the recognition accuracy becomes higher. On the other hand, as the position of the feature is closer to the upper edge a2, the distance weight w increases and the recognition accuracy of the feature decreases. In FIG. 8, the position of the feature is represented by the number of pixels from the lower edge a1, and the number of pixels at the lower edge a1 is set to zero (0).

  In the present embodiment, as described above, when the vehicle speed S is low, the recognition area AR2 is moved toward the lower edge a1 of the image area AR1, so that the recognition accuracy can be increased.

  By the way, the recognition rate can be increased by moving the recognition area AR2 upward in the image area AR1, and the recognition accuracy can be increased by moving the recognition area AR2 downward in the image area AR1. However, even if the recognition area AR2 is placed at the top of the image area AR1, if the number N of recognition target frames cannot be increased sufficiently, the recognition rate cannot be increased sufficiently.

  Therefore, when the recognition area AR2 is placed at the top of the image area AR1 and the number N of recognition target frames cannot be sufficiently increased, the recognition area capacity changing processing means of the image recognition processing means performs the recognition area capacity changing process. The length Lf2 is increased while the position of the center line M is maintained, the capacity of the recognition area AR2 is changed, and the recognition area AR2 is enlarged. Therefore, since usable image data can be increased, the recognition rate can be increased.

  On the other hand, even if the recognition area AR2 is placed at the bottom of the image area AR1, if the number N of recognition target frames is sufficiently large, the image data is uselessly large, and the feature is erroneously recognized. Therefore, if the recognition target frame number N is sufficiently large even when the recognition area AR2 is placed at the bottom of the image area AR1, the recognition area capacity changing processing means sets the length Lf2 while maintaining the position of the center line M. Decrease, change the capacity of the recognition area AR2, and reduce the recognition area AR2. Accordingly, since usable image data can be reduced, it is possible to prevent erroneous recognition of the feature.

  Subsequently, the recognition object recognition processing means of the image recognition processing means performs a recognition object recognition process, and recognizes a feature in the recognition area AR2 as a recognition object.

  In this way, the feature can be recognized accurately.

  Thus, in the present embodiment, the recognition area AR2 can be moved in accordance with the vehicle speed S in the image area AR1, so that the feature recognition rate is increased or the recognition accuracy is increased. be able to. Therefore, it is possible to accurately recognize the feature.

Next, a flowchart will be described.
Step S1: Obtain image recognition parameters.
Step S2 The vehicle speed S is read.
Step S3: The number N of recognition target frames is calculated.
Step S4: The position of the center line M is calculated.
Step S5: A recognition area moving process is performed.
Step S6: It is determined whether the recognition target frame number N is equal to or greater than the reference frame number Nr. If the recognition target frame number N is greater than or equal to the reference frame number Nr, the process proceeds to step S9. If the recognition target frame number N is smaller than the reference frame number Nr, the process proceeds to step S7.
Step S7: It is determined whether the recognition area AR2 is placed at the top. If the recognition area AR2 is placed on the top, the process proceeds to step S8. If the recognition area AR2 is not placed on the top, the process proceeds to step S11.
Step S8: The recognition area AR2 is enlarged.
Step S9: It is determined whether the recognition area AR2 is placed at the bottom. If the recognition area AR2 is placed at the bottom, the process proceeds to step S10, and if it is not placed at the bottom, the process proceeds to step S11.
Step S10: The recognition area AR2 is reduced.
Step S11: A recognition object recognition process is performed, and the process ends.

  Next, as described above, the distance calculation processing unit calculates the distance La based on the position of the feature in the image.

  In FIG. 9, 61 is a CCD element as an image sensor, f is a focal point, Pc is the number of pixels from the center to the feature on the image area AR1, and Pd is the number of pixels from the center to the edge on the image area AR1. , Lf is a focal length. E2 is a line indicating the lower edge of the shooting range, E3 is an optical axis of the back camera 49, E4 is a line extending from the focal point f toward the feature, and E6 is a line indicating the upper edge of the shooting range.

  Θ2 is a half angle of view representing the range from the optical axis E3 to the line E6 as an angle, and θ4 is an angle formed by the optical axis E3 and the line E4.

By the way, in FIG.
tan (θ3-θ2) = L1 / h
So
tan θ2 = (h · tan θ3−L1) / (h + L1 · tan θ3) (1)
become. Also,
tan (θ3 + θ4) = La / h
Therefore, the distance La is
La = h · (tan θ3 + tan θ4)
/ (1-tan θ3 · tan θ4) (2)
become.

Here, since each pixel has a unit size ρ,
tan θ2 = Pd · ρ / Lf (3)
tan θ4 = Pc · ρ / Lf
So
tan θ4 = Pc · tan θ2 / Pd (4)
become. Therefore, substituting tan θ2 of equation (1) into equation (4),
tan θ4 = Pc · {(h · tan 3θ−L1)
/ (H + L1 · tan3θ)} / Pd (5)
become.

  Accordingly, when tan θ4 of the equation (4) is substituted into the equation (2), the distance La can be expressed by the distance L1, the number Pc, Pd, the height h, and the depression angle θ3. Here, the distance L1, the height h, and the depression angle θ3 are determined by the mounting state of the back camera 49, and the numbers Pc and Pd are defined by the specifications of the back camera 49, so that the distance La can be calculated.

  In the present embodiment, tan θ2 of equation (1) is substituted into equation (4), but tan θ2 of equation (3) can be substituted. However, since the numbers Pc, Pd and the unit size ρ are defined by the specifications of the back camera 49, the value of tan θ2 varies depending on the tolerance of the back camera 49, the positive hit to the back camera 49, etc. The calculation accuracy is lowered. On the other hand, tan θ2 in the expression (1) is expressed by the distance L1, the height h, and the depression angle θ3, so that the value of tan θ2 does not vary and the calculation accuracy of the distance La can be increased.

  In the present embodiment, a back camera 49 is provided as an imaging device. However, instead of the back camera 49, a front camera that is attached to a predetermined location at the front end of the vehicle and photographs the front of the vehicle. A camera (front monitoring camera) can be used as an imaging device and a front monitoring device.

  In addition, this invention is not limited to the said embodiment, It can change variously based on the meaning of this invention, and does not exclude them from the scope of the present invention.

It is a figure which shows the navigation system in embodiment of this invention. It is a flowchart which shows operation | movement of the image recognition process means in embodiment of this invention. It is a figure which shows the attachment state of the back camera in embodiment of this invention. It is a figure which shows the relationship between the image area and recognition area in embodiment of this invention. It is a figure which shows the relationship between the vehicle speed and number of recognition object frames in embodiment of this invention. It is a 1st figure which shows the example of a change of the position of the recognition area in embodiment of this invention. It is a 2nd figure which shows the example of a change of the position of the recognition area in embodiment of this invention. It is a figure which shows the relationship between the position on the image area | region and the weight of distance in embodiment of this invention. It is a figure which shows the detail of the attachment state of the back camera in embodiment of this invention.

Explanation of symbols

31 CPU
44 Vehicle speed sensor 49 Back camera AR1 Image area AR2 Recognition area

Claims (6)

  A vehicle speed detection unit that detects a vehicle speed, an imaging device that is attached to a predetermined portion of the vehicle and shoots an object to generate image data, and a recognition area in an image area in which an image composed of the image data is formed A recognition area setting processing means for setting the recognition area, a recognition area movement processing means for moving the recognition area according to a vehicle speed, and a recognition object recognition processing means for recognizing the recognition object in the recognition area. Image processing system.   Used for recognition of a recognition object based on a vertical range index for setting the size of the recognition area, a frame rate representing the number of images acquired per unit time defined by the specification of the imaging device, and a vehicle speed. The frame number calculation processing means for calculating the number of recognition target frames, and the position calculation processing means for calculating the position of the recognition area so that the number of recognition target frames becomes the reference frame number. The image processing system according to claim 1, wherein the recognition area is moved toward the calculated position.   The recognition area movement processing means moves the recognition area in a direction away from the imaging device when the vehicle speed is high, and moves the recognition area in a direction close to the imaging device when the vehicle speed is low. Image processing system.   The image processing system according to claim 1, further comprising a recognition area capacity change processing unit configured to change a capacity of the recognition area in the image area.   The image processing system according to claim 4, wherein the recognition area capacity change processing unit changes the capacity of the recognition area in correspondence with the position of the recognition area in the image area. The vehicle speed is detected, the object is photographed to generate image data, a recognition area is set in an image area where an image composed of the image data is formed, the recognition area is moved according to the vehicle speed, An image processing method characterized by recognizing a recognition object in a recognition area.

Images