JP2013250694A - Image processing apparatus - Google Patents

Abstract

PROBLEM TO BE SOLVED: To properly perform functions of a driving support system by changing the size of an object recognition range depending on moving body information of a vehicle and whether or not a road on which the vehicle travels is a general road.SOLUTION: An image processing apparatus includes a determination unit 202 that determines whether or not a road on which a vehicle travels is a general road. The image processing apparatus changes, according to a determination result by the determination unit 202, the size of an object recognition range that is a range in which objects in front of the vehicle are recognized on a photographed image photographed by imaging means on the basis of moving body information of the vehicle.

Description

  The present invention relates to an image processing apparatus that performs image processing on a captured image obtained by capturing an image of the front of a host vehicle with an imaging unit.

  2. Description of the Related Art Conventionally, an object recognition device that recognizes an object based on a captured image taken in front of the host vehicle, for example, a driver such as ACC (Adaptive Cruise Control) for reducing the driving load on the driver of the vehicle. It is used for support systems. This driver support system is designed to maintain an automatic braking function and alarm function for avoiding the collision of the own vehicle with an obstacle, etc., and reducing the impact at the time of collision, and the inter-vehicle distance from the preceding vehicle. Various functions such as a self-vehicle speed adjustment function and a function for supporting the prevention of deviation from the lane in which the vehicle is traveling are realized.

  Patent Document 1 discloses the following image processing apparatus. In the image processing apparatus of Patent Document 1, the arrival point after a predetermined time of the host vehicle is predicted using the moving body information of the host vehicle to which the imaging unit is attached. The moving body information used for this prediction includes steering angle information and moving speed information indicating the moving direction of the host vehicle. Then, an object recognition range that includes the predicted arrival point of the host vehicle and is smaller than the entire size of the imaging screen is set on the imaging screen. Then, the object is recognized on the imaging screen within the set object recognition range, and the distance from the position of the host vehicle to the recognized object is calculated. The distance calculated by the distance calculation process is used for each function of the driver assistance system. Therefore, by performing object recognition only for the object recognition range smaller than the entire imaging screen, the burden of object recognition processing is reduced compared to performing object recognition for the entire imaging screen, and the object recognition processing The time is shortened. In the image processing apparatus disclosed in Patent Document 1, the distance between the arrival point and the traveling position of the host vehicle is calculated, and the size of the object recognition range is switched in three stages according to the distance. Specifically, when the distance between the arrival point and the traveling position of the host vehicle is within a predetermined range, the object recognition range is switched to an intermediate size. When the distance is smaller than the lower limit of the predetermined range, the object recognition range is switched to be larger than the intermediate size. When the distance is larger than the upper limit value of the predetermined range, the object recognition range is switched to be smaller than the intermediate size.

  However, the image processing apparatus disclosed in Patent Document 1 recognizes an object with respect to a captured image within the object recognition range, and does not recognize an object with respect to a captured image outside the object recognition range. For this reason, even if an object that moves from the edge of the imaging screen between the traveling position of the host vehicle and the edge near the host vehicle in the object recognition range toward the center portion suddenly appears, the imaging screen on which the object appears Is outside the object recognition range, the object cannot be recognized. For example, even if a pedestrian jumps out immediately before the host vehicle when the host vehicle is traveling on a general road with an intersection or a side road, if the pedestrian's imaging screen is outside the object recognition range, An object cannot be recognized for the pedestrian. Therefore, it becomes difficult to properly realize a driver support system function for a pedestrian, for example, an automatic brake function or a warning function when traveling on a general road.

  The present invention has been made in view of the above problems, and the object of the present invention is to increase the object recognition range depending on the moving body information of the host vehicle and whether the road on which the host vehicle is traveling is a general road. Another object is to provide an image processing apparatus that can appropriately realize the functions of the driving support system.

  In order to achieve the above object, the invention according to claim 1 sets an object recognition range for recognizing an object ahead of the host vehicle on a captured image captured by the imaging unit based on the moving body information of the host vehicle. The image processing apparatus includes a determination unit that determines whether the road on which the host vehicle is traveling is a general road, and changes the size of the object recognition range according to a determination result by the determination unit. It is characterized by.

  According to the present invention, as a result of the determination by the determination unit, when the road on which the host vehicle is traveling is a general road, for example, there is a possibility that a pedestrian may jump out to the traveling roadway. A pedestrian who jumps out on the roadway is allowed to enter the object recognition range. Thereby, the pedestrian who jumped out can be recognized, and the function of a driver support system for a pedestrian, for example, an automatic brake function and an alarm function can be realized. Therefore, the function of the driving support system can be appropriately realized by changing the size of the object recognition range depending on the moving body information of the own vehicle and whether or not the road on which the own vehicle is traveling is a general road. Effects can be obtained.

It is a mimetic diagram showing a schematic structure of an in-vehicle device control system in an embodiment. It is a schematic diagram which shows schematic structure of the imaging unit and image analysis unit which comprise the same vehicle equipment control system. It is a model enlarged view when the optical filter and image sensor in the imaging part of the imaging unit are seen from the direction orthogonal to the light transmission direction. It is explanatory drawing which shows the area | region division pattern of the same optical filter. It is a functional block diagram in connection with the image processing of this embodiment. It is a figure which shows the relationship between the distance to an object, and the change of the object recognition range on a captured image. (A) is an imaging screen when the object recognition range is not limited, and (b) is a diagram illustrating an imaging screen when the object recognition range is limited. It is a functional block diagram concerning the modification 1 of the image processing of this embodiment. 10 is a flowchart illustrating image processing according to a first modification. It is a functional block diagram concerning the modification 2 of the image processing of this embodiment. 10 is a flowchart illustrating image processing according to a second modification. It is a functional block diagram concerning the modification 3 of the image processing of this embodiment. 10 is a flowchart illustrating image processing according to a third modification.

  Hereinafter, an embodiment in which an object recognition device according to the present invention is used in an in-vehicle device control system as a vehicle system will be described. Note that the object recognition apparatus according to the present invention is not limited to an in-vehicle device control system, and can be applied to other systems equipped with an object detection apparatus that detects an object based on a captured image, for example.

FIG. 1 is a schematic diagram showing a schematic configuration of an in-vehicle device control system in the present embodiment.
The in-vehicle device control system of the present embodiment is provided with an image pickup unit 101 as an image pickup unit that picks up an image of the traveling direction front area of the traveling vehicle 100 as an image pickup area. For example, the imaging unit 101 is installed in the vicinity of a room mirror (not shown) of the windshield 105 of the host vehicle 100. Various data such as captured image data obtained by imaging by the imaging unit 101 is input to an image analysis unit 102 as image processing means. The image analysis unit 102 analyzes the data transmitted from the imaging unit 101 to calculate the position, direction, and distance of another vehicle existing ahead of the host vehicle 100, or on the road surface existing in the imaging area. Detecting lane boundaries such as white lines. In detecting another vehicle, an object on the road surface is detected as a vehicle based on the parallax image.

  The calculation result of the image analysis unit 102 is also sent to the vehicle travel control unit 106. The vehicle travel control unit 106 determines that the host vehicle 100 from the travelable area is based on the detection result of the lane boundary line (in the present embodiment, a white line will be described as an example) detected by the image analysis unit 102 and the road side step. When it is likely to come off, a warning is notified to the driver of the host vehicle 100, or driving support control such as controlling the steering wheel and brake of the host vehicle is performed.

FIG. 2 is a schematic diagram illustrating a schematic configuration of the imaging unit 101 and the image analysis unit 102.
The imaging unit 101 is a stereo camera including two imaging units 110A and 110B, and the configuration of the two imaging units 110A and 110B is the same. The imaging units 110A and 110B respectively include imaging lenses 111A and 111B, optical filters 112A and 112B, sensor substrates 114A and 114B including image sensors 113A and 113B in which imaging elements are two-dimensionally arranged, and sensor substrates 114A. , 114B from signal processing units 115A, 115B that generate and output captured image data obtained by converting analog electrical signals (the amounts of light received by the light receiving elements on the image sensors 113A, 113B) into digital electrical signals. It is configured. From the imaging unit 101 of the present embodiment, red image data, luminance image data, and parallax image data are output.

  In addition, the imaging unit 101 includes a processing hardware unit 120 including an FPGA (Field-Programmable Gate Array) or the like. In order to obtain a parallax image from the luminance image data output from each of the imaging units 110A and 110B, the processing hardware unit 120 obtains the parallax value of the corresponding image portion between the captured images captured by the imaging units 110A and 110B. A parallax calculation unit 121 for calculation is provided. The parallax value here refers to a comparison image for an image portion on the reference image corresponding to the same point in the imaging region, with one of the captured images captured by each of the imaging units 110A and 110B as a reference image and the other as a comparison image. The positional deviation amount of the upper image part is calculated as the parallax value of the image part. By using the principle of triangulation, the distance to the same point in the imaging area corresponding to the image portion can be calculated from the parallax value.

  On the other hand, the image analysis unit 102 has a built-in memory 130 for storing red image data, luminance image data, and parallax image data output from the imaging unit 101, and software for performing recognition processing of an identification object, parallax calculation control, and the like. MPU (Micro Processing Unit) 140 is provided. The MPU 140 executes various recognition processes using the red image data, luminance image data, and parallax image data stored in the memory 130.

FIG. 3 is a schematic enlarged view when the optical filters 112A and 112B and the image sensors 113A and 113B are viewed from a direction orthogonal to the light transmission direction.
The image sensors 113A and 113B are image sensors using a CCD (Charge Coupled Device), a CMOS (Complementary Metal Oxide Semiconductor), or the like, and a photodiode 113a is used as an imaging element (light receiving element). The photodiodes 113a are two-dimensionally arranged for each imaging pixel, and a microlens 113b is provided on the incident side of each photodiode 113a in order to increase the light collection efficiency of the photodiode 113a. The image sensors 113A and 113B are bonded to a PWB (printed wiring board) by a technique such as wire bonding to form sensor substrates 114A and 114B.

  Optical filters 112A and 112B are arranged close to the surfaces of the image sensors 113A and 113B on the microlens 113b side. As shown in FIG. 3, the optical filters 112A and 112B of this embodiment are obtained by forming a spectral filter layer 112b on a transparent filter substrate 112a. In place of the spectral filter or in addition to the spectral filter, another optical filter such as a polarizing filter may be provided. The spectral filter layer 112b is divided into regions so as to correspond to one photodiode 113a on the image sensors 113A and 113B.

  It is good also as a structure with a space | gap between optical filter 112A, 112B and image sensor 113A, 113B. However, when the optical filters 112A and 112B are in close contact with the image sensors 113A and 113B, the boundaries of the filter regions of the optical filters 112A and 112B coincide with the boundaries between the photodiodes 113a on the image sensors 113A and 113B. It becomes easy to let you. The optical filters 112A and 112B and the image sensors 113A and 113B may be bonded with, for example, a UV adhesive, or UV bonding may be performed on a four-side region outside the effective pixel while being supported by a spacer outside the effective pixel range used for imaging. Thermocompression bonding may be performed.

FIG. 4 is an explanatory diagram showing a region division pattern of the optical filters 112A and 112B according to the present embodiment.
In the optical filters 112A and 112B, two types of regions, a first region and a second region, are arranged corresponding to one photodiode 113a on the image sensors 113A and 113B. Thus, the amount of light received by each photodiode 113a on the image sensors 113A and 113B can be acquired as spectral information according to the type of region of the spectral filter layer 112b through which the received light is transmitted.

  In the optical filters 112A and 112B in the present embodiment, the first region is a red spectral region 112r that selects and transmits only light in the red wavelength band, and the second region transmits light without performing wavelength selection. It is a non-spectral region 112c. As shown in FIG. 4, the optical filters 112A and 112B use those in which the first region 112r and the second region 112c are distributed in a checkered pattern. Therefore, in the present embodiment, a red luminance image is obtained from the output signal of the imaging pixel corresponding to the first region 112r, and a non-spectral luminance image is obtained from the output signal of the imaging pixel corresponding to the second region 112c. Therefore, according to the present embodiment, two types of captured image data corresponding to a red luminance image and a non-spectral luminance image can be obtained by a single imaging operation. In these captured image data, the number of image pixels is smaller than the number of captured pixels, but generally known image interpolation processing may be used when obtaining a higher resolution image.

Next, image processing which is a characteristic part of the present invention will be described.
FIG. 5 is a functional block diagram related to image processing of the present embodiment. In the figure, an image processing apparatus 200 according to the present embodiment includes a stereo imaging unit 201, a determination unit 202, a moving body information acquisition unit 203, an arrival distance prediction unit 204, an arrival time setting unit 205, an object recognition range calculation unit 206, a distance. An image generation unit 207 and an object recognition processing unit 208 are included. The stereo imaging unit 201 acquires a stereo image (right and left luminance images) from the left and right cameras. The determination unit 202 sets the determination result by setting whether or not the road on which the current vehicle is traveling is a general road manually by the user. The determination result is divided into two categories, “general road” and “not a general road”. When there are many objects to be framed in on the road that is currently running, the road is set as a general road. Otherwise, for example, an expressway is set as not a general road.

  And the mobile body information acquisition part 203 is a mobile body here, and acquires the moving speed of a motor vehicle. The vehicle speed can be acquired from the CAN (Controller Area Network) communication of the automobile. The arrival distance prediction unit 204 predicts the arrival distance at the set time by multiplying the movement speed acquired by the moving body information acquisition unit 203 by the time set by the arrival time setting unit 205. The arrival time setting unit 205 sets the time used for the arrival distance prediction in the arrival distance prediction unit 204. The distance data that arrives in a time shorter than the set time here is not calculated and is not used in the recognition process. Specifically, when the set time is 3 seconds, distance data that arrives after 1 second or 2 seconds from the current position is not calculated. The object recognition range calculation unit 206 calculates the object recognition range according to the predicted distance acquired by the reach distance prediction unit 204. Using the tendency that the distance increases as the distance image approaches the center of the image, the object recognition range corresponding to the distance is held as a table as shown in FIG. 6 and the object recognition range corresponding to the predicted distance is acquired. For example, if the predicted distance is 12 [m], it is necessary to set the object recognition range including the point of the predicted distance 12 [m] and perform the object recognition process on the set object recognition range. The object recognition range is (300, 350)-(1000, 700) in the 10 [m] frame that is larger than the [m] frame. The object recognition processing unit 208 performs recognition processing for an object within the object recognition range using the parallax image generated by the distance image generation unit 207. Whether the road on which the host vehicle is traveling is a general road, for example, in the case of a general road, it is switched to the 5 [m] frame in FIG. 6, and in the case of a highway or the like, the 30 [m] frame in FIG. It may be switched to.

  A specific parallax image input to the object recognition processing unit 208 is as shown in FIG. For example, in an urban area, the recognition process is performed using an image that does not restrict the calculation area of FIG. 7A, and the image of FIG. 7B is used on an expressway or the like. Furthermore, in order to reduce the calculation processing load of the recognition process, the recognition process is performed only on pixels having a distance larger than the distance (parallax) predicted by the reach distance prediction unit 204 in FIG. The distance image generation unit 207 changes the distance calculation area based on the determination result of the determination unit 202. When the determination unit 202 determines that the road is a general road, it is necessary to calculate the distance of the object that suddenly enters the frame, so the object recognition range is not changed (the distance is calculated up to the screen edge), as shown in FIG. Such a distance image is generated. On the other hand, if it is determined that the road is not a general road, distance calculation is performed using the object recognition range calculated by the object recognition range calculation unit 206 to generate a distance image as shown in FIG.

  FIG. 8 is a functional block diagram relating to the first modification of the image processing of the present embodiment. FIG. 9 is a flowchart showing image processing according to the first modification. In this modification, a GPS data acquisition unit 302 for acquiring GPS data is provided, and whether or not the road on which the vehicle is traveling is a general road based on the GPS data, for example, whether it is a frame-in scene or not. Determine whether. First, the captured image frame and GPS data are acquired (steps S101 and S102). Using this GPS data, it is determined from position information whether the current point is an automobile-only road such as an expressway or not (step S103). In the case of an automobile-only road, it is assumed that the possibility of a pedestrian or the like entering a frame is extremely low. Then, it is determined that the road on which the host vehicle is currently traveling is a road that does not enter the frame, and the parallax calculation is performed by limiting the object recognition range (step S203: YES, steps S205, S206). On the other hand, it is assumed that there is an extremely high possibility that a pedestrian or the like will frame in if the road is not a car-only road. Then, it is determined that the road on which the host vehicle is currently traveling is a frame-in road, and the parallax calculation is performed without limiting the object recognition range (step S203: NO, steps S204, S206).

  FIG. 10 is a functional block diagram relating to the second modification of the image processing of the present embodiment. FIG. 11 is a flowchart showing the image processing of the second modification. In this modification, vehicle information indicating the state of the host vehicle output from the vehicle main body by the vehicle information acquisition unit 402, for example, CAN data, is received, and the determination unit 403 determines the situation around the movement from the vehicle information. In the second modification, it is determined whether or not the traveling road is a general road in the vehicle information with the frequency with which the driver steps on the brake. As shown in FIG. 11, when the time when the brake is not depressed becomes equal to or longer than a certain time (steps S302 to S304, step S305: YES), it is assumed that the vehicle is traveling on a non-urban area such as an expressway. Then, it is determined that the pedestrian does not enter the frame, and the object recognition process is performed by limiting the object recognition range and performing the parallax calculation (steps S306 and S308). If the time when the brake is not depressed is not a certain time or more (steps S302 to S304, step 305: NO), it is assumed that the vehicle is traveling on a general road in an urban area, and it is determined that the pedestrian enters the frame, thereby limiting the object recognition range Without performing the parallax calculation, the object recognition process is performed (steps S307 and S308).

  FIG. 12 is a functional block diagram relating to the third modification of the image processing of the present embodiment. FIG. 13 is a flowchart showing the image processing of the third modification. This modification is an example in which the determination unit 503 feeds back an object recognition result. Specifically, the determination unit 503 determines whether or not the traveling road is a general road based on the result of object recognition by the object recognition processing unit 504. For example, the object recognition processing unit 504 recognizes a traffic signal and a road width to determine whether the current traveling road is a general road in an urban area and whether frame-in is likely to occur. In the third modification, it is determined whether or not the traveling road is a general road based on whether or not the traffic signal is recognized (step S405). When the traffic signal is recognized, it is assumed that the current driving road is a general road in the city, and it is determined that the pedestrian enters the frame, and parallax calculation is performed without limiting the object recognition range (step S405: YES, Steps S402 and S404). When the traffic signal is not recognized, it is assumed that the current traveling road is a non-urban road such as an expressway, it is determined that the pedestrian does not enter the frame, the object recognition range is limited, and the parallax calculation is performed (step S405: NO) , Steps S403, S404).

What has been described above is merely an example, and the present invention has a specific effect for each of the following modes.
(Aspect 1)
A determination unit that determines whether or not the road on which the host vehicle is traveling is a general road, and changes the size of the object recognition range according to a determination result by the determination unit. According to this, as described in the above embodiment, when the determination result of the determination unit 202 indicates that the road on which the host vehicle is traveling is a general road, for example, there is a possibility that a pedestrian may jump out to the traveling roadway. The size of the range is increased so that a pedestrian who has jumped out to the traveling roadway enters the object recognition range. Thereby, the pedestrian who jumped out can be recognized, and the function of a driver support system for a pedestrian, for example, an automatic brake function and an alarm function can be realized. Therefore, the function of the driving support system can be appropriately realized by changing the size of the object recognition range depending on the moving body information of the host vehicle and whether the road on which the host vehicle is traveling is a general road.
(Aspect 2)
In (Aspect 1), a GPS data acquisition unit that acquires GPS data is provided, and the determination unit determines whether or not the road on which the vehicle is traveling is a general road based on the GPS data acquired by the GPS data acquisition unit. Determine whether. According to this, as described in the first modification of the above embodiment, the determination unit 303 determines whether the current point is an automobile-only road such as an expressway or not based on position information. This makes it possible to appropriately change the object recognition range of the imaging means depending on whether the road on which the host vehicle is traveling is a general road. Therefore, the function of the driving support system can be appropriately realized.
(Aspect 3)
In (Aspect 1), the determination unit determines the moving scene based on the frequency of stepping on the brake of the host vehicle. According to this, as described in the second modification of the above-described embodiment, vehicle information indicating the state of the host vehicle output from the vehicle body, for example, CAN data is received, and the host vehicle is detected from the vehicle information by the determination unit 403. It is determined whether or not the traveling road is a general road. In the vehicle information, it is determined whether or not the road is a general road at a frequency that the driver steps on the brake. This makes it possible to appropriately change the object recognition range of the imaging unit depending on whether or not the road on which the host vehicle is traveling is a general road. Therefore, the function of the driving support system can be appropriately realized.
(Aspect 4)
In (Aspect 1), the determination unit determines whether the road is a general road based on the object recognition result of the captured image. According to this, as described in the third modification of the above embodiment, the road on which the vehicle is traveling by the determination unit 503 is determined based on the result of the traffic recognition and the road width recognized by the object recognition processing unit 504. It is determined whether the road is a general road. Accordingly, it is possible to appropriately change the size of the object recognition range of the imaging unit in accordance with whether the road on which the host vehicle is traveling is a general road. Therefore, the function of the driving support system can be appropriately realized.
(Aspect 5)
In (Aspect 1), the determination result by the determination unit can be arbitrarily set. According to this, as described in the above embodiment, it is determined whether the driver is a manual and the road on which the vehicle is currently traveling is a general road. This makes it possible to appropriately change the object recognition range of the imaging unit. Therefore, the function of the driving support system can be appropriately realized.
(Aspect 6)
In (Aspect 1), a moving body information acquisition unit that acquires moving body information of the host vehicle, an arrival time setting unit that sets a time used to predict a reach distance to the position where the host vehicle reaches, and a moving body From the information acquisition unit and the arrival time setting unit, the arrival distance prediction unit that predicts the distance that the host vehicle will reach with the set arrival time, and the size of the object recognition range using the predicted arrival distance obtained from the arrival distance prediction unit Between the object recognition range calculation unit that calculates the image, the recognition processing unit that performs the recognition process using the predicted arrival distance obtained from the arrival distance prediction unit, and the object within the object recognition range captured by the imaging unit and the imaging unit And a distance image generation unit that generates a distance image based on the determination result of the determination unit and the object recognition range of the object recognition range calculation unit. According to this, as described in the above embodiment, the moving body information acquisition unit 203 acquires the moving speed of the host vehicle. The arrival distance prediction unit 204 predicts the arrival distance at the set time by multiplying the movement speed acquired by the moving body information acquisition unit 203 by the time set by the arrival time setting unit 205. The arrival time setting unit 205 sets the time used for the arrival distance prediction in the arrival distance prediction unit 204. The distance calculation area calculation unit 206 calculates a distance calculation area according to the predicted distance acquired by the reach distance prediction unit 204. The object recognition processing unit 208 performs object recognition processing using the parallax image generated by the distance image generation unit 207. Accordingly, it is possible to appropriately change the size of the object recognition range of the imaging unit in accordance with whether or not the road on which the host vehicle is traveling is a general road. Therefore, the function of the driving support system can be appropriately realized.
(Aspect 7)
In (Aspect 1), the distance calculation range calculation unit calculates using the table information in which the distance and the recognition target range corresponding to the distance are stored. According to this, as described in the above embodiment, it is possible to reduce the burden of arithmetic processing.

DESCRIPTION OF SYMBOLS 100 Own vehicle 101 Imaging unit 102 Image analysis unit 103 Headlamp control unit 104 Headlamp 105 Windshield 106 Vehicle travel control unit 200 Image processing apparatus 201 Stereo imaging unit 202 Determination unit 203 Moving body information acquisition unit 204 Reach distance prediction unit 205 Time setting unit 206 Distance calculation area calculation unit 207 Distance image generation unit 208 Object recognition processing unit 301 Stereo imaging unit 302 GPS data acquisition unit 303 Determination unit 304 Distance image generation unit 305 Object recognition processing unit 401 Stereo imaging unit 402 Vehicle information acquisition unit 403 determination unit 404 distance image generation unit 405 object recognition processing unit 501 stereo imaging unit 502 distance image generation unit 503 determination unit 504 object recognition processing unit

JP 2006-322796 A

Claims (7)

In an image processing apparatus that sets an object recognition range for recognizing an object ahead of the host vehicle on a captured image captured by the imaging unit based on the moving body information of the host vehicle.
An image processing comprising: a determination unit that determines whether a road on which the host vehicle is traveling is a general road, and changing a size of the object recognition range according to a determination result by the determination unit apparatus. The image processing apparatus according to claim 1.
A GPS data acquisition unit that acquires GPS data is included, and the determination unit determines whether the road on which the vehicle is traveling is a general road based on the GPS data acquired by the GPS data acquisition unit An image processing apparatus. The image processing apparatus according to claim 1 or 2,
The determination unit determines whether or not the road on which the host vehicle is traveling is a general road based on the frequency of stepping on the brake of the host vehicle. The image processing apparatus according to any one of claims 1 to 3,
The determination unit determines whether or not a road on which the host vehicle is traveling is a general road based on an object recognition result of a captured image. The image processing apparatus according to any one of claims 1 to 4,
An image processing apparatus, wherein the determination result by the determination unit can be arbitrarily set. The image processing apparatus according to claim 1.
A moving body information acquisition unit that acquires moving body information of the host vehicle, an arrival time setting unit that sets a time used to predict a reach distance to a position where the host vehicle reaches, and the moving body information acquisition unit; From the arrival time setting unit, the arrival distance prediction unit that predicts the distance that the host vehicle will reach in the set arrival time, and the size of the object recognition range using the predicted arrival distance obtained from the arrival distance prediction unit An object recognition range calculation unit to calculate, a recognition processing unit that performs a recognition process using the predicted arrival distance obtained from the arrival distance prediction unit, an object in the object recognition range imaged by the imaging unit, and the imaging unit And a distance image generation unit that generates a distance image based on a determination result of the determination unit and an object recognition range of the object recognition range calculation unit. The image processing apparatus according to claim 6.
The object recognition range calculation unit calculates the distance using table information in which a distance and a recognition target range corresponding to the distance are stored.