JP2007328631A - Object candidate region detector, object candidate region detection method, pedestrian recognition system, and vehicle control device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To detect a region where an object may exist with high accuracy from an image of an on-vehicle camera. <P>SOLUTION: A pedestrian candidate region detecting section 19 detects a pedestrian candidate region from an input image that is photographed by a camera 31 and processed by a preprocessing section 11, a pedestrian recognizing section 18 recognizes a pedestrian, a learning processing section 12 creates a reference pattern from the region having no pedestrian of the input image and updates a reference pattern database 15, and it is used for detecting a next pedestrian candidate region. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an object candidate area detection device, an object candidate area detection method, and an object candidate area detection for detecting an area where a specific object may exist as an object candidate area from an input image taken by an in-vehicle camera. The present invention relates to a pedestrian recognition device and a vehicle control device used.

  Conventionally, a technique for detecting a pedestrian or the like by image recognition on an image captured by a camera has been devised. For example, Patent Document 1 discloses a technique for recognizing a pedestrian or a vehicle from an image taken by a fixed point camera fixed at a specific location.

  Further, as a specific method of such image recognition, a saliency calculation method (saliency algorithm) that learns a background pattern in advance and calculates a difference between an input image and a background pattern as saliency can be applied (for example, (See Patent Document 2).

Japanese Patent Laid-Open No. 2002-190012 JP 2001-236508 A

  By the way, in recent years, it has become an important issue to implement a technology that supports a driving by mounting a camera or the like on a vehicle and recognizing a pedestrian or the like by an image from the in-vehicle camera and preventing an accident.

  However, in an image taken from a moving body such as an in-vehicle camera, the background image always changes due to the movement. Therefore, even if the above-described saliency calculation method is used, there is a problem that an event that needs to be learned for setting a background pattern becomes large and detection accuracy is lowered.

  The present invention has been made to solve the above-described problems in the prior art and to solve the problems, and is an object candidate area for detecting an area where an object may exist with high accuracy from an image of a vehicle-mounted camera. An object is to provide a detection device, an object candidate region detection method, a pedestrian recognition device that recognizes a pedestrian with high accuracy, and a vehicle control device that uses pedestrian recognition.

  In order to solve the above-described problems and achieve the object, the object candidate area detection device according to the invention of claim 1 uses, as an object candidate area, an area in which a specific object may exist from an input image captured by a camera. An object candidate area detection device for detecting, wherein a comparison is made between a determination area cut out from an input image currently input by a camera and a reference pattern in which an input image is stored in advance, and the object candidate area of the determination area And a reference pattern updating means for updating the reference pattern using a region in which the specific object does not exist in the current input image using the detection result. To do.

  According to the first aspect of the present invention, the object candidate area detection device detects an object candidate area by comparing the determination area cut out from the input image with the reference pattern, and uses the detection result to identify the input image. The reference pattern is updated using an area where no object exists.

  An object candidate area detection device according to a second aspect of the present invention is the object candidate area detection apparatus according to the first aspect, wherein the reference pattern update means detects the object candidate area when there is no object candidate area as a result of detection by the detection means. The reference pattern is updated from the entire input image.

  According to the second aspect of the present invention, the object candidate area detection device detects the object candidate area by comparing the determination target area cut out from the input image with the reference pattern, and when the object candidate area does not exist as a result of the detection. In addition, the reference pattern is updated from the entire input image.

  According to a third aspect of the present invention, in the object candidate region detection device according to the first or second aspect, the reference pattern update unit excludes the object candidate region detected by the detection unit from the input image. And updating the reference pattern.

  According to the third aspect of the present invention, the object candidate area detection device detects an object candidate area by comparing the determination area cut out from the input image with the reference pattern, and an image in which the object candidate area is excluded from the input image. Is used to update the reference pattern.

  According to a fourth aspect of the present invention, there is provided the object candidate area detecting device according to the first, second or third aspect, wherein the object recognition means recognizes whether or not the specific object exists in the object candidate area. The reference pattern update means updates the reference pattern from the entire input image when the specific object does not exist as a result of recognition by the object recognition means.

  According to the fourth aspect of the present invention, the object candidate area detection device detects an object candidate area by comparing the determination area extracted from the input image with the reference pattern, and recognizes whether or not a specific object exists. At the same time, if the specific object does not exist as a result of recognition, the reference pattern is updated from the entire input image.

  An object candidate region detection apparatus according to claim 5 recognizes whether or not the specific object exists in the object candidate region in the invention according to any one of claims 1 to 4. The apparatus further comprises object recognition means, wherein the reference pattern update means updates the reference pattern by excluding a specific object recognized by the object recognition means from the input image.

  According to the fifth aspect of the present invention, the object candidate area detection device detects an object candidate area by comparing the determination area extracted from the input image with the reference pattern, and recognizes whether or not a specific object exists. At the same time, the recognized specific object is excluded from the input image and the reference pattern is updated.

  The object candidate area detection method according to the invention of claim 6 is an object candidate area detection method for detecting an area where a specific object may exist as an object candidate area from an input image captured by a camera, A detection step of detecting the object candidate area in the determination area by comparing the determination area cut out from the input image currently input by the camera and a reference pattern in which the input image is stored in advance, and the detection result And a reference pattern update step of updating the reference pattern using a region where the specific object does not exist in the input image.

  According to the sixth aspect of the present invention, the object candidate region detection method detects an object candidate region by comparing the determination target region cut out from the input image with the reference pattern, and uses the detection result to identify the input candidate image. The reference pattern is updated using an area where no object exists.

  The pedestrian recognition device according to the invention of claim 7 is a pedestrian recognition device for recognizing a pedestrian from an input image taken by an in-vehicle camera, and a to-be-determined area cut out from an input image currently input by the camera Detecting means for detecting an area where a pedestrian may exist as a pedestrian candidate area by comparison with a reference pattern in which an input image is stored in advance, and whether the pedestrian candidate area corresponds to a pedestrian Pedestrian discrimination means for discriminating; and reference pattern update means for updating the reference pattern using a region where the specific object does not exist in the current input image using the detection result. And

  According to the invention of claim 7, the pedestrian recognition device determines whether or not the pedestrian candidate area detected by comparing the determination target area cut out from the input image with the reference pattern is a pedestrian, Using the result of detection of the pedestrian candidate area, the reference pattern is updated using an area where no pedestrian exists in the input image.

  In the vehicle control device according to the eighth aspect of the present invention, there is a possibility that a pedestrian exists by comparing the determination area cut out from the input image currently input by the camera and the reference pattern in which the input image is stored in advance. Detection means for detecting an area as a pedestrian candidate area; pedestrian discrimination means for determining whether the pedestrian candidate area corresponds to a pedestrian; and Reference pattern updating means for updating the reference pattern using a region where no specific object exists, and notification control for notifying the presence of a pedestrian when a pedestrian is recognized by the pedestrian discrimination means, and / or And control means for executing travel control for controlling the travel state of the vehicle.

  According to the eighth aspect of the invention, the vehicle control device determines whether or not the pedestrian candidate region detected by comparing the determination target region cut out from the input image with the reference pattern is a pedestrian, and the determination result And the reference pattern is updated using a region where no pedestrian exists in the input image using the result of detection of the pedestrian candidate region.

  According to the first aspect of the present invention, the object candidate region detection device detects an object candidate region by comparing the determination target region cut out from the input image with the reference pattern, and uses the detection result to specify a specific part of the input image. Since the reference pattern is updated using a region where no object exists, there is an effect that it is possible to obtain an object candidate region detection device that detects a region where an object may exist with high accuracy from a camera image.

  According to the invention of claim 2, the object candidate area detection device detects the object candidate area by comparing the determination area cut out from the input image with the reference pattern, and the object candidate area does not exist as a result of the detection. In this case, since the reference pattern is updated from the entire input image, the reference pattern according to the situation is easily updated, and an object candidate area detection device that detects an area where an object may exist with high accuracy from the camera image There is an effect that can be obtained.

  According to the invention of claim 3, the object candidate area detection device detects the object candidate area by comparing the determination area cut out from the input image and the reference pattern, and excludes the object candidate area from the input image. Since the reference pattern is updated using an image, the reference pattern is updated even from an image in which a pedestrian candidate area exists, and an object that can detect an area where an object may exist with high accuracy from the camera image There is an effect that a candidate area detecting device can be obtained.

  According to a fourth aspect of the present invention, the object candidate area detection device detects an object candidate area by comparing the determination area cut out from the input image with a reference pattern, and recognizes whether or not a specific object exists. In addition, if the specific object does not exist as a result of recognition, the reference pattern is updated from the entire input image, so the reference pattern according to the situation is easily updated, and the specific object is recognized from the camera image with high accuracy. It is possible to obtain an object candidate area detection device that performs the above-described process.

  According to the invention of claim 5, the object candidate area detection device detects an object candidate area by comparing the determination area cut out from the input image with the reference pattern, and recognizes whether or not a specific object exists. In addition, since the reference pattern is updated by excluding the recognized specific object from the input image, the reference pattern is updated even from an image in which the target object exists, and the specific image is accurately identified from the camera image. There is an effect that an object candidate area detecting device for recognizing an object can be obtained.

  According to the invention of claim 6, the object candidate area detection method detects an object candidate area by comparing the determination target area cut out from the input image with a reference pattern, Since the reference pattern is updated using a region where a specific object does not exist, an object candidate region detection method for detecting a region where an object may exist with high accuracy can be obtained from a camera image. .

  According to the invention of claim 7, the pedestrian recognition apparatus determines whether or not the pedestrian candidate area detected by comparing the determination area cut out from the input image with the reference pattern is a pedestrian. Since the reference pattern is updated using the area where no pedestrian exists in the input image using the detection result of the pedestrian candidate area, a pedestrian recognition device that recognizes the pedestrian with high accuracy from the camera image is obtained. There is an effect that can be.

  According to the invention of claim 8, the vehicle control device determines whether or not the pedestrian candidate region detected by comparing the determination target region cut out from the input image with the reference pattern is a pedestrian. The vehicle is controlled based on the result, and the reference pattern is updated using the area where no pedestrian exists in the input image using the result of detection of the pedestrian candidate area. It is possible to obtain a vehicle control device that recognizes the vehicle and secures its safety.

  Exemplary embodiments of an object candidate region detection device, an object candidate region detection method, a pedestrian recognition device, and a vehicle control device according to the present invention will be described below in detail with reference to the accompanying drawings.

  FIG. 1 is a schematic configuration diagram showing a schematic configuration of an in-vehicle image recognition apparatus 10 that is Embodiment 1 of the present invention. The vehicle has the following configuration. As shown in the figure, the image recognition device 10 is connected to a navigation device 30, a camera 31, and a pre-crash ECU 40.

  The navigation device 30 is an in-vehicle device that sets and guides a travel route using the position of the host vehicle specified by communicating with a GPS (Global Positioning System) artificial satellite and map data 30a stored in advance. In addition, the navigation device 30 provides the image recognition device 10 with position information of the own vehicle, surrounding map information, information about roads, and the like.

  The camera 31 captures the vicinity of the host vehicle and inputs the captured result to the image recognition apparatus 10. When the image recognition unit 10 predicts a collision of the host vehicle, the pre-crash ECU 40 is an electronic device that performs notification of occupants by the display 43 and the speaker 44, and the operation control of the vehicle by the brake 41 and the engine control device (EFI) 42. It is a control device and functions as a vehicle control device.

  The image recognition apparatus 10 includes a preprocessing unit 11, a learning processing unit 12, a reference pattern database 15, a vehicle recognition unit 16, a white line recognition unit 17, a pedestrian recognition unit 18, a pedestrian candidate region detection unit 19, and a collision determination. Part 20. Here, the learning processing unit 12, the reference pattern database 15, the vehicle recognition unit 16, the white line recognition unit 17, the pedestrian recognition unit 18, the pedestrian candidate area detection unit 19, and the collision determination unit 20 are, for example, a single microcomputer 10 a ( An arithmetic processing unit (combination of CPU, ROM, and RAM) is preferable.

  The preprocessing unit 11 performs processing such as filtering, edge detection, and contour extraction on the image captured by the camera 31, and then outputs the image to the vehicle recognition unit 16, the white line recognition unit 17, and the pedestrian candidate region detection unit 19. .

  The vehicle recognition unit 16 performs pattern matching on the image output from the preprocessing unit 11 to recognize the vehicle, and outputs the recognition result to the collision determination unit 20. Similarly, the white line recognition unit 18 performs pattern matching on the image output from the preprocessing unit 11 to recognize a white line and outputs the recognition result to the collision determination unit 20.

  On the other hand, the pedestrian candidate area detection unit 19 detects an area where a pedestrian may exist from the image output by the preprocessing unit 11 using a saliency algorithm, and the detection result is sent to the pedestrian recognition unit 18. Output. Thereafter, the pedestrian recognition unit 18 performs pattern matching or neuro-determination processing using a neural network on the pedestrian candidate region to recognize the pedestrian and outputs the pedestrian to the collision determination unit 20. And when a pedestrian is recognized, the distance to a pedestrian is calculated by image processing etc., and the distance is also output to the collision determination part 20 as pedestrian information.

  The collision determination unit 20 predicts a collision between a pedestrian or another vehicle and the host vehicle using the recognition results obtained by the vehicle recognition unit 16, the white line recognition unit 17, the pedestrian recognition unit 18, and the position information output by the navigation device 30. Then, the prediction result is output to the pre-crash ECU 40. On the other hand, the pre-crash ECU 40 controls the driver using the display 43 or the speaker 44 if there is a possibility of a collision based on the prediction result (eg, a pedestrian is present ahead and the distance is close to several meters). In addition, vehicle travel control (brake control, accelerator control, etc.) is performed depending on the risk of collision.

  Here, when recognizing a vehicle or a white line with little variation in shape, pattern matching is directly performed on the image output by the pre-processing unit 11. In the case of recognition, the detection accuracy is improved and the processing load is reduced by detecting candidate regions in advance by a saliency algorithm.

  Detection of candidate areas by the saliency algorithm will be described with reference to FIG. As shown in the figure, the saliency algorithm first updates the reference pattern by the learning process, and the pedestrian candidate area detection process calculates the saliency by comparing the input image with the reference pattern.

  In the learning process, a plurality of learning images are input in advance before using the apparatus, and a learning area is cut out from the learning image. This learning area is cut out in a size of 20 × 20 pixels, for example, in accordance with the size of the pedestrian in the image. The learning image is a background image of a road or the like that does not include a target such as a pedestrian.

  This cut-out learning area is treated as an N-dimensional (N is the number of pixels, and if it is 20 × 20 pixels, 400 dimensions) vector, N-dimensional principal component analysis is performed on all learning areas, and a feature vector (N The principal component of the dimension vector) is calculated. The calculation of the feature vector is executed for all learning images, and the common vector component is used as a reference pattern.

  In the pedestrian candidate area detection process, a determination area having the same size as the learning area is cut out from the input image captured by the camera. Then, the cut-out determination area is set as an N-dimensional vector and developed with a reference pattern (takes an inner product).

  By this expansion, a vector component similar to the reference pattern is obtained in the judgment area, so that the residual between the vector obtained by the development and the vector of the judgment area is significant (a value indicating the degree of deviation from the reference pattern). And outputs a result image in which only a highly significant area is left as a pedestrian candidate area.

  However, depending on the learning image to be input, an appropriate reference pattern cannot be obtained, and the detection accuracy of the candidate area may decrease. For example, when various images are used as learning images, each learning image has a different main component, so that the reference pattern obtained therefrom has many directions, and a residual with a pedestrian is obtained. Becomes difficult. That is, the pedestrian's features are buried in the background, and it is determined that there is no saliency.

  Further, if the threshold is lowered to a point where there is little saliency, and if any saliency is present, it is detected as a pedestrian candidate. For example, as shown in FIG. 3, when a tree and a building are input as learning images in order to detect objects other than trees and buildings from the input image, a reference pattern in which the characteristics of the trees and the characteristics of the buildings are mixed is created.

  As a result, it may be determined that the tree pattern or the building image is different from the reference pattern, that is, “conspicuous”.

  In this way, when the events to be input in the learning process are large (the commonality between the images for learning is low and wide-ranging), an appropriate reference pattern cannot be obtained, the saliency detection accuracy is low, and the pedestrian Or a large number of areas are output as “significant pedestrian candidate areas”. As a result, a processing load increase and a recognition accuracy decrease in the pedestrian recognition unit 18 are caused.

  Therefore, in the image recognition apparatus 10, after the pedestrian is recognized from the input image as shown in FIG. 4, the learning processing unit 12 uses the result image obtained by detecting the used input image and the pedestrian candidate area as a learning image. And the reference pattern database 15 is updated.

  Since the created reference pattern is used by the pedestrian area selection unit 19 for detection of the next pedestrian candidate area, as shown in FIG. 5, the reference pattern used when calculating the saliency is the previous pedestrian recognition. It will be obtained from the background image of the time. Therefore, even if the image is taken by the in-vehicle camera 31, the influence of the background change due to the movement of the vehicle can be made extremely small, and the pedestrian candidate can be obtained with high accuracy in the same manner as the saliency calculation for the taken image of the fixed point camera. An area can be detected. That is, in the saliency calculation, the current frame image and the learning (reference) pattern including the previous frame are compared. Since each frame is about several milliseconds, the previous frame is not significantly different from the current frame image, so that it can be compared with a learning pattern close to the current frame, and the accuracy is improved.

  Here, as a result of detection by the pedestrian candidate area detection unit 19, when the pedestrian candidate area does not exist, or when the pedestrian recognition unit 18 recognizes that the pedestrian candidate area exists, it is not a pedestrian. As shown in FIG. 6, the input image can be used as it is as a learning image.

  On the other hand, when the pedestrian recognition unit 18 recognizes a pedestrian, the learning processing unit 12 uses an image obtained by removing an area corresponding to the pedestrian from the input image by the pedestrian mask processing unit 12a therein as a learning image. To do.

  Next, the processing operation for pedestrian recognition in the microcomputer 10a will be described with reference to the flowchart of FIG. This processing flow starts when power is supplied to the microcomputer 10a when the IG is turned on, and is repeatedly executed for each image frame processing (for example, every several milliseconds) when the image processing apparatus 10 is executing image recognition. Process. The microcomputer 10a also performs white line recognition and vehicle recognition, but a description thereof is omitted in this processing flow.

  First, the pedestrian candidate area detection unit 19 cuts out the determination area (step S101), and the pedestrian candidate area detection unit 19 detects the pedestrian candidate area (step S102). Further, the pedestrian recognition unit 18 performs pattern matching on the pedestrian candidate area, and determines whether or not the pedestrian candidate area is a pedestrian (step S103).

  As a result, if there is no pedestrian in the input image (No at Step S104), the learning processing unit 12 creates a reference pattern from the entire image (Step S105), and updates the reference pattern database (Step S106). The process is terminated.

  On the other hand, when a pedestrian exists (step S104, Yes), first, the pedestrian information and the distance to the pedestrian are output to the collision determination unit 20 (step S107). And after masking a pedestrian by the pedestrian mask process part 12a (step S108), a reference pattern is produced (step S109), a reference pattern database is updated (step S106), and a process is complete | finished.

  Here, “update” means adding the latest frame image vector component to the background image vector component learned so far to change the vector component.

  As for the pedestrian mask, only the pedestrian image recognized by the pedestrian recognition unit 18 may be removed, or the pedestrian candidate area itself recognized as a pedestrian by the pedestrian recognition unit 18. May be removed. Moreover, you may remove all the pedestrian candidate areas based on the detection result by the pedestrian candidate area | region detection part 19 irrespective of the recognition result by the pedestrian recognition part 18. FIG.

  Furthermore, the image used as the learning image may be an image captured by the camera 31 or may be an image output by the preprocessing unit 11. Furthermore, a processing result image by another arbitrary processing unit may be used.

  Next, the processing operation of the pre-crash ECU 40 will be described with reference to the flowchart of FIG. This process flow is a process that starts when power is supplied when IG is turned on and the like, and is repeatedly executed.

  First, the pre-crash ECU 40 receives data indicating the result of image recognition from the image recognition device 10 (step S201). If the risk of collision with a pedestrian or the like is high (step S202, Yes), the driver 44 is notified by a warning sound output such as a buzzer by the speaker 44 or a display output by the display 43 (step S203). Or vehicle control by EFI 42 is executed (step S204), and the process is terminated.

  As described above, the image recognition apparatus 10 according to the present embodiment improves the detection accuracy of the pedestrian candidate area by the saliency algorithm by creating a reference pattern as needed from the image captured by the camera 31 during traveling. ing.

  In this embodiment, the case where a specific object, that is, a pedestrian is recognized from an image captured by the in-vehicle camera is described as an example. For example, an image captured by a movable (rotating) traffic monitoring camera is used. It is applicable to. In this embodiment, the saliency calculation is applied. However, the present invention is not limited to this, and a background difference method of storing a background image as a reference pattern and extracting a candidate image based on a difference from the current image may be applied.

  As described above, the object candidate region detection device, the object candidate region detection method, the pedestrian recognition device, and the vehicle control device according to the present invention are useful for image recognition in a vehicle, and particularly for improving detection accuracy of a pedestrian candidate region. Is suitable.

1 is a schematic configuration diagram illustrating a schematic configuration of an image recognition apparatus according to an embodiment of the present invention. It is explanatory drawing explaining the detection of the candidate area | region by a saliency algorithm. It is explanatory drawing explaining the detection accuracy fall of a candidate area | region. It is explanatory drawing explaining preparation of the reference pattern which concerns on this invention. It is explanatory drawing explaining saliency calculation which concerns on this invention. It is explanatory drawing explaining the image for learning, and a pedestrian's mask. It is a flowchart explaining the processing operation | movement of a reference | standard pattern update. It is a flowchart explaining the processing operation of the pre-crash ECU shown in FIG.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 Image recognition apparatus 10a Microcomputer 11 Pre-processing part 12 Learning processing part 12a Pedestrian mask processing part 12b Lane recognition part 15 Reference pattern database 16 Vehicle recognition part 17 White line recognition part 18 Pedestrian recognition part 19 Pedestrian candidate area | region detection part 20 Collision Determining unit 30 Navigation device 30a Map data 31 Camera

Claims (8)

An object candidate area detection device that detects an area where a specific object may exist from an input image captured by a camera as an object candidate area,
A detection means for detecting the object candidate area in the determination area by comparing the determination area cut out from the input image currently input by the camera and a reference pattern in which the input image is stored in advance;
Using the detection result, reference pattern update means for updating the reference pattern using a region in which the specific object does not exist in the current input image;
An object candidate area detecting apparatus comprising:   2. The object candidate region detection according to claim 1, wherein the reference pattern update unit updates the reference pattern from the entire input image when an object candidate region does not exist as a result of detection by the detection unit. apparatus.   The object candidate region detection apparatus according to claim 1, wherein the reference pattern update unit updates the reference pattern by excluding the object candidate region detected by the detection unit from the input image.   Object recognition means for recognizing whether or not the specific object is present in the object candidate area is further provided, and the reference pattern update means is configured to detect when the specific object does not exist as a result of recognition by the object recognition means. The object candidate region detection apparatus according to claim 1, wherein the reference pattern is updated from the entire input image.   The apparatus further comprises object recognition means for recognizing whether or not the specific object exists in the object candidate area, and the reference pattern update means excludes the specific object recognized by the object recognition means from the input image. The object candidate region detection apparatus according to claim 1, wherein the reference pattern is updated. An object candidate area detection method for detecting an area where a specific object may exist from an input image captured by a camera as an object candidate area,
A detection step of detecting the object candidate area among the determination areas by comparing the determination area extracted from the input image currently input by the camera and a reference pattern in which the input image is stored in advance.
Using the detection result, a reference pattern update step of updating the reference pattern using a region in the input image where the specific object does not exist;
The object candidate area | region detection method characterized by including. A pedestrian recognition device that recognizes a pedestrian from an input image taken by an in-vehicle camera,
A detection means for detecting, as a pedestrian candidate region, a region where a pedestrian may exist by comparing a determination target region cut out from an input image currently input by a camera and a reference pattern in which an input image is stored in advance
Pedestrian determination means for determining whether the pedestrian candidate area corresponds to a pedestrian,
Using the detection result, reference pattern update means for updating the reference pattern using a region in which the specific object does not exist in the current input image;
A pedestrian recognition device comprising: A detection means for detecting, as a pedestrian candidate region, a region where a pedestrian may exist by comparing a determination target region cut out from an input image currently input by a camera and a reference pattern in which the input image is stored in advance;
Pedestrian determination means for determining whether the pedestrian candidate area corresponds to a pedestrian,
Using the detection result, reference pattern update means for updating the reference pattern using a region in which the specific object does not exist in the current input image;
Control means for executing notification control for notifying the presence of a pedestrian and / or running control for controlling the running state of the vehicle when a pedestrian is recognized by the pedestrian discrimination means;
A vehicle control device comprising:

Images