JP2022048481A - Object recognition control device and object recognition control method - Google Patents

Abstract

To appropriately recognize an object.SOLUTION: A control section 20 being an object recognition control device includes: a video data acquisition section 21 for acquiring video data photographed by a camera 11 for photographing the periphery of a vehicle; a confirmation direction detection section 22 for detecting a visual line direction of an operator of the vehicle and detecting a direction which is not surely visually confirmed by the operator; a recognition processing section 23 for recognizing the video data acquired by the video data acquisition section 21 as a specific object when a score indicating specific object likeness is equal to or more than a threshold in the video data; and a presentation processing section 24 for presenting information of the specific object recognized by the recognition processing section 23 to the operator of the vehicle. The recognition processing section 23 changes a threshold of a score based on a direction which is detected by the confirmation direction detection section 22 and which is not surely visually confirmed by the operator.SELECTED DRAWING: Figure 1

Description

The present invention relates to an object recognition control device and an object recognition control method.

In the recognition process using the person recognition dictionary, the person recognition in the captured image is determined to be a person when the score indicating the person-likeness is equal to or higher than a predetermined threshold value. There is known a technique for determining that an object is a pedestrian based on a high score indicating pedestrian-likeness using a recognition dictionary for captured images (see, for example, Patent Document 1).

Japanese Unexamined Patent Publication No. 2016-015029

Normally, the driver of the vehicle visually confirms a person and a specific object that requires attention, such as a bicycle on which the person is riding, while driving. If the driver's visual confirmation is concentrated in a certain direction, there is a risk that the person in the direction in which the visual confirmation is neglected and the bicycle on which the person is riding may be delayed or overlooked. In such a state, if recognition omission occurs in the recognition process of a person and a bicycle on which the person is riding, safety may be impaired.

The present invention has been made in view of the above, and an object of the present invention is to appropriately recognize an object.

In order to solve the above-mentioned problems and achieve the object, the object recognition control device according to the present invention includes a video data acquisition unit that acquires video data taken by a shooting unit that shoots the periphery of the vehicle, and an operation of the vehicle. The confirmation direction detection unit that detects the line-of-sight direction of the person and detects the direction in which the visual confirmation by the driver is sparse, and the video data acquired by the video data acquisition unit show the specific object-likeness. When the score is equal to or higher than the threshold value, the recognition processing unit that recognizes the specific object and the presentation processing unit that presents the information of the specific object recognized by the recognition processing unit to the driver of the vehicle are provided. The processing unit changes the threshold value based on the direction in which the visual confirmation by the driver detected by the confirmation direction detection unit is neglected.

The object recognition control method executed by the object recognition control device according to the present invention detects a video data acquisition step of acquiring video data taken by a shooting unit that shoots the periphery of the vehicle and a line-of-sight direction of the driver of the vehicle. When the score indicating the specific object-likeness is equal to or higher than the threshold value for the video data acquired in the confirmation direction detection step for detecting the direction in which the visual confirmation by the driver is sparse and the video data acquisition step. In the recognition processing step, the confirmation direction includes a recognition processing step of recognizing the specific object and a presentation processing step of presenting the information of the specific object recognized in the recognition processing step to the driver of the vehicle. The threshold value is changed based on the direction in which the visual confirmation by the driver detected by the detection step is sparse.

According to the present invention, there is an effect that the object can be recognized appropriately.

FIG. 1 is a block diagram showing a configuration example of an object recognition device having an object recognition control device according to the first embodiment. FIG. 2 is a schematic diagram showing an example of a range in video data. FIG. 3 is a schematic diagram showing another example of the range in the video data. FIG. 4 is a flowchart showing a processing flow in the object recognition control device according to the first embodiment. FIG. 5 is a schematic diagram showing an example of a range in video data. FIG. 6 is a schematic diagram showing another example of the range in the video data.

Hereinafter, embodiments of the object recognition control device and the object recognition control method according to the present invention will be described in detail with reference to the accompanying drawings. The present invention is not limited to the following embodiments.

[First Embodiment]
<Object recognition device>
FIG. 1 is a block diagram showing a configuration example of an object recognition device 10 having a control unit 20 which is an object recognition control device according to the first embodiment. The object recognition device 10 recognizes an object by performing a recognition process using an object recognition dictionary on the video data. The object recognition device 10 notifies the driver of information about the recognized object.

The object recognition device 10 includes a camera (shooting unit) 11, an in-vehicle camera 12, a recognition dictionary storage unit 13, a display unit 14, and a control unit (object recognition control device) 20. The object recognition device 10 may be implemented as a function of, for example, a device having a safe driving support function, a navigation device, a drive recorder, etc., which are installed in advance in the vehicle.

The camera 11 is a camera that photographs the periphery of the vehicle. The camera 11 is mounted on the vehicle and photographs the traveling direction of the vehicle. The camera 11 is composed of a far-infrared camera, a visible light camera, or a combination of a far-infrared camera and a visible light camera. The camera 11 is arranged, for example, at a position where the front side, which is the traveling direction of the vehicle, can be photographed. The camera 11 constantly captures images from the start of the engine to the stop of the engine, that is, while the vehicle is in operation. The camera 11 outputs the captured video data to the video data acquisition unit 21 of the control unit 20. The video data is, for example, a moving image composed of an image of 30 frames per second. In this embodiment, the camera 11 is arranged in front of the vehicle.

The in-vehicle camera 12 is a camera that photographs the interior of the vehicle. The in-vehicle camera 12 is arranged at a position where the face of the driver sitting in the driver's seat can be photographed. The in-vehicle camera 12 is composed of, for example, a visible light camera, a far-infrared camera, or a near-infrared camera. The in-vehicle camera 12 may be composed of, for example, a combination of a visible light camera and a far-infrared camera or a near-infrared camera. The in-vehicle camera 12 constantly captures an image from the start of the engine to the stop of the engine, that is, while the vehicle is in operation. The in-vehicle camera 12 outputs the captured in-vehicle video data to the video data acquisition unit 21 of the control unit 20. The in-vehicle video data is, for example, a moving image composed of an image of 30 frames per second.

The recognition dictionary storage unit 13 stores dictionary data for recognizing various objects from video data. The recognition dictionary storage unit 13 stores, for example, an object recognition dictionary capable of machine learning various images captured by a specific object and collating that the object included in the image data is a specific object. The recognition dictionary storage unit 13 is, for example, a storage device such as a ROM (Read Only Memory), a semiconductor memory element such as a flash memory, or an external storage device via a network.

The display unit 14 is a device that displays various types of information, and as an example, is a display device unique to the object recognition device 10, or a display device shared with other systems including a drive recorder and a navigation system. The display unit 14 is a display including, for example, a liquid crystal display (LCD: Liquid Crystal Display) or an organic EL (Electro-Luminence) display. The display unit 14 displays a video based on the video signal output from the presentation processing unit 24 of the control unit 20. In the present embodiment, the display unit 14 is arranged at a position that can be visually recognized by the driver of the vehicle while driving.

<Object recognition control device>
The control unit 20 is, for example, an arithmetic processing unit (control device) configured by a CPU (Central Processing Unit) or the like. The control unit 20 loads the stored program into the memory and executes the instruction included in the program. The control unit 20 includes an internal memory (not shown), and the internal memory is used for temporary storage of data in the control unit 20 and the like. Therefore, the control unit 20 causes the object recognition device 10 to execute the object recognition method. Further, the control unit 20 is a computer that operates the program according to the present invention. The control unit 20 includes a video data acquisition unit 21, a confirmation direction detection unit 22, a recognition processing unit 23, and a presentation processing unit 24, which are connected to the bus 20X.

The video data acquisition unit 21 acquires video data taken by the camera 11. More specifically, the video data acquisition unit 21 acquires video data output by the camera 11 and captured in front of the vehicle in the traveling direction.

The video data acquisition unit 21 acquires video data taken by the in-vehicle camera 12. More specifically, the video data acquisition unit 21 acquires in-vehicle video data output by the in-vehicle camera 12 and acquires video data in which the face of the driver of the vehicle is photographed.

The confirmation direction detection unit 22 detects the line-of-sight direction of the driver of the vehicle, and detects the direction in which the visual confirmation by the driver is neglected. In the present embodiment, the confirmation direction detection unit 22 performs image processing on the in-vehicle video data taken by the in-vehicle camera 12, recognizes the driver's face, and indicates a direction in which the driver's visual confirmation is neglected. To detect. More specifically, the confirmation direction detection unit 22 recognizes the driver's eyes from, for example, in-vehicle video data, and acquires information indicating the direction of the line of sight. The confirmation direction detection unit 22 indicates whether or not there is a bias in the direction visually confirmed by the driver from the direction of the driver's line of sight of the vehicle, in other words, the direction in which the driver's visual confirmation is sparse. Determine if it exists. Any method can be applied to the line-of-sight detection based on the image of the driver's eyes, such as the line-of-sight detection based on the positional relationship between the inner corner of the eye and the glow detected from the image of the eye, or the line-of-sight detection based on the positional relationship between the corneal reflex and the pupil. Is.

In the present embodiment, the confirmation direction detection unit 22 detects a direction in which visual confirmation is sparse with respect to the front direction or the left-right direction when the driver of the vehicle is facing forward, which is the traveling direction of the vehicle. do.

The confirmation direction detection unit 22 faces the front direction, which is the traveling direction of the vehicle, while the driver is driving, or periodically faces the left-right direction, etc., from the direction of the driver's face and the line-of-sight direction. If so, it is judged that there is no direction in which the visual confirmation by the driver of the vehicle is neglected. The confirmation direction detection unit 22 determines that, for example, when the period in which the driver is looking forward to the right continues for, for example, 5 seconds or more, the visual confirmation in the left direction is sparse. The confirmation direction detection unit 22 determines that, for example, when the period in which the driver is looking forward to the left continues for, for example, 5 seconds or more, the visual confirmation in the right direction is sparse.

The recognition processing unit 23 recognizes a specific object around the vehicle from the video data acquired by the video data acquisition unit 21. The recognition processing unit 23 performs pattern matching on the video data using the object recognition dictionary stored in the recognition dictionary storage unit 13 to perform object recognition processing for recognizing a specific object. A known method can be used in the object recognition process. The recognition processing unit 23 may always perform processing while the object recognition device 10 is running.

The specific object includes a person, a two-wheeled vehicle including a bicycle on which the person is riding, and another vehicle.

The recognition processing unit 23 recognizes the video data acquired by the video data acquisition unit 21 as a specific object when the score indicating the specific object-likeness is equal to or higher than a predetermined threshold value. The threshold value of the normal score is set to the specified value A. The threshold value of the score is changed according to the detection result by the confirmation direction detection unit 22. Let B be the threshold of the changed score.

The recognition processing unit 23 recognizes a specific object by changing the threshold value of the score based on the detection result of the confirmation direction detection unit 22. The recognition processing unit 23 changes the score threshold value based on the direction in which the driver's visual confirmation detected by the confirmation direction detection unit 22 is sparse. More specifically, when the detection result indicates that there is a direction in which the visual confirmation by the driver is sparse, the recognition processing unit 23 sets the normal score with respect to the direction in which the visual confirmation is sparse. It is recognized as a specific object by using a threshold value B (B <A) lower than the threshold value A of. This makes it easier for the driver to recognize the object as a specific object when it indicates that there is a direction in which the visual confirmation by the driver is sparse. When the detection result indicates that there is no direction in which the visual confirmation by the driver is sparse, the recognition processing unit 23 recognizes the object as a specific object by using the threshold value A of the score at the normal time.

For example, the maximum score indicating the uniqueness of a specific object is 1.0. As an example, the threshold value A is 0.9 and the threshold value B is 0.7. Normally, when the score is 0.9 or more, the recognition processing unit 23 determines that the detected object is a specific object. When the recognition processing unit 23 has a direction in which the visual confirmation by the driver is sparse, the detected object is detected when the score is 0.7 or more with respect to the direction in which the visual confirmation is sparse. Judge that it is a specific object. When the recognition processing unit 23 performs object recognition on the condition that the score is 0.7 or more, the recognition processing unit 23 uses a normal threshold value when there is no direction in which the visual confirmation by the driver is sparse. Return to the recognition process.

The score threshold value may be set for each specific object, in other words, for each recognition dictionary.

The threshold value of the score may be changed stepwise, or may be changed linearly from the direction in which the visual confirmation is sparse to the direction in which the visual confirmation is not sparse.

Even if the recognition processing unit 23 lowers the threshold value of the score in the video data acquired by the video data acquisition unit 21, the threshold value of the score is lowered with respect to the direction in which the driver's visual confirmation detected by the confirmation direction detection unit 22 is sparse. good.

FIG. 2 is a schematic diagram showing an example of the range in the video data 100. As shown in FIG. 2, the video data 100 may be divided into a left range AL and a right range AR with the center line in the left-right direction as a boundary. For example, when the direction in which the driver does not visually confirm the video data 100 is the right range AR, the recognition processing unit 23 lowers the score threshold value for the right range AR of the video data 100. May be good. In this case, the threshold value of the score is the normal threshold value for the left range AL, which is not neglected by the driver.

FIG. 3 is a schematic diagram showing another example of the range in the video data. As shown in FIG. 3, the video data 100 may be divided into a left range AL and a right range AR by setting a central range AC which is a central portion in the left-right direction. For example, when the direction in which the driver does not visually confirm the video data 100 is the right range AR, the recognition processing unit 23 lowers the score threshold value for the right range AR of the video data 100. May be good. In this case, the score threshold is the normal threshold for the left range AL and the center range AC where the visual confirmation by the driver is not neglected.

The presentation processing unit 24 presents the information of the specific object recognized by the recognition processing unit 23 to the driver of the vehicle. By presenting the information of the specific object recognized by the presentation processing unit 24, the driver of the vehicle is alerted to the specific object. The presentation processing unit 24 presents the recognized specific object information to the driver by using the display by the display unit 14 or the voice output from the voice output unit (not shown). Therefore, the presentation processing unit 24 functions as a display control unit when the information of the specific object is presented to the driver by the display by the display unit 14. More specifically, the presentation processing unit 24 generates an image that presents information to the driver of the vehicle. The presentation processing unit 24 generates, for example, presentation video data for displaying video data by superimposing a frame line on a recognized specific object range. The presentation processing unit 24 may generate presentation video data for displaying characters or icons that call attention to a specific object, for example. The presentation processing unit 24 may generate audio such as a warning sound to be output together with the video. The presentation processing unit 24 outputs a video signal for displaying the generated video to the display unit 14 to display the video. The presentation processing unit 24 may output an audio signal for outputting the audio generated together with the video to a speaker (not shown).

The image presented to the driver of the vehicle is, for example, an image such as a character or an icon indicating that a specific object has been detected around the vehicle.

<Processing in the control unit>
Next, the flow of processing in the control unit 20 will be described with reference to FIG. FIG. 4 is a flowchart showing a processing flow in the control unit 20 which is the object recognition control device according to the first embodiment. When the object recognition device 10 is activated, the processing of the flowchart shown in FIG. 4 is started. The start of the process of FIG. 4 is started under arbitrary conditions. For example, when the vehicle becomes available, such as when the engine of the vehicle equipped with the object recognition device 10 starts, or when the operation of the object recognition device 10 is started by the user's operation. Further, the process of step S101 may be executed on condition that the vehicle is running.

With the start of the process of FIG. 4, the control unit 20 starts the shooting and the object recognition process (step S101). More specifically, the control unit 20 starts shooting by the camera 11. The control unit 20 acquires the video data output by the camera 11 by the video data acquisition unit 21. The control unit 20 recognizes a specific object around the vehicle from the video data acquired by the video data acquisition unit 21 by the recognition processing unit 23. The threshold value of the score of the object recognition process in step S101 is the threshold value A of the score at the normal time. For example, the control unit 20 determines that the detected object is a specific object when the score is 0.9 or more by the recognition processing unit 23. Further, the control unit 20 starts shooting by the in-vehicle camera 12. The control unit 20 acquires the in-vehicle video data output by the in-vehicle camera 12 by the video data acquisition unit 21. The control unit 20 proceeds to step S102.

At the same time as the process in step S101 is started, the control unit 20 determines whether or not there is a direction in which the visual confirmation by the driver is neglected (step S102). More specifically, the control unit 20 detects the driver's line of sight from the video data acquired by the video data acquisition unit 21 by the confirmation direction detection unit 22. When the detection result of the confirmation direction detection unit 22 indicates that there is a direction in which the visual confirmation by the driver is sparse (Yes in step S102), the control unit 20 proceeds to step S104. When the detection result of the confirmation direction detection unit 22 indicates that there is no direction in which the visual confirmation by the driver is sparse (No in step S102), the control unit 20 proceeds to step S103.

When it is shown that there is no direction in which the visual confirmation by the driver is sparse (No in step S102), the control unit 20 performs the specific object recognition process by the recognition process unit 23 using the threshold value A of the normal score. Is executed (step S103). More specifically, when the score is 0.9 or more, the recognition processing unit 23 determines that the detected object is a specific object. The control unit 20 proceeds to step S105.

When it indicates that there is a direction in which the visual confirmation by the driver is sparse (Yes in step S102), the control unit 20 uses the threshold value B lower than the threshold value A of the normal score by the recognition processing unit 23. To execute the specific object recognition process (step S104). More specifically, when the score is 0.7 or more, the recognition processing unit 23 determines that the detected object is a specific object. As a result, when there is a direction in which the visual confirmation by the driver is sparse, the detected object is more likely to be recognized as a specific object as compared with the normal time. The control unit 20 proceeds to step S105.

The control unit 20 determines whether or not the specific object has been recognized based on the object recognition result of the recognition processing unit 23 (step S105). When the control unit 20 determines that the specific object has been recognized (Yes in step S105), the control unit 20 proceeds to step S106. If the control unit 20 does not determine that the specific object has been recognized (No in step S105), the control unit 20 proceeds to step S107.

The control unit 20 displays a frame line in the range of the specific object recognized by the presentation processing unit 24 (step S106). More specifically, the control unit 20 causes the presentation processing unit 24 to superimpose a frame line surrounding a specific object around the vehicle on the video data and display it on the display unit 14. The control unit 20 proceeds to step S107.

The control unit 20 determines whether or not to end the shooting and object recognition processing (step S107). The control unit 20 determines that the shooting and the object recognition process are finished, for example, when the operation for ending the object recognition process is detected, or when the vehicle is stopped and the engine is turned off. When the control unit 20 determines that the shooting and the object recognition process are completed (Yes in step S107), the control unit 20 ends the process. If the control unit 20 does not determine that the photographing and object recognition processing is completed (No in step S107), the control unit 20 re-executes the processing in step S102.

<Effect>
As described above, in the present embodiment, the threshold value of the score in the object recognition process is changed depending on whether or not there is a direction in which the visual confirmation by the driver is sparse. According to the present embodiment, it is possible to appropriately recognize a specific object depending on whether or not there is a direction in which the driver's visual confirmation is neglected.

In the present embodiment, when it is shown that there is a direction in which the visual confirmation by the driver is sparse, the threshold value of the score in the object recognition process is lowered with respect to the direction. According to the present embodiment, when there is a direction in which the driver's visual confirmation is neglected and there is a possibility that the driver's attention to the person or the like is neglected, it is easy to recognize the specific object in the direction. can do. According to this embodiment, safer driving can be supported.

Further, in the present embodiment, when it is shown that there is a direction in which the visual confirmation by the driver is sparse, a part of the object is behind the object in order to lower the threshold of the score in the object recognition process with respect to the direction. Even if it is not recognized as a specific object by a normal score like a specific object such as a hidden person, it is recognized as a specific object. Therefore, the driver of the vehicle can more appropriately know the existence of the specific object.

Further, in the present embodiment, when it is shown that there is a direction in which the visual confirmation by the driver is sparse, an object that is not a specific object is specified in order to lower the threshold value of the score in the object recognition process with respect to the direction. Misrecognition as an object increases. However, even if it is a misrecognition, it is presented as the existence of a specific object, so that the driver of the vehicle can be made to drive with more emphasis on safety.

[Second Embodiment]
The object recognition device 10 according to the present embodiment will be described with reference to FIGS. 5 and 6. FIG. 5 is a schematic diagram showing an example of a range in video data. FIG. 6 is a schematic diagram showing another example of the range in the video data. Since the configuration of the object recognition device 10 according to the second embodiment is the same as that of the object recognition device 10 of the first embodiment and the processing is different, the description of the configuration will be omitted.

The recognition processing unit 23 reduces the score threshold value in a direction farther from the front of the driver, based on the left-right direction in which the driver's visual confirmation detected by the confirmation direction detection unit 22 is sparse. To change.

As shown in FIG. 5, the video data 100 is divided into four in the left-right direction, and in order from the left, the first left side range AL1, the second left side range AL2, the second right side range AR2, and the first right side range AR1. You may divide it. For example, when the driver of the vehicle is not visually confirmed in the right direction, the threshold value of the first right range AR1 is 0.6 and the threshold value of the second right range AR2 is 0.7. For example, when the driver of the vehicle is not visually confirmed in the left direction, the threshold value of the first left side range AL1 is 0.6 and the threshold value of the second left side range AL2 is 0.7.

As shown in FIG. 6, the video data 100 is divided into four by setting AC2, which is the central portion in the left-right direction, and in order from the left, the left range AL1, the left range AL2, the right range AR2, and the right range AR1. You may divide it. In this case as well, the threshold value can be set in the same manner as described above.

As described above, in the present embodiment, when the biometric information indicates that the concentration is reduced, the threshold value of the score of the object recognition process is lowered. According to this embodiment, the object can be appropriately recognized.

In each of the above-described embodiments, the example in which the driver of the vehicle is not visually confirmed with respect to the right or left direction in the traveling direction of the vehicle has been described, but the driver of the vehicle is in the traveling direction of the vehicle. In the state in which the line of sight does not move for a predetermined period from the front direction, that is, the direction of the central range AC in FIG. 3 or the direction of the central range AC2 in FIG. 6, the score threshold may be lowered in the left-right direction.

Although the object recognition device 10 according to the present invention has been described so far, it may be implemented in various different embodiments other than the above-described embodiment.

Each component of the illustrated object recognition device 10 is functionally conceptual and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically dispersed or integrated in an arbitrary unit according to the processing load and usage status of each device. You may.

The configuration of the object recognition device 10 is realized by, for example, a program loaded in a memory as software. In the above embodiment, it has been described as a functional block realized by cooperation of these hardware or software. That is, these functional blocks can be realized in various forms by hardware only, software only, or a combination thereof.

The above-mentioned components include those that can be easily assumed by those skilled in the art and those that are substantially the same. Further, the above configurations can be combined as appropriate. Further, various omissions, substitutions or changes of the configuration can be made without departing from the gist of the present invention.

In the above, the output control unit has been described as displaying information on the display unit, but the present invention is not limited to this. The output control unit may, for example, output sound from a speaker installed in the vehicle.

10 Object recognition device 11 Camera (shooting unit)
12 In-vehicle camera 13 Recognition dictionary storage unit 14 Display unit 20 Control unit (object recognition control device)
21 Video data acquisition unit 22 Confirmation direction detection unit 23 Recognition processing unit 24 Presentation processing unit

Claims (5)

The video data acquisition unit that acquires the video data taken by the shooting unit that shoots the surroundings of the vehicle, and the video data acquisition unit.
A confirmation direction detection unit that detects the line-of-sight direction of the driver of the vehicle and detects a direction in which the visual confirmation by the driver is sparse.
When the score indicating the specific object-likeness is equal to or higher than the threshold value for the video data acquired by the video data acquisition unit, the recognition processing unit recognizes the video data as the specific object.
A presentation processing unit that presents information on the specific object recognized by the recognition processing unit to the driver of the vehicle, and a presentation processing unit.
Equipped with
The recognition processing unit changes the threshold value based on the direction in which the visual confirmation by the driver detected by the confirmation direction detection unit is sparse.
Object recognition controller. The recognition processing unit lowers the threshold value with respect to the direction in which the visual confirmation by the driver detected by the confirmation direction detection unit is neglected in the video data acquired by the video data acquisition unit.
The object recognition control device according to claim 1. The confirmation direction detection unit detects a direction in which the driver of the vehicle has not turned his / her line of sight for a predetermined period as a direction in which visual confirmation is sparse.
The object recognition control device according to claim 1 or 2. The recognition processing unit sets the threshold value smaller with respect to a direction farther from the front of the driver, based on the left-right direction in which the visual confirmation by the driver detected by the confirmation direction detection unit is sparse. Change to be,
The object recognition control device according to claim 3. A video data acquisition step to acquire video data taken by the shooting unit that shoots the surroundings of the vehicle, and
A confirmation direction detection step that detects the line-of-sight direction of the driver of the vehicle and detects a direction in which the visual confirmation by the driver is sparse.
When the score indicating the specific object-likeness is equal to or higher than the threshold value for the video data acquired in the video data acquisition step, the recognition processing step for recognizing the specific object and the recognition processing step.
A presentation processing step that presents information on the specific object recognized in the recognition processing step to the driver of the vehicle, and a presentation processing step.
Including
In the recognition processing step, the threshold value is changed based on the direction in which the visual confirmation by the driver detected by the confirmation direction detection step is sparse.
The object recognition control method executed by the object recognition control device.

Images