Infrared light supplement control method and device for monitoring camera in vehicle and computer readable storage medium
By performing image recognition and human eye position calculation on the real-time video images collected by the in-vehicle surveillance camera, accurate human eye safety control of infrared fill lights is achieved, and the problems of misjudgment and unrecognition in the prior art are solved, and safety and calculation accuracy are improved.
Patent Information
- Application Number
- CN202411979886.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-31
- Publication Date
- 2025-06-03
AI Technical Summary
The existing infrared fill light control method of in-vehicle surveillance cameras has the problem of misjudging the external strong light to be reflected by the human eye and incorrectly extinguishing the infrared fill light. It cannot effectively identify the situation where the infrared fill light is turned off when the human eye is not facing the lens, resulting in damage to the human eye.
By obtaining real-time video images collected by the in-car surveillance camera, image recognition is performed to filter out the target image containing the human eye, calculate the actual relative distance of the human eye to the infrared fill light, and compare it with the preset safety distance threshold. If the distance is less than or equal to the threshold, the command to turn off the infrared fill light is output.
Accurate human eye safety control of infrared fill lights is achieved, avoiding the risk of misjudgment and human eye damage, and has high calculation accuracy and strong stability, and is not disturbed by external strong light.
Smart Images

Figure CN120091211A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the technical field of in-vehicle camera device control, and in particular, to an infrared supplementary light control method, device, and computer-readable storage medium for an in-vehicle monitoring camera. Background Art
[0002] Currently, in-vehicle monitoring cameras (such as DMS cameras) are usually installed in the cockpit of motor vehicles to monitor drivers and passengers. To ensure good image acquisition under poor lighting conditions, in-vehicle monitoring cameras are usually equipped with infrared supplementary lights. Since infrared light can cause harm to the human eye, an infrared supplementary light control device is usually provided for the in-vehicle monitoring camera to automatically turn off the infrared supplementary light when a human eye enters the warning distance range.
[0003] There is a current infrared supplementary light control device for an in-vehicle monitoring camera that mainly realizes automatic control based on the intensity of reflected light, that is, by analyzing the lighting intensity of the image captured by the in-vehicle monitoring camera to determine the relative distance between the human eye and the infrared supplementary light. When the human eye is closer to the infrared supplementary light, the lighting intensity of its reflected light is greater. When the lighting intensity of the reflected light is greater than a preset value, the infrared supplementary light is controlled to turn off.
[0004] However, the inventor found during specific implementation that the existing infrared supplementary light control method and its device have the following defects: when the in-vehicle monitoring camera is irradiated by strong external light, it is easy for the in-vehicle monitoring camera to misjudge the strong external light as the reflected light of the human eye and wrongly turn off the infrared supplementary light; moreover, when the human eye enters the warning distance range of the infrared supplementary light without being directly opposite the lens of the in-vehicle monitoring camera, since the reflected light of the human eye cannot be effectively recognized, the infrared supplementary light cannot be turned off in time, resulting in harm to the human eye. Summary of the Invention
[0005] The technical problem to be solved by the embodiments of the present invention is to provide an infrared supplementary light control method for an in-vehicle monitoring camera, which can accurately achieve human eye safety control for the infrared supplementary light of the in-vehicle monitoring camera.
[0006] The further technical problem to be solved by the embodiments of the present invention is to provide an infrared supplementary light control device for an in-vehicle monitoring camera, which can accurately achieve human eye safety control for the infrared supplementary light of the in-vehicle monitoring camera.
[0007] The further technical problem to be solved by the embodiments of the present invention is to provide a computer-readable storage medium for storing a computer program that can accurately achieve human eye safety control for the infrared supplementary light of the in-vehicle monitoring camera.
[0008] To solve the above technical problems, the embodiments of the present invention provide the following technical solutions: An infrared supplementary light control method for an in-vehicle monitoring camera, comprising: Obtain the real-time video image inside the motor vehicle collected by the in-vehicle monitoring camera when the infrared fill light of the in-vehicle monitoring camera is in the on state; Perform image recognition on the real-time video image and screen out the target images containing human eyes therefrom; Based on the target image, calculate the actual relative distance of the human eye relative to the infrared fill light of the monitoring camera; and Compare the actual relative distance with a preset safety distance threshold. When the actual distance is less than or equal to the preset safety distance threshold, output a turn-off instruction for controlling the infrared fill light to remain off to the in-vehicle monitoring camera.
[0009] Further, the calculating the actual relative distance of the human eye relative to the infrared fill light of the monitoring camera based on the target image specifically includes: Calculate the actual relative depth of the human eye in the target image and the image sensor of the in-vehicle monitoring camera; and Combine the actual relative depth and the spatial three-dimensional coordinates of the image sensor and the infrared fill light of the in-vehicle monitoring camera that are respectively pre-calibrated to calculate the actual relative distance of the human eye in the target image relative to the infrared fill light.
[0010] Further, the performing image recognition on the real-time video image and screening out the target images containing human eyes therefrom specifically includes: performing face recognition on the real-time video image and screening out the face images with the face facing the in-vehicle monitoring camera, and the face images contain human eyes.
[0011] Further, the calculating the actual relative depth of the human eye in the target image and the image sensor of the in-vehicle monitoring camera specifically includes: based on the three-dimensional face center-of-brow coordinate detection algorithm model, combine the face image to calculate the actual relative depth of the human eye in the face image and the image sensor of the in-vehicle monitoring camera.
[0012] Further, after recognizing a face in the real-time video image, use the head pose estimation algorithm model to calculate the actual pitch angle and actual yaw angle of the face relative to the in-vehicle monitoring camera. If the actual pitch angle and actual yaw angle respectively meet the preset pitch angle threshold range and preset yaw angle threshold range, determine that the face is facing the in-vehicle monitoring camera.
[0013] Further, the performing image recognition on the real-time video image and screening out the target images containing human eyes therefrom further includes: performing human eye recognition on the real-time video image and screening out the real-time images containing human eyes.
[0014] Further, calculating the actual relative depth between the human eyes in the target image and the image sensor of the in-vehicle monitoring camera further includes: calculating the actual pixel area occupied by the human eye image region in the real-time image containing the human eyes based on an object segmentation algorithm model, and calculating the actual relative depth between the human eyes in the real-time image and the image sensor of the in-vehicle monitoring camera based on the actual pixel area and the original pixel area of the real-time image.
[0015] Further, after it is determined that the actual relative distance is less than or equal to a preset safety distance threshold, the real-time video image is periodically subjected to image detection and distance comparison until the actual relative distance is greater than the preset safety distance threshold, and then the output of the shutdown instruction is stopped.
[0016] On the other hand, to solve the above further technical problems, an embodiment of the present invention provides the following technical solution: an infrared supplementary light control device for an in-vehicle monitoring camera, connected to the in-vehicle monitoring camera, the device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the infrared supplementary light control method for the in-vehicle monitoring camera as described in any one of the above.
[0017] On the other hand, to solve the above further technical problems, an embodiment of the present invention provides the following technical solution: a computer-readable storage medium, the computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the infrared supplementary light control method for the in-vehicle monitoring camera as described in any one of the above.
[0018] After adopting the above technical solutions, the embodiments of the present invention at least have the following beneficial effects: After the embodiments of the present invention obtain the real-time video image inside the motor vehicle collected by the in-vehicle monitoring camera, the real-time video image is subjected to image detection to screen out the target image containing the human eyes. When there are human eyes in the video image, it indicates that there is a safety hazard of the human eyes being exposed in front of the infrared supplementary light. Therefore, by combining the target image, the actual relative distance of the human eyes relative to the infrared supplementary light is calculated, with high calculation accuracy and not being affected by external strong light interference, and strong stability; finally, by comparing the actual relative distance with the preset safety distance threshold, when the actual distance is less than or equal to the preset safety distance threshold, a shutdown instruction for controlling the infrared supplementary light to remain off is output to the in-vehicle monitoring camera, realizing the human eye safety detection and control of the infrared supplementary light. Description of the Drawings
[0019] Figure 1 It is a flowchart of the steps of an optional embodiment of the infrared supplementary light control method for the in-vehicle monitoring camera of the present invention.
[0020] Figure 2 This is a specific flowchart of step S3 in an alternative embodiment of the infrared supplementary light control method for the in-vehicle monitoring camera of the present invention.
[0021] Figure 3 This is a subsequent processing flowchart after the first output of the shutdown instruction in an alternative embodiment of the infrared supplementary light control method for the in-vehicle monitoring camera of the present invention.
[0022] Figure 4 This is a principle block diagram of an alternative embodiment of the infrared supplementary light control device for the in-vehicle monitoring camera of the present invention.
[0023] Figure 5 This is a functional module diagram of an alternative embodiment of the infrared supplementary light control device for the in-vehicle monitoring camera of the present invention. Specific embodiments
[0024] The following further describes the present application in detail with reference to the accompanying drawings and specific embodiments. It should be understood that the following illustrative embodiments and descriptions are only used to explain the present invention and are not intended to limit the present invention. Moreover, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.
[0025] As Figure 1 shown, an alternative embodiment of the present invention provides an infrared supplementary light control method for an in-vehicle monitoring camera, including: S1: When the infrared supplementary light 10 of the in-vehicle monitoring camera 1 is in the on state, obtain the real-time video image inside the motor vehicle collected by the in-vehicle monitoring camera 1; S2: Perform image recognition on the real-time video image to screen out the target image containing human eyes; S3: Calculate the actual relative distance of the human eyes relative to the infrared supplementary light of the monitoring camera based on the target image; and S4: Compare the actual relative distance with a preset safety distance threshold, and when the actual distance is less than or equal to the preset safety distance threshold, output a shutdown instruction for controlling the infrared supplementary light 10 to remain off to the in-vehicle monitoring camera 1.
[0026] In an embodiment of the present invention, after obtaining the real-time video image inside the motor vehicle collected by the in-vehicle monitoring camera 1, the real-time video image is subjected to image detection to screen out the target image containing human eyes. When there are human eyes in the video image, it indicates that there is a safety hazard that the human eyes are exposed in front of the infrared supplementary light 10. Therefore, the actual relative distance of the human eyes relative to the infrared supplementary light 10 is calculated by combining the target image, with high calculation accuracy, not being interfered by external strong light, and strong stability; finally, by comparing the actual relative distance with the preset safety distance threshold, when the actual distance is less than or equal to the preset safety distance threshold, a closing instruction for controlling the infrared supplementary light 10 to remain closed is output to the in-vehicle monitoring camera 1, realizing the human eye safety detection and control of the infrared supplementary light 10.
[0027] In an alternative embodiment of the present invention, as Figure 2 shown, step S3 specifically includes: S31: calculating the actual relative depth of the human eyes in the target image relative to the image sensor 12 of the in-vehicle monitoring camera 1; and S32: calculating the actual relative distance of the human eyes in the target image relative to the infrared supplementary light 10 by combining the actual relative depth and the spatial three-dimensional coordinates of the image sensor 12 of the in-vehicle monitoring camera 1 and the infrared supplementary light 10 that are respectively pre-calibrated.
[0028] In this embodiment, by first calculating the actual relative depth of the human eyes in the target image relative to the image sensor 12 of the in-vehicle monitoring camera 1, and then further combining the actual relative depth and the spatial three-dimensional coordinates of the image sensor 12 of the in-vehicle monitoring camera 1 and the infrared supplementary light 10 that are respectively pre-calibrated, the actual relative distance of the human eyes relative to the infrared supplementary light 10 can be calculated, with high calculation accuracy and high efficiency.
[0029] In specific implementation, it can be understood that the spatial three-dimensional coordinates of the image sensor 12 of the in-vehicle monitoring camera 1 and the infrared supplementary light 10 are both coordinates in the body coordinate system of the motor vehicle; in addition, the specific value of the preset safety distance threshold refers to the IEC 62471 standard.
[0030] In an alternative embodiment of the present invention, step S2 specifically includes: performing face recognition on the real-time video image to screen out the face image in which the face faces the in-vehicle monitoring camera 1, and the face image contains human eyes. In this embodiment, when the user's face faces the in-vehicle monitoring camera 1 and the distance from the in-vehicle monitoring camera 1 is relatively far, the in-vehicle monitoring camera 1 can completely capture the face. Through face recognition technology, a face image containing human eyes can be quickly obtained, and the target image can be obtained more efficiently for subsequent data processing.
[0031] In an alternative embodiment of the present invention, step S31 specifically includes: calculating, based on a three-dimensional face center-of-brow coordinate detection algorithm model and in combination with the face image, the actual relative depth between the human eyes in the face image and the image sensor 12 of the in-vehicle monitoring camera 1. This embodiment proposes a method for calculating the actual relative depth of the human eyes relative to the image sensor 12 for the face image obtained in the previous steps, which can quickly calculate the actual relative depth between the human eyes in the face image and the image sensor 12 of the in-vehicle monitoring camera 1, and is beneficial to improving the data processing efficiency.
[0032] In an alternative embodiment of the present invention, after identifying a face in the real-time video image, a head pose estimation algorithm model is used to calculate the actual pitch angle and actual yaw angle of the face relative to the in-vehicle monitoring camera 1. When the actual pitch angle and actual yaw angle respectively meet the preset pitch angle threshold range and preset yaw angle threshold range, it is determined that the face is facing the in-vehicle monitoring camera 1. In this embodiment, after detecting a face, by first using the corresponding pose estimation algorithm model to calculate the actual pitch angle and actual yaw angle of the detected face relative to the in-vehicle monitoring camera 1, it can be understood that if the face is directly facing the in-vehicle monitoring camera 1, the actual pitch angle and actual yaw angle of both faces relative to the in-vehicle monitoring camera 1 should be zero. In this embodiment, considering calculation and detection errors, corresponding preset pitch angle threshold ranges and preset yaw angle threshold ranges are set, so as to ensure that the faces facing the in-vehicle monitoring camera 1 are screened out.
[0033] In an alternative embodiment of the present invention, step S2 further includes: performing eye recognition on the real-time video image to screen out real-time images containing eyes. In this embodiment, when the distance between the eyes and the in-vehicle monitoring camera 1 is relatively close or the user's face is not directly facing the in-vehicle monitoring camera 1, at this time, the lens cannot capture a complete face image. At this time, in order to implement distance detection, the eyes in the real-time video image can also be detected to screen out the target image. Thus, through double recognition of face recognition and eye recognition, the occurrence of omission situations can be effectively avoided and the safety can be improved.
[0034] In an alternative embodiment of the present invention, step S31 further includes: calculating, based on an object segmentation algorithm model, the actual pixel area occupied by the human eye image region corresponding to the human eye in the real-time image including the human eye, and calculating, based on the actual pixel area and the original pixel area of the real-time image, the actual relative depth between the human eye in the real-time image and the image sensor 12 of the in-vehicle monitoring camera 1. In this embodiment, when the distance between the human eye and the in-vehicle monitoring camera 1 is relatively close or the user's face is not facing the in-vehicle monitoring camera 1 directly, in order to implement distance detection, the actual relative depth between the human eye and the image sensor 12 of the in-vehicle monitoring camera 1 can also be calculated using the pixel area of the eye in the image.
[0035] In an alternative embodiment of the present invention, when it is determined that the actual relative distance is less than or equal to a preset safety distance threshold, the real-time video image is periodically (for example: every 20 seconds) subjected to image detection and distance comparison until the actual relative distance is greater than the preset safety distance threshold, and then an activation instruction for controlling the activation of the infrared fill light 10 is output to the in-vehicle monitoring camera 1. In this embodiment, when it is determined that the actual relative distance between the human eye and the infrared fill light 10 is less than or equal to the preset safety distance threshold, by periodically performing image detection and distance comparison, when the actual relative distance is greater than the preset safety distance threshold, the human eye safety detection function is cancelled to restart the infrared fill light 10. At this time, the infrared fill light 10 can be restored to its original activated state to perform normal fill light.
[0036] Specifically, in the subsequent processing flow after the first determination that the actual relative distance is less than or equal to the preset safety distance threshold and the output of the shutdown instruction is as Figure 3 shown.
[0037] On the other hand, as Figure 4 shown, an infrared fill light control device 3 for an in-vehicle monitoring camera provided by an embodiment of the present invention is connected to the in-vehicle monitoring camera 1. The device 3 includes a processor 30, a memory 32, and a computer program stored in the memory 32 and configured to be executed by the processor 30. When the processor 30 executes the computer program, the infrared fill light control method for the in-vehicle monitoring camera as described in any one of the above is implemented.
[0038] Exemplarily, the computer program can be divided into one or more modules / units. The one or more modules / units are stored in the memory 32 and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the infrared fill light control device 3 for the in-vehicle monitoring camera. For example, the computer program can be divided into Figure 5The functional modules in the infrared supplementary light control device 3 of the in-vehicle monitoring camera, wherein the image acquisition module 41, the image detection module 42, the relative distance calculation module 43, and the supplementary light control module 44 respectively execute the above steps S1 - step S4.
[0039] The infrared supplementary light control device 3 of the in-vehicle monitoring camera can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The infrared supplementary light control device 3 of the in-vehicle monitoring camera may include, but is not limited to, a processor 30 and a memory 32. Those skilled in the art can understand that the schematic diagram is only an example of the infrared supplementary light control device 3 of the in-vehicle monitoring camera, and does not constitute a limitation on the infrared supplementary light control device 3 of the in-vehicle monitoring camera. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, the infrared supplementary light control device 3 of the in-vehicle monitoring camera may also include input / output devices, network access devices, a bus, etc.
[0040] The processor 30 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor 30 is the control center of the infrared supplementary light control device 3 of the in-vehicle monitoring camera, and connects various parts of the entire infrared supplementary light control device 3 of the in-vehicle monitoring camera through various interfaces and lines.
[0041] The memory 32 can be used to store the computer programs and / or modules. By running or executing the computer programs and / or modules stored in the memory 32, and invoking the data stored in the memory 32, the processor 30 realizes various functions of the infrared supplementary light control device 3 of the in-vehicle monitoring camera. The memory 32 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a graphic recognition function, a graphic stacking function, etc.); the data storage area can store data created according to the use of the control device (such as graphic data, etc.). In addition, the memory 32 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0042] If the functions described in the embodiments of the present invention are implemented in the form of software function modules or units and sold or used as independent products, they can be stored in a storage medium readable by a computing device. Based on such an understanding, to implement all or part of the processes in the above method embodiments, the present invention embodiments can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor 30, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disc, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.
[0043] On the other hand, the embodiments of the present invention provide a computer-readable storage medium, which includes a stored computer program. When the computer program runs, it controls the device where the computer-readable storage medium is located to execute the infrared supplementary light control method of the in-vehicle monitoring camera as described in any one of the above.
[0044] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the various embodiments, reference can be made to each other.
[0045] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative rather than restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the purpose of the present invention and the scope protected by the claims. All of these fall within the protection scope of the present invention.
Claims
1. A method for controlling infrared fill light of an in-vehicle surveillance camera, characterized in that: The method comprises: Acquire real-time video images of the interior of a motor vehicle collected by the in-vehicle surveillance camera when the infrared fill light of the in-vehicle surveillance camera is turned on; Performing image recognition on the real-time video image to filter out a target image containing a human eye; Calculating and obtaining the actual relative distance between the human eye and the infrared fill light of the surveillance camera based on the target image; and The actual relative distance is compared with a preset safety distance threshold, and when the actual distance is less than or equal to the preset safety distance threshold, a closing instruction for controlling the infrared fill light to remain closed is output to the in-vehicle monitoring camera.
2. The infrared fill light control method for the in-vehicle monitoring camera according to claim 1, characterized in that: The step of calculating the actual relative distance between the human eye and the infrared fill light of the surveillance camera based on the target image specifically includes: Calculating the actual relative depth between the human eye in the target image and the image sensor of the in-vehicle monitoring camera; and The actual relative distance between the human eye in the target image and the infrared fill light is calculated by combining the actual relative depth and the spatial three-dimensional coordinates of the image sensor of the in-vehicle monitoring camera and the infrared fill light which are pre-calibrated respectively.
3. The infrared fill light control method for the in-vehicle monitoring camera as claimed in claim 2, characterized in that: The performing image recognition on the real-time video image to filter out the target image containing human eyes specifically includes: performing face recognition on the real-time video image to filter out the face image of the face facing the in-vehicle monitoring camera, and the face image contains human eyes.
4. The infrared fill light control method for the in-vehicle monitoring camera as claimed in claim 3, characterized in that: The calculating the actual relative depth between the human eyes in the target image and the image sensor of the in-vehicle surveillance camera specifically includes: calculating based on a three-dimensional face eyebrow center coordinate detection algorithm model combined with the face image to obtain the actual relative depth between the human eyes in the face image and the image sensor of the in-vehicle surveillance camera.
5. The infrared fill light control method for the in-vehicle monitoring camera as claimed in claim 3, characterized in that: After a face is recognized in the real-time video image, a head posture estimation algorithm model is used to calculate the actual pitch angle and actual yaw angle of the face relative to the in-vehicle surveillance camera. If the actual pitch angle and the actual yaw angle respectively correspond to and satisfy a preset pitch angle threshold range and a preset yaw angle threshold range, it is determined that the face is facing the in-vehicle surveillance camera.
6. The infrared fill light control method for the in-vehicle monitoring camera as claimed in claim 3, characterized in that: The performing image recognition on the real-time video image to filter out the target image containing human eyes therefrom further comprises: performing human eye recognition on the real-time video image to filter out the real-time image containing human eyes.
7. The infrared fill light control method for the in-vehicle monitoring camera as claimed in claim 6, characterized in that: The calculating the actual relative depth between the human eye in the target image and the image sensor of the in-vehicle surveillance camera also includes: calculating the actual pixel area occupied by the human eye image area in the real-time image containing the human eye based on the object segmentation algorithm model, and calculating the actual relative depth between the human eye in the real-time image and the image sensor of the in-vehicle surveillance camera based on the actual pixel area and the original pixel area of the real-time image.
8. The infrared fill light control method for the in-vehicle monitoring camera as claimed in claim 1, characterized in that: When it is determined that the actual relative distance is less than or equal to the preset safety distance threshold, image detection and distance comparison are periodically performed on the real-time video image until the actual relative distance is greater than the preset safety distance threshold, and then the closing instruction is stopped from being output.
9. An infrared fill light control device for an in-vehicle surveillance camera, connected to the in-vehicle surveillance camera, characterized in that: The device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the infrared fill light control method for the in-vehicle monitoring camera according to any one of claims 1 to 8 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the infrared fill light control method for the in-vehicle monitoring camera according to any one of claims 1 to 8.