Anti-shake method and equipment for automobile data recorder

Abstract

The invention aims to provide the anti-shake method and equipment for the automobile data recorder, the speed of automatic exposure ae adjustment of the automobile data recorder is reduced when the ambient brightness is strongly turned, the anti-shake effect is achieved, and no matter whether the speed of a large-area shadow is reduced or the speed of a plurality of small-area shadow zones is sharply reduced, the anti-shake effect is achieved. According to the method, obvious anti-shake can be achieved when the current frame is in a preset state, the automatic exposure speed of the automobile data recorder can be intelligently recovered when the environment brightness value of the current frame and the preset target brightness value are too large in difference, and the adaptability in an actual application scene is higher.

Description

Technical Field

[0001] This application relates to the technical field of driving recorders, and particularly to an anti-shake method and device for a driving recorder. Background Art

[0002] In the prior art, the commonly used Auto Exposure (AE) anti-shake technology has a certain tolerance threshold for environmental changes, and the exposure will only be adjusted when it accumulates to a certain extent. However, this will cause the AE adjustment to be too slow and have a certain lag; and during driving, only tree shades and short-distance shadows require anti-shake.

[0003] For the existing conventional AE anti-shake technology, taking the target brightness as A, when the environment changes from A to B, the change amount is B - A = Δa, and the threshold is C. The cumulative value of Δa: Δa_sum = Δa_sum + Δa. When Δa_sum < C, the exposure will not be adjusted immediately. It is not until the cumulative Δa_sum of multiple frames > the threshold C that the AE algorithm will be triggered to adjust the exposure gain. This is of certain anti-shake value for conventional security products, as most of them are static images, and there is occasional entry of people or rapid passing of objects. However, for the driving industry, it will cause a lag in AE adjustment because the environmental change needs to accumulate to the threshold before adjustment, and the vehicle is constantly moving during driving. Any AE change scenarios (such as entering and exiting tunnels, passing through large areas of shadows, etc.) will have a certain lag, which will instead introduce more image quality problems.

[0004] Currently, the core of the driving anti-shake algorithm is how to distinguish which scenarios should adjust the AE and which should not. Among them, Ai is a good solution, but the resources it consumes are not worth the gain for embedded devices; the traditional algorithm is a one-size-fits-all approach and cannot distinguish such scenarios. Summary of the Invention

[0005] An object of this application is to provide an anti-shake method and device for a driving recorder. By reducing the adjustment speed of the automatic exposure AE of the driving recorder when there is a strong transition in the environmental brightness, the anti-shake effect can be achieved. Whether it is a large area of shadow without speed reduction or a sharp speed reduction in multiple small-area shadow bands, obvious anti-shake can be achieved. And when the difference between the environmental brightness value of the current frame and the preset target brightness value is too large, the automatic exposure speed of the driving recorder will be intelligently restored, making it more adaptable in actual application scenarios.

[0006] According to one aspect of this application, an anti-shake method for a driving recorder is provided. The driving recorder is installed in a vehicle, and the method includes:

[0007] Obtaining brightness statistical information of a current frame of the vehicle during driving from an image signal processing module of the driving recorder, and calculating an ambient brightness value of the current frame based on the brightness statistical information of the current frame;

[0008] Determine whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame,

[0009] If yes, start or continue counting cnt++ and record the current change direction;

[0010] When the accumulated cnt is less than the preset counting threshold N, it is determined whether the current change direction is opposite to the previous change direction.

[0011] If the opposite is true, the current speed of the automatic exposure of the driving recorder is halved, and it is determined whether the brightness difference between the ambient brightness value and the target brightness value of the current frame is greater than a preset brightness difference threshold;

[0012] If the brightness difference is greater than or equal to the preset brightness difference threshold, stop counting cnt, restore the current speed of the automatic exposure of the driving recorder to the initial speed of the automatic exposure of the driving recorder, and continue to obtain the brightness statistical information of the next frame of the vehicle during driving through the driving recorder.

[0013] Furthermore, in the above method, determining whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame includes:

[0014] Obtaining, from the image signal processing module of the driving recorder, the ambient brightness value of the previous frame during the driving of the vehicle;

[0015] It is determined whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame.

[0016] Furthermore, in the above method, after determining whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame, the method further includes:

[0017] If the ambient brightness value of the current frame is the same as the ambient brightness value of the previous frame, and the accumulated cnt is greater than 0, then continue to count cnt++ and record the current change direction.

[0018] Furthermore, in the above method, after determining whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame, the method further includes:

[0019] If the ambient brightness value of the current frame is the same as the ambient brightness value of the previous frame, and the accumulated cnt is less than or equal to 0, the current speed of the automatic exposure of the driving recorder will not be adjusted, and the brightness statistical information of the next frame of the vehicle during driving will continue to be obtained through the driving recorder.

[0020] Furthermore, in the above method, after starting or continuing to count cnt++ and recording the current change direction, the method further includes:

[0021] When the accumulated cnt is greater than or equal to N, stop counting cnt, restore the current speed of the automatic exposure of the driving recorder to the initial speed of the automatic exposure of the driving recorder, and continue to obtain the brightness statistics of the next frame of the vehicle during driving through the driving recorder.

[0022] Furthermore, in the above method, when the accumulated cnt is less than the preset counting threshold N, after determining whether the current change direction is opposite to the previous change direction, the method further includes:

[0023] If the last change direction is not opposite to the previous change direction, the current speed of the automatic exposure of the driving recorder is not adjusted, and the brightness statistical information of the next frame of the vehicle during driving is continuously obtained through the driving recorder.

[0024] Furthermore, in the above method, after determining whether the brightness difference between the ambient brightness value and the target brightness value of the current frame is greater than a preset brightness difference threshold, the method further includes:

[0025] If the brightness difference is less than a preset brightness difference threshold, then continue to obtain the brightness statistics of the next frame of the vehicle during driving. According to another aspect of the present application, a non-volatile storage medium is also provided, on which computer-readable instructions are stored, and when the computer-readable instructions can be executed by a processor, the processor implements the anti-shake method of the driving recorder as described above.

[0026] According to another aspect of the present application, an anti-shake device for a driving recorder is also provided, wherein the device comprises:

[0027] one or more processors;

[0028] A computer readable medium for storing one or more computer readable instructions,

[0029] When the one or more computer-readable instructions are executed by the one or more processors, the one or more processors implement the anti-shake method for the driving recorder as described above.

[0030] Compared with the prior art, the present application obtains the brightness statistical information of the current frame of the vehicle during driving from the image signal processing module of the driving recorder, and calculates the ambient brightness value of the current frame through the brightness statistical information of the current frame; determines whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame, and if so, starts or continues to count cnt++, and records the current change direction; when the accumulated cnt is less than the preset counting threshold N, determines whether the current change direction is opposite to the previous change direction, and if opposite, reduces the current speed of the automatic exposure of the driving recorder by half, and determines whether the brightness difference between the ambient brightness value of the current frame and the target brightness value is greater than the preset brightness difference threshold; if the brightness difference is greater than or equal to the preset brightness difference threshold, stops counting cnt, and restores the current speed of the automatic exposure of the driving recorder to the initial speed of the automatic exposure of the driving recorder, and continues to obtain the brightness statistical information of the next frame of the vehicle during driving through the driving recorder. When the ambient brightness changes drastically, the speed of the dash cam's automatic exposure AE adjustment is reduced to achieve the effect of anti-shake. Whether it is a large area of ​​shadow without speed reduction, or a small area of ​​multiple shadow bands with a sharp speed reduction, it can achieve obvious anti-shake. When the difference between the ambient brightness value of the current frame and the preset target brightness value is too large, the dash cam's automatic exposure speed will be intelligently restored, which is more adaptable in actual application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0032] Figure 1 A schematic diagram showing the main flow of an anti-shake method for a driving recorder according to one aspect of the present application;

[0033] Figure 2 A schematic diagram showing a complete processing flow of an anti-shake method for a driving recorder according to one aspect of the present application in an actual application scenario;

[0034] Figure 3 A schematic diagram showing an anti-shake comparison between an anti-shake method for a driving recorder according to one aspect of a preferred embodiment of the present application and a traditional anti-shake technology in an actual application scenario is shown.

[0035] The same or similar reference numerals in the drawings represent the same or similar components. DETAILED DESCRIPTION

[0036] The present application is described in further detail below in conjunction with the accompanying drawings.

[0037] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (CPU), input / output interfaces, network interfaces and memories.

[0038] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0039] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0040] like Figure 1 As shown, Figure 1 A schematic diagram of the main flow of an anti-shake method for a driving recorder proposed in one aspect of the present application, wherein the driving recorder is installed in a vehicle, wherein the method comprises step S11, step S12, step S13, step S14, step S15 and step S16, specifically comprising the following steps:

[0041] Step S11, obtaining brightness statistical information of a current frame of the vehicle during driving from an image signal processing module of the driving recorder, and calculating an ambient brightness value of the current frame according to the brightness statistical information of the current frame;

[0042] Step S12, determining whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame,

[0043] Step S13: If yes, that is, the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame, then start or continue counting cnt++ after the ambient brightness changes, and record the current change direction;

[0044] Step S14: When the accumulated cnt is less than the preset counting threshold N, it is determined whether the current change direction is opposite to the previous change direction.

[0045] Step S15: if the opposite is true, the current speed of the automatic exposure of the driving recorder is halved, and it is determined whether the brightness difference between the ambient brightness value and the target brightness value of the current frame is greater than a preset brightness difference threshold;

[0046] Step S16: If the brightness difference is greater than or equal to the preset brightness difference threshold, stop counting cnt, restore the current speed of the automatic exposure of the driving recorder to the initial speed of the automatic exposure of the driving recorder, and continue to obtain the brightness statistical information of the next frame of the vehicle during driving through the driving recorder.

[0047] Through the above steps S11 to S16, it is achieved that when the ambient brightness changes sharply, the speed of the automatic exposure ae adjustment of the driving recorder is reduced to achieve the effect of anti-shake. Whether it is a large area of ​​shadow without speed reduction, or a small area of ​​multiple shadow bands with a sharp speed reduction, obvious anti-shake can be achieved. In addition, when the difference between the ambient brightness value of the current frame and the preset target brightness value is too large, the automatic exposure speed of the driving recorder will be intelligently restored, which has stronger adaptability in actual application scenarios.

[0048] like Figure 2 As shown, in an anti-shake method for a driving recorder provided by an embodiment of one aspect of the present application, first, the brightness statistical information of the current frame of the vehicle during driving is obtained from the image signal processing module of the driving recorder installed in the vehicle, and the ambient brightness value of the current frame is calculated according to the brightness statistical information of the current frame: now_lv, wherein the calculation formula of the ambient brightness value now_lv of the current frame is: the brightness value luma of the picture corresponding to the current frame / (exposure*gain), and the ambient brightness value of the previous frame of the vehicle during driving is set to last_lv.

[0049] Then, determine whether the ambient brightness value now_lv of the current frame is different from the ambient brightness value last_lv of the previous frame. If different, start counting cnt++. Once cnt starts counting, cnt will be +1 in each subsequent frame. At the same time, record the current change direction as now_direction. The calculation formula of the current change direction now_direction is: now_lv-last_lv.

[0050] Next, when the accumulated cnt is less than the preset counting threshold N, it is necessary to determine whether the current change direction now_direction is opposite to the previous change direction last_direction. If they are opposite, that is, now_direction*last_direction<1, it means that the ambient brightness has changed, such as from brightening to darkening, or from darkening to brightening. In this case, the current speed of the automatic exposure of the driving recorder needs to be halved to make cnt=1 and count again.

[0051] Finally, determine whether the brightness difference between the ambient brightness value and the target brightness value of the current frame is greater than a preset brightness difference threshold; if the brightness difference is greater than or equal to the preset brightness difference threshold, stop counting cnt, set cnt=0, and restore the current speed of the automatic exposure of the driving recorder to the initial speed of the automatic exposure of the driving recorder, and continue to obtain the brightness statistical information of the next frame of the vehicle during driving through the driving recorder. Here, in the actual application scenario, there is a target brightness value in the automatic exposure of the driving recorder. In order to keep the image brightness in the driving recorder consistent or similar, when the anti-shake speed reduction occurs in an extreme situation, the brightness difference between the statistical ambient brightness value and the target brightness value is too large, which will be unfriendly. Then, it is necessary to restore the current speed of the automatic exposure and then speed it up. Then, the counting cnt is stopped to make cnt=0, and the current speed of the automatic exposure of the driving recorder is restored to the initial speed of the automatic exposure of the driving recorder. When the brightness difference between the ambient brightness value and the target brightness value of the current frame is greater than or equal to the preset brightness difference threshold, the initial speed of the automatic exposure of the driving recorder can be intelligently restored.

[0052] Following the above embodiment of the present application, the step S12 determines whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame, specifically including:

[0053] First, the ambient brightness value last_lv of the previous frame of the vehicle during the driving process is obtained from the image signal processing module of the driving recorder, wherein the ambient brightness value of each frame of the vehicle during the driving process is stored in the driving recorder; then, it is determined whether the ambient brightness value now_lv of the current frame is different from the ambient brightness value last_lv of the previous frame, so that after the ambient brightness value of the previous frame is obtained, it is determined whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame.

[0054] Following the above embodiment of the present application, after the step S12 determines whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame, the method further includes:

[0055] If the ambient brightness value of the current frame is the same as the ambient brightness value of the previous frame, and the accumulated cnt is greater than 0, then continue to count cnt++ and record the current change direction.

[0056] like Figure 2 As shown, for example, when the vehicle is traveling under the condition of uniform or stable ambient brightness (in a long tunnel or long tree shade, etc.), the ambient brightness value of the current frame is the same as the ambient brightness value of the previous frame, and the accumulated cnt is greater than 0, indicating that before entering the long tunnel or long tree shade, there is a change in ambient brightness, and cnt will be greater than 0. In order to keep counting cnt, it is necessary to continue counting cnt++ and record the current change direction, so as to realize the counting of cnt during the vehicle driving process in a stable or uniform brightness environment after the vehicle enters a stable ambient brightness from a driving environment with changing ambient brightness.

[0057] Following the above embodiment of the present application, after the step S12 determines whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame, the method further includes:

[0058] If the ambient brightness value of the current frame is the same as the ambient brightness value of the previous frame, and the accumulated cnt is less than or equal to 0, the current speed of the automatic exposure of the driving recorder will not be adjusted, and the brightness statistical information of the next frame of the vehicle during driving will continue to be obtained through the driving recorder.

[0059] like Figure 2 As shown, for example, when a vehicle is traveling under uniform or stable ambient brightness (in a long tunnel or under long tree shades, etc.), the ambient brightness value of the current frame is the same as the ambient brightness value of the previous frame, and the accumulated cnt is less than or equal to 0, then the current speed of the automatic exposure of the driving recorder is not adjusted, and the brightness statistical information of the next frame of the vehicle during the driving process is continuously obtained through the driving recorder, ensuring that the vehicle continues to maintain the current speed of the automatic exposure of the driving recorder under stable or uniform ambient brightness, thereby ensuring that the image brightness in the driving recorder remains consistent or similar.

[0060] Following the above embodiment of the present application, if the ambient brightness value of the current frame in step S13 is different from the ambient brightness value of the previous frame, then after starting or continuing to count cnt++ and recording the current change direction, the method further includes:

[0061] When the accumulated cnt is greater than or equal to the preset counting threshold N, it means that the direction of the long-term change direction has not changed, then stop counting cnt, make cnt=0, and restore the current speed of the automatic exposure of the driving recorder to the initial speed of the automatic exposure of the driving recorder, that is, cnt=0 and stop counting, such as Figure 2 As shown, the brightness statistics of the next frame of the vehicle during driving are continuously obtained through the driving recorder, so as to stop counting and restore the current speed of the automatic exposure of the driving recorder to the initial speed of the automatic exposure of the driving recorder when the direction of change does not change for a long time.

[0062] Following the above embodiment of the present application, in step S14, when the accumulated cnt is less than the preset counting threshold N, after determining whether the current change direction is opposite to the previous change direction, the method further includes:

[0063] If the previous change direction is not opposite to the previous change direction, for example, the previous change direction last_direction = the previous change direction now_direction, then the current speed of the automatic exposure of the driving recorder is not adjusted, and the brightness statistical information of the next frame of the vehicle during driving is continued to be obtained through the driving recorder.

[0064] Following the above embodiment of the present application, in step S15, when the current change direction is opposite to the previous change direction, the current speed of the automatic exposure of the driving recorder is halved, and after determining whether the brightness difference between the ambient brightness value and the target brightness value of the current frame is greater than a preset brightness difference threshold, the method further includes:

[0065] If the brightness difference is less than the preset brightness difference threshold, the brightness statistical information of the next frame of the vehicle during driving continues to be obtained. That is, when the brightness difference between the ambient brightness value and the target brightness value of the current frame is still within the controllable preset brightness value threshold range, the brightness statistical information of the next frame of the vehicle during driving can continue to be obtained through the driving recorder.

[0066] like Figure 3 FIG. 1 is a schematic diagram showing a comparison of an anti-shake method for a driving recorder in a preferred embodiment of the present application and a traditional anti-shake technology in an actual application scenario, which simulates the adaptability of the anti-shake method for a driving recorder in the present application and the traditional anti-shake technology to different scenarios from the data. Figure 3It can be seen that for the algorithm of traditional anti-shake technology, if the threshold is too small, it basically has no great effect; and if the threshold is too large, although the anti-shake effect is very good, it will bring a lot of lag for large-area shadow scenes, which is difficult to accept. The new AE anti-shake method adopted by this application uses the directionality of brightness changes to significantly reduce the adjustment speed after multiple changes, similar to the principle of speed bumps. When the brightness changes sharply, the speed of AE adjustment is reduced to achieve the effect of anti-shake. Whether it is a large area of ​​shadows without speed reduction, or a small area of ​​multiple shadow bands with a sharp speed reduction, it can achieve obvious anti-shake, and the brightness difference between the ambient brightness value and the target brightness value of the current frame will be too large. The speed will be restored intelligently. Fundamentally, the traditional anti-shake technology is to judge that the change in a short period of time is not greater than the preset count threshold and then not to adjust, which is more suitable for traditional security; and the anti-shake method of a driving recorder provided by this application is to judge that there are multiple changes in the brightness direction in a short period of time and then reduce the adjustment speed, which is more suitable for driving recorders, making it more adaptable.

[0067] According to another aspect of the present application, a non-volatile storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions can be executed by a processor, the processor implements the anti-shake method of the driving recorder as described above.

[0068] According to another aspect of the present application, an anti-shake device for a driving recorder is also provided, wherein the device includes:

[0069] one or more processors;

[0070] A computer readable medium for storing one or more computer readable instructions,

[0071] When the one or more computer-readable instructions are executed by the one or more processors, the one or more processors implement the anti-shake method for the driving recorder as described above.

[0072] Here, for the detailed contents of each embodiment of the device for intercepting ANR based on the operating system of the mobile terminal, please refer to the corresponding part of the embodiment of the anti-shake method of the above-mentioned driving recorder, which will not be repeated here.

[0073] In summary, the present application obtains the brightness statistical information of the current frame of the vehicle during driving from the image signal processing module of the driving recorder, and calculates the ambient brightness value of the current frame through the brightness statistical information of the current frame; determines whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame, and if so, starts or continues to count cnt++, and records the current change direction; when the accumulated cnt is less than the preset counting threshold N, determines whether the current change direction is opposite to the previous change direction, if opposite, the current speed of the automatic exposure of the driving recorder is halved, and determines whether the brightness difference between the ambient brightness value of the current frame and the target brightness value is greater than the preset brightness difference threshold; if the brightness difference is greater than or equal to the preset brightness difference threshold, stops counting cnt, and restores the current speed of the automatic exposure of the driving recorder to the initial speed of the automatic exposure of the driving recorder, and continues to obtain the brightness statistical information of the next frame of the vehicle during driving through the driving recorder. When the ambient brightness changes drastically, the speed of the dash cam's automatic exposure AE adjustment is reduced to achieve the effect of anti-shake. Whether it is a large area of ​​shadow without speed reduction, or a small area of ​​multiple shadow bands with a sharp speed reduction, it can achieve obvious anti-shake. When the difference between the ambient brightness value of the current frame and the preset target brightness value is too large, the dash cam's automatic exposure speed will be intelligently restored, which is more adaptable in actual application scenarios.

[0074] It should be noted that the present application can be implemented in software and / or a combination of software and hardware, for example, can be implemented using an application specific integrated circuit (ASIC), a general purpose computer or any other similar hardware device. In one embodiment, the software program of the present application can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0075] In addition, a part of the present application may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present application through the operation of the computer. The program instruction for calling the method of the present application may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-bearing medium, and / or stored in a working memory of a computer device that runs according to the program instruction. Here, according to an embodiment of the present application, a device is included, the device including a memory for storing computer program instructions and a processor for executing program instructions, wherein, when the computer program instruction is executed by the processor, the device is triggered to run the method and / or technical solution based on the aforementioned multiple embodiments according to the present application.

[0076] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present application is limited by the attached claims rather than the above description, so it is intended to include all changes that fall within the meaning and scope of the equivalent elements of the claims in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A method for anti-shaking a driving recorder, wherein the driving recorder is installed in a vehicle, The method comprises: Obtaining brightness statistical information of a current frame of the vehicle during driving from an image signal processing module of the driving recorder, and calculating an ambient brightness value of the current frame based on the brightness statistical information of the current frame; Determine whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame, If yes, start or continue counting cnt++ and record the current change direction; When the accumulated cnt is less than the preset counting threshold N, it is determined whether the current change direction is opposite to the previous change direction. If the opposite is true, the current speed of the automatic exposure of the driving recorder is halved, and it is determined whether the brightness difference between the ambient brightness value and the target brightness value of the current frame is greater than a preset brightness difference threshold; If the brightness difference is greater than or equal to the preset brightness difference threshold, stop counting cnt, restore the current speed of the automatic exposure of the driving recorder to the initial speed of the automatic exposure of the driving recorder, and continue to obtain the brightness statistical information of the next frame of the vehicle during driving through the driving recorder.

2. The method according to claim 1, wherein: Determining whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame includes: Obtaining, from the image signal processing module of the driving recorder, the ambient brightness value of the previous frame during the driving of the vehicle; It is determined whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame.

3. The method according to claim 1, wherein: After determining whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame, the method further includes: If the ambient brightness value of the current frame is the same as the ambient brightness value of the previous frame, and the accumulated cnt is greater than 0, then continue to count cnt++ and record the current change direction.

4. The method according to claim 1, wherein: After determining whether the ambient brightness value of the current frame is different from the ambient brightness value of the previous frame, the method further includes: If the ambient brightness value of the current frame is the same as the ambient brightness value of the previous frame, and the accumulated cnt is less than or equal to 0, the current speed of the automatic exposure of the driving recorder will not be adjusted, and the brightness statistical information of the next frame of the vehicle during driving will continue to be obtained through the driving recorder.

5. The method according to claim 1, wherein: After starting or continuing to count cnt++ and recording the current change direction, the method further includes: When the accumulated cnt is greater than or equal to N, stop counting cnt, restore the current speed of the automatic exposure of the driving recorder to the initial speed of the automatic exposure of the driving recorder, and continue to obtain the brightness statistics of the next frame of the vehicle during driving through the driving recorder.

6. The method according to claim 1, wherein: When the accumulated cnt is less than the preset counting threshold N, after determining whether the current change direction is opposite to the previous change direction, the method further includes: If the last change direction is not opposite to the previous change direction, the current speed of the automatic exposure of the driving recorder is not adjusted, and the brightness statistical information of the next frame of the vehicle during driving is continuously obtained through the driving recorder.

7. The method according to claim 1, wherein: After determining whether the brightness difference between the ambient brightness value and the target brightness value of the current frame is greater than a preset brightness difference threshold, the method further includes: If the brightness difference is less than the preset brightness difference threshold, then continue to obtain brightness statistics information of the next frame during the driving process of the vehicle.

8. A non-volatile storage medium having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executable by a processor, the processor is enabled to implement the method according to any one of claims 1 to 7.

9. An anti-shake device for a driving recorder, wherein: The equipment includes: one or more processors; A computer readable medium for storing one or more computer readable instructions, When the one or more computer-readable instructions are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

Images