CN110830728A - Exposure adjusting method and device - Google Patents

Abstract

The invention relates to the technical field of image acquisition, and in particular to an exposure adjustment method and device. The method includes: detecting whether an image transmitted by a camera of an image acquisition device is in an overexposed state, and acquiring exposure parameters corresponding to the camera when the detection result is yes, and obtaining the depth position information corresponding to the image, mapping the image and the depth position information to obtain a depth image, inputting the depth image into a preset depth image learning model for detection to obtain a detection target, and reflecting the image and the detection target The corresponding position of the detection target in the image is obtained and the corresponding position is taken as the target position, and the target position is focused after adjusting the exposure parameters of the camera according to the light intensity value. Through the above method, the exposure parameters can be adjusted automatically, and the situation of time waste and inaccurate adjustment caused by manual adjustment can be effectively avoided.

Description

Exposure adjustment method and device

technical field

The present invention relates to the technical field of image acquisition, and in particular, to an exposure adjustment method and device.

Background technique

At present, in the process of using a camera for image acquisition, there is usually over-exposure or under-exposure, which causes image aberrations. At present, refocusing is mainly performed by manual adjustment, thereby correcting the image aberration caused by excessive exposure time caused by strong light. , or the image is too dark due to insufficient lighting.

The inventor found through research that manual adjustment usually takes too much time to focus, and in the adjustment process, due to the limited use of human subjective judgment, inaccurate adjustment may affect the shooting effect of the image.

SUMMARY OF THE INVENTION

In view of this, an object of the present invention is to provide an exposure adjustment method and device to effectively alleviate the above-mentioned technical problems.

To achieve the above purpose, the embodiment of the present invention adopts the following technical solutions:

An exposure adjustment method, applied to an image acquisition device, includes:

Detecting whether the image transmitted by the camera of the image acquisition device is in an overexposed state, and acquiring exposure parameters corresponding to the camera when the detection result is yes, and acquiring depth position information corresponding to the image;

After the image is mapped with the depth position information, a depth image is obtained, and the depth image is input into a preset depth image learning model for detection to obtain a detection target;

Perform inverse mapping on the image and the detection target to obtain the corresponding position of the detection target in the image and use the corresponding position as the target position;

Adjust the exposure parameters of the camera, and use the adjusted exposure parameters to refocus the target position.

In a preferred embodiment of the present invention, in the above exposure adjustment method, a depth sensor is provided at the viewport position of the camera, and the step of acquiring depth position information corresponding to the image includes:

Acquire depth position information obtained by performing image depth detection on the image by the depth sensor.

In a preferred embodiment of the present invention, in the above exposure adjustment method, the preset deep image learning model is a Faster R-CNN deep image learning model, an R-FCN deep image learning model or an SSD deep image learning model.

In a preferred embodiment of the present invention, in the above exposure adjustment method, the depth position information includes the position coordinates and depth values of each pixel in the image corresponding to the depth position information, and the image and the depth position information The steps of obtaining a depth image after mapping include:

Get the position coordinates of each pixel in the image;

A depth image is obtained by mapping the acquired position coordinates of each pixel with the position coordinates and depth values of each pixel in the depth position information.

In a preferred embodiment of the present invention, in the above exposure adjustment method, the step of detecting whether the image transmitted by the camera of the image acquisition device is in an overexposed state includes:

Perform light intensity detection on the image transmitted by the camera of the image acquisition device to obtain a light intensity value corresponding to the image;

It is judged whether the light intensity value is within the preset light intensity range, and when the light intensity value is not within the preset light intensity range, the exposure parameter corresponding to the camera under the light intensity value is obtained.

An exposure adjustment device, applied to image acquisition equipment, includes:

an exposure state detection module, configured to detect whether the image transmitted by the camera of the image acquisition device is in an overexposed state, and when the detection result is yes, obtain the exposure parameter corresponding to the camera, and obtain the depth position information corresponding to the image;

a depth image obtaining module, configured to obtain a depth image after mapping the image with the depth position information, and input the depth image into a preset depth image learning model for detection to obtain a detection target;

a target position obtaining module, used for inversely mapping the image and the detection target to obtain the corresponding position of the detection target in the image and using the corresponding position as the target position;

The exposure parameter adjustment module is used to adjust the exposure parameter of the camera, and use the adjusted exposure parameter to refocus the target position.

In a preferred embodiment of the present invention, in the above-mentioned exposure adjustment device, a depth sensor is provided at the viewport position of the camera, and the depth image obtaining module is further configured to obtain the depth sensor for image depth of the image. The detected depth position information.

In a preferred embodiment of the present invention, in the exposure adjustment device, the preset deep image learning model is a Faster R-CNN deep image learning model, an R-FCN deep image learning model or an SSD deep image learning model.

In a preferred embodiment of the present invention, in the above exposure adjustment device, the depth position information includes the position coordinates and depth values of each pixel in the image corresponding to the depth position information, and the depth image obtaining module includes:

The coordinate acquisition sub-module is used to acquire the position coordinates of each pixel in the image;

The mapping submodule is used for mapping the acquired position coordinates of each pixel with the position coordinates and depth values of each pixel in the depth position information to obtain a depth image.

In a preferred embodiment of the present invention, in the above exposure adjustment device, the exposure state detection module includes:

a detection sub-module, configured to perform light intensity detection on the image transmitted by the camera of the image acquisition device to obtain a light intensity value corresponding to the image;

The judgment sub-module is used to judge whether the light intensity value is within the preset light intensity range, and when the light intensity value is not within the preset light intensity range, obtain the exposure corresponding to the camera under the light intensity value parameter.

An exposure adjustment method and device provided by the present invention, by acquiring exposure parameters corresponding to the camera and acquiring depth position information corresponding to the image when detecting that the image transmitted by the camera of the image acquisition device is in an overexposed state, The detection target and the target position corresponding to the detection target are obtained according to the depth position information corresponding to the image, and after adjusting the exposure parameters of the camera, the target position is focused according to the adjusted exposure parameters, thereby realizing automatic adjustment of the exposure parameters. And effectively avoid the waste of time and inaccurate adjustment caused by manual adjustment.

In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below, and are described in detail as follows in conjunction with the accompanying drawings.

Description of drawings

FIG. 1 is a connection block diagram of an image acquisition device according to an embodiment of the present invention.

FIG. 2 is a schematic flowchart of an image processing method according to an embodiment of the present invention.

FIG. 3 is a schematic flowchart of step S110 in FIG. 2 .

FIG. 4 is a schematic flowchart of step S120 in FIG. 2 .

FIG. 5 is a connection block diagram of an exposure adjustment device according to an embodiment of the present invention.

FIG. 6 is a connection block diagram of an exposure state detection module provided by an embodiment of the present invention.

FIG. 7 is a connection block diagram of a depth image obtaining module according to an embodiment of the present invention.

Icon: 10-image acquisition device; 11-camera; 12-memory; 13-processor; 14-depth sensor; 15-display; 100-exposure adjustment device; 110-exposure state detection module; 112-detection sub-module; 114 - Judgment sub-module; 120 - Depth image acquisition module; 122 - Coordinate acquisition sub-module; 124 - Mapping sub-module; 130 - Target position acquisition module; 140 - Exposure parameter adjustment module.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments It is only a part of the embodiments of the present invention, but not all of the embodiments. The components of the embodiments of the invention generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations.

Thus, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

It should be noted that like numerals and letters refer to like items in the following figures, so once an item is defined in one figure, it does not require further definition and explanation in subsequent figures.

As shown in FIG. 1, an embodiment of the present invention provides an image acquisition device 10, including a camera 11, a memory 12, a processor 13, a depth sensor 14, and a display 15, the camera 11, memory 12, processor 13, depth sensor 15 The sensor 14 and the display 15 are directly or indirectly electrically connected to each other to realize data transmission or interaction.

Specifically, the camera 11 , the memory 12 , the depth sensor 14 and the display 15 are respectively electrically connected to the processor 13 , the camera 11 is used for capturing images, and the memory 12 stores software or firmware. A software function module stored in the memory 12 in the form of a software function module, the processor 13 executes various functional applications by running the software programs and modules stored in the memory 12, such as the exposure adjustment device 100 in the embodiment of the present invention and data processing, that is, to implement the exposure adjustment method in the embodiment of the present invention, the depth sensor 14 is used to detect the depth position information of the image captured by the camera 11, and the display 15 is used to display the image captured by the camera 11, so as to Viewed by users.

Wherein, the image acquisition device 10 may be, but not limited to, a mobile phone, a tablet or a camera, which is not specifically limited herein.

The memory 12 can be, but is not limited to, random access memory (Random Access Memory, RAM), read only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only Memory, PROM), erasable memory In addition to read-only memory (Erasable Programmable Read-Only Memory, EPROM), Electrically Erasable Programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM) and the like. The memory 12 is used for storing a program, and the processor 13 executes the program after receiving the execution instruction.

The processor 13 may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc., and may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC). ), field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. Various methods, steps, and logical block diagrams disclosed in the embodiments of the present invention can be implemented or executed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

It can be understood that the structure shown in FIG. 1 is only for illustration, and the image capturing device 10 may further include more or less components than those shown in FIG. 1 , or have different configurations from those shown in FIG. 1 . Each component shown in FIG. 1 may be implemented in hardware, software, or a combination thereof.

Referring to FIG. 2 , the present invention provides an exposure adjustment method applicable to the above-mentioned image acquisition device 10 . When the exposure adjustment method is applied to the above-mentioned image acquisition device 10 , four steps of steps S110 - S140 are implemented.

Step S110: Detect whether the image transmitted by the camera 11 of the image acquisition device 10 is in an overexposed state, and when the detection result is yes, acquire exposure parameters corresponding to the camera 11, and acquire depth position information corresponding to the image.

Specifically, the method of detecting whether the image transmitted by the camera 11 of the image acquisition device 10 is in an overexposed state is to measure the transmission of each image by the camera 11 during the shooting process or in the focusing process according to the image quality. Exposure detection based on the light intensity value, or exposure detection based on the sharpness and brightness of the image.

Please refer to FIG. 3 , optionally, in this embodiment, the step of detecting whether the image transmitted by the camera 11 of the image capturing device 10 is in an overexposed state includes:

Step S112: Perform light intensity detection on the image transmitted by the camera 11 of the image acquisition device 10 to obtain a light intensity value corresponding to the image.

Step S114: Determine whether the light intensity value is within the preset light intensity range, and when the light intensity value is not within the preset light intensity range, obtain the corresponding light intensity value of the camera 11 under the light intensity value. exposure parameters.

Specifically, the light intensity detection may be performed according to the light intensity sensor provided in the camera 11, or the light intensity detection may be performed according to a deep image learning model capable of light intensity detection, which is not specifically limited here. You can set it according to actual needs.

In order to make the result of the light intensity detection more accurate, and to effectively avoid the problem of increasing the cost of the image acquisition device 10 due to the increase in hardware structure, in this embodiment, the gogleNet deep learning model, the AlexNet deep learning model or the VGG can be used but not limited to. The deep learning model performs exposure degree detection on the image to obtain the light intensity value corresponding to the image.

It can be understood that, in this embodiment, the situation that the light intensity value is not within the preset light intensity range generally includes the situation that the light intensity value is greater than the maximum value of the preset light intensity value range and is in an overexposure state, and all The light intensity value is less than the minimum value of the preset light intensity value range and is in an under-exposure state.

The preset light intensity value range can be selected according to the needs of the user. Specifically, the memory 12 can store a plurality of preset light intensity value ranges, and different preset light intensity value ranges correspond to different For example, the environmental scene may include climatic conditions, such as sunny, cloudy, or rainy days, and the corresponding light intensity value ranges are different under different environmental scenes. The user can select the desired environmental scene according to the actual needs to obtain the corresponding preset range.

It can be understood that, in order to enable the user to select different scenes, in this embodiment, the image capture device 10 includes a display 15 , so that the user can view and select a desired environmental scene according to the display 15 .

The exposure parameters may include, but are not limited to, factors such as exposure time and exposure aperture, which affect the light intensity value of the image obtained after the image is captured. Optionally, in this embodiment, the exposure parameters include exposure time and exposure aperture.

Wherein, the method of acquiring the depth position information corresponding to the target image may be by performing depth detection on the target image by using a depth detection algorithm or model to obtain the depth position information, or by using a depth detector to perform detection to obtain the depth position information. The depth position information of the target image is not specifically limited here.

Please refer to FIG. 3 , optionally, in this embodiment, a depth sensor 14 is provided at the viewport position of the camera 11 , and the step of acquiring the depth position information corresponding to the target image includes: acquiring the depth sensor 14 Depth position information obtained by performing image depth detection on the target image.

Through the above settings, the accuracy of the detected depth position information can be effectively guaranteed.

Step S120: A depth image is obtained after mapping the target image and the depth position information, and a preset depth image learning model is used to detect the depth image to obtain a detection target.

The method of mapping the target image and the depth position information may be to map the target image and the depth position information in a parameterized manner, or may be mapped according to a corresponding relationship, which is not specifically limited here. , set according to actual needs.

In order to make the mapping more efficient, the target image and the depth position information are mapped in a parameterized manner. Specifically, please refer to FIG. 4 , in this embodiment, the depth position information includes the depth position information. The depth position information corresponds to the position coordinates and depth values of each pixel in the image, and step S120 includes:

Step S122: Obtain the position coordinates of each pixel in the image.

Step S124: Map the acquired position coordinates of each pixel with the position coordinates and depth values of each pixel in the depth position information to obtain a depth image.

The preset deep image learning model may be, but is not limited to, Faster R-CNN, R-FCN or SSD deep learning target detection model, as long as the depth image can be detected by using the preset deep image learning model and based on actual conditions. It can be selected according to the requirements, which is not specifically limited here.

The detection target may be, but is not limited to, a person, a scene, a vehicle or a license plate, etc., which is not specifically limited here. The method of inputting the depth image into a preset depth image learning model for detection to obtain the detection target may be: The depth image is input to a preset depth image learning model for detection to obtain multiple detection images, and a detection image selected by the user from the multiple detection images is received as a detection target. Specifically, the depth image is input into a preset depth image learning model for detection to obtain a plurality of detection images, and the display 15 is controlled to display the plurality of detection images, and a detection method selected by the user based on one of the plurality of detection images is received. image as the target image.

Step S130: Perform inverse mapping of the image and the detection target to obtain a corresponding position of the detection target in the image, and use the corresponding position as a target position.

It can be understood that when the target image and the depth position information are mapped using a parameterized mapping method, the inverse mapping of the target image and the detection target is also performed using a parameterized mapping method.

Step S140: Adjust the exposure parameters of the camera 11, and use the adjusted exposure parameters to refocus the target position.

The method of adjusting the exposure parameter of the camera 11 may be to adjust the exposure parameter of the camera 11 according to the light intensity value. Specifically, when the light intensity value is greater than the maximum value of the preset light intensity range When the light intensity value is smaller than the minimum value of the preset light intensity value range, the exposure time is decreased and/or the exposure aperture is decreased, and when the light intensity value is less than the minimum value of the preset light intensity value range, the exposure time is increased and/or the exposure aperture is increased. And after the adjustment of the exposure parameters is completed, the target position is focused to realize shooting, thereby ensuring the acquisition of high-quality images.

Through the above method, the exposure parameters can be automatically adjusted to avoid the overexposure state, and without manual intervention, the camera 11 will keep the exposure parameters corresponding to the light intensity value and continue to shoot, thereby affecting the shooting effect, thereby effectively avoiding the use of The manual adjustment method results in a waste of time and inaccurate adjustment.

It can be understood that the above-mentioned exposure adjustment method can be applied to the image acquisition device 10 with image acquisition function such as personal computer, driving recorder, and drone, while maintaining the integrity of the camera 11 and saving the cost, and can be extended to the general public. Suitable for home use.

Therefore, through the above method, it is also possible to effectively avoid the high cost of materials, easy generation of heat and other situations that can easily affect the judgment, such as judging the position of key points by X-ray infrared sensing, etc. The sensing method is only for the use of dual cameras and cameras with auxiliary functions for collaborative judgment, which leads to the problem of high cost. Therefore, the exposure adjustment method provided by the present invention can not only automatically reprocess focusing and automatically adjust exposure parameters for shooting, but also can overcome the problem of high cost, can process quickly and efficiently, and ensure the acquisition of high-quality images.

Referring to FIG. 5 , on the basis of the above, the present invention further provides an exposure adjustment device 100 , including an exposure state detection module 110 , a depth image acquisition module 120 , a target position acquisition module 130 and an exposure parameter adjustment module 140 .

The exposure state detection module 110 is used to detect whether the image transmitted by the camera 11 of the image acquisition device 10 is in an overexposed state, and when the detection result is yes, obtain the exposure parameters corresponding to the camera 11, and obtain the corresponding exposure parameters of the image. depth position information. In this embodiment, the exposure state detection module 110 may be configured to perform step S110 shown in FIG. 2 , and for the specific description of the exposure state detection module 110 , reference may be made to the foregoing description of step S110 .

Please refer to FIG. 6 , optionally, in this embodiment, the light intensity value acquisition module 110 is further configured to include a detection sub-module 112 and a judgment sub-module 114 .

The detection sub-module 112 performs light intensity detection on the image transmitted by the camera 11 of the image acquisition device 10 to obtain a light intensity value corresponding to the image. In this embodiment, the detection sub-module 112 may be configured to perform step S112 shown in FIG. 3 , and for the specific description of the detection sub-module 112 , reference may be made to the foregoing description of step S112 .

The judging sub-module 114 is used to judge whether the light intensity value is within the preset light intensity range, and when the light intensity value is not within the preset light intensity range, obtain the camera at the light intensity value. 11 corresponds to the exposure parameters. In this embodiment, the judging sub-module 114 may be configured to perform step S114 shown in FIG. 3 , and for the specific description of the judging sub-module 114 , reference may be made to the foregoing description of step S114 .

The depth image obtaining module 120 is configured to obtain a depth image after mapping the image with the depth position information, and input the depth image into a preset depth image learning model for detection to obtain a detection target. In this embodiment, the depth image obtaining module 120 may be configured to perform step S120 shown in FIG. 2 , and for the specific description of the depth image obtaining module 120 , reference may be made to the foregoing description of step S120 .

Optionally, in this embodiment, a depth sensor 14 is provided at the viewport position of the camera 11, and the depth image obtaining module 120 is further configured to obtain the image obtained by performing the image depth detection on the image by the depth sensor 14. Deep location information.

Optionally, in this embodiment, the preset deep image learning model is a Faster R-CNN deep image learning model, an R-FCN deep image learning model, or an SSD deep image learning model.

Please refer to FIG. 7 , optionally, in this embodiment, the depth position information includes the position coordinates and depth values of each pixel in the image corresponding to the depth position information, and the depth image obtaining module 120 includes: obtaining coordinates Submodule 122 and Mapping Submodule 124.

The coordinate obtaining sub-module 122 is used to obtain the position coordinates of each pixel in the image. In this embodiment, the coordinate acquisition sub-module 122 may be configured to execute step S122 shown in FIG. 4 , and for the specific description of the coordinate acquisition sub-module 122 , reference may be made to the foregoing description of step S122 .

The mapping sub-module 124 is configured to map the acquired position coordinates of each pixel with the position coordinates and depth values of each pixel in the depth position information to obtain a depth image. In this embodiment, the mapping sub-module 124 may be configured to execute step S124 shown in FIG. 4 , and for the specific description of the mapping sub-module 124 , reference may be made to the foregoing description of step S124 .

The target position obtaining module 130 is configured to perform inverse mapping between the image and the detection target to obtain the corresponding position of the detection target in the image, and use the corresponding position as the target position. In this embodiment, the target position obtaining module 130 may be configured to execute the step S130 shown in FIG. 2 . For the specific description of the target position obtaining module 130 , reference may be made to the foregoing description of the step S130 .

The exposure parameter adjustment module 140 is configured to adjust the exposure parameter of the camera 11 according to the light intensity value and then focus on the target position. In this embodiment, the exposure parameter adjustment module 140 may be configured to execute step S140 shown in FIG. 2 , and for the specific description of the exposure parameter adjustment module 140 , reference may be made to the foregoing description of step S140 .

To sum up, the present invention provides an exposure adjustment method and device. The method obtains exposure parameters corresponding to the camera 11 when it is detected that the image transmitted by the camera 11 of the image acquisition device 10 is in an overexposed state, and obtains the image. Corresponding depth position information, map the image and depth position information to obtain a depth image, input the depth image into a preset depth image learning model for detection to obtain a detection target, and inversely map the image and the detection target to obtain a detection target At the corresponding position in the image and taking the corresponding position as the target position, the target position is focused after adjusting the exposure parameters of the camera 11 according to the light intensity value. Through the above method, the exposure parameters can be adjusted automatically, and the situation of time waste and inaccurate adjustment caused by manual adjustment can be effectively avoided.

In the several embodiments provided by the embodiments of the present invention, it should be understood that the disclosed apparatus and method may also be implemented in other manners. The apparatus and method embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention, function and operation. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. An exposure adjustment method, applied to an image acquisition device, is characterized in that, comprising: Detecting whether the image transmitted by the camera of the image acquisition device is in an overexposed state, and acquiring exposure parameters corresponding to the camera when the detection result is yes, and acquiring depth position information corresponding to the image; After the image is mapped with the depth position information, a depth image is obtained, and the depth image is input into a preset depth image learning model for detection to obtain a detection target; Perform inverse mapping on the image and the detection target to obtain the corresponding position of the detection target in the image and use the corresponding position as the target position; Adjust the exposure parameters of the camera, and use the adjusted exposure parameters to refocus the target position. 2. The exposure adjustment method according to claim 1, wherein a depth sensor is provided at the viewport position of the camera, and the step of acquiring depth position information corresponding to the image comprises: Acquire depth position information obtained by performing image depth detection on the image by the depth sensor. 3. The exposure adjustment method according to claim 1, wherein the preset deep image learning model is a Faster R-CNN deep image learning model, an R-FCN deep image learning model or an SSD deep image learning model. 4 . The exposure adjustment method according to claim 1 , wherein the depth position information includes the position coordinates and depth values of each pixel in the image corresponding to the depth position information, and the image is compared with the depth position information. 5 . The steps of obtaining a depth image after mapping include: Get the position coordinates of each pixel in the image; A depth image is obtained by mapping the acquired position coordinates of each pixel with the position coordinates and depth values of each pixel in the depth position information. 5. The exposure adjustment method according to claim 1, wherein the step of detecting whether the image transmitted by the camera of the image acquisition device is in an overexposed state comprises: Perform light intensity detection on the image transmitted by the camera of the image acquisition device to obtain a light intensity value corresponding to the image; It is judged whether the light intensity value is within the preset light intensity range, and when the light intensity value is not within the preset light intensity range, the exposure parameter corresponding to the camera under the light intensity value is obtained. 6. An exposure adjustment device, applied to an image acquisition device, characterized in that, comprising: an exposure state detection module, configured to detect whether the image transmitted by the camera of the image acquisition device is in an overexposed state, and when the detection result is yes, obtain the exposure parameter corresponding to the camera, and obtain the depth position information corresponding to the image; a depth image obtaining module, configured to obtain a depth image after mapping the image with the depth position information, and input the depth image into a preset depth image learning model for detection to obtain a detection target; a target position obtaining module, used for inversely mapping the image and the detection target to obtain the corresponding position of the detection target in the image and using the corresponding position as the target position; The exposure parameter adjustment module is used to adjust the exposure parameter of the camera, and use the adjusted exposure parameter to refocus the target position. 7 . The exposure adjustment device according to claim 6 , wherein a depth sensor is provided at the viewport position of the camera, and the depth image obtaining module is further configured to obtain the image depth of the image by the depth sensor. 8 . The detected depth position information. 8 . The exposure adjustment device according to claim 6 , wherein the preset deep image learning model is a Faster R-CNN deep image learning model, an R-FCN deep image learning model or an SSD deep image learning model. 9 . 9. The exposure adjustment device according to claim 6, wherein the depth position information includes position coordinates and depth values of each pixel in the image corresponding to the depth position information, and the depth image obtaining module comprises: The coordinate acquisition sub-module is used to acquire the position coordinates of each pixel in the image; The mapping submodule is used for mapping the acquired position coordinates of each pixel with the position coordinates and depth values of each pixel in the depth position information to obtain a depth image. 10. The exposure adjustment device according to claim 6, wherein the exposure state detection module comprises: a detection sub-module, configured to perform light intensity detection on the image transmitted by the camera of the image acquisition device to obtain a light intensity value corresponding to the image; The judgment sub-module is used for judging whether the light intensity value is within the preset light intensity range, and when the light intensity value is not within the preset light intensity range, obtains the corresponding light intensity value of the camera under the light intensity value. exposure parameters.

Images