WO2021016846A1

WO2021016846A1 - Image processing method and system, movable platform, and storage medium

Info

Publication number: WO2021016846A1
Application number: PCT/CN2019/098329
Authority: WO
Inventors: 岳书威; 杜捷; 张树汉
Original assignee: 深圳市大疆创新科技有限公司
Priority date: 2019-07-30
Filing date: 2019-07-30
Publication date: 2021-02-04
Also published as: CN112166598B; CN112166598A

Abstract

An image processing method and system, a movable platform, and a storage medium. The method comprises: acquiring image data to be processed, wherein the image data is environmental image data acquired by a vision sensor mounted on a movable platform; performing adaptive global brightness adjustment on the image data to acquire first image data; and performing contrast adjustment on the first image data to acquire second image data, wherein the second image data is for online image processing on the movable platform. The acquired image data is sequentially subjected to global brightness adjustment and contrast adjustment, and the processing process is simple and clear. The method quickly compresses image data having a high dynamic range, and has fast computational speeds and high performance in real-time, while allowing details of the image data to be preserved as much as possible, thereby improving the contrast of an image having been subjected to brightness adjustment.

Description

Image processing method, system, movable platform and storage medium

Technical field

The embodiments of the present application relate to the field of automatic driving, and in particular, to an image processing method, system, movable platform, and storage medium.

Background technique

With the research and development of autonomous driving technology, autonomous driving technology and autonomous driving equipment have begun to be applied. Autopilot equipment, such as autonomous vehicles, drones, etc. In the process of driving or flying, the automatic driving equipment needs to collect images of the current environment, and then analyze and process the images to complete automatic driving or complete predetermined tasks. Among them, the captured image is a high-bit image. Due to data transmission limitations and hardware limitations of the display device, it is necessary to compress the high dynamic range image into a low dynamic range image; thereby completing image analysis or predetermined tasks.

In normal image processing, for example, in the post-processing of taking a photo with a camera, the image can be subjected to global mapping processing, that is, a preset function is used to process the pixel value of the image to obtain the processed image. However, when the image is processed by the global mapping processing method, because the pixel values of all pixels are processed uniformly, the local detail information of the image will be lost, and the contrast and brightness of the obtained image are poor, such as the brightness of the image. Too dark or bright; the resulting image is of poor quality. Normal image processing can also perform local mapping processing on the image, that is, using different mapping curves according to changes in the dynamic range of different regions, which can improve the local contrast of the mapping result and show more details, but will lose a certain global imaging effect.

However, in the process of driving or flying of the automatic driving equipment, because the scene is complex and often changes greatly, the collected images are often high dynamic range images; and because the automatic driving equipment is driving or flying, the collected images are It is used for subsequent algorithm processing, so it has high requirements on the processing effect, data volume and real-time processing of the captured image. The aforementioned general global mapping processing is difficult to obtain stable processing effects, and the local mapping processing is computationally complex. It is difficult to meet real-time requirements, and it is difficult to meet the requirements for image processing on automatic driving equipment.

Summary of the invention

The embodiments of the application provide an image processing method, system, removable platform, and storage medium to retain local detailed information of the image, and the contrast and brightness of the obtained image are better, improve the quality of low dynamic range images, and facilitate real-time性算。 Calculations.

In the first aspect, an embodiment of the present application provides an image processing method, including:

Acquiring image data to be processed, where the image data to be processed is environmental image data acquired by a visual sensor mounted on a movable platform;

Performing adaptive global brightness adjustment on the image data to be processed to obtain first image data;

Performing contrast adjustment on the first image data to obtain second image data;

Wherein, the second image data is used for online image processing of the movable platform.

In the second aspect, an embodiment of the present application provides an image processing system, including: a processor, a memory, and a vision sensor;

The memory is used to store program codes;

The vision sensor is used to obtain image data to be processed, wherein the image data to be processed is carried on a movable platform, and the image data to be processed is environmental image data;

The processor calls the program code, and when the program code is executed, is used to perform the following operations:

In the third aspect, an embodiment of the present application provides a movable platform, including a processor, a memory, and a vision sensor;

The memory is used to store program codes;

The visual sensor is used to obtain image data to be processed, and the image data to be processed is environmental image data;

Perform online image processing on the second image data.

In a fourth aspect, an embodiment of the present application provides a readable storage medium with a computer program stored on the readable storage medium; when the computer program is executed, the image described in the embodiment of the present application in the first aspect is realized. Approach.

In a fifth aspect, an embodiment of the present application provides a program product, the program product includes a computer program, the computer program is stored in a readable storage medium, and at least one processor of an image processing system or a movable platform can download from the The readable storage medium reads the computer program, and the at least one processor executes the computer program to enable the image processing system or the mobile platform to implement the image processing method described in the embodiment of the present application in the first aspect.

The image processing method, system, movable platform, and storage medium provided by the embodiments of the application obtain the image data to be processed by acquiring the environment image data of the environment in which the movable platform is in the process of moving; then, the environment image data is sequentially processed After global brightness adjustment and contrast adjustment, low dynamic range images are obtained; since the acquired image data to be processed is the environmental image data of the environment in which the movable platform is moving, the second image data generated can be used Online image processing on a mobile platform. Since the acquired image data to be processed can be sequentially adjusted for global brightness and contrast, the processing process is simple and clear, and the image data to be processed with high dynamic range can be compressed quickly, with fast calculation speed and high real-time performance; and , Adaptive global brightness adjustment, can make the details of the image data to be processed be preserved as much as possible; Contrast adjustment method can improve the contrast of the image after brightness adjustment; Adaptive global brightness adjustment and contrast adjustment adjustment process It is stable, and the image data to be processed can be processed stably without noise, halo, etc.

Description of the drawings

In order to more clearly describe the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

Figure 1 is a schematic diagram 1 of the application scenario provided by this application;

Figure 2 is a second schematic diagram of the application scenario provided by this application;

Figure 3 is the third schematic diagram of the application scenario provided by this application;

Figure 4 is the fourth schematic diagram of the application scenario provided by this application;

FIG. 5 is a flowchart of an image processing method provided by an embodiment of the application;

FIG. 6 is a flowchart of an image processing method provided by another embodiment of this application;

FIG. 7 is a schematic diagram 1 of the prior art image provided by this application;

FIG. 8 is the first image diagram of the second image data provided by this application;

FIG. 9 is a second schematic diagram of an image of the prior art provided by this application;

FIG. 10 is a second image diagram of the second image data provided by this application;

FIG. 11 is a third image diagram of the prior art provided by this application;

FIG. 12 is a third image diagram of the second image data provided by this application;

FIG. 13 is a schematic structural diagram of an image processing system provided by an embodiment of this application;

FIG. 14 is a schematic structural diagram of a movable platform provided by an embodiment of this application;

15 is a schematic structural diagram of an image processing system provided by another embodiment of this application;

FIG. 16 is a schematic structural diagram of a movable platform provided by another embodiment of this application.

Detailed ways

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments It is a part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of this application.

It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or a central component may also exist. When a component is considered to be "connected" to another component, it can be directly connected to another component or there may be a centered component at the same time.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of this application. The terms used in the description of the application herein are only for the purpose of describing specific embodiments, and are not intended to limit the application. The term "and/or" as used herein includes any and all combinations of one or more related listed items.

Hereinafter, some embodiments of the present application will be described in detail with reference to the accompanying drawings. In the case of no conflict, the following embodiments and features in the embodiments can be combined with each other.

The embodiments of the present application provide an image processing method, system, removable platform, and storage medium. Figure 1 is a schematic diagram of the first application scenario provided by this application, Figure 2 is a schematic diagram of the second application scenario provided by this application, and Figure 3 is a schematic diagram three of the application scenario provided by this application, as shown in Figures 1 to 3, the image processing method can be applied As for the image processing system, the image processing system includes but is not limited to any one of the following devices: network device 1, terminal device 2, vehicle 3.

Among them, the network device 1 includes but is not limited to: Transmission Reception Point (TRP), base station (eg, gNB), Radio Network Controller (RNC), Node B (Node B, NB) , Base Station Controller (Base Station Controller, referred to as BSC), BTS (Base Transceiver Station), HeNB (Home Evolved NodeB), or HNB (Home Node B), Baseband Unit (Baseband Uit, referred to as BBU), etc.

Terminal equipment 2 includes but is not limited to vehicle terminals, vehicle terminals, vehicle equipment, mobile terminals, public terminals, etc., where vehicle terminals include, but are not limited to, vehicle navigators, etc., and mobile terminals include, but are not limited to, mobile phones, wearable devices, and tablets Wait.

The vehicle 3 includes but is not limited to ordinary vehicles, autonomous vehicles, unmanned vehicles, and so on.

Figure 4 is the fourth schematic diagram of the application scenario provided by this application. As shown in Figure 4, the image processing method can be applied to a movable platform, which includes but is not limited to UAV 4 and so on.

The image processing method can also be applied to any device or system to complete the image processing process provided in this application.

It should be understood that the aforementioned naming of the components of the device is only for identification purposes, and should not be understood as a limitation to the embodiments of the present application.

On automatic driving equipment, during driving or flying, the automatic driving equipment needs to collect images of the current environment, and then analyze and process the images to complete automatic driving or complete predetermined tasks.

Since the High Dynamic Range image records the rich details of the image, the High Dynamic Range image can be applied to security monitoring, equipment imaging, medical imaging, automatic driving, automatic flight and other technical fields; among them, high Dynamic range images can also be called high-bit images. In the technical field involved in this application, after acquiring the high dynamic range image, due to the large high dynamic range image, the data transmission is slower, the image display is slower, and the storage space is occupied more. The high dynamic range image is compressed into a low dynamic range image, and then the image analysis or predetermined task is completed.

In the process of compressing a high dynamic range image into a low dynamic range image, a global mapping processing method or a local mapping processing method can usually be used.

When the image is processed by the global mapping processing method, the overall effect of the image can be better presented, and the calculation efficiency of the global mapping processing method is higher; however, when the image is processed by the global mapping processing method, because it is for all pixels The unified processing of the pixel value of the image will lose the local detail information of the image, and the contrast and brightness of the image will be poor, such as the brightness of the image is dark or bright; the quality of the resulting image is poor, and the image processing The effect is poor.

When the image is processed by the local mapping processing method, because the local mapping processing method can adopt different mapping curves according to the dynamic range of different regions, it can improve the local contrast of the image and show more details of the image; but the local mapping processing is adopted When processing the image in this way, a certain global imaging effect is lost, and it is easy to produce halo, noise, etc. in the image, and the calculation complexity of the local mapping processing method is relatively high.

However, in the process of driving or flying, the automatic driving equipment has high requirements for the algorithm response speed and image processing effects of the collected high dynamic range images; the global mapping processing method is difficult to obtain stable processing effects Moreover, it is impossible to perform good compression for high dynamic range images; the high computational complexity of the local mapping processing method is difficult to meet the real-time requirements, and it is difficult to meet the requirements for image processing on automatic driving equipment.

The image processing method, system, removable platform, and storage medium provided in this embodiment can solve the foregoing problems.

FIG. 5 is a flowchart of an image processing method provided by an embodiment of this application. As shown in FIG. 5, the method of this embodiment may include:

S101. Acquire image data to be processed, where the image data to be processed is environmental image data acquired by a vision sensor mounted on a movable platform.

In this embodiment, the execution subject of this embodiment may be an image processing system, or an image processing device, or a movable platform. This embodiment is described with the execution subject as the image processing system.

A visual sensor is provided on the movable platform, where the movable platform may be an automatic driving vehicle, an automatic flying device, and so on. Vision sensors are used to obtain environmental image data.

Therefore, when the visual sensor on the movable platform obtains the environmental image data, the image processing system can obtain the environmental image data obtained by the visual sensor, and further, the image processing system can obtain the image data to be processed. The image data to be processed is a high dynamic range image, that is, the image data to be processed is a high-bit image.

For example, the image processing system and the movable platform are two different devices. The movable platform is equipped with a vision sensor, and the image processing system is connected to the vision sensor; as the movable platform moves, the vision sensor can be acquired in real time Environmental image data, and then obtain high dynamic range images; then, the image processing system can obtain real-time environmental image data collected by the vision sensor.

For another example, the image processing system and the movable platform are the same equipment, that is, the image processing system is a movable platform; the movable platform is equipped with a vision sensor, and the movable platform is connected to the vision sensor; With the movement of the platform, the visual sensor can obtain real-time environmental image data, and then obtain high dynamic range images, so that the movable platform can obtain real-time environmental image data collected by the visual sensor.

For example, the image processing system is an autonomous driving vehicle. During the driving of the autonomous driving vehicle, the autonomous driving vehicle can obtain environmental image data in the driving environment of the autonomous driving vehicle through the visual sensor.

For another example, the image processing system is an automatic flight device. During the flight of the automatic flight device, the automatic flight device can obtain the environmental image data of the flight environment of the automatic flight device through the visual sensor.

S102: Perform adaptive global brightness adjustment on the image data to be processed to obtain first image data.

In this embodiment, after obtaining the image data to be processed, the image processing system adopts an adaptive processing method to perform global brightness adjustment on the image data to be processed, and then generates the first image data. Optionally, the adaptive processing method is an adaptive function, for example, the adaptive function is a gamma correction function, or the adaptive function is another correction function in the prior art.

S103. Perform contrast adjustment on the first image data to obtain second image data, where the second image data is used for online image processing of the movable platform.

In this embodiment, after the image processing system performs global brightness adjustment on the image data to be processed, the contrast adjustment is performed on the obtained first image data to generate the second image data. Optionally, the contrast adjustment method may be the use of histogram equalization, or an adaptive histogram equalization algorithm, an interpolation acceleration algorithm, etc.; the above algorithm is an image contrast adjustment algorithm provided in the prior art.

In this application, the acquired image data to be processed is the environmental image data of the environment in which the mobile platform is moving during the movement process, and the second image data generated is to sequentially adjust the global brightness of the environmental image data, The image obtained after the contrast adjustment; the second image data can be used for online image processing of the mobile platform, that is, the mobile platform can perform online image processing on the second image data. For example, the movable platform may directly display the second image data, or the movable platform may recognize objects in the second image data.

And, the above-mentioned second image data is a low dynamic range image.

For example, the image processing system and the movable platform are two different devices. According to the example in step S101, the image processing system can obtain the environmental image data collected by the visual sensor in real time; After the global brightness adjustment and contrast adjustment are performed, the second image data is obtained; the image processing system can send the second image data to the movable platform for image processing.

For another example, the image processing system and the movable platform are the same equipment. According to the example in step S101, the movable platform can obtain the environmental image data collected by the visual sensor in real time; the movable platform performs sequential processing on the environmental image data After adjusting the global brightness and contrast, the second image data is obtained; then, the movable platform directly performs image processing on the second image data.

For example, the image processing system is a self-driving vehicle. During the driving of the self-driving vehicle, the self-driving vehicle can obtain the environmental image data in the driving environment of the self-driving vehicle through the visual sensor; because the environmental image data obtained by the self-driving vehicle is High dynamic range images. The image size of high dynamic range images is relatively large. Autonomous vehicles need to compress the high dynamic range images into low dynamic range images in order to process or transmit the images quickly; then the autonomous vehicles will respond to the environment After the image data is adjusted for global brightness and contrast in sequence, the second image data is obtained, and then the low dynamic range image is obtained; then, the autonomous vehicle performs subsequent image analysis, image display, etc. processes on the second image data.

For another example, the image processing system is an automatic flight device. During the flight of the automatic flight device, the automatic flight device can obtain the environmental image data of the flight environment of the automatic flight device through the vision sensor; due to the environmental image obtained by the automatic flight device The data is a high dynamic range image, and the image size of the high dynamic range image is relatively large. The automatic flight equipment needs to compress the high dynamic range image into a low dynamic range image in order to quickly process or transmit the image; then the automatic flight equipment After global brightness adjustment and contrast adjustment are sequentially performed on the environmental image data, the second image data is obtained, and then the low dynamic range image is obtained; then, the autopilot device performs subsequent image analysis and image display processes on the second image data.

In this embodiment, by acquiring image data to be processed, the image data to be processed is environmental image data acquired by a visual sensor mounted on a movable platform; adaptive global brightness adjustment is performed on the image data to be processed to obtain the first image data; The contrast of the first image data is adjusted to obtain the second image data; the second image data is used for online image processing of the movable platform. Obtain the environmental image data of the environment in which the mobile platform is in the process of moving, and then obtain the image data to be processed; then perform global brightness adjustment and contrast adjustment on the environmental image data in turn to obtain a low dynamic range image; due to the acquired waiting The processed image data is environmental image data of the environment in which the movable platform is in the process of moving, so that the generated second image data can be used for online image processing by the movable platform. Since the acquired image data to be processed can be sequentially adjusted for global brightness and contrast, the processing process is simple and clear, and the image data to be processed with high dynamic range can be compressed quickly, with fast calculation speed and high real-time performance; and , Adaptive global brightness adjustment, can make the details of the image data to be processed be preserved as much as possible; Contrast adjustment method can improve the contrast of the image after brightness adjustment; Adaptive global brightness adjustment and contrast adjustment adjustment process It is stable, and the image data to be processed can be processed stably without noise, halo, etc.

FIG. 6 is a flowchart of an image processing method provided by another embodiment of this application. As shown in FIG. 6, the method in this embodiment may include:

S201. Acquire a photographed image, where the photographed image is environment image data with a high dynamic range acquired by a vision sensor mounted on a movable platform.

With the movement of the movable platform, the visual sensor on the movable platform can obtain real-time environmental image data of the surrounding environment, where the environmental image data is a high dynamic range image; then, the image processing system can obtain the data collected by the visual sensor Environment image data, that is, the image processing system acquires the captured image.

Wherein, the above-mentioned image processing system and the above-mentioned movable platform may be the same device or different devices.

For example, the image processing system is an autonomous driving vehicle, and the vision sensor is set on the autonomous driving vehicle; during the driving process of the autonomous driving vehicle, the vision sensor can collect environmental image data in real time, that is, the captured image; The self-driving vehicle acquires the captured image.

For another example, the image processing system is an automatic flight device, and a vision sensor is provided on the automatic flight device; during the flight of the automatic flight device, the vision sensor can collect environmental image data in real time, that is, collect captured images; , The automatic flight equipment acquires the captured image.

S202: Perform normalization processing on the captured image, and perform compression processing on the normalized captured image to obtain image data to be processed.

In this embodiment, in order to speed up the image processing process of the captured image, the image processing system needs to compress the captured image.

Before performing compression processing, the image processing system first needs to normalize the captured image to obtain the normalized captured image. Specifically, if the captured image is a grayscale image, the image processing system needs to normalize the pixel value of each pixel in the captured image to a preset range, for example, the preset range is the pixel value [0, 1 ]. If the captured image is a color image, and the captured image is an RGB (Red Green Blue) image, the image processing system can convert the RGB image into a YUV (Luminance Chrominance Chroma) image; then, the image processing system converts the value of the image data in the Y dimension , Normalize to a preset range, and normalize the value of the image data in the U dimension to another preset range, and normalize the value of the image data in the V dimension to Within a preset range; or, the image processing system can only normalize the value of the image data in the Y dimension, and the image processing system can normalize the value of the image data in the Y dimension to a preset range. Set within the range, and then in the subsequent image processing process, the image processing system only analyzes the image data in the Y dimension.

Then, after the image processing system obtains the normalized captured image, it can compress the normalized captured image, and then obtain the image data to be processed, which is a low dynamic range image.

Optionally, an existing compression algorithm can be used to compress the high dynamic range captured image into a low dynamic range image, that is, to obtain image data to be processed.

Optionally, the formula L _out =(A*log(B+L _in ))/(log(C+D*L _in )) can be used to obtain the compressed image data to be processed, where _Lin is the return In the photographed image after unified processing, L _out is the image data to be processed, and A, B, C and D are all preset compression parameters.

In this application, there is no limitation on the above-mentioned compression processing method. After the above-mentioned compression processing, the data volume of the captured image can be reduced, and the processing speed of the subsequent image processing process can be improved.

For example, the image processing system is a self-driving vehicle. After the self-driving vehicle acquires the captured image, since the self-driving vehicle is in the process of driving, the control device in the self-driving vehicle also needs to control the entire driving process of the self-driving vehicle, so the need to reduce The complexity of image processing is to prevent image processing from affecting the control process and response time of the control equipment in the autonomous vehicle; therefore, the autonomous vehicle needs to compress the captured image, and then the autonomous vehicle can perform the above compression process .

For another example, the image processing system is an automatic flight device. After the automatic flight device acquires the captured image, since the automatic flight device is in flight, the control device in the automatic flight device also needs to control the entire flight process of the automatic flight device. Reduce the complexity of image processing to prevent image processing from affecting the control process and response time of the control device in the automatic flight equipment; thus, the automatic flight equipment needs to compress the captured image, and then the automatic flight equipment can perform the above compression processing process.

S203. Determine cumulative histogram information of the image data to be processed according to the pixel values of the image data to be processed, where the cumulative histogram information includes cumulative probability distribution values of the pixel values of the image data to be processed.

In this embodiment, the image processing system needs to perform adaptive global brightness adjustment and contrast adjustment on the compressed image data to be processed in sequence; before performing adaptive global brightness adjustment on the image data to be processed, image processing The system needs to determine the coefficients required for adaptive global brightness adjustment and the coefficients required for contrast adjustment.

First, the image processing system needs to count the accumulated histogram information of the image data to be processed. Specifically, each pixel in the image data to be processed has a pixel value, so the image data to be processed has a different pixel value; for each pixel value, the image processing system calculates the number of pixels on each pixel value. Then, the image processing system divides the number of pixels on each pixel value by the total number of pixels in the image data to be processed to obtain the pixel probability of each pixel value; then, the image processing system depends on the pixel The value of each pixel value is accumulated in turn to obtain the cumulative probability distribution value of each pixel value; the cumulative probability distribution value of each pixel value constitutes the cumulative histogram information of the image data to be processed.

For example, there are P pixels in the image data to be processed, and the pixel value of each pixel is k, which belongs to a preset range; for example, the image data to be processed is a grayscale image, then k∈[ 0,L], k and L are integers. If the number of pixels with pixel value k is n _k , then the probability of pixel points with pixel value k is n _k /P; the cumulative probability distribution value of pixel value k is

Among them, j∈[0,k], j is an integer.

S204: Determine the first coefficient and the second coefficient according to the accumulated histogram information.

Optionally, the cumulative probability distribution value of the pixel values having the first coefficient and the second coefficient is greater than a preset threshold.

Optionally, step S204 specifically includes the following process:

Set the initial value of i to 1, and repeat the following steps until the first coefficient and the second coefficient are determined.

Determine whether the cumulative probability distribution value of the i-th selected value in the selected value set is greater than the preset threshold, where the selected value set includes N selected values, and each selected value is a pixel of the image data to be processed Value, the i-th selected value is less than the i+1-th selected value, N is a positive integer greater than or equal to 1, i∈[1, N], i is a positive integer.

If it is determined to be greater than, the i-th first preselection coefficient in the preset first preselection set will be determined as the first coefficient, and the i-th second preselection coefficient in the preset second preselection set will be determined as the second Coefficients, where the first preselection set includes N+1 first preselection coefficients, the i-th first preselection coefficient is smaller than the i+1th first preselection coefficient, and the second preselection set includes N+1 second preselection coefficients Coefficient, the i-th second preselection coefficient is greater than the i+1th second preselection coefficient.

If it is determined that it is less than or equal to, it is determined that i is accumulated by 1.

Optionally, step S204 further includes the following process: when the cumulative probability distribution value of the N-1th selected value in the selected value set is less than or equal to the preset threshold, if it is determined that the Nth selected value set is If the cumulative probability distribution value of the selected value is less than or equal to the preset threshold, the N+1 first preselection coefficient in the first preselection set is determined as the first coefficient, and the Nth preselection coefficient in the preset second preselection set is determined +1 second preselection coefficient is the second coefficient.

In this embodiment, the image processing system can directly divide the first coefficient for global brightness adjustment and the second coefficient for contrast adjustment according to the cumulative probability distribution value of the pixel values in the cumulative histogram information.

Specifically, the image processing system selects N pixel values from the pixel values of the image data to be processed, and uses these N pixel values as N selection values, and the N selection values form a selection value set; It is convenient to determine the appropriate first coefficient and second coefficient according to the value of the pixel value of the image data to be processed, so as to adjust the brightness and contrast of the image data to be processed. In the selected value set, you can The N selected values are placed in the selected value set according to the order of the selected values from small to large; thus, in the selected value set, the i-th selected value is less than the i+th 1 selected value. Moreover, since each of the N pixel values has a cumulative probability distribution value, each of the N selected values also has a corresponding cumulative probability distribution value; that is, the value of the i-th pixel value The cumulative probability distribution value and the cumulative probability distribution value of the i-th selected value are the same between the two.

In addition, the image processing system is configured with different N+1 first preselection coefficients and different N+1 second preselection coefficients. The N+1 first preselection coefficients are used to form a first preselection set, and each first preselection coefficient is used as a candidate for the first coefficient; and, since the first coefficient is used for global brightness adjustment of the image, it is convenient to To select a suitable first preselection coefficient as the first coefficient, it is necessary to multiply the N+1 first preselection coefficients into the first preselection set according to the descending order of the N+1 first preselection coefficients, namely , The i-th first pre-selection coefficient is smaller than the i+1-th first pre-selection coefficient. N+1 second preselection coefficients are used to form a second preselection set, and each second preselection coefficient is used as a candidate for the second coefficient; and, since the second coefficient is used to adjust the contrast of the image, it can be selected for convenience To obtain a suitable second preselection coefficient as the second coefficient, it is necessary to multiply the N+1 second preselection coefficients into the second preselection set according to the descending order of the N+1 second preselection coefficients, that is, The i-th first preselection coefficient is greater than the (i+1)th second preselection coefficient.

Then, the image processing system analyzes the selected values in turn. First, the image processing system determines whether the cumulative probability distribution value of the first selected value is greater than a preset threshold; if the image processing system determines the value of the first selected value If the cumulative probability distribution value is greater than a preset threshold, the image processing system can use the first first preselected coefficient as the first coefficient for global brightness adjustment, and use the first second preselected coefficient as the The second coefficient for contrast adjustment; if the image processing system determines that the cumulative probability distribution value of the first selected value is less than or equal to the aforementioned preset threshold, the image processing system needs to analyze the second selected value. Then, the image processing system determines whether the cumulative probability distribution value of the second selected value is greater than the above preset threshold; if the image processing system determines that the cumulative probability distribution value of the second selected value is greater than the above preset threshold, the image processing The system can use the second first preselected coefficient as the first coefficient for global brightness adjustment, and the second second preselected coefficient as the second coefficient for contrast adjustment; if the image processing system determines If the cumulative probability distribution value of the second selected value is less than or equal to the above preset threshold, the image processing system needs to analyze the third selected value. By analogy, the image processing system determines whether the cumulative probability distribution value of the i-th selected value is greater than the aforementioned preset threshold; if the image processing system determines that the cumulative probability distribution value of the i-th selected value is greater than the aforementioned preset threshold, then The image processing system may use the i-th first preselected coefficient as the first coefficient for global brightness adjustment, and use the i-th second preselected coefficient as the second coefficient for contrast adjustment; if image processing The system determines that the cumulative probability distribution value of the i-th selected value is less than or equal to the aforementioned preset threshold, and the image processing system needs to analyze the i-th selected value. And so on, until the first coefficient and the second coefficient can be determined. Optionally, when the image processing system analyzes the Nth selected value according to the above process, and determines that the cumulative probability distribution value of the Nth selected value is less than or equal to the above preset threshold, the image processing system can directly The N+1 first preselected coefficients are used as the first coefficient, and the N+1 second preselected coefficient is used as the second coefficient.

According to the foregoing process, it can be known that the cumulative probability distribution value of the pixel values having the first coefficient and the second coefficient is greater than the foregoing preset threshold.

For example, the image processing system is configured with two selected values, each of which is a different pixel value of the image data to be processed, and the two selected values are the selected value thr1 and the selected value thr2, and , The selected value thr1 is less than the selected value thr2; if the image processing system determines that the selected value thr1 is greater than the preset threshold xp_value, the image processing system can use a first preselected coefficient γ1 as the first coefficient γ, and a The second preselection coefficient stret1 is used as the second coefficient stret; if the image processing system determines that the selected value thr1 is less than or equal to the preset threshold xp_value, the image processing system determines whether the selected value thr2 is greater than the preset threshold xp_value; if the image processing system If the selected value thr2 is determined to be greater than the preset threshold xp_value, the image processing system can use a first preselected coefficient γ2 as the first coefficient γ, and a second preselected coefficient stret2 as the second coefficient stret; image processing system If it is determined that the selected value thr2 is less than or equal to the preset threshold xp_value, the image processing system may use a first preselected coefficient γ3 as the first coefficient γ, and a second preselected coefficient stret3 as the second coefficient stret. In addition, the first preselection coefficient γ1 is smaller than the first preselection coefficient γ2, the first preselection coefficient γ2 is smaller than the first preselection coefficient γ3; the second preselection coefficient stret3 is smaller than the second preselection coefficient stret2, and the second preselection coefficient stret2 is smaller than the second preselection coefficient stret1.

S205. The adaptive function is used to perform global brightness adjustment on the image data to be processed to obtain first image data; wherein the adaptive function is correlated with the brightness of the environmental image data.

Optionally, the first coefficient in the adaptive function has a positive correlation with the brightness of the environmental image data, and the first coefficient is used to adjust the brightness of the environmental image data.

Optionally, the adaptive function is a gamma correction function.

In this embodiment, the image processing system has been pre-configured with an adaptive function, which is used to perform adaptive global brightness adjustment of the image; preferably, the adaptive function is a gamma correction function.

Then, the image processing system can directly perform adaptive global brightness adjustment on the image data to be processed according to the adaptive function to obtain first image data; the first image data is the image data to be processed that has undergone adaptive global brightness adjustment.

Moreover, in order to improve the global brightness of the image data to be processed, the coefficients and parameters involved in the adaptive function are determined according to the brightness of the image data to be processed; because of the environmental image data collected by the visual sensor, The above-mentioned image data to be processed is formed, so it can be seen that the coefficients and parameters involved in the adaptive function are related to the brightness of the environmental image data.

Preferably, according to the first coefficient determined in step S205, adaptive global brightness adjustment is performed on the image data to be processed to obtain the first image data. In addition, the first coefficient is positively correlated with the brightness of the environmental image data, that is, the higher the brightness of the environmental image data, the larger the first coefficient; in turn, the first coefficient may be positively correlated with the brightness of the environmental image data, To adjust the global brightness to be processed.

For example, when the adaptive function is a gamma correction function, the following formula can be used to determine that the first image data is

among them,

Is the image data to be processed, and γ is the first coefficient.

S206. Perform contrast adjustment on the first image data to obtain second image data, where the second image data is used for online image processing of the movable platform.

Optionally, the second coefficient used in the contrast adjustment is negatively correlated with the brightness of the environmental image data.

Optionally, step S206 specifically includes the following process:

According to the second coefficient, map the first value range of the first image data to the second value range, where the first value range is the value range of the pixel value of the first image data, and the second value The range is the value range between the second coefficient and the preset value.

The second image data is determined according to the pixel value, the first value range and the second value range of each pixel in the first image data.

In this embodiment, the image processing system adjusts the image contrast of the first image data according to the above-mentioned second coefficient, so that the difference of the pixel values of the pixels in the first image data is more obvious, and then the second image data is obtained .

Specifically, the pixel value range of the first image data constitutes a first value range; in order to adjust the contrast, when the image processing system performs the contrast stretching operation on the first image data, the image processing The system needs to first map the first value range of the first image data to the second value range. The second value range is formed by the value between the second coefficient and the preset value; The value range of the pixel value of an image data is reduced to a smaller value range.

Then, the image processing system generates a pixel value corresponding to each pixel in the first image data according to the pixel value, the first value range, and the second value range of each pixel in the first image data; Furthermore, the pixel value corresponding to each pixel in the first image data constitutes the second image data.

Optionally, the pixel value of each pixel in the second image data is y=((xa)*(dc)/(ba))+c; wherein, the first value range is [a,b], The second value range is [c, d], a is the minimum pixel value of the first image data, b is the maximum pixel value of the first image data, c is the second coefficient, and d is the preset value.

Moreover, in the above process, in order to make the difference of the pixel values of the pixels in the generated second image data more obvious, when the contrast is adjusted, the second coefficient used is the same as the environment collected by the vision sensor. The brightness of the image data is negatively correlated, that is, the higher the brightness of the environmental image data, the smaller the value of the second coefficient.

S207: Transmit the second image data to the processing device for processing.

In this embodiment, the image processing system transmits the generated second image data to the processing device for processing. For example, the processing device can directly display the second image data, or the processing device can identify objects in the second image data.

The processing device may be another controller in the image processing system, or the processing device may be a movable platform.

For example, the image processing system is a self-driving vehicle. During the driving of the self-driving vehicle, the self-driving vehicle can obtain the environmental image data in the driving environment of the self-driving vehicle through the visual sensor; then, in order to reduce the amount of calculation, the self-driving vehicle adopts The process of step S202 compresses the environmental image data to obtain the image data to be processed; then, the autonomous vehicle uses the determined first coefficient and uses the adaptive function to perform global brightness adjustment on the image data to be processed; then, the autonomous vehicle Using the determined second coefficient, perform contrast adjustment on the image that has undergone global brightness adjustment to obtain second image data; furthermore, the autonomous vehicle can perform processing processes such as display and recognition of the second image data. When the image processing system is an automatic flight device, you can also refer to the above process.

For example, FIG. 7 is the first image diagram of the prior art provided by this application, and FIG. 8 is the first image diagram of the second image data provided by this application. The image processing system is an autonomous vehicle, and the autonomous vehicle is running on the road. At the time, the self-driving vehicle uses the above process to obtain environmental image data, but the brightness and contrast of the image represented by the environmental image data are very poor, and the self-driving vehicle cannot perform the automatic driving process based on the acquired environmental image data; therefore, The automatic driving vehicle adopts the solution provided in this embodiment, and after sequentially performing global brightness adjustment and contrast adjustment on the environmental image data, the second image data shown in FIG. 8 is obtained. Figure 7 is an image obtained after adjusting the environmental image data using the Reinhard algorithm in the prior art. The Reinhard algorithm is used to adjust an image with a single global color tone; comparing Figures 7 and 8, it can be seen that this The proposed solution can significantly improve the global brightness and contrast of environmental image data in a scene where an autonomous vehicle is driving on the road.

For another example, FIG. 9 is a second image diagram of the prior art provided by this application, and FIG. 10 is a second image diagram of the second image data provided by this application. The image processing system is an autonomous vehicle, and the autonomous vehicle is in a tunnel. When driving, the autonomous vehicle uses the above process to obtain environmental image data, but the brightness and contrast of the image represented by the environmental image data are very poor. The self-driving vehicle cannot perform automatic operation in the tunnel based on the acquired environmental image data. Driving process; thus, the automatic driving vehicle adopts the solution provided in this embodiment, and sequentially performs global brightness adjustment and contrast adjustment on the environmental image data to obtain the second image data shown in FIG. 10. Fig. 9 is an image obtained after adjusting the environmental image data by using the Reinhard algorithm in the prior art; comparing Fig. 9 with Fig. 10, it can be seen that the scheme of this application is adopted in the scene of an autonomous vehicle driving in a tunnel , Can significantly improve the global brightness and contrast of environmental image data.

For another example, FIG. 11 is a third image diagram of the prior art provided by this application, and FIG. 12 is a third image diagram of the second image data provided by this application. The image processing system is an autonomous vehicle, and the autonomous vehicle runs at night When the self-driving vehicle uses the above process to obtain environmental image data, because the pipeline at night is dark, the brightness and contrast of the image represented by the obtained environmental image data are very poor, and the self-driving vehicle cannot obtain it according to According to the environmental image data, the automatic driving process is carried out at night; thus, the automatic driving vehicle adopts the solution provided in this embodiment, and after sequentially performing global brightness adjustment and contrast adjustment on the environmental image data, the second Image data. Fig. 11 is an image obtained after adjusting the environmental image data by using the Reinhard algorithm in the prior art; comparing Fig. 11 and Fig. 12, it can be seen that the solution of the present application is used to drive the autonomous vehicle in a night environment At this time, the global brightness and contrast of the environmental image data can be significantly improved.

In this embodiment, the image data to be processed is obtained by compressing the captured images acquired by the vision sensor mounted on the movable platform, which can reduce the amount of image processing data and accelerate the image processing speed; then, according to the first coefficient , The adaptive function is used to adjust the global brightness of the image data to be processed to obtain the first image data; then according to the second coefficient, the contrast adjustment of the first image data is performed to obtain the second image data; thus, the image data to be processed can be improved Global brightness and contrast can be used to obtain a clearer environment image; then, the second image data can be transmitted to processing equipment such as a mobile platform for online image processing. Therefore, because the acquired image data to be processed can be sequentially adjusted for global brightness and contrast, the processing process is simple and clear, and the image data to be processed with a high dynamic range can be compressed quickly, with faster calculation speed and high real-time performance. ; And, the adaptive global brightness adjustment can make the details of the image data to be processed be preserved as much as possible; the contrast adjustment method can improve the contrast of the image after the brightness adjustment; the adaptive global brightness adjustment and contrast adjustment The adjustment process is stable, and the image data to be processed can be processed stably without noise, halo, etc.

FIG. 13 is a schematic structural diagram of an image processing system provided by an embodiment of the application. As shown in FIG. 13, the image processing system 600 provided in this embodiment may include a processor 601, a memory 602, and a vision sensor 603.

Among them, the memory 602 is used to store program codes.

The visual sensor 603 is used to obtain image data to be processed, where the image data to be processed is carried on a movable platform, and the image data to be processed is environmental image data.

The processor 601 calls the program code. When the program code is executed, it is used to perform the following operations: perform adaptive global brightness adjustment on the image data to be processed to obtain the first image data; perform contrast adjustment on the first image data to obtain the first image data 2. Image data; where the second image data is used for online image processing of the mobile platform.

In some embodiments, when the processor 601 performs adaptive global brightness adjustment on the image data to be processed to obtain the first image data, it is configured to: use an adaptive function to perform global brightness adjustment on the image data to be processed to obtain the first image data ; Among them, the adaptive function is related to the brightness of the environmental image data.

In some embodiments, the first coefficient in the adaptive function is related to the brightness of the environmental image data, and the first coefficient is used to adjust the brightness of the environmental image data.

In some embodiments, the second coefficient used for contrast adjustment is correlated with the brightness of the environmental image data.

In some embodiments, before the processor 601 performs adaptive global brightness adjustment on the image data to be processed to obtain the first image data, it is further configured to: determine the cumulative histogram of the image data to be processed according to the pixel values of the image data to be processed Information, wherein the cumulative histogram information includes the cumulative probability distribution value of each pixel value of the image data to be processed; the first coefficient and the second coefficient are determined according to the cumulative histogram information.

In some embodiments, the cumulative probability distribution value of the pixel values having the first coefficient and the second coefficient is greater than a preset threshold.

In some embodiments, when the processor 601 determines the first coefficient and the second coefficient according to the accumulated histogram information, it is used to: set the initial value of i to 1, and repeat the following steps until the first coefficient is determined And the second coefficient: determine whether the cumulative probability distribution value of the i-th selected value in the selected value set is greater than the preset threshold, where the selected value set includes N selected values, and each selected value is pending Processing the pixel value of image data, the i-th selected value is less than the i+1-th selected value, N is a positive integer greater than or equal to 1, i∈[1, N], i is a positive integer; if it is determined to be greater than, then The i-th first preselection coefficient in the preset first preselection set will be determined as the first coefficient, and the i-th second preselection coefficient in the preset second preselection set will be determined as the second coefficient. A preselection set includes N+1 first preselection coefficients, the i-th first preselection coefficient is smaller than the i+1th first preselection coefficient, the second preselection set includes N+1 second preselection coefficients, and the i-th The second preselection coefficient is greater than the i+1th second preselection coefficient; if it is determined that it is less than or equal to, it is determined that i is accumulated by 1.

In some embodiments, the processor 601 is further configured to: when the cumulative probability distribution value of the N-1th selected value in the selected value set is less than or equal to the preset threshold, if it is determined that the value in the selected value set If the cumulative probability distribution value of the Nth selected value is less than or equal to the preset threshold, the N+1 first preselection coefficient in the first preselection set is determined as the first coefficient, and the preset second preselection set is determined The N+1 second preselected coefficient in the middle is the second coefficient.

In some embodiments, the adaptive function is a gamma correction function.

In some embodiments, when the processor 601 performs contrast adjustment on the first image data to obtain the second image data, it is used to: according to the second coefficient, map the first value range of the first image data to the second In terms of the value range, the first value range is the value range of the pixel value of the first image data, and the second value range is the value range between the second coefficient and the preset value; according to the first image The pixel value, the first value range and the second value range of each pixel in the data determine the second image data.

In some embodiments, when the visual sensor 603 acquires the image data to be processed, it is used to: acquire a photographed image, where the photographed image is environment image data with a high dynamic range acquired by the visual sensor 603.

The processor 601 is also configured to perform normalization processing on the captured image, and perform compression processing on the normalized captured image to obtain image data to be processed.

In some embodiments, the image processing system 600 further includes: a transmitter 604; the transmitter 604 is configured to transmit the second image data to the processing device for processing.

The image processing system 600 of this embodiment can be used to implement the technical solutions of the method embodiments provided in FIGS. 5 to 6, and its implementation principles and technical effects are similar, and will not be repeated here.

FIG. 14 is a schematic structural diagram of a movable platform provided by an embodiment of this application. As shown in FIG. 14, the movable platform 700 provided in this embodiment may include a processor 701, a memory 702, and a vision sensor 703.

Among them, the memory 702 is used to store program codes.

The visual sensor 703 is used to obtain image data to be processed, and the image data to be processed is environmental image data.

The processor 701 calls the program code. When the program code is executed, it is used to perform the following operations: perform adaptive global brightness adjustment on the image data to be processed to obtain the first image data; perform contrast adjustment on the first image data to obtain the first image data Two image data; online image processing is performed on the second image data.

In some embodiments, when the processor 701 performs adaptive global brightness adjustment on the image data to be processed to obtain the first image data, it is configured to: use an adaptive function to perform global brightness adjustment on the image data to be processed to obtain the first image data ; Among them, the adaptive function is related to the brightness of the environmental image data.

In some embodiments, before the processor 701 performs adaptive global brightness adjustment on the image data to be processed to obtain the first image data, it is further configured to: determine the cumulative histogram of the image data to be processed according to the pixel values of the image data to be processed Information, wherein the cumulative histogram information includes the cumulative probability distribution value of each pixel value of the image data to be processed; the first coefficient and the second coefficient are determined according to the cumulative histogram information.

In some embodiments, when the processor 701 determines the first coefficient and the second coefficient according to the accumulated histogram information, it is used to: set the initial value of i to 1, and repeat the following steps until the first coefficient is determined And the second coefficient: determine whether the cumulative probability distribution value of the i-th selected value in the selected value set is greater than the preset threshold, where the selected value set includes N selected values, and each selected value is pending Processing the pixel value of image data, the i-th selected value is less than the i+1-th selected value, N is a positive integer greater than or equal to 1, i∈[1, N], i is a positive integer; if it is determined to be greater than, then The i-th first preselection coefficient in the preset first preselection set will be determined as the first coefficient, and the i-th second preselection coefficient in the preset second preselection set will be determined as the second coefficient. A preselection set includes N+1 first preselection coefficients, the i-th first preselection coefficient is smaller than the i+1th first preselection coefficient, the second preselection set includes N+1 second preselection coefficients, and the i-th The second preselection coefficient is greater than the i+1th second preselection coefficient; if it is determined that it is less than or equal to, it is determined that i is accumulated by 1.

In some embodiments, the processor 701 is further configured to: when the cumulative probability distribution value of the N-1th selected value in the selected value set is less than or equal to the preset threshold, if it is determined that the value in the selected value set If the cumulative probability distribution value of the Nth selected value is less than or equal to the preset threshold, the N+1th first preselection coefficient in the first preselection set is determined as the first coefficient, and the preset second preselection set is determined The N+1 second preselected coefficient in the middle is the second coefficient.

In some embodiments, the adaptive function is a gamma correction function.

In some embodiments, when the processor 701 adjusts the contrast of the first image data to obtain the second image data, it is used to: according to the second coefficient, map the first value range of the first image data to the second In terms of the value range, the first value range is the value range of the pixel value of the first image data, and the second value range is the value range between the second coefficient and the preset value; according to the first image The pixel value, the first value range and the second value range of each pixel in the data determine the second image data.

In some embodiments, when the visual sensor 703 acquires the image data to be processed, it is used to: acquire a photographed image, where the photographed image is environment image data with a high dynamic range acquired by the visual sensor.

The processor 701 is further configured to perform normalization processing on the captured image, and perform compression processing on the normalized captured image to obtain image data to be processed.

The mobile platform 700 of this embodiment can be used to implement the technical solutions of the method embodiments provided in FIGS. 5 to 6, and the implementation principles and technical effects are similar, and will not be repeated here.

The embodiment of the present application also provides a computer storage medium. The computer storage medium stores program instructions. When the program is executed, it may include some or all of the steps of the image processing method in Figures 5 to 6 and the corresponding embodiments. Or, the program execution may include part or all of the steps of the image processing method as shown in FIGS. 5 to 6 and corresponding embodiments.

FIG. 15 is a schematic structural diagram of an image processing system provided by another embodiment of this application. As shown in FIG. 15, the image processing system 800 of this embodiment may include: an image processing system body 801 and an image processing device 802.

The image processing device 802 is installed on the main body 801 of the image processing system. The image processing device 802 may be a device independent of the image processing system body 801.

Wherein, the image processing device 802 can adopt the structure of the embodiment shown in FIG. 13, and correspondingly, it can implement the technical solutions of the embodiments of FIGS. 5 to 6 and the corresponding method. The implementation principles and technical effects are similar, and will not be omitted here. Repeat.

FIG. 16 is a schematic structural diagram of a movable platform provided by another embodiment of this application. As shown in FIG. 16, the movable platform 900 of this embodiment may include a movable platform body 901 and an image processing device 902.

Among them, the image processing device 902 is installed on the movable platform body 901. The image processing device 902 may be a device independent of the movable platform body 901.

Wherein, the image processing device 902 can adopt the structure of the embodiment shown in FIG. 14, and correspondingly, it can execute the technical solutions of the embodiments of FIGS. 5 to 6 and the corresponding method embodiments. The implementation principles and technical effects are similar and will not be repeated here. Repeat.

A person of ordinary skill in the art can understand that all or part of the steps in the above method embodiments can be implemented by a program instructing relevant hardware. The foregoing program can be stored in a computer readable storage medium. When the program is executed, it is executed. Including the steps of the foregoing method embodiment; and the foregoing storage medium includes: read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disks or optical disks, etc., which can store program codes Medium.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the application, not to limit them; although the application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: It is still possible to modify the technical solutions described in the foregoing embodiments, or equivalently replace some or all of the technical features; these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the application range.

Claims

An image processing method, characterized by comprising:

Acquiring image data to be processed, where the image data to be processed is environmental image data acquired by a visual sensor mounted on a movable platform;

Performing adaptive global brightness adjustment on the image data to be processed to obtain first image data;

Performing contrast adjustment on the first image data to obtain second image data;

Wherein, the second image data is used for online image processing of the movable platform.
The method according to claim 1, wherein performing adaptive global brightness adjustment on the image data to be processed to obtain the first image data comprises:

An adaptive function is used to perform global brightness adjustment on the image data to be processed to obtain first image data; wherein the adaptive function is correlated with the brightness of the environmental image data.
The method according to claim 2, wherein the first coefficient in the adaptive function is positively correlated with the brightness of the environmental image data, and the first coefficient is used to perform the Dimming.
The method according to claim 3, wherein the second coefficient used in the contrast adjustment is negatively correlated with the brightness of the environmental image data.
The method according to claim 4, wherein before performing adaptive global brightness adjustment on the image data to be processed to obtain the first image data, the method further comprises:

Determine the cumulative histogram information of the to-be-processed image data according to the pixel value of the to-be-processed image data, wherein the cumulative histogram information includes the cumulative probability distribution value of each pixel value of the to-be-processed image data;

According to the cumulative histogram information, the first coefficient and the second coefficient are determined.
The method according to claim 5, wherein the cumulative probability distribution value of the pixel values having the first coefficient and the second coefficient is greater than a preset threshold.
The method according to claim 5 or 6, wherein determining the first coefficient and the second coefficient according to the cumulative histogram information includes:

Set the initial value of i to 1, and repeat the following steps until the first coefficient and the second coefficient are determined:

Determine whether the cumulative probability distribution value of the i-th selected value in the selected value set is greater than a preset threshold, wherein the selected value set includes N selected values, and each of the selected values is the The pixel value of the image data to be processed, the i-th selected value is less than the i+1-th selected value, N is a positive integer greater than or equal to 1, i∈[1, N], i is a positive integer;

If it is determined to be greater than, the i-th first preselection coefficient in the preset first preselection set will be determined as the first coefficient, and the i-th second preselection coefficient in the preset second preselection set will be determined as The second coefficient, wherein, the first preselected set includes N+1 first preselected coefficients, the i-th first preselected coefficient is smaller than the i+1th first preselected coefficient, and the second preselected set Including N+1 second pre-selection coefficients, the i-th second pre-selection coefficient is greater than the i+1-th second pre-selection coefficient;

If it is determined that it is less than or equal to, it is determined that i is accumulated by 1.
The method according to claim 7, characterized in that, the method further comprises:

When the cumulative probability distribution value of the N-1th selected value in the selected value set is less than or equal to the preset threshold, if the cumulative probability distribution of the Nth selected value in the selected value set is determined If the probability distribution value is less than or equal to the preset threshold, it is determined that the N+1th first preselection coefficient in the first preselection set is the first coefficient, and the first preselection coefficient in the preset second preselection set is determined N+1 second preselection coefficients are the second coefficients.
The method according to any one of claims 2-8, wherein the adaptive function is a gamma correction function.
The method according to any one of claims 3-8, wherein the adjusting the contrast of the first image data to obtain the second image data comprises:

According to the second coefficient, map the first value range of the first image data to the second value range, wherein the first value range is the value range of the pixel value of the first image data, The second value range is a value range between the second coefficient and a preset value;

The second image data is determined according to the pixel value of each pixel in the first image data, the first value range and the second value range.
The method according to any one of claims 1-10, wherein said acquiring image data to be processed comprises:

Acquiring a photographed image, where the photographed image is environment image data with a high dynamic range acquired by the vision sensor;

Perform normalization processing on the captured image, and perform compression processing on the normalized captured image to obtain the image data to be processed.
The method according to any one of claims 1-11, wherein after performing contrast adjustment on the first image data to obtain the second image data, the method further comprises:

The second image data is transmitted to the processing device for processing.
An image processing system, which is characterized by comprising: a processor, a memory and a vision sensor;

The memory is used to store program codes;

The vision sensor is used to obtain image data to be processed, wherein the image data to be processed is carried on a movable platform, and the image data to be processed is environmental image data;

The processor calls the program code, and when the program code is executed, is used to perform the following operations:

Performing adaptive global brightness adjustment on the image data to be processed to obtain first image data;

Performing contrast adjustment on the first image data to obtain second image data;

Wherein, the second image data is used for online image processing of the movable platform.
The image processing system according to claim 13, wherein the processor is configured to: when performing adaptive global brightness adjustment on the image data to be processed to obtain the first image data:

An adaptive function is used to perform global brightness adjustment on the image data to be processed to obtain first image data; wherein the adaptive function is correlated with the brightness of the environmental image data.
The image processing system according to claim 14, wherein the first coefficient in the adaptive function is correlated with the brightness of the environmental image data, and the first coefficient is used to compare the environmental image data Perform brightness adjustment.
15. The image processing system according to claim 15, wherein the second coefficient used in the contrast adjustment is correlated with the brightness of the environmental image data.
The image processing system according to claim 16, wherein the processor is further configured to: before performing adaptive global brightness adjustment on the image data to be processed to obtain the first image data:

Determine the cumulative histogram information of the to-be-processed image data according to the pixel value of the to-be-processed image data, wherein the cumulative histogram information includes the cumulative probability distribution value of each pixel value of the to-be-processed image data;

According to the cumulative histogram information, the first coefficient and the second coefficient are determined.
The image processing system according to claim 17, wherein the cumulative probability distribution value of the pixel values having the first coefficient and the second coefficient is greater than a preset threshold.
The image processing system according to claim 17 or 18, wherein the processor is configured to: when determining the first coefficient and the second coefficient according to the accumulated histogram information:

Set the initial value of i to 1, and repeat the following steps until the first coefficient and the second coefficient are determined:

Determine whether the cumulative probability distribution value of the i-th selected value in the selected value set is greater than a preset threshold, wherein the selected value set includes N selected values, and each of the selected values is the The pixel value of the image data to be processed, the i-th selected value is less than the i+1-th selected value, N is a positive integer greater than or equal to 1, i∈[1, N], i is a positive integer;

If it is determined to be greater than, the i-th first preselection coefficient in the preset first preselection set will be determined as the first coefficient, and the i-th second preselection coefficient in the preset second preselection set will be determined as The second coefficient, wherein the first preselected set includes N+1 first preselected coefficients, the i-th first preselected coefficient is smaller than the i+1th first preselected coefficient, and the second preselected set Including N+1 second preselection coefficients, the i-th second preselection coefficient is greater than the i+1th second preselection coefficient;

If it is determined that it is less than or equal to, it is determined that i is accumulated by 1.
The image processing system according to claim 19, wherein the processor is further configured to:

When the cumulative probability distribution value of the N-1th selected value in the selected value set is less than or equal to the preset threshold, if it is determined that the cumulative value of the Nth selected value in the selected value set is If the probability distribution value is less than or equal to the preset threshold, it is determined that the N+1th first preselection coefficient in the first preselection set is the first coefficient, and the first preselection coefficient in the preset second preselection set is determined N+1 second preselection coefficients are the second coefficients.
The image processing system according to any one of claims 14-20, wherein the adaptive function is a gamma correction function.
The image processing system according to any one of claims 15-20, wherein the processor is configured to: when performing contrast adjustment on the first image data to obtain the second image data:

According to the second coefficient, map the first value range of the first image data to the second value range, wherein the first value range is the value range of the pixel value of the first image data, The second value range is a value range between the second coefficient and a preset value;

The second image data is determined according to the pixel value of each pixel in the first image data, the first value range and the second value range.
The image processing system according to any one of claims 13-22, wherein the visual sensor is used to obtain a photographed image when acquiring image data to be processed, wherein the photographed image is the vision sensor The acquired high dynamic range environmental image data;

The processor is further configured to perform normalization processing on the captured image, and perform compression processing on the normalized captured image to obtain the image data to be processed.
The image processing system according to any one of claims 13-23, wherein the image processing system further comprises: a transmitter;

The transmitter is used to transmit the second image data to a processing device for processing.
A movable platform, which is characterized by comprising: a processor, a memory and a vision sensor;

The memory is used to store program codes;

The visual sensor is used to obtain image data to be processed, and the image data to be processed is environmental image data;

The processor calls the program code, and when the program code is executed, is used to perform the following operations:

Performing adaptive global brightness adjustment on the image data to be processed to obtain first image data;

Performing contrast adjustment on the first image data to obtain second image data;

Perform online image processing on the second image data.
The mobile platform according to claim 25, wherein the processor is configured to: when performing adaptive global brightness adjustment on the image data to be processed to obtain the first image data:

An adaptive function is used to perform global brightness adjustment on the image data to be processed to obtain first image data; wherein the adaptive function is correlated with the brightness of the environmental image data.
The mobile platform of claim 26, wherein the first coefficient in the adaptive function is correlated with the brightness of the environmental image data, and the first coefficient is used to compare the environmental image data Perform brightness adjustment.
The movable platform of claim 27, wherein the second coefficient used in the contrast adjustment is correlated with the brightness of the environmental image data.
The mobile platform according to claim 28, wherein the processor is further configured to: before performing adaptive global brightness adjustment on the image data to be processed to obtain the first image data:

Determine the cumulative histogram information of the to-be-processed image data according to the pixel value of the to-be-processed image data, wherein the cumulative histogram information includes the cumulative probability distribution value of each pixel value of the to-be-processed image data;

According to the cumulative histogram information, the first coefficient and the second coefficient are determined.
The mobile platform of claim 29, wherein the cumulative probability distribution value of the pixel values having the first coefficient and the second coefficient is greater than a preset threshold.
The movable platform according to claim 29 or 30, wherein the processor is configured to: when determining the first coefficient and the second coefficient according to the cumulative histogram information:

Set the initial value of i to 1, and repeat the following steps until the first coefficient and the second coefficient are determined:

Determine whether the cumulative probability distribution value of the i-th selected value in the selected value set is greater than a preset threshold, wherein the selected value set includes N selected values, and each of the selected values is the The pixel value of the image data to be processed, the i-th selected value is less than the i+1-th selected value, N is a positive integer greater than or equal to 1, i∈[1, N], i is a positive integer;

If it is determined to be greater than, the i-th first preselection coefficient in the preset first preselection set will be determined as the first coefficient, and the i-th second preselection coefficient in the preset second preselection set will be determined as The second coefficient, wherein the first preselected set includes N+1 first preselected coefficients, the i-th first preselected coefficient is smaller than the i+1th first preselected coefficient, and the second preselected set Including N+1 second preselection coefficients, the i-th second preselection coefficient is greater than the i+1th second preselection coefficient;

If it is determined that it is less than or equal to, it is determined that i is accumulated by 1.
The movable platform according to claim 31, wherein the processor is further configured to:

When the cumulative probability distribution value of the N-1th selected value in the selected value set is less than or equal to the preset threshold, if it is determined that the cumulative value of the Nth selected value in the selected value set is If the probability distribution value is less than or equal to the preset threshold, it is determined that the N+1th first preselection coefficient in the first preselection set is the first coefficient, and the first preselection coefficient in the preset second preselection set is determined N+1 second preselection coefficients are the second coefficients.
The movable platform according to any one of claims 26-32, wherein the adaptive function is a gamma correction function.
The movable platform according to any one of claims 27-32, wherein the processor is configured to: when performing contrast adjustment on the first image data to obtain the second image data:

According to the second coefficient, map the first value range of the first image data to the second value range, wherein the first value range is the value range of the pixel value of the first image data, The second value range is a value range between the second coefficient and a preset value;

The second image data is determined according to the pixel value of each pixel in the first image data, the first value range and the second value range.
The movable platform according to any one of claims 25-34, wherein the visual sensor is used to obtain a photographed image when acquiring image data to be processed, wherein the photographed image is the vision sensor The acquired high dynamic range environmental image data;

The processor is further configured to perform normalization processing on the captured image, and perform compression processing on the normalized captured image to obtain the image data to be processed.
A computer-readable storage medium, characterized in that a computer program is stored thereon, and the computer program is executed by a processor to implement the method according to any one of claims 1-12.