Exposure control method, updating method, device, controller, vehicle and medium

Abstract

The invention relates to the technical field of exposure control, and discloses an exposure control method, an updating method and device, a controller, a vehicle and a medium, and the exposure control method comprises the steps: carrying out the brightness segmentation of an obtained current image, and determining a plurality of ambient illuminances corresponding to a plurality of brightness intervals one by one; determining an illumination condition scene corresponding to the current image according to the plurality of ambient illuminance; determining a brightness statistical value of the current image according to the illumination condition scene; and determining a next exposure parameter according to the brightness statistical value, the next exposure parameter being an exposure parameter corresponding to the next image. According to the invention, the brightness statistical value is closer to the brightness value of the target concerned by automatic driving, so that the exposure effect is improved.

Description

Technical Field

[0001] The present invention relates to the field of exposure control technology, and in particular to an exposure control method, an updating method, a device, a controller, a vehicle and a medium. Background Art

[0002] A native high dynamic range (HDR) image sensor is an image sensor that can capture images with a wider brightness range. Compared with traditional image sensors, when faced with high-contrast scenes, the Native HDR Sensor can reduce the occurrence of overexposure of bright areas and underexposure of dark areas, meeting the needs of autonomous driving and other fields for high-quality images in complex lighting environments.

[0003] However, in the field of autonomous driving, since the targets it focuses on are different from those in the traditional smartphone industry, if Native HDRSensor directly adopts the automatic exposure method similar to that in the field of mobile phones, there will be a problem that the determined brightness statistics are significantly different from the brightness values ​​of the targets that autonomous driving focuses on. Among them, the brightness statistics are an important basis for adjusting exposure parameters.

[0004] At present, in order to solve the above problems, in the process of image brightness statistics, the image can be divided into multiple grid areas, the brightness of the image in the grid area can be counted in blocks, and the brightness in different grid areas can be weighted. Statistics are performed, or only the brightness of some areas in the image is directly counted, so that the brightness statistics value is closer to the brightness value of the target of autonomous driving. However, for brightness statistics, the scene complexity and diversity faced by the on-board camera are high, and it is difficult to obtain good brightness statistics in different autonomous driving scenarios, resulting in poor exposure effect. Summary of the invention

[0005] In view of this, the present invention provides an exposure control method, an update method, a device, a controller, a vehicle and a medium to improve the problem that it is difficult to obtain good brightness statistics in different autonomous driving scenarios, thereby resulting in poor exposure effects.

[0006] In a first aspect, the present invention provides an exposure control method, comprising: performing brightness segmentation processing on a current image acquired to determine a plurality of ambient light illuminations corresponding one to one to a plurality of brightness intervals; determining a lighting condition scene corresponding to the current image based on the plurality of ambient light illuminations; determining a brightness statistic of the current image based on the lighting condition scene; determining a next exposure parameter based on the brightness statistic, wherein the next exposure parameter is an exposure parameter corresponding to a next image.

[0007] The exposure control method provided in this embodiment performs brightness segmentation processing on the acquired current image after acquiring the current image, determines multiple ambient light illuminances corresponding to multiple brightness intervals, and then determines the lighting condition scene corresponding to the current image based on the multiple ambient light illuminances, determines the brightness statistics of the current image based on the lighting condition scene, and finally uses the determined brightness statistics as a lookup parameter to determine the next exposure parameter. In this embodiment, the brightness statistics of the current image are determined based on the lighting condition scene, so that the determined brightness statistics can be closer to or the same as the brightness value of the target of interest for autonomous driving, thereby improving the exposure effect, enabling the on-board camera to accurately obtain a clear image containing key information such as the road surface, and ensuring the stability and safety of vehicle driving.

[0008] In an optional embodiment, the multiple brightness intervals include bright parts and dark parts, and the acquired current image is subjected to brightness segmentation processing to determine multiple ambient light illuminations corresponding to the multiple brightness intervals, including: segmenting the current image into bright parts and dark parts according to the histogram data of the current image; determining the ambient light illumination of the bright part according to a first corresponding relationship and the pixel mean corresponding to the bright part; and determining the ambient light illumination of the dark part according to the first corresponding relationship and the pixel mean corresponding to the dark part, wherein the first corresponding relationship is a functional relationship between the ambient light illumination and the pixel mean.

[0009] In this embodiment, after acquiring the current image, the current image is divided into a bright part and a dark part according to the histogram data of the current image, and then the ambient light illumination of the bright part and the dark part is determined according to the first corresponding relationship. This can more conveniently and accurately determine multiple ambient light illuminations, and then more accurately determine the lighting condition scene corresponding to the image.

[0010] In an optional embodiment, the current image includes N×M grid areas, and the multiple brightness intervals include a bright part and a dark part, N and M are both integers greater than 1. The acquired current image is subjected to brightness segmentation processing to determine multiple ambient light illuminations corresponding to the multiple brightness intervals, including: dividing the current image into a bright part and a dark part according to pixel statistical data in the N×M grid areas; determining the ambient light illumination of the bright part according to a first corresponding relationship and a pixel mean corresponding to the bright part; and determining the ambient light illumination of the dark part according to the first corresponding relationship and a pixel mean corresponding to the dark part, wherein the first corresponding relationship is a functional relationship between the ambient light illumination and the pixel mean.

[0011] In an optional embodiment, the lighting condition scene includes a daytime scene, a nighttime scene, a tunnel scene and a dusk scene. According to the lighting condition scene, the brightness statistics of the current image are determined, including: when the lighting condition scene is a daytime scene, the brightness statistics are determined based on the pixel mean of the dark part; when the lighting condition scene is a nighttime scene, the brightness statistics are determined based on the pixel mean of the bright part; when the lighting condition scene is a tunnel scene, the brightness statistics are determined based on the pixel mean of the bright part, a first bright part weight coefficient, the pixel mean of the dark part and the first dark part weight coefficient; when the lighting condition scene is a dusk scene, the brightness statistics are determined based on the pixel mean of the bright part, the second bright part weight coefficient, the pixel mean of the dark part and the second dark part weight coefficient.

[0012] In this embodiment, different statistical strategies are used to determine brightness statistics under different lighting conditions, so that better brightness statistics can be obtained in different autonomous driving scenarios, further improving the exposure effect.

[0013] In an optional embodiment, determining the next exposure parameter according to the brightness statistical value includes: determining the next exposure parameter according to the brightness statistical value and a gear correspondence table, wherein the gear correspondence table includes multiple exposure gears corresponding one-to-one to multiple preset brightness statistical value ranges, and the multiple exposure gears correspond one-to-one to multiple preset exposure parameters.

[0014] The exposure control method provided in this embodiment determines the next exposure parameter according to the brightness statistics and the gear correspondence table after determining the brightness statistics, which can reduce the frequency of changing the exposure state of the image sensor and avoid frequent jumps in image brightness.

[0015] In an optional embodiment, a buffer zone is provided between two adjacent preset brightness statistical value ranges, the buffer zone corresponds to two exposure gears corresponding to the two adjacent preset brightness statistical value ranges, and the next exposure parameter is determined according to a brightness statistical value and gear correspondence table, including: when the brightness statistical value is located in the buffer zone, if the exposure gear at which the current exposure parameter is located is one of the two exposure gears corresponding to the buffer zone, the current exposure parameter is determined as the next exposure parameter; when the brightness statistical value is not located in the buffer zone, the exposure parameter of the exposure gear corresponding to the preset brightness statistical value range at which the brightness statistical value is located is determined as the next exposure parameter.

[0016] In this embodiment, when determining the next exposure parameter based on the gear correspondence table, a buffer zone is set in the gear correspondence table, so that the exposure table parameters can be determined without causing exposure parameter oscillation.

[0017] In an optional embodiment, the lighting condition scene corresponding to the current image is determined based on multiple ambient light illuminations, including: determining the lighting condition scene corresponding to the current image based on multiple ambient light illuminations and a second corresponding relationship, wherein the second corresponding relationship is a correspondence table of multiple preset ambient light illumination ranges and multiple lighting condition scenes.

[0018] In a second aspect, the present invention provides a method for updating image post-processing parameters, the method comprising: performing brightness segmentation processing on a current image acquired to determine a plurality of ambient light illuminations corresponding one-to-one to a plurality of brightness intervals; determining a lighting condition scene corresponding to the current image based on the plurality of ambient light illuminations; determining a brightness statistical value of the current image based on the lighting condition scene; determining a next exposure parameter based on the brightness statistical value, wherein the next exposure parameter is an exposure parameter corresponding to the next image; updating the image post-processing parameters when the exposure parameter change and / or the brightness distribution characterization value change exceeds a preset change, wherein the brightness distribution characterization value is used to indicate the uniformity of pixels of the current image.

[0019] In this embodiment, after determining the next exposure parameter, if the next exposure parameter is different from the current parameter, and / or the change in the brightness distribution characterization value exceeds the preset change, the image post-processing parameter is triggered to be recalculated, thereby avoiding abnormal image effects caused by large changes in the scene under the unified exposure parameters and the image post-processing parameters are not changed in time, thereby improving the safety of autonomous driving.

[0020] In an optional implementation, the brightness distribution characterization value is a flatness residual or a standard deviation of the histogram data of the current image.

[0021] In a third aspect, the present invention provides an exposure control device, comprising: a brightness segmentation module, used to perform brightness segmentation processing on a current image acquired, and determine a plurality of ambient light illuminations corresponding one to one to a plurality of brightness intervals; a scene estimation module, used to determine the lighting condition scene corresponding to the current image based on the plurality of ambient light illuminations; a brightness statistics module, used to determine the brightness statistics of the current image based on the lighting condition scene; and a parameter determination module, used to determine a next exposure parameter based on the brightness statistics, wherein the next exposure parameter is the exposure parameter corresponding to the next image.

[0022] In an optional embodiment, the multiple brightness intervals include a bright part and a dark part, and the brightness segmentation module includes: a first segmentation unit, used to segment the current image into a bright part and a dark part according to the histogram data of the current image; a first determination unit, used to determine the ambient light illumination of the bright part according to a first corresponding relationship and a pixel mean corresponding to the bright part; and determine the ambient light illumination of the dark part according to the first corresponding relationship and the pixel mean corresponding to the dark part, wherein the first corresponding relationship is a functional relationship between the ambient light illumination and the pixel mean.

[0023] In an optional embodiment, the current image includes N×M grid areas, the multiple brightness intervals include a bright part and a dark part, N and M are both integers greater than 1, and the brightness segmentation module includes: a second segmentation unit, used to segment the current image into a bright part and a dark part according to pixel statistical data in the N×M grid areas; a second determination unit, used to determine the ambient light illumination of the bright part according to a first corresponding relationship and a pixel mean corresponding to the bright part; and determine the ambient light illumination of the dark part according to the first corresponding relationship and the pixel mean corresponding to the dark part, wherein the first corresponding relationship is a functional relationship between the ambient light illumination and the pixel mean.

[0024] In an optional embodiment, the lighting condition scene includes a daytime scene, a nighttime scene, a tunnel scene and a dusk scene, and the brightness statistics module includes: a third determination unit, which is used to determine the brightness statistics based on the pixel mean of the dark part when the lighting condition scene is a daytime scene; a fourth determination unit, which is used to determine the brightness statistics based on the pixel mean of the bright part when the lighting condition scene is a nighttime scene; a fifth determination unit, which is used to determine the brightness statistics based on the pixel mean of the bright part, the first bright part weight coefficient, the pixel mean of the dark part and the first dark part weight coefficient when the lighting condition scene is a tunnel scene; and a sixth determination unit, which is used to determine the brightness statistics based on the pixel mean of the bright part, the second bright part weight coefficient, the pixel mean of the dark part and the second dark part weight coefficient when the lighting condition scene is a dusk scene.

[0025] In an optional embodiment, the parameter determination module includes: a seventh determination unit, used to determine the next exposure parameter based on the brightness statistical value and the gear correspondence table, wherein the gear correspondence table includes multiple exposure gears corresponding one-to-one to multiple preset brightness statistical value ranges, and the multiple exposure gears correspond one-to-one to multiple preset exposure parameters.

[0026] In an optional embodiment, a buffer zone is provided between two adjacent preset brightness statistical value ranges, and the buffer zone corresponds to two exposure gears corresponding to the two adjacent preset brightness statistical value ranges. The seventh determination unit includes: a first processing unit, which is used to determine the current exposure parameter as the next exposure parameter when the brightness statistical value is located in the buffer zone if the exposure gear in which the current exposure parameter is located is one of the two exposure gears corresponding to the buffer zone; and a second processing unit, which is used to determine the exposure parameter of the exposure gear corresponding to the preset brightness statistical value range in which the brightness statistical value is located as the next exposure parameter when the brightness statistical value is not located in the buffer zone.

[0027] In an optional embodiment, the scene estimation module includes: a first estimation unit, used to determine the lighting condition scene corresponding to the current image based on multiple ambient light illuminations and a second corresponding relationship, wherein the second corresponding relationship is a correspondence table of multiple preset ambient light illumination ranges and multiple lighting condition scenes.

[0028] In a fourth aspect, the present invention also provides an image post-processing parameter updating device, the device comprising: a brightness segmentation module, used to perform brightness segmentation processing on the acquired current image, and determine multiple ambient light illuminations corresponding to multiple brightness intervals; a scene estimation module, used to determine the lighting condition scene corresponding to the current image based on the multiple ambient light illuminations; a brightness statistics module, used to determine the brightness statistics of the current image based on the lighting condition scene; a parameter determination module, used to determine the next exposure parameter based on the brightness statistics, wherein the next exposure parameter is the exposure parameter corresponding to the next image; an update module, used to update the image post-processing parameters when the exposure parameter change and / or the brightness distribution representation value change exceeds a preset change amount, wherein the brightness distribution representation value is used to indicate the uniformity of the pixels of the current image.

[0029] In an optional implementation, the brightness distribution characterization value is a flatness residual or a standard deviation of the histogram data of the current image.

[0030] In a fifth aspect, the present invention provides a vehicle controller comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, computer instructions being stored in the memory, and the processor executing the computer instructions to thereby execute the exposure control method of the above-mentioned first aspect or any corresponding embodiment, or execute the above-mentioned second aspect or any corresponding embodiment to thereby execute the method for updating image post-processing parameters.

[0031] In a sixth aspect, the present invention provides a vehicle comprising at least one image sensor and the vehicle controller of the fifth aspect, wherein the image sensor and the vehicle controller are communicatively connected.

[0032] In the seventh aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the exposure control method of the above-mentioned first aspect or any corresponding embodiment thereof, or to execute the image post-processing parameter updating method of the above-mentioned second aspect or any corresponding embodiment thereof.

[0033] In an eighth aspect, the present invention provides a computer program product comprising computer instructions, wherein the computer instructions are used to enable a computer to execute the exposure control method of the above-mentioned first aspect or any corresponding embodiment thereof, or to execute the image post-processing parameter updating method of the above-mentioned second aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the related technologies, the drawings required for use in the specific embodiments or the related technical descriptions will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 is a flow chart of an exposure control method according to an embodiment of the present invention;

[0036] Figure 2 is a flow chart of another exposure control method according to an embodiment of the present invention;

[0037] Figure 3 is a schematic diagram of a current image according to an embodiment of the present invention;

[0038] Figure 4 is a schematic diagram of a histogram according to an embodiment of the present invention;

[0039] Figure 5 is a schematic diagram of ISP block statistics according to an embodiment of the present invention;

[0040] Figure 6 is a schematic diagram of a first corresponding relationship according to an embodiment of the present invention;

[0041] Figure 7 is a flow chart of another exposure control method according to an embodiment of the present invention;

[0042] Figure 8 is a schematic diagram of a buffer zone according to an embodiment of the present invention;

[0043] Fig. 9 is a flow chart of a method for updating image post-processing parameters according to an embodiment of the present invention;

[0044] Fig.10 is a structural block diagram of an exposure control device according to an embodiment of the present invention;

[0045] Fig.11 is a structural block diagram of a device for updating image post-processing parameters according to an embodiment of the present invention;

[0046] Fig.12 Schematic diagram of the hardware structure of the vehicle controller according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. According to the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0048] In the field of autonomous driving, visual solutions that rely on visual sensors such as cameras to obtain environmental information and realize autonomous driving functions are gradually becoming the mainstream of the market. In real vehicle applications, image sensors (Sensors) usually need to face complex high-dynamic scenes, so NativeHDRSensor (native high dynamic range image sensor) is widely used. For NativeHDRSensor, it is a difficult problem to clearly image the road information that autonomous driving focuses on while keeping the sensor state relatively stable.

[0049] In view of this, the present invention provides an exposure control method, which estimates the brightness statistics based on the lighting condition scene corresponding to the acquired image, so that the brightness statistics can be closer to the brightness value of the target of interest for autonomous driving, thereby improving the exposure effect and enabling the on-board camera to accurately obtain clear images containing key information such as the road surface, thereby ensuring the stability and safety of vehicle driving.

[0050] According to an embodiment of the present invention, an exposure control method embodiment is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a vehicle controller such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0051] In this embodiment, an exposure control method is provided, which can be used in a vehicle controller. Figure 1 is a flow chart of an exposure control method according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0052] Step S101 , performing brightness segmentation processing on the acquired current image, and determining a plurality of ambient light illuminations corresponding to a plurality of brightness intervals.

[0053] Specifically, the current image may be an image captured by the vehicle camera at the current acquisition moment, the brightness may refer to the brightness of the pixels in the image, the brightness may be represented by the pixel value of the image, the brightness range may refer to the value range of the brightness, and may be pre-configured by the designer. The ambient light illuminance refers to the luminous flux of visible light received per unit area, which is used to measure the intensity of light in the environment, and the unit is Lux. Usually, under the same exposure parameters (exposure time and gain), the pixel mean is linearly correlated with the ambient light illuminance.

[0054] Among them, exposure time refers to the length of time that the image sensor receives light, which directly affects the brightness of the image. The longer the exposure time, the more light the image sensor receives, and the higher the image brightness. Conversely, the shorter the exposure time, the less light is received, and the lower the image brightness (the image is darker). Gain refers to the amplification factor of the image sensor to the input signal. In the case of insufficient light, by increasing the gain, the signal output by the sensor can be made stronger, thereby improving the brightness of the image.

[0055] Exemplarily, after acquiring the current image, the current image can be divided into multiple parts based on multiple brightness intervals, and then the ambient light illumination of each of the multiple parts is determined based on the linear relationship between the pixel mean and the ambient light illumination. The multiple parts correspond to the brightness intervals one by one. The multiple parts can be two parts (bright part and dark part) or three parts (bright part, transition area and dark part), etc., which is not specifically limited in the present invention.

[0056] Step S102: determining the lighting condition scene corresponding to the current image according to multiple ambient light illuminations.

[0057] Among them, the lighting condition scene can reflect the lighting conditions during the vehicle driving process. The lighting condition scene can be a daytime scene, a nighttime scene, a dusk scene or a tunnel scene, etc.

[0058] Exemplarily, the lighting condition scene corresponding to the current image can be determined based on the ambient light illumination interval pre-configured by the designer. For example, when the ambient light illumination corresponding to the multiple parts obtained by the above segmentation is greater than the first preset ambient light illumination (such as 600 Lux), the lighting condition scene corresponding to the current image can be determined as a daytime scene; when the ambient light illumination corresponding to the multiple parts is less than the second preset ambient light illumination (such as 50 Lux), the lighting condition scene corresponding to the current image can be determined as a nighttime scene.

[0059] Step S103, determining brightness statistics of the current image according to the lighting condition scene.

[0060] Exemplarily, the vehicle controller may include brightness statistics strategies corresponding to different lighting condition scenes preconfigured by designers. After determining the lighting condition scene, the brightness statistics of the current image may be determined based on the brightness statistics strategy corresponding to the lighting condition scene.

[0061] Specifically, the lighting condition scene can reflect the position of key information such as the road surface that autonomous driving pays attention to in the current image. For example, in the daytime scene, the sky and other areas are brighter than the road surface and other key information, and the road surface and other key information are located in the darker areas of the current image (that is, the dark part mentioned above); in the night scene, the car lights are on, the sky and other areas are darker than the road surface and other key information, and the road surface and other key information are located in the brighter areas of the current image (that is, the bright part mentioned above).

[0062] The brightness statistics strategy is used to determine the brightness value corresponding to the area where the key information is located in the current image as the brightness statistics, so that the final determined brightness statistics are consistent with or closer to the brightness value of the target that the autonomous driving is concerned about.

[0063] Step S104, determining the next exposure parameter according to the brightness statistics.

[0064] The next exposure parameter is an exposure parameter corresponding to the next image. The next image may be an image captured by the vehicle-mounted camera at the next capture moment. The exposure parameter includes exposure time and gain.

[0065] Exemplarily, the vehicle controller may include a correspondence table of brightness statistics and exposure parameters pre-configured by a designer. After determining the brightness statistics, the brightness statistics are used as a lookup parameter to find a suitable exposure parameter, the exposure parameter is determined as the next exposure parameter, and an image is acquired based on the exposure parameter.

[0066] The exposure control method provided in this embodiment performs brightness segmentation processing on the acquired current image after acquiring the current image, determines multiple ambient light illuminances corresponding to multiple brightness intervals, and then determines the lighting condition scene corresponding to the current image based on the multiple ambient light illuminances, determines the brightness statistics of the current image based on the lighting condition scene, and finally uses the determined brightness statistics as a lookup parameter to determine the next exposure parameter. In this embodiment, the brightness statistics of the current image are determined based on the lighting condition scene, so that the determined brightness statistics can be closer to or the same as the brightness value of the target of interest for autonomous driving, thereby improving the exposure effect, enabling the on-board camera to accurately obtain a clear image containing key information such as the road surface, and ensuring the stability and safety of vehicle driving.

[0067] In this embodiment, another exposure control method is provided, which can be used for a vehicle controller. Figure 2FIG. 1 is a flow chart of another exposure control method according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0068] Step S201 , performing brightness segmentation processing on the acquired current image, and determining a plurality of ambient light illuminations corresponding to a plurality of brightness intervals.

[0069] The number of brightness intervals is 2, and the plurality of brightness intervals includes a bright portion and a dark portion.

[0070] In some optional implementations, the above step S201 includes step S2011 and step S2012:

[0071] Step S2011, dividing the current image into a bright part and a dark part according to the histogram data of the current image.

[0072] Among them, the histogram data is a set of data used to intuitively display the distribution of pixel values ​​in the image. The horizontal axis of the histogram represents the pixel value of the pixel, and the vertical axis of the histogram represents the number corresponding to each pixel value. For example, the current image can be as follows Figure 3 As shown, the histogram can be Figure 4 shown.

[0073] Exemplarily, the histogram data may come from an image signal processor (ISP), and the ISP may accumulate block statistical information to obtain the histogram data. The histogram data may also come directly from an image sensor.

[0074] Specifically, Figure 5 As shown, the sensor array 510 can be divided into 5×5 active measurement windows 511 , and the ISP can count the number of each pixel value in each active measurement window 511 respectively, and then accumulate the data in all active measurement windows to obtain histogram data.

[0075] Exemplarily, after acquiring the histogram data of the current image, a segmentation algorithm may be used to segment the histogram data into two parts, where the image region where the part with larger pixel values ​​is located is the bright part, and the image region where the part with smaller pixel values ​​is located is the dark part.

[0076] Specifically, the segmentation algorithm may be a bimodal method, an Otsu algorithm or a maximum entropy method.

[0077] The bimodal method assumes that an image consists of two parts: the foreground and the background. In the grayscale histogram of the image, the foreground and the background each form a peak, and there is a valley between the two peaks. The goal of this method is to find the grayscale value corresponding to this valley and use it as a threshold to segment the image. The separation of the foreground and the background is achieved by dividing the pixels in the image with a grayscale value less than the threshold into the background and the pixels greater than the threshold into the foreground.

[0078] The Otsu algorithm is an automatic threshold selection method based on maximizing the inter-class variance. The core idea is to divide the grayscale values ​​of the image into two groups (foreground and background), calculate the inter-class variance of the two groups under different thresholds, and find the threshold that maximizes the inter-class variance as the segmentation threshold. The inter-class variance reflects the degree of difference between the two groups of data. When the inter-class variance is the largest, it means that the threshold at this time can best distinguish the foreground from the background.

[0079] The maximum entropy method is based on the concept of entropy in information theory. Entropy represents the uncertainty or disorder of information, and the entropy of an image reflects the uniformity of grayscale distribution in the image. The goal of the maximum entropy method is to find a threshold value that maximizes the sum of the entropy of the foreground and background after segmentation. The threshold value is determined by maximizing the sum of the entropy of the foreground and background, thereby achieving image segmentation.

[0080] Step S2012, determining the ambient light illumination of the bright part according to the first corresponding relationship and the average value of pixels corresponding to the bright part, and determining the ambient light illumination of the dark part according to the first corresponding relationship and the average value of pixels corresponding to the dark part.

[0081] The first corresponding relationship is a functional relationship between the ambient light illumination and the pixel mean value, and the first corresponding relationship can be pre-configured in the vehicle controller by a designer.

[0082] Exemplarily, the first correspondence may be as follows: Figure 6 As shown in (y=0.0247x+4.4556), under the same exposure parameters, the ambient light intensity is positively correlated with the pixel mean value. The larger the pixel mean value, the greater the ambient light intensity. Figure 6 In the figure, the horizontal axis x represents the ambient light intensity, and the vertical axis y represents the pixel mean / (exposure time × gain).

[0083] Specifically, after dividing the current image into a bright part and a dark part, the mean pixel value of the bright part of the image (i.e., the pixel mean) and the mean pixel value of the dark part of the image can be calculated respectively. Then, the pixel mean corresponding to the bright part is substituted into the first corresponding relationship to obtain the ambient light illumination of the bright part, and the pixel mean corresponding to the dark part is substituted into the first corresponding relationship to obtain the ambient light illumination of the dark part.

[0084] In some other optional implementations, the current image includes N×M grid areas, where N and M are both integers greater than 1, for example, N is 4, 5 or 6, and M can also be 4, 5 or 6. N and M can be the same or different. The above step S201 includes step a1 and step a2:

[0085] Step a1, dividing the current image into a bright part and a dark part according to the pixel statistics in the N×M grid areas.

[0086] Specifically, after acquiring the current image, the current image may be divided into N×M grid areas, and the number of each pixel value in each grid area is determined, and then based on a segmentation algorithm, the current image is segmented into a bright part and a dark part.

[0087] Step a2, determining the ambient light illumination of the bright part according to the first corresponding relationship and the average value of pixels corresponding to the bright part; and determining the ambient light illumination of the dark part according to the first corresponding relationship and the average value of pixels corresponding to the dark part.

[0088] Please refer to the above step S2012 for details, which will not be repeated here.

[0089] Step S202: determining the lighting condition scene corresponding to the current image according to the multiple ambient light illuminations and the second corresponding relationship.

[0090] Specifically, this step is Figure 1 A specific implementation of step S102 of the illustrated embodiment.

[0091] Among them, the second corresponding relationship is a corresponding relationship table of multiple preset ambient light illumination ranges and multiple lighting condition scenes, and the second corresponding relationship can be a preset value determined by the designer.

[0092] Exemplarily, the second corresponding relationship may be as shown in Table 1:

[0093] Table 1

[0094]

[0095] Wherein, y may refer to pixel mean / (exposure time×gain), and x refers to ambient light illumination.

[0096] Specifically, after determining multiple ambient light illuminations, the multiple ambient light illuminations are compared with the second corresponding relationship to determine a preset ambient light illumination range in which the multiple ambient light illuminations are located. The lighting condition scene corresponding to the preset ambient light illumination range is the lighting condition scene corresponding to the current image.

[0097] For example, if the determined ambient light illuminance of the bright part is 45 Lux and the ambient light illuminance of the dark part is 30 Lux, then based on Table 2, it can be determined that the lighting condition scene is a night scene.

[0098] Step S203: determining brightness statistics of the current image according to the lighting condition scene.

[0099] Among them, the lighting condition scenes include daytime scenes, nighttime scenes, tunnel scenes and dusk scenes.

[0100] Specifically, the above step S203 may include steps S2031 to S2034:

[0101] Step S2031, when the illumination condition scene is a daytime scene, the brightness statistics are determined based on the pixel mean of the dark part.

[0102] For example, when the illumination condition scene is a daytime scene, the mean pixel value of the dark part / (exposure time×gain) can be determined as the brightness statistical value, or the product of the mean pixel value of the dark part / (exposure time×gain) and the first coefficient can be determined as the brightness statistical value. The first coefficient is a preset value and can be determined by the designer.

[0103] Step S2032: When the illumination condition scene is a night scene, a brightness statistical value is determined based on the pixel mean of the bright part.

[0104] For example, when the illumination condition scene is a night scene, the pixel mean value of the bright part / (exposure time×gain) can be determined as the brightness statistics value, or the product of the pixel mean value of the bright part / (exposure time×gain) and the second coefficient can be determined as the brightness statistics value. The second coefficient is a preset value and can be determined by the designer.

[0105] Step S2033, when the lighting condition scene is a tunnel scene, determine the brightness statistics based on the pixel mean of the bright part, the first bright part weight coefficient, the pixel mean of the dark part and the first dark part weight coefficient.

[0106] Among them, the first bright part weight coefficient and the first dark part weight coefficient can be preset values. For example, the first dark part weight coefficient can be 0.6, the first bright part weight coefficient can be 0.4, or the first bright part weight coefficient and the first dark part weight coefficient can both be 0.5, etc.

[0107] Exemplarily, when the lighting condition scene is a tunnel scene, the sum of the product of the pixel mean of the bright part / (exposure time×gain) and the first bright part weight coefficient and the product of the pixel mean of the dark part / (exposure time×gain) and the first dark part weight coefficient can be determined as the brightness statistical value, that is, the brightness statistical value = the first bright part weight coefficient × the pixel mean of the bright part / (exposure time×gain) + the first dark part weight coefficient × the pixel mean of the dark part / (exposure time×gain).

[0108] Step S2034, when the lighting condition scene is a dusk scene, determine the brightness statistics based on the pixel mean of the bright part, the second bright part weight coefficient, the pixel mean of the dark part and the second dark part weight coefficient.

[0109] Among them, the second bright part weight coefficient and the second dark part weight coefficient can be preset values, for example, the second dark part weight coefficient can be 0.4, the second bright part weight coefficient can be 0.6, or the second bright part weight coefficient and the second dark part weight coefficient can both be 0.5, etc.

[0110] Exemplarily, when the lighting condition scene is a dusk scene, the sum of the product of the pixel mean of the bright part / (exposure time×gain) and the second bright part weight coefficient and the product of the pixel mean of the dark part / (exposure time×gain) and the second dark part weight coefficient can be determined as the brightness statistical value, that is, the brightness statistical value = the second bright part weight coefficient × the pixel mean of the bright part / (exposure time×gain) + the second dark part weight coefficient × the pixel mean of the dark part / (exposure time×gain).

[0111] Step S204, determining the next exposure parameter according to the brightness statistics.

[0112] For details, please see Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0113] In this embodiment, after acquiring the current image, the current image is divided into a bright part and a dark part according to the histogram data of the current image, and then the ambient light illumination of the bright part and the dark part is determined according to the first corresponding relationship, so that multiple ambient light illuminations can be determined more conveniently and accurately, and then the lighting condition scene corresponding to the image can be determined more accurately. Afterwards, different statistical strategies are used to determine the brightness statistical value in different lighting condition scenes, so that better brightness statistical values ​​can be obtained in different autonomous driving scenes, further improving the exposure effect.

[0114] Specifically, in the automatic exposure method in the traditional mobile phone field, in order to improve the image quality, the polishing parameters will change in real time according to the brightness of the lighting scene. However, in the autonomous driving scene, the vehicle may experience a variety of different natural lighting scenes in a short period of time. Therefore, in the field of autonomous driving, if the automatic exposure method similar to that in the mobile phone field is directly adopted, there will still be problems such as frequent changes in exposure status and frequent jumps in picture brightness, which will affect the stability and even safety of the autonomous driving function.

[0115] Based on this, this embodiment also provides an exposure control method, which can be used in a vehicle controller. Figure 7 FIG. 1 is a flow chart of another exposure control method according to an embodiment of the present invention. Figure 7 As shown, the method comprises the following steps:

[0116] Step S701 , performing brightness segmentation processing on the acquired current image, and determining a plurality of ambient light illuminations corresponding to a plurality of brightness intervals.

[0117] For details, please see Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0118] Step S702: determining the lighting condition scene corresponding to the current image according to multiple ambient light illuminations.

[0119] For details, please see Figure 1 Step S102 of the embodiment shown, or Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0120] Step S703: Determine the brightness statistics of the current image according to the lighting condition scene.

[0121] For details, please see Figure 1 Step S103 of the illustrated embodiment, or Figure 2 Step S203 of the illustrated embodiment will not be described in detail here.

[0122] Step S704, determining the next exposure parameter according to the brightness statistics and the gear position correspondence table.

[0123] The gear correspondence table includes a plurality of exposure gears corresponding one-to-one to a plurality of preset brightness statistical value ranges, and the plurality of exposure gears correspond one-to-one to a plurality of preset exposure parameters.

[0124] Exemplarily, the gear position correspondence table may be shown in Table 2:

[0125] Table 2

[0126]

[0127] Among them, each parameter in the example in Table 2 is a preset value, which is determined by the designer according to the actual needs of the autonomous driving scenario. For example, the first threshold value can be 3.5, the first preset time length can be 0×22e, and the first preset gain can be 2.0. The above exposure gear is only an example, and the exposure gear can be any value between 2 and 10.

[0128] Specifically, after the brightness statistical value is determined, a preset brightness statistical value range corresponding to the brightness statistical value may be determined by looking up a table, and an exposure parameter corresponding to the preset brightness statistical value range may be determined as the next exposure parameter.

[0129] In this embodiment, the exposure parameters are determined by using the exposure gear, which can reduce the frequency of changing the exposure state of the image sensor and avoid frequent jumps in image brightness.

[0130] Furthermore, in the above process of determining the exposure parameters, in order to prevent the image sensor from jumping back and forth between two exposure states with a large difference, a buffer zone is set between two adjacent preset brightness statistical value ranges.

[0131] Specifically, Figure 8 As shown, the buffer 801 includes a partial area of ​​two adjacent preset brightness statistical value ranges, and the buffer corresponds to two exposure gears (such as the Pth gear and the P+1th gear) corresponding to the two adjacent preset brightness statistical value ranges. At this time, the above step S704 includes step b1 and step b2:

[0132] Step b1: when the brightness statistics value is in the buffer, if the exposure level of the current exposure parameter is one of the two exposure levels corresponding to the buffer, the current exposure parameter is determined as the next exposure parameter.

[0133] Among them, the current exposure parameter is the exposure parameter corresponding to the current image.

[0134] Exemplarily, when the brightness statistics are located in the cache area, the exposure gears corresponding to the buffer area are the Pth gear and the P+1th gear. If the exposure gear of the current exposure parameter is the Pth gear or the P+1th gear, the current exposure parameter is determined as the next exposure parameter. This can avoid the problem of exposure state oscillation near the threshold, so as to complete the determination of the exposure table parameters without causing exposure parameter oscillation.

[0135] Specifically, if the exposure gear of the current exposure parameter is the P-1th gear (neither the Pth gear nor the P+1th gear), the exposure parameter of the exposure gear corresponding to the preset brightness statistical value range of the brightness statistical value is determined as the next exposure parameter.

[0136] Step b2: when the brightness statistical value is not located in the buffer zone, an exposure parameter of an exposure level corresponding to a preset brightness statistical value range in which the brightness statistical value is located is determined as a next exposure parameter.

[0137] Specifically, when the brightness statistical value is not in the buffer, the brightness statistical value is still used as the table lookup parameter to find the preset brightness statistical value range of the brightness statistical value in the gear corresponding table, and the exposure parameter recorded in the exposure gear corresponding to the preset brightness statistical value range is determined as the next exposure parameter.

[0138] The exposure control method provided in this embodiment determines the next exposure parameter according to the brightness statistics and the gear correspondence table after determining the brightness statistics, which can reduce the frequency of changes in the exposure state of the image sensor and avoid frequent jumps in image brightness. Furthermore, when determining the next exposure parameter based on the gear correspondence table, a buffer is set in the gear correspondence table, which can complete the determination of the exposure table parameters without causing exposure parameter oscillation.

[0139] In this embodiment, a method for updating image post-processing parameters is also provided, which can be used for a vehicle controller. Fig. 9 FIG. 1 is a flow chart of a method for updating image post-processing parameters according to an embodiment of the present invention. Fig. 9 As shown, the method comprises the following steps:

[0140] Step S901 , performing brightness segmentation processing on the acquired current image, and determining a plurality of ambient light illuminations corresponding to a plurality of brightness intervals.

[0141] For details, please see Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0142] Step S902: determining the lighting condition scene corresponding to the current image according to multiple ambient light illuminations.

[0143] For details, please see Figure 1 Step S102 of the embodiment shown, or Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0144] Step S903: Determine the brightness statistics of the current image according to the lighting condition scene.

[0145] For details, please see Figure 1 Step S103 of the illustrated embodiment, or Figure 2 Step S203 of the illustrated embodiment will not be described in detail here.

[0146] Step S904, determining the next exposure parameter according to the brightness statistics.

[0147] For details, please see Figure 7 Step S904 of the illustrated embodiment will not be described in detail here.

[0148] Step S905 , when the exposure parameter change and / or the brightness distribution characterization value change amount exceeds a preset change amount, the image post-processing parameters are updated.

[0149] The brightness distribution characterization value is used to indicate the uniformity of pixels of the current image, and the preset change amount may be a preset value, for example, a change range of more than 30%.

[0150] Exemplarily, the brightness distribution characterization value may be a flatness residual or a standard deviation of the histogram data of the current image.

[0151] Flatness residual is used to measure the difference between the actual histogram and the completely flat histogram. A completely flat histogram means that each gray level or data interval has the same frequency of occurrence, while the actual histogram may deviate from this flat distribution due to the content and characteristics of the image. Flatness residual is an indicator used to quantify the degree of this deviation. Usually, the absolute value sum or square sum of all interval residuals can be calculated to represent the flatness residual of the entire histogram.

[0152] The standard deviation of histogram data is used to measure the degree of dispersion of data distribution in the histogram, that is, the dispersion of the frequency of each gray level or data interval relative to the mean. The larger the standard deviation, the more dispersed the data distribution; the smaller the standard deviation, the more concentrated the data is near the mean.

[0153] Specifically, the image post-processing parameters may include global histogram equalization (Global Histogram Matching, GTM) parameters, local histogram equalization (Local Histogram Matching, LTM) parameters, edge enhancement (Edge Enhancement, EE) parameters, and the like.

[0154] The global histogram equalization parameter adjusts the global grayscale histogram of the image to make the grayscale distribution of the image more uniform, thereby enhancing the overall contrast of the image. The local histogram equalization parameter performs histogram equalization on the local area of ​​the image, divides the image into multiple small sub-areas, and then performs histogram equalization on each sub-area separately. This can adaptively enhance the local contrast according to the characteristics of different areas of the image and better preserve the local details and features of the image. The edge enhancement parameter is an image processing technology used to highlight the edge information in the image. By using various algorithms and filters, the edges in the image are detected and enhanced to make the edges clearer and more obvious.

[0155] In some implementations, the image post-processing parameters may also be recalculated every N frames of images.

[0156] In this embodiment, after determining the next exposure parameter, if the next exposure parameter is different from the current parameter, and / or the change in the brightness distribution characterization value exceeds the preset change, the image post-processing parameter is triggered to be recalculated, thereby avoiding abnormal image effects caused by large changes in the scene under the unified exposure parameters and the image post-processing parameters are not changed in time, thereby improving the safety of autonomous driving.

[0157] In this embodiment, an exposure control device and an image post-processing parameter updating device are also provided, which are used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0158] This embodiment provides an exposure control device, such as Fig.10 As shown, including:

[0159] The brightness segmentation module 1001 is used to perform brightness segmentation processing on the acquired current image to determine multiple ambient light illuminations corresponding to multiple brightness intervals;

[0160] A scene estimation module 1002 is used to determine the lighting condition scene corresponding to the current image according to multiple ambient light illuminations;

[0161] The brightness statistics module 1003 is used to determine the brightness statistics of the current image according to the lighting condition scene;

[0162] The parameter determination module 1004 is used to determine the next exposure parameter according to the brightness statistical value, wherein the next exposure parameter is the exposure parameter corresponding to the next image.

[0163] In some optional implementations, the plurality of brightness intervals include bright parts and dark parts, and the brightness segmentation module 1001 includes:

[0164] A first segmentation unit, used for segmenting the current image into a bright part and a dark part according to the histogram data of the current image;

[0165] The first determination unit is used to determine the ambient light illumination of the bright part according to the first corresponding relationship and the pixel mean corresponding to the bright part; and to determine the ambient light illumination of the dark part according to the first corresponding relationship and the pixel mean corresponding to the dark part, wherein the first corresponding relationship is a functional relationship between the ambient light illumination and the pixel mean.

[0166] In some optional implementations, the current image includes N×M grid areas, the multiple brightness intervals include bright parts and dark parts, N and M are both integers greater than 1, and the brightness segmentation module 1001 includes:

[0167] The second segmentation unit is used to segment the current image into a bright part and a dark part according to pixel statistics in the N×M grid areas;

[0168] The second determination unit is used to determine the ambient light illumination of the bright part according to the first corresponding relationship and the pixel mean corresponding to the bright part; and to determine the ambient light illumination of the dark part according to the first corresponding relationship and the pixel mean corresponding to the dark part, wherein the first corresponding relationship is a functional relationship between the ambient light illumination and the pixel mean.

[0169] In some optional implementations, the lighting condition scenes include daytime scenes, nighttime scenes, tunnel scenes, and dusk scenes, and the brightness statistics module 1003 includes:

[0170] A third determining unit, configured to determine a brightness statistical value based on a pixel mean value of a dark portion when the illumination condition scene is a daytime scene;

[0171] A fourth determining unit, configured to determine a brightness statistical value based on a pixel mean of a bright part when the illumination condition scene is a night scene;

[0172] a fifth determining unit, configured to determine the brightness statistics based on the pixel mean of the bright part, the first bright part weight coefficient, the pixel mean of the dark part, and the first dark part weight coefficient when the illumination condition scene is a tunnel scene;

[0173] The sixth determination unit is used to determine the brightness statistics based on the pixel mean of the bright part, the second bright part weight coefficient, the pixel mean of the dark part and the second dark part weight coefficient when the lighting condition scene is a dusk scene.

[0174] In some optional implementations, the parameter determination module 1004 includes:

[0175] The seventh determination unit is used to determine the next exposure parameter according to the brightness statistical value and the gear correspondence table, wherein the gear correspondence table includes multiple exposure gears corresponding one-to-one to multiple preset brightness statistical value ranges, and the multiple exposure gears correspond one-to-one to multiple preset exposure parameters.

[0176] In some optional implementations, a buffer zone is provided between two adjacent preset brightness statistical value ranges, the buffer zone corresponds to two exposure gears corresponding to the two adjacent preset brightness statistical value ranges, and the seventh determination unit includes:

[0177] A first processing unit, configured to determine the current exposure parameter as the next exposure parameter when the brightness statistics value is in the buffer and if the exposure level of the current exposure parameter is one of the two exposure levels corresponding to the buffer;

[0178] The second processing unit is configured to determine, when the brightness statistical value is not located in the buffer zone, an exposure parameter of an exposure level corresponding to a preset brightness statistical value range in which the brightness statistical value is located as a next exposure parameter.

[0179] In some optional implementations, the scene estimation module 1002 includes:

[0180] The first estimation unit is used to determine the lighting condition scene corresponding to the current image according to multiple ambient light illuminations and a second corresponding relationship, wherein the second corresponding relationship is a corresponding relationship table between multiple preset ambient light illumination ranges and multiple lighting condition scenes.

[0181] This embodiment also provides a device for updating image post-processing parameters, such as Fig.11 As shown, the device comprises:

[0182] The brightness segmentation module 1001 is used to perform brightness segmentation processing on the acquired current image to determine multiple ambient light illuminations corresponding to multiple brightness intervals;

[0183] A scene estimation module 1002 is used to determine the lighting condition scene corresponding to the current image according to multiple ambient light illuminations;

[0184] The brightness statistics module 1003 is used to determine the brightness statistics of the current image according to the lighting condition scene;

[0185] A parameter determination module 1004 is used to determine a next exposure parameter according to the brightness statistics, wherein the next exposure parameter is an exposure parameter corresponding to the next image;

[0186] The updating module 1101 is used to update the image post-processing parameters when the exposure parameter changes and / or the brightness distribution representation value changes by more than a preset amount, wherein the brightness distribution representation value is used to indicate the uniformity of the pixels of the current image.

[0187] In some optional implementations, the brightness distribution characterization value is a flatness residual or a standard deviation of the histogram data of the current image.

[0188] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0189] The exposure control device and the image post-processing parameter updating device in this embodiment are presented in the form of functional units, where the units refer to application specific integrated circuits (ASIC), processors and memories that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0190] The embodiment of the present invention also provides a vehicle controller, such as Fig.12As shown, the vehicle controller includes: one or more processors 1210, a memory 1220, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common motherboard or installed in other ways as needed. The processor can process instructions executed in the vehicle controller, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). Fig.12 A processor 1210 is taken as an example.

[0191] The processor 1210 may be a central processing unit, a network processor or a combination thereof. The processor 1210 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable logic gate array, a general purpose array logic or any combination thereof.

[0192] The memory 1220 stores instructions executable by at least one processor 1210 so as to enable at least one processor 1210 to implement the method shown in the above embodiment.

[0193] The memory 1220 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the vehicle controller, etc. In addition, the memory 1220 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 1220 may optionally include a memory remotely arranged relative to the processor 1210, and these remote memories may be connected to the vehicle controller via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0194] The memory 1220 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 1220 may also include a combination of the above types of memory.

[0195] The vehicle controller also includes a communication interface 1230 for the vehicle controller to communicate with other devices or a communication network.

[0196] This embodiment also provides a vehicle, which includes at least one image sensor and a vehicle controller provided by any of the above embodiments, wherein the image sensor and the vehicle controller are communicatively connected.

[0197] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0198] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0199] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0200] In the description of this specification, the description with reference to the terms "this embodiment", "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0201] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0202] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the present invention.

Claims

1. An exposure control method, characterized in that: The method comprises: Performing brightness segmentation processing on the acquired current image to determine multiple ambient light illuminations corresponding to multiple brightness intervals; Determining a lighting condition scene corresponding to the current image according to the multiple ambient light illuminations; Determining a brightness statistical value of the current image according to the lighting condition scene; A next exposure parameter is determined according to the brightness statistical value, wherein the next exposure parameter is an exposure parameter corresponding to a next image.

2. The method according to claim 1, characterized in that The multiple brightness intervals include bright parts and dark parts, and the brightness segmentation processing is performed on the acquired current image to determine multiple ambient light illuminations corresponding to the multiple brightness intervals, including: According to the histogram data of the current image, the current image is divided into a bright part and a dark part; The ambient light illumination of the bright part is determined according to the first corresponding relationship and the pixel mean corresponding to the bright part; and the ambient light illumination of the dark part is determined according to the first corresponding relationship and the pixel mean corresponding to the dark part, wherein the first corresponding relationship is a functional relationship between the ambient light illumination and the pixel mean.

3. The method according to claim 1, characterized in that The current image includes N×M grid areas, the multiple brightness intervals include bright parts and dark parts, N and M are both integers greater than 1, and the brightness segmentation processing is performed on the acquired current image to determine multiple ambient light illuminations corresponding to the multiple brightness intervals, including: According to the pixel statistics in the N×M grid areas, the current image is divided into a bright part and a dark part; The ambient light illumination of the bright part is determined according to the first corresponding relationship and the pixel mean corresponding to the bright part; and the ambient light illumination of the dark part is determined according to the first corresponding relationship and the pixel mean corresponding to the dark part, wherein the first corresponding relationship is a functional relationship between the ambient light illumination and the pixel mean.

4. The method according to claim 2 or 3, characterized in that: The illumination condition scene includes a daytime scene, a nighttime scene, a tunnel scene, and a dusk scene, and determining the brightness statistics of the current image according to the illumination condition scene includes: When the illumination condition scene is the daytime scene, determining the brightness statistical value based on the pixel mean of the dark part; When the illumination condition scene is a night scene, determining the brightness statistical value based on the pixel mean of the bright part; When the illumination condition scene is a tunnel scene, determining the brightness statistics based on the pixel mean of the bright part, the first bright part weight coefficient, the pixel mean of the dark part, and the first dark part weight coefficient; When the illumination condition scene is a dusk scene, the brightness statistics are determined based on the pixel mean of the bright part, the second bright part weight coefficient, the pixel mean of the dark part, and the second dark part weight coefficient.

5. The method according to any one of claims 1 to 3, characterized in that The determining the next exposure parameter according to the brightness statistical value includes: The next exposure parameter is determined according to the brightness statistics and the gear correspondence table, wherein the gear correspondence table includes multiple exposure gears corresponding one-to-one to multiple preset brightness statistics ranges, and the multiple exposure gears correspond one-to-one to multiple preset exposure parameters.

6. The method according to claim 5, characterized in that A buffer zone is provided between two adjacent preset brightness statistical value ranges, and the buffer zone corresponds to two exposure gears corresponding to the two adjacent preset brightness statistical value ranges. The determining of the next exposure parameter according to the brightness statistical value and gear correspondence table includes: When the brightness statistics value is in the buffer, if the exposure level of the current exposure parameter is one of the two exposure levels corresponding to the buffer, determining the current exposure parameter as the next exposure parameter; When the brightness statistical value is not located in the buffer zone, an exposure parameter of an exposure level corresponding to a preset brightness statistical value range in which the brightness statistical value is located is determined as the next exposure parameter.

7. The method according to any one of claims 1 to 3, characterized in that The step of determining the lighting condition scene corresponding to the current image according to the multiple ambient light illuminations includes: The lighting condition scene corresponding to the current image is determined according to the multiple ambient light illuminations and the second corresponding relationship, wherein the second corresponding relationship is a corresponding relationship table between multiple preset ambient light illumination ranges and multiple lighting condition scenes.

8. A method for updating image post-processing parameters, characterized in that: The method comprises: Performing brightness segmentation processing on the acquired current image to determine multiple ambient light illuminations corresponding to multiple brightness intervals; Determining a lighting condition scene corresponding to the current image according to the multiple ambient light illuminations; Determining a brightness statistical value of the current image according to the lighting condition scene; Determine a next exposure parameter according to the brightness statistical value, wherein the next exposure parameter is an exposure parameter corresponding to a next image; When the exposure parameter change and / or the brightness distribution characterization value change amount exceeds a preset change amount, the image post-processing parameters are updated, wherein the brightness distribution characterization value is used to indicate the uniformity of pixels of the current image.

9. The method according to claim 8, characterized in that The brightness distribution characterization value is a flatness residual or a standard deviation of the histogram data of the current image.

10. An exposure control device, characterized in that: The device comprises: A brightness segmentation module is used to perform brightness segmentation processing on the acquired current image to determine multiple ambient light illuminations corresponding to multiple brightness intervals; A scene estimation module, used to determine the lighting condition scene corresponding to the current image according to the multiple ambient light illuminations; A brightness statistics module, used to determine the brightness statistics of the current image according to the lighting condition scene; A parameter determination module is used to determine a next exposure parameter according to the brightness statistical value, wherein the next exposure parameter is an exposure parameter corresponding to a next image.

11. A device for updating image post-processing parameters, characterized in that: The device comprises: A brightness segmentation module is used to perform brightness segmentation processing on the acquired current image to determine multiple ambient light illuminations corresponding to multiple brightness intervals; A scene estimation module, used to determine the lighting condition scene corresponding to the current image according to the multiple ambient light illuminations; A brightness statistics module, used to determine the brightness statistics of the current image according to the lighting condition scene; A parameter determination module, used to determine a next exposure parameter according to the brightness statistical value, wherein the next exposure parameter is an exposure parameter corresponding to a next image; An updating module is used to update the image post-processing parameters when the exposure parameter changes and / or the change amount of the brightness distribution characterization value exceeds a preset change amount, wherein the brightness distribution characterization value is used to indicate the uniformity of the pixels of the current image.

12. A vehicle controller, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the exposure control method described in any one of claims 1 to 7, or the image post-processing parameter updating method described in any one of claims 8 to 9 by executing the computer instructions.

13. A vehicle, characterized in that: The invention comprises at least one image sensor and a vehicle controller as claimed in claim 12, wherein the image sensor and the vehicle controller are communicatively connected.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which are used to enable a vehicle controller to execute the exposure control method described in any one of claims 1 to 7, or to execute the image post-processing parameter updating method described in any one of claims 8 to 9.

15. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to cause a vehicle controller to execute the exposure control method according to any one of claims 1 to 7, or to execute the image post-processing parameter updating method according to any one of claims 8 to 9.

Images