Multi-view angle image acquisition method and device, computer device and storage medium

Abstract

A multi-view angle image acquisition method, comprising: in an automatic driving process, collecting a driving environment according to an original view angle of a camera device to obtain a driving environment image; inputting the driving environment image into a first image processing channel and a second image processing channel respectively; through the first image processing channel, cutting at least one target view angle image according to a target view angle in the driving environment image; through the second image processing channel, down-sampling the driving environment image to obtain a down-sampled driving environment image of the original view angle; and taking the extracted target view angle image and the down-sampled driving environment image as a multi-view angle image.

Description

Technical Field

[0001] This application relates to an image generation method, apparatus, computer device, and storage medium. Background Technology

[0002] With the development of computer technology, autonomous driving technology has emerged. Autonomous driving technology requires the acquisition of environmental information through camera equipment, so the camera equipment is required to capture images from multiple different field of view angles, so that the captured images can cover a wide field of view range and clearly distinguish distant objects.

[0003] However, the inventors realized that although images with different field of view could be obtained by using multiple image sensors with different field of view, the number of image sensors was large, requiring additional space in the camera equipment. Summary of the Invention

[0004] According to various embodiments disclosed in this application, a method, apparatus, computer device, and storage medium for acquiring images with multiple field of view are provided.

[0005] A multi-view image acquisition method, executed by a camera device, includes:

[0006] During autonomous driving, the driving environment is captured according to the original field of view of the camera device to obtain a driving environment image;

[0007] The driving environment images are input into the first image processing path and the second image processing path respectively;

[0008] Through the first image processing path, at least one target field of view image is cropped from the driving environment image according to the target field of view.

[0009] The driving environment image is downsampled through the second image processing path to obtain the downsampled driving environment image of the original field of view.

[0010] The extracted target field-of-view image and the downsampled driving environment image are used as a multi-field-of-view image.

[0011] A multi-view image acquisition device, comprising:

[0012] The image acquisition module is used to acquire the driving environment according to the original field of view of the camera device during autonomous driving, and obtain the driving environment image;

[0013] The input module is used to input the driving environment image into the first image processing path and the second image processing path respectively;

[0014] The cropping module is used to crop at least one target field of view image from the driving environment image according to the target field of view through the first image processing path;

[0015] The downsampling module is used to downsample the driving environment image through the second image processing path to obtain the downsampled driving environment image of the original field of view.

[0016] The multi-view image acquisition module is used to combine the extracted target view image and the downsampled driving environment image as a multi-view image.

[0017] A computer device includes a memory and one or more processors, the memory storing computer-readable instructions that, when executed by the processors, implement the steps of the multi-viewpoint image acquisition method.

[0018] One or more non-volatile storage media storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to implement the steps of the multi-viewpoint image acquisition method.

[0019] Details of one or more embodiments of this application are set forth in the following drawings and description. Other features and advantages of this application will become apparent from the specification, drawings, and claims. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is an application scenario diagram of the multi-viewpoint image acquisition method according to one or more embodiments.

[0022] Figure 2 This is a flowchart illustrating a multi-viewpoint image acquisition method according to one or more embodiments.

[0023] Figure 3a This is a schematic diagram of the horizontal field of view according to one or more embodiments.

[0024] Figure 3b This is a schematic diagram of the vertical field of view according to one or more embodiments.

[0025] Figure 4 This is a flowchart illustrating a method for capturing images of the driving environment according to one or more embodiments.

[0026] Figure 5 This is a schematic diagram of a moving image cropping region according to one or more embodiments.

[0027] Figure 6 This is a flowchart illustrating a method for capturing a second target field of view image according to one or more embodiments.

[0028] Figure 7a This is a schematic diagram of the target image cropping region according to one or more embodiments.

[0029] Figure 7b This is a schematic diagram of the target image cropping area in another embodiment.

[0030] Figure 8 This is a schematic diagram of the process of image processing of driving environment images according to one or more embodiments.

[0031] Figure 9 This is a block diagram of a multi-view image acquisition apparatus according to one or more embodiments.

[0032] Figure 10 This is a block diagram of a multi-view image acquisition device in another embodiment.

[0033] Figure 11 This is a block diagram of a computer device according to one or more embodiments. Detailed Implementation

[0034] To make the technical solutions and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0035] The multi-viewpoint image acquisition method provided in this application can be applied to, for example... Figure 1 In the application environment shown, during autonomous driving, the camera device 120 mounted on the autonomous driving tool 110 captures the driving environment according to the original field of view, obtaining a driving environment image, and inputs the driving environment image into a first image processing path and a second image processing path respectively. The camera device 120, through the first image processing path, extracts at least one target field of view image from the driving environment image according to the target field of view, and through the second image processing path, downsamples the driving environment image to obtain a downsampled driving environment image of the original field of view. The camera device 120 uses the extracted target field of view image and the downsampled driving environment image as a multi-field-of-view image. The camera device 120 can be, but is not limited to, various cameras, video cameras, vehicle-mounted cameras, etc.

[0036] In one embodiment, such as Figure 2As shown, a multi-viewpoint image acquisition method is provided, which can be applied to... Figure 1 Taking the camera equipment in the image as an example, the following steps are included:

[0037] Step 202: During the autonomous driving process, the driving environment is acquired according to the original field of view of the camera device to obtain the driving environment image.

[0038] Autonomous driving is a driving method in which a motor vehicle is controlled safely on the road without any human intervention, through a pre-set control program. Camera equipment is a device that uses image sensors to collect light signals from the driving environment and converts these signals into electrical signals. The image sensor in the camera equipment has a specific field of view; the larger the field of view, the wider the range of the driving environment captured.

[0039] Using the focal point of the camera as the vertex, two straight lines are formed from the vertex to the boundary of the driving environment that the camera can capture. The field of view is the angle between these two lines. The field of view determines the range of the camera's field of view; the larger the field of view, the wider the range of the driving environment that the camera can capture, and the more objects appear in the driving environment image. The original field of view is the default field of view of the image sensor in the camera when it leaves the factory, or the field of view set by the user before capturing the image.

[0040] Step 204: The camera device inputs the driving environment images into the first image processing path and the second image processing path respectively.

[0041] The first image processing path and the second image processing path are hardware paths for processing driving environment images. For example, the first image processing path and the second image processing path can be two different hardware processing paths, such as two different hardware chips. Alternatively, different processing paths can be formed by time-division multiplexing a single hardware processing path, with different image processing methods applied to the driving environment images at different times.

[0042] The camera device inputs driving environment images into the first image processing path and the second image processing path respectively, so as to process the driving environment images through hardware circuits.

[0043] Step 206: The camera device extracts at least one target field of view image from the driving environment image according to the target field of view through the first image processing path.

[0044] Cropping is the process of extracting a portion of an image from another image based on a defined area. When cropping an image, the camera does not change the image's resolution or the pixel values ​​of the pixels.

[0045] The target field of view is the field of view set by computer equipment to narrow the range of the field of view. The target field of view image is an image extracted from the driving environment image by the camera equipment according to the target field of view; it is equivalent to the image obtained by the camera equipment capturing the driving environment according to the target field of view.

[0046] After acquiring images of the driving environment, the camera, because these images are captured from the original field of view, has a relatively large field of view. To obtain an image with a smaller field of view than the driving environment image itself, the camera cropes the driving environment image according to a target field of view, extracting at least one target field of view image. Since the target field of view image extracted by the camera is only a part of the driving environment image, its data volume is smaller than that of the driving environment image, resulting in less computation when performing image recognition on the target field of view image.

[0047] Step 208: The camera device downsamples the driving environment image through the second image processing path to obtain a downsampled driving environment image of the original field of view.

[0048] Downsampling is the process of reducing the number of sampling points in an image. For an N×M image, if the downsampling coefficient is k, then one pixel is taken from every k pixels in each row and column of the driving environment image to form the downsampled driving environment image. The image downsampling process does not change the field of view of the original image, but reduces the resolution of the image, thereby reducing the amount of image data.

[0049] In one embodiment, the camera device outputs a downsampled image of the driving environment to an image recognition unit, which identifies objects in the image and controls the autonomous vehicle based on the identified objects. For example, if a zebra crossing is identified in the driving environment image, the autonomous vehicle is controlled to stop or slow down.

[0050] Step 210: The camera device uses the extracted target field-of-view image and the downsampled driving environment image as a multi-field-of-view image.

[0051] The field of view of the target image is smaller than that of the original image, while the field of view of the downsampled driving environment image is the same as that of the original image. The camera device obtains multiple images with different field of view from only one driving environment image acquired at the original field of view.

[0052] In the aforementioned multi-field-of-view image acquisition method, the camera device first acquires the driving environment image according to the original field of view, obtaining the driving environment image with the largest field of view. Then, the driving environment image is cropped through a first image processing path to obtain a target field of view image with a field of view smaller than the original field of view; the driving environment image is then downsampled through a second image processing path to obtain a downsampled driving environment image with the original field of view. Ultimately, the camera device only needs one image sensor to obtain multiple images with different field of view from the driving environment image acquired by that image sensor at the original field of view. This reduces the cost of acquiring multiple images with different field of view, and also reduces the size of the camera device because only one image sensor is used.

[0053] In one embodiment, the target field of view includes a target horizontal field of view and a target vertical field of view; the original field of view includes an original horizontal field of view and an original vertical field of view; cropping at least one target field of view image from the driving environment image according to the target field of view includes: calculating the image cropping length according to a length calculation formula; the length calculation formula is: Where l is the image cropping length, l′ is the length of the driving environment image, α1 is the original horizontal field of view, and β1 is the target horizontal field of view; the image cropping width is calculated according to the width calculation formula; the width calculation formula is: Where w is the image cropping width, w′ is the width of the driving environment image, α2 is the original vertical field of view, and β2 is the target vertical field of view; at least one image cropping region is determined based on the image cropping length and the image cropping width; in the driving environment image, the target field of view image is cropped according to the determined image cropping region.

[0054] like Figure 3a As shown, the horizontal field of view is the angle between two straight lines determined by the boundary of the driving environment that the camera can capture in the horizontal direction and the focal point of the camera. Figure 3b As shown, the vertical field of view is the angle between two straight lines determined by the boundary of the driving environment that the camera can capture in the vertical direction and the focal point of the camera.

[0055] In one embodiment, the camera device determines a rectangular region according to the image cropping length and the image cropping width, and then crops the target field of view image according to the rectangular region in the driving environment image.

[0056] In one embodiment, such as Figure 4 As shown, the camera device extracts the target field of view image from the driving environment image according to the determined image cropping area, including the following steps:

[0057] S402, The camera device determines the starting point for cropping in the image of the driving environment.

[0058] S404, the camera captures the target field of view image in the driving environment image according to the image capture area at the capture starting point.

[0059] S406, the camera device moves the image capture area step by step from the capture starting point according to a preset moving step size, and after each movement, captures the target field of view image in the driving environment image according to the moved image capture area.

[0060] The cropping start point is the pixel selected by the camera device from the driving environment image. The camera device can use the cropping start point as the center of the image cropping area and crop the target field of view image from the driving environment image according to the image cropping area. Alternatively, the camera device can use the cropping start point as a corner point of the image cropping area and crop the target field of view image from the driving environment image according to the image cropping area.

[0061] The preset movement step size is the step size by which the camera moves towards the starting point of the image capture each time. Gradually moving the image capture area by the camera means that the camera moves the image capture area according to the preset movement step size. For example... Figure 5 As shown, the camera first uses cropping point 1 as the lower left corner of image cropping area 1, and crops the target field of view image from the driving environment image according to image cropping area 1. Then, the camera moves the cropping point to cropping point 2, using cropping point 2 as the lower left corner of image cropping area 2, and crops the target field of view image from the driving environment image according to image cropping area 2. Then, the camera moves the cropping point to cropping point 3, using cropping point 3 as the lower left corner of image cropping area 3, and crops the target field of view image from the driving environment image according to image cropping area 3.

[0062] The camera device translates the image capture area according to a preset movement step size, and extracts multiple target field-of-view images based on the translated image capture area.

[0063] In one embodiment, such as Figure 6 As shown, the camera device extracts the target field of view image from the driving environment image according to the determined image cropping area, including the following steps:

[0064] S602, the camera device performs scaling processing on the image cropping area to obtain at least one target image cropping area.

[0065] S604, the camera device captures a first target field of view image according to the image capture area in the driving environment image, and captures a second target field of view image according to the target image capture area.

[0066] Scaling a captured image area using a camera device refers to enlarging or reducing the size of that area. The camera device can scale the captured area using its center point as the center. Alternatively, it can select a point within the captured area and then scale the area using that selected point as the center.

[0067] like Figure 7a As shown, the camera device magnifies the image cropping area twice to obtain target image cropping area 1 and target image cropping area 2 respectively. Then, the driving environment image is cropped according to target image cropping area 1 and target image cropping area 2 respectively to obtain two second target field-of-view images of different sizes.

[0068] In one embodiment, such as Figure 7b As shown, the camera device scales the image cropping area to obtain target image cropping area 1 and target image cropping area 2. Then, the camera device selects pixels at different locations in the driving environment image as center point 1 and center point 2. Using center point 1 as the center of target image cropping area 1, the camera device crops a second target field-of-view image from the driving environment image. Similarly, using center point 2 as the center of target image cropping area 2, the camera device crops a second target field-of-view image from the driving environment image.

[0069] In one embodiment, the camera device performs statistical analysis on the grayscale values ​​of pixels in the first target field-of-view image to obtain a first grayscale histogram, and performs statistical analysis on the grayscale values ​​of pixels in the second target field-of-view image to obtain a second grayscale histogram; the gain of the first target field-of-view image is adjusted according to the first grayscale histogram, and the gain of the second target field-of-view image is adjusted according to the second grayscale histogram.

[0070] Grayscale value is a numerical value representing the color between white and black in a black and white image. Typically, 0 represents black and 255 represents white. Grayscale values ​​are values ​​between 0 and 255. A grayscale histogram is a statistical graph created by statistically analyzing the grayscale values ​​of all pixels in a digital image to obtain the frequency of each grayscale value. A grayscale histogram represents the number of pixels in an image with a certain grayscale value, reflecting the frequency of each grayscale value in the image.

[0071] If there are more pixels with smaller gray values ​​in either the first or second gray-level histogram, it indicates that the brightness of the first and second target field-of-view images is low. In this case, the camera increases the gain of both images to brighten them. Conversely, if there are more pixels with larger gray values ​​in either the first or second gray-level histogram, it indicates that the brightness of both images is high. In this case, the camera decreases the gain of both images to darken them.

[0072] In one embodiment, the camera device calculates a first average brightness of the first target field-of-view image and a second average brightness of the second target field-of-view image; the first average brightness and the brightness values ​​of pixels in the first target field-of-view image are used as calculation parameters in a first mapping calculation formula to obtain an adjusted brightness value; the first mapping calculation formula is: Where L1(x, y) represents the adjusted brightness value of a pixel in the first target field-of-view image. L represents the first average brightness. w1(x，y) Let 'a' represent the brightness value of a pixel in the first target field-of-view image, where 'a' is a constant. The second average brightness and the brightness values ​​of pixels in the second target field-of-view image are used as calculation parameters in the second mapping formula to perform mapping calculations, resulting in the adjusted brightness value. The second mapping formula is: Where L2(x, y) represents the adjusted brightness value of a pixel in the second target field-of-view image. L represents the second average brightness. w2(x，y) This represents the brightness value of a pixel in the second target's field of view image.

[0073] The first average brightness is the average brightness of the image from the first target's field of view, and the second average brightness is the average brightness of the image from the second target's field of view. For YUV format images, the average brightness of the image is obtained by calculating the average value of the Y channel. For RGB format images, the Y brightness value of a pixel is first calculated using the formula Y = 0.299R + 0.587G + 0.114B, based on the R, G, and B values ​​of the pixel, and then the average brightness of the image is calculated.

[0074] The camera device performs mapping calculations on the brightness values ​​of pixels in the first target field-of-view image and the second target field-of-view image using a first mapping calculation formula and a second mapping calculation formula, so as to adjust the brightness of pixels in the first target field-of-view image and the second target field-of-view image, making the brightness distribution more uniform and the image clearer.

[0075] In one embodiment, the camera device receives a field of view selection instruction and extracts a target field of view from the field of view selection instruction; or, it obtains a configuration file and configures the field of view extracted from the configuration file as the target field of view.

[0076] A field-of-view selection command can include one or more target field-of-view angles. For example, a field-of-view selection command can include three target field-of-view angles: 30 degrees, 60 degrees, and 90 degrees. The field-of-view selection command can be triggered via a touchscreen or input via an external hardware device, such as a mouse or keyboard.

[0077] A configuration file is a file that configures parameters for a computer program. Configuration files can be files that have been configured for the camera device before it leaves the factory, or files created temporarily while the camera device is in use.

[0078] In one embodiment, such as Figure 8 As shown, the camera device acquires light signals through a camera lens, then converts the light signals into electrical signals through an image sensor to generate a driving environment image. The camera device then inputs the driving environment image into pathway 1 and pathway 2 respectively. In pathway 1, the camera device crops the driving environment image to obtain a target field-of-view image with at least one different field of view from the original field of view, and then performs ISP (Image Signal Processing) image processing on the cropped target field-of-view image. In pathway 2, the camera device downsamples the driving environment image to obtain a downsampled driving environment image, and then performs ISP image processing on the downsampled driving environment image. ISP image processing includes adjusting image gain, white balance, and tone mapping. Pathways 1 and 2 can be different hardware pathways, or they can be different processing pathways formed by multiplexing the same hardware circuit. Before being processed through input paths 1 and 2, the driving environment image output by the image sensor may have passed through a serializer / deserializer, a network, MIPI (Mobile Industry Processor Interface), LVDS (Low Voltage Differential Signaling), etc. The image sensor can also integrate an image cropping program to crop the driving environment image and obtain the target field-of-view image.

[0079] It should be understood that, although Figure 2 , 4The steps in flowchart 6 are shown sequentially as indicated by the arrows; however, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise explicitly stated herein, there is no strict order requirement for the execution of these steps, and they can be executed in other orders. Furthermore, Figure 2 , 4 At least some of the steps in step 6 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0080] In one embodiment, such as Figure 9 As shown, a multi-view image acquisition device is provided, including: an acquisition module 902, an input module 904, an image cropping module 906, a downsampling module 908, and an acquisition module 910, wherein:

[0081] The acquisition module 902 is used to acquire the driving environment according to the original field of view of the camera device during autonomous driving, and obtain the driving environment image.

[0082] Input module 904 is used to input driving environment images into the first image processing path and the second image processing path respectively;

[0083] The image cropping module 906 is used to crop at least one target field of view image from the driving environment image according to the target field of view through the first image processing path;

[0084] The downsampling module 908 is used to downsample the driving environment image through the second image processing path to obtain a downsampled driving environment image of the original field of view.

[0085] The acquisition module 910 is used to extract the target field-of-view image and the downsampled driving environment image as a multi-field-of-view image.

[0086] In one embodiment, the target field of view includes a target horizontal field of view and a target vertical field of view; the original field of view includes an original horizontal field of view and an original vertical field of view; the image cropping module 906 is further configured to:

[0087] The length of the image crop is calculated using the length calculation formula; the length calculation formula is: Where l is the image cropping length, l′ is the length of the driving environment image, α1 is the original horizontal field of view, and β1 is the target horizontal field of view;

[0088] The image cropping width is calculated using the width calculation formula; the width calculation formula is: Where w is the image cropping width, w′ is the width of the driving environment image, α2 is the original vertical field of view, and β2 is the target vertical field of view.

[0089] The image cropping area is determined based on the image cropping length and image cropping width;

[0090] In the driving environment image, the target field of view image is cropped according to the determined image cropping area.

[0091] In one embodiment, the image cropping module 906 is further configured to:

[0092] Determine the starting point for cropping in the driving environment image;

[0093] The target field of view image in the driving environment image is captured at the starting point of the capture according to the image capture area; and the image capture area is moved step by step at the starting point of the capture according to a preset moving step size, and after each movement, the target field of view image in the driving environment image is captured according to the moved image capture area.

[0094] In one embodiment, the image cropping module 906 is further configured to:

[0095] The image cropping area is scaled to obtain at least one target image cropping area;

[0096] In the driving environment image, a first target field of view image is cropped according to the image cropping area, and a second target field of view image is cropped according to the target image cropping area.

[0097] In one embodiment, such as Figure 10 As shown, the device also includes:

[0098] The statistics module 912 is used to perform statistics on the gray values ​​of pixels in the first target field of view image to obtain a first gray-level histogram, and to perform statistics on the gray values ​​of pixels in the second target field of view image to obtain a second gray-level histogram.

[0099] The adjustment module 914 is used to adjust the gain of the first target field of view image according to the first gray-level histogram, and to adjust the gain of the second target field of view image according to the second gray-level histogram.

[0100] In one embodiment, the device further includes:

[0101] Calculation module 916 is used to calculate the first average brightness of the first target field of view image and the second average brightness of the second target field of view image;

[0102] The calculation module 916 is also used to perform mapping calculations by using the first average brightness and the brightness values ​​of pixels in the first target field of view image as calculation parameters in the first mapping calculation formula to obtain the adjusted brightness value.

[0103] The first mapping calculation formula is: Where L1(x, y) represents the adjusted brightness value of a pixel in the first target field-of-view image. L represents the first average brightness. w1(x，y) This represents the brightness value of a pixel in the first target's field of view image, where a is a constant;

[0104] The calculation module 916 is also used to perform mapping calculations by using the second average brightness and the brightness values ​​of pixels in the second target field of view image as calculation parameters in the second mapping calculation formula to obtain the adjusted brightness value.

[0105] The second mapping calculation formula is: Where L2(x, y) represents the adjusted brightness value of a pixel in the second target field-of-view image. L represents the second average brightness. w2(x，y) This represents the brightness value of a pixel in the second target's field of view image.

[0106] In one embodiment, the device further includes:

[0107] The receiving module 918 is used to receive a field of view selection instruction and extract the target field of view from the field of view selection instruction; or, to obtain a configuration file and configure the field of view extracted from the configuration file as the target field of view.

[0108] For specific limitations regarding the multi-field-of-view image acquisition device, please refer to the limitations of the multi-field-of-view image acquisition method above, which will not be repeated here. Each module in the aforementioned multi-field-of-view image acquisition device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0109] In one embodiment, a computer device is provided, which may be a camera device, and its internal structure diagram may be as follows: Figure 11As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer-readable instructions. The internal memory provides an environment for the operation of the operating system and computer-readable instructions stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When the computer-readable instructions are executed by the processor, a multi-view image acquisition method is implemented. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0110] Those skilled in the art will understand that Figure 11 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0111] A computer device includes a memory and one or more processors. The memory stores computer-readable instructions, which, when executed by the processors, cause the one or more processors to perform the following steps: during autonomous driving, acquiring a driving environment image according to the original field of view of a camera; inputting the driving environment image into a first image processing path and a second image processing path respectively; extracting at least one target field of view image from the driving environment image according to the target field of view through the first image processing path; downsampling the driving environment image through the second image processing path to obtain a downsampled driving environment image of the original field of view; and using the extracted target field of view image and the downsampled driving environment image as a multi-field-of-view image.

[0112] In one embodiment, the target field of view includes a target horizontal field of view and a target vertical field of view; the original field of view includes an original horizontal field of view and an original vertical field of view; the processor, when executing computer-readable instructions, further implements the following steps: calculating the image cropping length according to a length calculation formula; the length calculation formula is: Where l is the image cropping length, l′ is the length of the driving environment image, α1 is the original horizontal field of view, and β1 is the target horizontal field of view; the image cropping width is calculated according to the width calculation formula; the width calculation formula is: Where w is the image cropping width, w′ is the width of the driving environment image, α2 is the original vertical field of view, and β2 is the target vertical field of view; the image cropping area is determined based on the image cropping length and the image cropping width; in the driving environment image, the target field of view image is cropped according to the determined image cropping area.

[0113] In one embodiment, when the processor executes computer-readable instructions, it further performs the following steps: determining a capture start point in the driving environment image; capturing a target field of view image in the driving environment image at the capture start point according to the image capture area; and gradually moving the image capture area at the capture start point according to a preset moving step size, and capturing a target field of view image in the driving environment image according to the moved image capture area after each movement.

[0114] In one embodiment, the processor, when executing computer-readable instructions, further performs the following steps: scaling the image cropping region to obtain at least one target image cropping region; cropping a first target field of view image according to the image cropping region in the driving environment image, and cropping a second target field of view image according to the target image cropping region.

[0115] In one embodiment, when the processor executes computer-readable instructions, it further performs the following steps: statistically analyzing the grayscale values ​​of pixels in the first target field-of-view image to obtain a first grayscale histogram, and statistically analyzing the grayscale values ​​of pixels in the second target field-of-view image to obtain a second grayscale histogram; adjusting the gain of the first target field-of-view image according to the first grayscale histogram, and adjusting the gain of the second target field-of-view image according to the second grayscale histogram.

[0116] In one embodiment, when the processor executes computer-readable instructions, it further performs the following steps: calculating a first average brightness of the first target field-of-view image and a second average brightness of the second target field-of-view image; using the first average brightness and the brightness values ​​of pixels in the first target field-of-view image as calculation parameters in a first mapping calculation formula to perform mapping calculations and obtain adjusted brightness values; the first mapping calculation formula is: Where L1(x, y) represents the adjusted brightness value of a pixel in the first target field-of-view image. L represents the first average brightness. w1(x，y) Let 'a' represent the brightness value of a pixel in the first target field-of-view image, where 'a' is a constant. The second average brightness and the brightness values ​​of pixels in the second target field-of-view image are used as calculation parameters in the second mapping formula to perform mapping calculations, resulting in the adjusted brightness value. The second mapping formula is: Where L2(x, y) represents the adjusted brightness value of a pixel in the second target field-of-view image. L represents the second average brightness. w2(x，y)This represents the brightness value of a pixel in the second target's field of view image.

[0117] In one embodiment, the processor, when executing computer-readable instructions, further performs the following steps: receiving a field-of-view selection instruction and extracting a target field of view from the field-of-view selection instruction; or, obtaining a configuration file and configuring the field of view extracted from the configuration file as the target field of view.

[0118] One or more non-volatile computer-readable storage media storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the following steps: during autonomous driving, acquiring a driving environment image according to the original field of view of a camera device; inputting the driving environment image into a first image processing path and a second image processing path respectively; through the first image processing path, cropping at least one target field of view image from the driving environment image according to the target field of view; through the second image processing path, downsampling the driving environment image to obtain a downsampled driving environment image of the original field of view; and using the extracted target field of view image and the downsampled driving environment image as a multi-field-of-view image.

[0119] In one embodiment, the target field of view includes a target horizontal field of view and a target vertical field of view; the original field of view includes an original horizontal field of view and an original vertical field of view; when the computer-readable instructions are executed by the processor, the following steps are also performed: calculating the image cropping length according to the length calculation formula; the length calculation formula is: Where l is the image cropping length, l′ is the length of the driving environment image, α1 is the original horizontal field of view, and β1 is the target horizontal field of view; the image cropping width is calculated according to the width calculation formula; the width calculation formula is: Where w is the image cropping width, w′ is the width of the driving environment image, α2 is the original vertical field of view, and β2 is the target vertical field of view; the image cropping area is determined based on the image cropping length and the image cropping width; in the driving environment image, the target field of view image is cropped according to the determined image cropping area.

[0120] In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are also performed: determining a capture start point in the driving environment image; capturing a target field of view image in the driving environment image at the capture start point according to the image capture area; and gradually moving the image capture area at the capture start point according to a preset moving step size, and capturing a target field of view image in the driving environment image according to the moved image capture area after each movement.

[0121] In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are also performed: scaling the image cropping region to obtain at least one target image cropping region; cropping a first target field of view image according to the image cropping region in the driving environment image, and cropping a second target field of view image according to the target image cropping region.

[0122] In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are also performed: statistically analyzing the grayscale values ​​of pixels in the first target field-of-view image to obtain a first grayscale histogram, and statistically analyzing the grayscale values ​​of pixels in the second target field-of-view image to obtain a second grayscale histogram; adjusting the gain of the first target field-of-view image according to the first grayscale histogram, and adjusting the gain of the second target field-of-view image according to the second grayscale histogram.

[0123] In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are further performed: calculating a first average brightness of the first target field-of-view image and a second average brightness of the second target field-of-view image; using the first average brightness and the brightness values ​​of pixels in the first target field-of-view image as calculation parameters in a first mapping calculation formula to perform mapping calculations and obtain adjusted brightness values; the first mapping calculation formula is: Where L1(x, y) represents the adjusted brightness value of a pixel in the first target field-of-view image. L represents the first average brightness. w1(x，y) Let 'a' represent the brightness value of a pixel in the first target field-of-view image, where 'a' is a constant. The second average brightness and the brightness values ​​of pixels in the second target field-of-view image are used as calculation parameters in the second mapping formula to perform mapping calculations, resulting in the adjusted brightness value. The second mapping formula is: Where L2(x, y) represents the adjusted brightness value of a pixel in the second target field-of-view image. L represents the second average brightness. w2(x，y) This represents the brightness value of a pixel in the second target's field of view image.

[0124] In one embodiment, when the computer-readable instructions are executed by the processor, the following steps are also performed: receiving a field-of-view selection instruction and extracting a target field of view from the field-of-view selection instruction; or, obtaining a configuration file and configuring the field of view extracted from the configuration file as the target field of view.

[0125] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware with computer-readable instructions. These computer-readable instructions can be stored in a non-volatile computer-readable storage medium. When executed, these computer-readable instructions can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0126] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0127] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for acquiring images from multiple viewpoints, executed by a camera device, characterized in that, The method includes: During autonomous driving, the driving environment is captured according to the original field of view of the camera equipment to obtain images of the driving environment; The driving environment image is input into the first image processing path and the second image processing path respectively; the first image processing path and the second image processing path are different processing paths formed by time-division multiplexing of the same hardware circuit; before the driving environment image is processed by the first image processing path and the second image processing path, it passes through a serializer, network, mobile industry processor interface and low voltage differential signal interface. Through the first image processing path, at least one target field of view image is cropped from the driving environment image according to the target field of view; the at least one target field of view image includes a target image field of view image cropped from the driving environment image according to the cropping area after each movement according to a preset moving step size, and a target image field of view image cropped from the driving environment image according to at least one target cropping area obtained after scaling the cropping area; the target field of view image is used for image recognition; the process of determining the target field of view includes: receiving a field of view selection instruction and extracting the target field of view from the field of view selection instruction; or, obtaining a configuration file and configuring the field of view extracted from the configuration file as the target field of view; through the second image processing path, the driving environment image is downsampled to obtain a downsampled driving environment image of the original field of view, including: according to the downsampling coefficient k, taking one pixel every k pixels from each row and each column of pixels in the driving environment image to form the downsampled driving environment image of the original field of view; the downsampling The downsampled driving environment image is used to identify objects in the image through an image recognition unit, and to control the autonomous vehicle based on the objects. Specifically, if a zebra crossing is identified in the driving environment image, the autonomous vehicle is controlled to pause or slow down. The downsampled driving environment image is processed through a second image processing path. This image processing includes adjusting image gain, white balance, and tone mapping. The process of adjusting image gain includes: statistically analyzing the grayscale values ​​of pixels in a first target field-of-view image to obtain a first grayscale histogram, and statistically analyzing the grayscale values ​​of pixels in a second target field-of-view image to obtain a second grayscale histogram. The gain of the first target field-of-view image is adjusted based on the first grayscale histogram, and the gain of the second target field-of-view image is adjusted based on the second grayscale histogram. The degree of increase in the gain of the first and second target field-of-view images is positively correlated with the number of pixels in the first or second grayscale histogram whose grayscale values ​​are less than a preset threshold. The extracted target field-of-view image and the downsampled driving environment image are used as a multi-field-of-view image.

2. The method according to claim 1, characterized in that, The target field of view includes the target horizontal field of view and the target vertical field of view; the original field of view includes the original horizontal field of view and the original vertical field of view. The step of cropping at least one target field of view image from the driving environment image according to the target field of view includes: The length of the image crop is calculated according to the length calculation formula; the length calculation formula is: Where l is the image cropping length, l′ is the length of the driving environment image, α1 is the original horizontal field of view, and β1 is the target horizontal field of view; The image cropping width is calculated according to the width calculation formula; the width calculation formula is: Where w is the image cropping width, w′ is the width of the driving environment image, α2 is the original vertical field of view, and β2 is the target vertical field of view; The image cropping area is determined based on the image cropping length and the image cropping width; In the driving environment image, the target field of view image is cropped according to the determined image cropping area.

3. The method according to claim 2, characterized in that, The step of cropping the target field of view image from the driving environment image according to the determined image cropping area includes: Determine the starting point for cropping in the driving environment image; At the starting point of the capture, the target field of view image in the driving environment image is captured according to the image capture area; and at the starting point of the capture, the image capture area is moved step by step according to a preset moving step size, and after each movement, the target field of view image in the driving environment image is captured according to the moved image capture area.

4. The method according to claim 2, characterized in that, The step of cropping the target field of view image from the driving environment image according to the determined image cropping area includes: The image cropping area is scaled to obtain at least one target image cropping area; In the driving environment image, a first target field of view image is cropped according to the image cropping area, and a second target field of view image is cropped according to the target image cropping area.

5. The method according to claim 4, characterized in that, The scaling process refers to enlarging or reducing the size of the image cropping area; it can be done by scaling the image cropping area with the center point of the image cropping area as the center; or, it can be done by selecting a point in the image cropping area and scaling the image cropping area with the selected point as the center.

6. The method according to claim 4, characterized in that, The method further includes: Calculate the first average brightness of the first target field-of-view image and the second average brightness of the second target field-of-view image; The first average brightness and the brightness values ​​of pixels in the first target field of view image are used as calculation parameters in the first mapping calculation formula to perform mapping calculation and obtain the adjusted brightness value. The first mapping calculation formula is: Where L1(x,y) represents the adjusted brightness value of a pixel in the first target field-of-view image. L represents the first average brightness. w1(x,y) α represents the brightness value of a pixel in the first target field-of-view image, where α is a constant; The second average brightness and the brightness values ​​of pixels in the second target field of view image are used as calculation parameters in the second mapping calculation formula to perform mapping calculation and obtain the adjusted brightness value. The second mapping calculation formula is: Where L2(x,y) represents the adjusted brightness value of a pixel in the second target field-of-view image. L represents the second average brightness. w2(x,y) This represents the brightness value of a pixel in the second target field of view image.

7. The method according to claim 1, characterized in that, The method further includes: Receive a field of view selection instruction and extract the target field of view from the field of view selection instruction; or, obtain a configuration file and configure the field of view extracted from the configuration file as the target field of view.

8. A multi-viewpoint image acquisition device, characterized in that, The device includes: The acquisition module is used to acquire the driving environment according to the original field of view of the camera device during autonomous driving, and obtain the driving environment image; The input module is used to input the driving environment image into the first image processing path and the second image processing path respectively; the first image processing path and the second image processing path are different processing paths formed by time-division multiplexing the same hardware circuit; before the driving environment image is processed by the first image processing path and the second image processing path, it passes through a serializer, network, mobile processor interface and low voltage differential signal interface. An image cropping module is used to crop at least one target field-of-view image from the driving environment image according to a target field of view through the first image processing path; the at least one target field-of-view image includes a target image field-of-view image cropped from the driving environment image according to the cropping area after each movement according to a preset movement step size, and a target image field-of-view image cropped from the driving environment image according to at least one target cropping area obtained after scaling the cropping area; the target field-of-view image is used for image recognition; the process of determining the target field of view includes: receiving a field-of-view selection instruction and extracting the target field of view from the field-of-view selection instruction; or, obtaining a configuration file and configuring the field of view extracted from the configuration file as the target field of view; The downsampling module is used to downsample the driving environment image through the second image processing path to obtain a downsampled driving environment image of the original field of view. This includes: taking one pixel every k pixels from each row and column of pixels in the driving environment image, based on a downsampling coefficient of k, to form the downsampled driving environment image of the original field of view; the downsampled driving environment image is used by an image recognition unit to identify objects in the downsampled driving environment image, and to control the autonomous vehicle based on the objects; wherein, if a zebra crossing is identified from the driving environment image, the autonomous vehicle is controlled to pause or decelerate; the downsampled driving environment image is processed through the second image processing path... Image processing is performed on the environmental image; the image processing includes adjusting the image gain, white balance, and tone mapping of the image; the process of adjusting the image gain includes: statistically analyzing the gray values ​​of pixels in the first target field-of-view image to obtain a first gray-level histogram, and statistically analyzing the gray values ​​of pixels in the second target field-of-view image to obtain a second gray-level histogram; adjusting the gain of the first target field-of-view image according to the first gray-level histogram, and adjusting the gain of the second target field-of-view image according to the second gray-level histogram; the degree of increase in the gain of the first target field-of-view image and the second target field-of-view image is positively correlated with the number of pixels in the first gray-level histogram or the second gray-level histogram whose gray values ​​are less than a preset threshold; The acquisition module is used to combine the extracted target field-of-view image and the downsampled driving environment image into a multi-field-of-view image.

9. The apparatus according to claim 8, characterized in that, The target field of view includes the target horizontal field of view and the target vertical field of view; the original field of view includes the original horizontal field of view and the original vertical field of view; the image cropping module is further used for: The length of the image crop is calculated according to the length calculation formula; the length calculation formula is: Where l is the image cropping length, l′ is the length of the driving environment image, α1 is the original horizontal field of view, and β1 is the target horizontal field of view; The image cropping width is calculated according to the width calculation formula; the width calculation formula is: Where w is the image cropping width, w′ is the width of the driving environment image, α2 is the original vertical field of view, and β2 is the target vertical field of view; The image cropping area is determined based on the image cropping length and the image cropping width; In the driving environment image, the target field of view image is cropped according to the determined image cropping area.

10. The apparatus according to claim 9, characterized in that, The image cropping module is also used for: Determine the starting point for cropping in the driving environment image; At the starting point of the cropping, the target field of view image in the driving environment image is cropped according to the image cropping area; Furthermore, the image capture area is gradually moved at the starting point of the capture according to a preset moving step size, and after each movement, the target field of view image in the driving environment image is captured according to the moved image capture area.

11. The apparatus according to claim 9, characterized in that, The image cropping module is also used for: The image cropping area is scaled to obtain at least one target image cropping area; In the driving environment image, the first target field of view image is cropped according to the image cropping area, and the second target field of view image is cropped according to the target image cropping area.

12. The apparatus according to claim 11, characterized in that, The device further includes: The statistics module is used to perform statistics on the gray values ​​of pixels in the first target field of view image to obtain a first gray-level histogram, and to perform statistics on the gray values ​​of pixels in the second target field of view image to obtain a second gray-level histogram. The adjustment module is used to adjust the gain of the first target field of view image according to the first gray-level histogram, and to adjust the gain of the second target field of view image according to the second gray-level histogram.

13. The apparatus according to claim 11, characterized in that, The device further includes: The calculation module is used to calculate the first average brightness of the first target field of view image and the second average brightness of the second target field of view image; The calculation module is further configured to use the first average brightness and the brightness values ​​of pixels in the first target field of view image as calculation parameters in the first mapping calculation formula to perform mapping calculation and obtain the adjusted brightness value. The first mapping calculation formula is: Where L1(x,y) represents the adjusted brightness value of a pixel in the first target field-of-view image. L represents the first average brightness. w1(x,y) This represents the brightness value of a pixel in the first target field-of-view image, where a is a constant; The calculation module is further configured to use the second average brightness and the brightness values ​​of pixels in the second target field of view image as calculation parameters in the second mapping calculation formula to perform mapping calculation and obtain the adjusted brightness value. The second mapping calculation formula is: Where L2(x,y) represents the adjusted brightness value of a pixel in the second target field-of-view image. L represents the second average brightness. w2(x,y) This represents the brightness value of a pixel in the second target field of view image.

14. The apparatus according to claim 8, characterized in that, The device further includes: A receiving module is configured to receive a field of view selection instruction and extract the target field of view from the field of view selection instruction; or, obtain a configuration file and configure the field of view extracted from the configuration file as the target field of view.

15. A computer device comprising a memory and one or more processors, the memory storing computer-readable instructions that, when executed by the one or more processors, cause the one or more processors to perform the following steps: During autonomous driving, the driving environment is captured according to the original field of view of the camera equipment to obtain images of the driving environment; The driving environment image is input into a first image processing path and a second image processing path, respectively; the first image processing path and the second image processing path are different processing paths formed by time-division multiplexing the same hardware circuit; before the driving environment image is processed by the first image processing path and the second image processing path, it passes through a serializer, a network, a mobile industrial processor interface, and a low-voltage differential signal interface. Through the first image processing path, at least one target field of view image is cropped from the driving environment image according to the target field of view; the at least one target field of view image includes a target image field of view image cropped from the driving environment image according to the cropping area after each movement according to a preset moving step size, and a target image field of view image cropped from the driving environment image according to at least one target cropping area obtained after scaling the cropping area. The target field-of-view image is used for image recognition; The process of determining the target field of view includes: receiving a field of view selection instruction and extracting the target field of view from the field of view selection instruction; or, obtaining a configuration file and configuring the field of view extracted from the configuration file as the target field of view. The driving environment image is downsampled through the second image processing path to obtain a downsampled driving environment image of the original field of view. This includes: taking one pixel every k pixels from each row and column of pixels in the driving environment image, based on a downsampling coefficient of k, to form the downsampled driving environment image of the original field of view; the downsampled driving environment image is used to identify objects in the downsampled driving environment image by an image recognition unit, and to control the autonomous vehicle based on the objects; wherein, if a zebra crossing is identified from the driving environment image, the autonomous vehicle is controlled to stop or slow down; the downsampled driving environment image is further processed through the second image processing path. Image processing is performed; the image processing includes adjusting the image gain, white balance, and tone mapping of the image; the process of adjusting the image gain includes: statistically analyzing the gray values ​​of pixels in a first target field-of-view image to obtain a first gray-level histogram, and statistically analyzing the gray values ​​of pixels in a second target field-of-view image to obtain a second gray-level histogram; adjusting the gain of the first target field-of-view image according to the first gray-level histogram, and adjusting the gain of the second target field-of-view image according to the second gray-level histogram; the degree of increase in the gain of the first target field-of-view image and the second target field-of-view image is positively correlated with the number of pixels in the first gray-level histogram or the second gray-level histogram whose gray values ​​are less than a preset threshold; The extracted target field-of-view image and the downsampled driving environment image are used as a multi-field-of-view image.

16. The computer device according to claim 15, characterized in that, The target field of view includes a target horizontal field of view and a target vertical field of view; the original field of view includes an original horizontal field of view and an original vertical field of view; when the processor executes the computer-readable instructions, it also performs the following steps: The length of the image crop is calculated according to the length calculation formula; the length calculation formula is: Where l is the image cropping length, l′ is the length of the driving environment image, α1 is the original horizontal field of view, and β1 is the target horizontal field of view; The image cropping width is calculated according to the width calculation formula; the width calculation formula is: Where w is the image cropping width, w′ is the width of the driving environment image, α2 is the original vertical field of view, and β2 is the target vertical field of view; The image cropping area is determined based on the image cropping length and the image cropping width; In the driving environment image, the target field of view image is cropped according to the determined image cropping area.

17. The computer device according to claim 16, characterized in that, When the processor executes the computer-readable instructions, it also performs the following steps: Determine the starting point for cropping in the driving environment image; At the starting point of the cropping, the target field of view image in the driving environment image is cropped according to the image cropping area; Furthermore, the image capture area is gradually moved at the starting point of the capture according to a preset moving step size, and after each movement, the target field of view image in the driving environment image is captured according to the moved image capture area.

18. One or more non-volatile computer-readable storage media storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the following steps: During autonomous driving, the driving environment is captured according to the original field of view of the camera equipment to obtain images of the driving environment; The driving environment image is input into a first image processing path and a second image processing path, respectively; the first image processing path and the second image processing path are different processing paths formed by time-division multiplexing the same hardware circuit; before the driving environment image is processed by the first image processing path and the second image processing path, it passes through a serializer, a network, a mobile industrial processor interface, and a low-voltage differential signal interface. Through the first image processing path, at least one target field of view image is cropped from the driving environment image according to the target field of view; the at least one target field of view image includes a target image field of view image cropped from the driving environment image according to the cropping area after each movement according to a preset moving step size, and a target image field of view image cropped from the driving environment image according to at least one target cropping area obtained after scaling the cropping area. The target field-of-view image is used for image recognition; The process of determining the target field of view includes: receiving a field of view selection instruction and extracting the target field of view from the field of view selection instruction; or, obtaining a configuration file and configuring the field of view extracted from the configuration file as the target field of view. The driving environment image is downsampled through the second image processing path to obtain a downsampled driving environment image of the original field of view. This includes: taking one pixel every k pixels from each row and column of pixels in the driving environment image, based on a downsampling coefficient of k, to form the downsampled driving environment image of the original field of view; the downsampled driving environment image is used to identify objects in the downsampled driving environment image by an image recognition unit, and to control the autonomous vehicle based on the objects; wherein, if a zebra crossing is identified from the driving environment image, the autonomous vehicle is controlled to stop or slow down; the downsampled driving environment image is further processed through the second image processing path. Image processing is performed; the image processing includes adjusting the image gain, white balance, and tone mapping of the image; the process of adjusting the image gain includes: statistically analyzing the gray values ​​of pixels in a first target field-of-view image to obtain a first gray-level histogram, and statistically analyzing the gray values ​​of pixels in a second target field-of-view image to obtain a second gray-level histogram; adjusting the gain of the first target field-of-view image according to the first gray-level histogram, and adjusting the gain of the second target field-of-view image according to the second gray-level histogram; the degree of increase in the gain of the first target field-of-view image and the second target field-of-view image is positively correlated with the number of pixels in the first gray-level histogram or the second gray-level histogram whose gray values ​​are less than a preset threshold; The extracted target field-of-view image and the downsampled driving environment image are used as a multi-field-of-view image.

19. The storage medium according to claim 18, characterized in that, The target field of view includes a target horizontal field of view and a target vertical field of view; the original field of view includes an original horizontal field of view and an original vertical field of view; when the computer-readable instruction is executed by the processor, the following steps are also performed: The length of the image crop is calculated according to the length calculation formula; the length calculation formula is: Where l is the image cropping length, l′ is the length of the driving environment image, α1 is the original horizontal field of view, and β1 is the target horizontal field of view; The image cropping width is calculated according to the width calculation formula; the width calculation formula is: Where w is the image cropping width, w′ is the width of the driving environment image, α2 is the original vertical field of view, and β2 is the target vertical field of view; The image cropping area is determined based on the image cropping length and the image cropping width; In the driving environment image, the target field of view image is cropped according to the determined image cropping area.

20. The storage medium according to claim 19, characterized in that, When the computer-readable instructions are executed by the processor, the following steps are also performed: Determine the starting point for cropping in the driving environment image; At the starting point of the cropping, the target field of view image in the driving environment image is cropped according to the image cropping area; Furthermore, the image capture area is gradually moved at the starting point of the capture according to a preset moving step size, and after each movement, the target field of view image in the driving environment image is captured according to the moved image capture area.

Images