License plate image fusion processing method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a license plate image fusion processing method and device, equipment and a storage medium, and belongs to the technical field of image processing. The method comprises the steps that in the same monitoring area, a reference exposure image under a reference exposure duration and a plurality of corresponding adjustment exposure images under a plurality of different adjustment exposure durations are acquired, and the monitoring area comprises a plurality of sub-monitoring areas; obtaining reference license plate information from different sub-monitoring areas of the reference exposure image, and obtaining corresponding multiple pieces of adjusted license plate information from the same sub-monitoring areas in the multiple different adjusted exposure images; respectively selecting calibration license plate information corresponding to the reference license plate information from the plurality of pieces of adjustment license plate information, and performing fusion processing to obtain sub-exposure images in the sub-monitoring areas; and splicing the plurality of sub-exposure images of different sub-monitoring areas to obtain a target exposure image after the brightness of the monitoring area is adjusted. According to the invention, the quality of the output image when the brightness distribution of the recorded picture is uneven can be improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, device, equipment and storage medium for fusion processing of license plate images. Background Art

[0002] Generally, vehicles will use dashcams to record images and sounds during driving, where the images include the license plate information of passing vehicles. Clear license plate information can provide important support for traffic accident handling, etc. However, when the image is overexposed or underexposed, the license plate information will become blurred and difficult to recognize, which will affect the handling of traffic accidents.

[0003] In the related art, the output image after exposure adjustment is obtained by fusing multiple sub-frames after overall exposure compensation. However, the light intensity in different areas of the recorded image during driving is different, which is more obvious when driving at night. Therefore, the output image obtained under such image processing method will still have the problem of partial overexposure or underexposure, resulting in poor output image quality and low clarity of license plate information. Summary of the invention

[0004] The main purpose of the embodiments of the present application is to propose a license plate image fusion processing method, device, equipment and storage medium, aiming to improve the quality of the output image when the brightness distribution of the recorded picture is uneven, so as to improve the clarity of the license plate information captured in the picture.

[0005] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a fusion processing method for license plate images, the method comprising:

[0006] In the same monitoring area, a reference exposure image under a preset reference exposure time and a plurality of adjusted exposure images corresponding to a plurality of different adjusted exposure time are obtained, wherein the adjusted exposure time is different from the reference exposure time, and the monitoring area includes a plurality of sub-monitoring areas;

[0007] Identify reference license plate information from different sub-monitoring areas of the reference exposure image, and identify corresponding multiple adjusted license plate information from the same sub-monitoring area in multiple different adjusted exposure images;

[0008] According to the reference brightness value corresponding to each reference license plate information, corresponding calibration license plate information is selected from multiple adjusted license plate information, and each reference license plate information and the corresponding calibration license plate information are fused to obtain a sub-exposure image under the sub-monitoring area;

[0009] Multiple sub-exposure images from different sub-monitoring areas are stitched together to obtain a target exposure image after brightness adjustment of the monitoring area.

[0010] In some embodiments, the plurality of adjusted exposure durations are obtained by following the steps, comprising:

[0011] According to the current recording time, a target time period is determined from a plurality of preset time periods;

[0012] Selecting a first dynamic adjustment value from a plurality of preset dynamic adjustment values ​​based on the target time period, and multiplying the first dynamic adjustment value by a preset length value to obtain a long exposure duration, wherein the long exposure duration is greater than a reference exposure duration;

[0013] A second dynamic adjustment value is selected from a plurality of preset dynamic adjustment values ​​based on a target time period, and the second dynamic adjustment value is multiplied by a preset short value to obtain a short exposure duration, wherein the short exposure duration is less than a reference exposure duration, and the plurality of adjusted exposure durations include at least one long exposure duration and at least one short exposure duration.

[0014] In some embodiments, the plurality of adjusted exposure durations are obtained by following the steps, comprising:

[0015] If the current recording time is the preset interval correction time, determining the average exposure value of the reference exposure image based on the grayscale values ​​of all pixels in the reference exposure image;

[0016] Selecting a third dynamic adjustment value from a plurality of preset dynamic adjustment values ​​based on the average exposure value, and multiplying the third dynamic adjustment value by a preset length value to obtain a long exposure duration, wherein the long exposure duration is greater than a reference exposure duration;

[0017] A fourth dynamic adjustment value is selected from a plurality of preset dynamic adjustment values ​​based on the average exposure value, and the fourth dynamic adjustment value is multiplied by a preset short value to obtain a short exposure duration, wherein the short exposure duration is less than a reference exposure duration, and the plurality of adjusted exposure durations include at least one long exposure duration and at least one short exposure duration.

[0018] In some embodiments, the adjusted exposure image includes at least one long exposure image and at least one short exposure image, wherein the long exposure image is obtained by taking pictures under a long exposure time, and the short exposure image is obtained by taking pictures under a short exposure time;

[0019] Identifying and obtaining corresponding multiple adjusted license plate information from the same sub-monitoring area in multiple different adjusted exposure images includes:

[0020] Determine a first sub-monitoring area in the long-exposure image that is the same as the sub-monitoring area where the reference license plate information is located, and identify and obtain the long-exposure license plate information within the first sub-monitoring area;

[0021] Determine a second sub-monitoring area in the short-exposure image that is the same as the sub-monitoring area where the reference license plate information is located, and identify the short-exposure license plate information from the second sub-monitoring area, wherein the adjusted license plate information includes the long-exposure license plate information and the short-exposure license plate information, and the adjusted license plate information corresponds to the license plate content of the reference license plate information.

[0022] In some embodiments, according to the reference brightness value corresponding to each reference license plate information, corresponding calibration license plate information is selected from a plurality of adjusted license plate information, including:

[0023] When the number of long-exposure license plate information is one and the reference brightness value is within a preset dim threshold, the long-exposure license plate information is selected as the calibration license plate information;

[0024] When the number of short-exposure license plate information is one and the reference brightness value is within a preset brightness threshold, the short-exposure license plate information is selected as the calibration license plate information.

[0025] In some embodiments, according to the reference brightness value corresponding to each reference license plate information, corresponding calibration license plate information is selected from a plurality of adjusted license plate information, further comprising:

[0026] When there are multiple long-exposure license plate information and multiple short-exposure license plate information, the multiple long-exposure license plate information are divided into different long-exposure levels based on the long-exposure duration, and the multiple short-exposure license plate information are divided into different short-exposure levels based on the short-exposure duration;

[0027] Determine a brightness level corresponding to the reference brightness value;

[0028] If the reference brightness value is within a preset dim threshold, a target long exposure level matching the brightness level is determined from a plurality of long exposure levels, and long exposure license plate information corresponding to the target long exposure level is selected as the calibration license plate information;

[0029] If the reference brightness value is within a preset brightness threshold, a target short exposure level matching the brightness level is determined from a plurality of short exposure levels, and short exposure license plate information corresponding to the target short exposure level is selected as the calibration license plate information.

[0030] In some embodiments, each reference license plate information and the corresponding calibration license plate information are fused to obtain a sub-exposure image under the sub-monitoring area, including:

[0031] Based on the preset reference weights, multiple reference license plate features are extracted from the reference license plate information;

[0032] Based on the preset calibration weights, a plurality of calibration license plate features are extracted from the calibration license plate information;

[0033] The reference license plate features and the calibration license plate features that match in spatial position are aligned one by one, and the image after alignment is determined to be the sub-exposure image under the sub-monitoring area.

[0034] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a fusion processing device for license plate images, the device comprising:

[0035] an acquisition module, configured to acquire, within the same monitoring area, a reference exposure image at a preset reference exposure time and a plurality of adjusted exposure images corresponding to a plurality of different adjusted exposure time periods, wherein the adjusted exposure time period is different from the reference exposure time period, and the monitoring area includes a plurality of sub-monitoring areas;

[0036] A recognition module, used to recognize reference license plate information from different sub-monitoring areas of a reference exposure image, and to recognize corresponding multiple adjusted license plate information from the same sub-monitoring area in multiple different adjusted exposure images;

[0037] A fusion module is used to select corresponding calibration license plate information from multiple adjustment license plate information according to the reference brightness value corresponding to each reference license plate information, and fuse each reference license plate information with the corresponding calibration license plate information to obtain a sub-exposure image under the sub-monitoring area;

[0038] A splicing module is used to splice multiple sub-exposure images from different sub-monitoring areas to obtain a target exposure image after brightness adjustment of the monitoring area. In the same monitoring area, a reference exposure image under a preset reference exposure time and multiple adjusted exposure images corresponding to multiple different adjusted exposure times are obtained, wherein the adjusted exposure time is obtained by dynamic adjustment based on the reference exposure time, and the monitoring area includes multiple sub-monitoring areas;

[0039] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present application proposes an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the method of the above-mentioned first aspect when executing the computer program.

[0040] To achieve the above objectives, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the method of the first aspect is implemented.

[0041] The fusion processing method, device, equipment and storage medium of the license plate image proposed in the present application obtains a reference exposure image under a preset reference exposure time and multiple corresponding adjusted exposure images under multiple different adjusted exposure time in the same monitoring area, wherein the adjusted exposure time is different from the reference exposure time, and the monitoring area includes multiple sub-monitoring areas; identifies reference license plate information from different sub-monitoring areas of the reference exposure image, and identifies corresponding multiple adjusted license plate information from the same sub-monitoring area in multiple different adjusted exposure images; selects corresponding calibration license plate information from multiple adjusted license plate information according to the reference brightness value corresponding to each reference license plate information, fuses each reference license plate information and the corresponding calibration license plate information, and obtains the sub-exposure image under the sub-monitoring area; splices multiple sub-exposure images from different sub-monitoring areas to obtain the target exposure image after the brightness of the monitoring area is adjusted. It can be understood that when the ambient light is unstable, the reference exposure image captured by the camera is usually unevenly distributed in brightness. For example, at night, if the target vehicle turns on its headlights, the brightness of the license plate illuminated by the headlights will be higher, while the brightness of the license plate not illuminated by the headlights will be lower. If the overall brightness of the reference exposure image is adjusted by obtaining the corresponding long exposure image and short exposure image of the reference exposure image, no matter how they are fused, there will always be problems of local overexposure or underexposure. Based on this, after obtaining the reference exposure image and the corresponding multiple adjusted exposure images, the embodiment of the present application fuses and splices the license plate information in each sub-monitoring area in the reference exposure image, so that the brightness value of each license plate information can be pixel-compensated based on its own brightness, ensuring that the brightness values ​​of all license plate information in the final target exposure image are bright and moderate, so that the target exposure image can present an appropriate contrast, thereby retaining the detail information in the image, improving the clarity of the target exposure image, and improving the image quality of the output target exposure image. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a schematic diagram of an optional application scenario of the license plate image fusion processing method provided in an embodiment of the present application;

[0043] Figure 2 This is an optional flow chart of the license plate image fusion processing method provided in the embodiment of the present application;

[0044] Figure 3 It is a schematic diagram of an optional monitoring area of ​​the license plate image fusion processing method provided in the embodiment of the present application;

[0045] Figure 4 It is another optional monitoring area schematic diagram of the license plate image fusion processing method provided in the embodiment of the present application;

[0046] Figure 5 It is a schematic diagram of an optional functional module of the license plate image fusion processing device provided in an embodiment of the present application;

[0047] Figure 6 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0049] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0051] First, some nouns involved in this application are analyzed:

[0052] Exposure time, also often referred to as shutter speed, refers to the time interval from the opening to the closing of the camera shutter. During this time, light can shine on the film or photosensitive element, leaving an image of the object on the film or photosensitive element. Exposure time is a very important parameter in photography, which directly affects the brightness and detail of the photo.

[0053] Generally, vehicles will use dashcams to record images and sounds during driving, where the images include the license plate information of passing vehicles. Clear license plate information can provide important support for traffic accident handling, etc. However, when the image is overexposed or underexposed, the license plate information will become blurred and difficult to recognize, which will affect the handling of traffic accidents.

[0054] In the related art, the output image after exposure adjustment is obtained by fusing multiple sub-frames after overall exposure compensation. However, the light intensity in different areas of the recorded image during driving is different, which is more obvious when driving at night. Therefore, the output image obtained under such image processing method will still have the problem of partial overexposure or underexposure, resulting in poor output image quality and low clarity of license plate information.

[0055] Based on this, the embodiments of the present application provide a license plate image fusion processing method, device, equipment and storage medium, aiming to improve the quality of the output image when the brightness distribution of the recorded picture is uneven, so as to improve the clarity of the license plate information captured in the picture.

[0056] It should be noted that in the embodiments of the present application, when it comes to information related to the user's identity or characteristics based on the user's basic information, user's geographic location information, etc., the user's permission or consent will be obtained first, and the collection, use and processing of these data will comply with relevant laws, regulations and standards. In addition, when the embodiments of the present application need to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained first. After the user's separate permission or consent is clearly obtained, the necessary data for the normal operation of the embodiments of the present application will be obtained. For example, when obtaining the reference exposure image and the adjusted exposure image containing the user's license plate information, the relevant user's consent will be obtained first, otherwise the reference exposure image and the adjusted exposure image used in the embodiments of the present application cannot be obtained.

[0057] The license plate image fusion processing method, device, equipment and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the application scenario of the license plate image fusion processing device in the embodiments of the present application is described. Among them, the license plate image fusion processing method provided in the embodiments of the present application (for the convenience of description, it may also be referred to as "processing method" below) can be applied to the license plate image fusion processing device (for the convenience of description, it may also be referred to as "processing device" below). Figure 1 As shown, Figure 1This is a schematic diagram of an optional application scenario of the fusion processing method of the license plate image provided in an embodiment of the present application. In one application scenario, a target vehicle is provided with a driving recorder, and the driving recorder is provided with the processing device proposed in an embodiment of the present application. When the vehicle is driving, the driving recorder shoots a reference exposure image under a preset reference exposure time and a plurality of adjusted exposure images corresponding to a plurality of different adjusted exposure times in a monitoring area, wherein the adjusted exposure time is different from the reference exposure time; then, the processing device can perform fusion adjustment based on the reference exposure image and the adjusted exposure image to obtain a target exposure image; wherein each license plate information captured in the target exposure image has its own relatively appropriate brightness value, and there will be no overexposure or underexposure, that is, the clarity of each license plate information in the target exposure image is high, so that subsequent image processing can be performed based on the high-quality target exposure image.

[0058] After understanding the actual application scenarios of the processing device of the present application, the processing method proposed in the embodiment of the present application is specifically described through the following embodiments.

[0059] In the embodiment of the present application, the fusion processing device of the license plate image will be described from the dimension, and the fusion processing device of the license plate image can be integrated in related equipment, such as a driving recorder. Figure 2 As shown, Figure 2 is an optional flow chart of the license plate image fusion processing method provided in the embodiment of the present application. Figure 2 The method may include but is not limited to steps 101 to 104. When the license plate image fusion processing device performs the license plate image fusion processing method, the specific process is as follows. It should be noted that the present embodiment Figure 2 The order of step 101 to step 104 is not specifically limited, and the order of steps can be adjusted or some steps can be reduced or added according to actual needs.

[0060] Step 101 : obtaining a reference exposure image at a preset reference exposure time and a plurality of adjusted exposure images corresponding to a plurality of different adjusted exposure time in the same monitoring area, wherein the adjusted exposure time is different from the reference exposure time.

[0061] The following is a detailed description of step 101.

[0062] In some embodiments, in order to generate the final target exposure image, the processing device first acquires corresponding exposure images based on different exposure times in the monitoring area. The exposure images include reference exposure images and adjusted exposure images, so that they can be fused based on the multiple exposure images acquired to obtain a target exposure image with higher clarity.

[0063] Among them, the processing device proposed in the present application may include a camera that takes exposure images at different exposure times, and then the processing device performs fusion processing on the captured images to obtain the final target exposure image; or, the processing device only includes a fusion processing function, and the processing device can be connected to different cameras to receive the reference exposure image and adjusted exposure image taken by the camera.

[0064] The monitoring area refers to the field of view of the camera. The monitoring area can be scaled according to actual needs. The embodiment of the present application does not limit the field of view of the monitoring area. Furthermore, the monitoring area can be divided into multiple sub-monitoring areas. For example, the sub-monitoring area can be divided into multiple strips, corresponding to lanes in real life; or the monitoring area can be divided into a grid, each grid corresponding to a sub-monitoring area; of course, the division method of the sub-monitoring area can be set according to actual conditions, and the embodiment of the present application does not limit it.

[0065] Furthermore, the monitoring areas corresponding to the reference exposure image and the multiple adjusted exposure images should be the same, such as Figure 3 As shown, Figure 3 It is a schematic diagram of an optional monitoring area of ​​the license plate image fusion processing method provided in an embodiment of the present application. If the monitoring area of ​​the reference exposure image includes sub-monitoring area A, sub-monitoring area B, sub-monitoring area C and sub-monitoring area D, then the monitoring area of ​​the adjusted exposure image also includes sub-monitoring area A, sub-monitoring area B, sub-monitoring area C and sub-monitoring area D.

[0066] The exposure time refers to the time length from the opening to the closing of the camera shutter, which determines the time length for the camera photosensitive element to receive light. In the embodiment of the present application, the reference exposure time is different from the multiple adjusted exposure times. The reference exposure time is usually set in advance under ideal conditions. Shooting under the reference exposure time can obtain the corresponding reference exposure image. For example, shooting an image under the reference exposure time A can obtain a reference exposure image with a brightness value of a.

[0067] It should be noted that the system programming in the vehicle-mounted embedded system has limited processing capabilities for continuous high-resolution, high-frame rate video streams. Therefore, the driving recorder cannot adjust the reference exposure time at all times through backward feedback. Therefore, the reference exposure time in the embodiment of the present application can be set in advance according to actual conditions, so that corresponding multiple adjusted exposure times can be obtained based on the reference exposure time. The embodiment of the present application does not limit the specific value of the reference exposure time.

[0068] The adjusted exposure duration is obtained by dynamic adjustment based on the reference exposure duration. For example, when the reference exposure duration is value B, the specific values ​​of the multiple adjusted exposure durations may be 1.2B, 1.5B, and 2B; or, when the reference exposure duration is value B, the specific values ​​of the multiple adjusted exposure durations may be 0.8B, 0.5B, and 0.2B; or, when the reference exposure duration is value B, the specific values ​​of the multiple adjusted exposure durations may be 0.2B, 0.8B, and 2B. The embodiment of the present application does not limit the specific values ​​of the adjusted exposure duration. Moreover, shooting under each adjusted exposure duration can obtain the corresponding adjusted exposure image.

[0069] In some embodiments, the multiple adjusted exposure durations are obtained by following steps 201 to 203:

[0070] Step 201, determining a target time period from a plurality of preset time periods according to the current recording time.

[0071] Step 202 : selecting a first dynamic adjustment value from a plurality of preset dynamic adjustment values ​​based on a target time period, and multiplying the first dynamic adjustment value by a preset length value to obtain a long exposure duration, wherein the long exposure duration is greater than a reference exposure duration.

[0072] Step 203: Select a second dynamic adjustment value from a plurality of preset dynamic adjustment values ​​based on a target time period, and multiply the second dynamic adjustment value by a preset short value to obtain a short exposure duration, wherein the short exposure duration is less than a reference exposure duration, and the plurality of adjusted exposure durations include at least one long exposure duration and at least one short exposure duration.

[0073] Steps 201 to 203 are described in detail below.

[0074] Among them, the embodiment of the present application presets multiple time periods. For example, the time periods can be divided into morning, afternoon, evening and night. If the current recording time is 15:00, then the corresponding target time period can be determined to be afternoon.

[0075] It should be noted that the specific division rules of the target time period can be adaptively adjusted according to different regions and different natural lighting conditions, and the embodiments of the present application do not limit this.

[0076] The preset long value is a preset longer exposure time value, for example, when the reference exposure time is a D value, the preset long value may be 2D; the preset short value is a preset shorter exposure time value, for example, when the reference exposure time is a D value, the preset short value may be 0.5D; the preset dynamic adjustment value includes a series of different values, such as the dynamic adjustment value includes a value of 0.6, a value of 0.8, a value of 1, and a value of 1.2. For example, if the current target time period is at night, it can be considered that the brightness values ​​of the exposure images captured in the target time period are all low, so a larger dynamic adjustment value can be selected in the target time period to achieve the purpose of increasing the exposure time adjustment, so as to increase the image brightness value of the exposure adjustment image. In this case, the value 1 can be selected as the first dynamic adjustment value, and the value 1.2 can be selected as the second dynamic adjustment value, so as to obtain a long exposure time of 2D and a short exposure time of 0.6D.

[0077] Furthermore, in addition to selecting a single first dynamic adjustment value and a second dynamic adjustment value, multiple first dynamic adjustment values ​​can also be selected and multiplied with a preset long value to obtain multiple long exposure times, and images can be captured based on the multiple long exposure times to obtain adjusted exposure images with different brightness values; similarly, multiple second dynamic adjustment values ​​can also be selected and multiplied with a preset short value to obtain multiple short exposure times, and images can be captured based on the multiple short exposure times to obtain adjusted exposure images with different brightness values; in this way, when the reference exposure image is subsequently adjusted, the processing device can select more suitable adjusted license plate information from the same sub-monitoring area of ​​multiple adjusted exposure images as the calibration license plate information based on the brightness values ​​of each sub-monitoring area of ​​the reference exposure image, thereby improving the clarity of the license plate information in the fused target exposure image.

[0078] It should be noted that the dynamic adjustment value can be adjusted and optimized according to the specific model, lens type, aperture size and other parameters of the camera to ensure that the best exposure effect can be obtained under different configurations. That is, the embodiment of the present application does not limit the specific value of the dynamic adjustment value, and adaptive adjustments can be made according to actual conditions.

[0079] It is understandable that, due to the different sensitivity and requirements of the camera or image capture device to light in different time periods, multiple adjusted exposure durations are adaptively obtained through the current recording moment, so that the brightness values ​​of the multiple adjusted exposure images obtained are more matched with the reference exposure image. For example, in the afternoon, the natural light is strong, and when the reference exposure duration is C, the adjusted exposure duration can be 1.5C to avoid the brightness value of the adjusted exposure image obtained under too long an exposure duration being too high; while in the evening, the natural light is weak, and when the reference exposure duration is C, the adjusted exposure duration can be 2C, and the brightness value of the adjusted exposure image obtained is enhanced by extending the exposure duration. In this way, the processing device can shoot multiple adjusted exposure images that are more suitable for the current environment by adaptively obtaining the adjusted exposure duration, so that the processing device can then select a more suitable one for the reference license plate information as the calibration license plate information for fusion, thereby ensuring the quality of the target exposure image finally obtained.

[0080] In another embodiment, the target time period is afternoon, and the natural light intensity is high. All license plate information in the reference exposure image captured by the camera is in a state of overexposure. In this case, multiple second dynamic adjustment values ​​can be selected from multiple preset dynamic adjustment values, and multiple second dynamic adjustment values ​​can be multiplied by the preset short value to obtain different short exposure durations; then, shooting is performed under different short exposure durations to obtain adjusted exposure images with different brightness values. It can be understood that the brightness value of each adjusted exposure image is lower than that of the reference exposure image, so that the brightness value of the reference exposure image can be adjusted in the same sub-monitoring area of ​​different adjusted exposure images.

[0081] In some embodiments, the multiple adjusted exposure durations are obtained by following the steps, which include the following steps 301 to 303:

[0082] Step 301: If the current recording time is a preset interval correction time, an average exposure value of the reference exposure image is determined based on the grayscale values ​​of all pixels in the reference exposure image.

[0083] Step 302: Select a third dynamic adjustment value from a plurality of preset dynamic adjustment values ​​based on the average exposure value, and multiply the third dynamic adjustment value by a preset length value to obtain a long exposure duration, wherein the long exposure duration is greater than a reference exposure duration.

[0084] Step 303: Select a fourth dynamic adjustment value from a plurality of preset dynamic adjustment values ​​based on the average exposure value, and multiply the fourth dynamic adjustment value by a preset short value to obtain a short exposure duration, wherein the short exposure duration is less than a reference exposure duration, and the plurality of adjusted exposure durations include at least one long exposure duration and at least one short exposure duration.

[0085] Steps 301 to 303 are described in detail below.

[0086] The processing device automatically triggers an interval correction moment at a certain interval, which may be once every five minutes; or, the moment when a significant change in light conditions is detected is determined as the interval correction moment. If the current recording moment is the preset interval correction moment, the corresponding average exposure value is determined based on the reference exposure image obtained at the current recording moment, wherein the average exposure value refers to the average value of the grayscale values ​​of all pixels in the reference exposure image, which reflects the overall brightness level of the reference exposure image. By determining the current brightness value of the reference exposure image at the interval correction moment, the subsequent adjusted exposure duration is adaptively adjusted to avoid the situation where the adjusted exposure image taken later is incompatible with the reference exposure image, thereby improving the efficiency of the subsequent fusion of the reference exposure image and the adjusted exposure image.

[0087] Furthermore, by obtaining the average exposure value corresponding to the currently captured reference exposure image at the interval correction moment, the driving environment of the target vehicle at the current moment is determined, so as to determine the dynamic adjustment value in the next period of time, thereby better adapting to the changing driving environment. For example, when the target vehicle enters a tunnel at a certain recording moment, the processing device senses that the surrounding light conditions have changed significantly, enters the interval correction moment, and obtains the average exposure value of the reference exposure image captured at the current recording moment; then, the processing device selects the third dynamic adjustment value and the fourth dynamic adjustment value from the multiple dynamic adjustment values ​​based on the average exposure value, so as to determine the corresponding long exposure duration and short exposure duration.

[0088] Similar to step 202 to step 203, the preset long value is a preset longer exposure time value, for example, when the reference exposure time is a value of D, the preset long value may be 2D; the preset short value is a preset shorter exposure time value, for example, when the reference exposure time is a value of D, the preset short value may be 0.5D; the preset dynamic adjustment value includes a series of different values, such as the dynamic adjustment value includes a value of 0.6, a value of 0.8, a value of 1, and a value of 1.2. For example, the average exposure value of the reference exposure image captured under the reference exposure time D is 50, which belongs to the dim range, so the purpose of increasing the adjusted exposure time can be achieved by selecting a dynamic adjustment value with a larger value, so as to increase the image brightness value of the adjusted exposure image. In this case, the value 1 can be selected as the third dynamic adjustment value, and the value 1.2 can be selected as the fourth dynamic adjustment value, so as to obtain a long exposure time of 2D and a short exposure time of 0.6D.

[0089] It should be noted that the brightness range to which the average exposure value belongs can be set according to actual conditions, and the embodiments of the present application do not limit this.

[0090] Furthermore, in addition to selecting a single third dynamic adjustment value and a fourth dynamic adjustment value, multiple third dynamic adjustment values ​​can be selected and multiplied with a preset long value to obtain multiple long exposure durations, and images can be taken based on multiple long exposure durations to obtain adjusted exposure images with different brightness values; similarly, multiple fourth dynamic adjustment values ​​can be selected and multiplied with a preset short value to obtain multiple short exposure durations, and images can be taken based on multiple short exposure durations to obtain adjusted exposure images with different brightness values; in this way, when the reference exposure image is subsequently adjusted, the processing device can select more appropriate adjusted license plate information from the same sub-monitoring area of ​​the multiple adjusted exposure images as the calibration license plate information based on the brightness values ​​of each sub-monitoring area of ​​the reference exposure image, thereby improving the clarity of the license plate information in the fused target exposure image. In addition, the method for determining the long exposure duration and the short exposure duration in steps 302 to 303 is similar to steps 202 to 203, and will not be repeated here.

[0091] It can be understood that, in step 302 to step 303, when the processing device does not perform backward feedback to continuously adjust the exposure time, by obtaining the average exposure value of the reference exposure image at the interval correction time to determine the third dynamic adjustment value and the fourth dynamic adjustment value for the next time, the adaptive dynamic setting of the exposure time can be achieved with less computing power resources; in step 202 to step 203, the first dynamic adjustment value and the second dynamic adjustment value are determined by determining the target time period of the current recording time, and the processing device does not need to determine the first dynamic adjustment value and the second dynamic adjustment value required for the next image processing according to the average exposure value of the reference exposure image currently obtained, and the computing power resources consumed are less than those of step 302 to step 303; the processing device can set the two dynamic adjustment value determination methods at the same time, and the two methods can be switched by manual setting by the user. In this way, the processing device can obtain multiple adjusted exposure images that are more matched with the reference exposure image under limited hardware and software resources, so that the reference exposure image can be processed based on the multiple adjusted exposure images to obtain the final target exposure image.

[0092] It should be noted that the time interval between two interval correction moments can be set according to actual conditions, and the embodiment of the present application does not limit this.

[0093] Step 102 : identifying reference license plate information from different sub-monitoring areas of the reference exposure image, and identifying corresponding multiple adjusted license plate information from the same sub-monitoring areas in multiple different adjusted exposure images.

[0094] The following is a detailed description of step 102.

[0095] Usually, each target vehicle is provided with a license plate at the front and rear of the vehicle. In the embodiment of the present application, the content related to the license plate in the exposure image is referred to as the license plate information. The license plate information is the unique identifier of the target vehicle and is the basis for target vehicle identification, traffic accident handling, etc. Among them, the reference license plate information is obtained based on the reference exposure image, and the multiple adjusted license plate information is obtained based on different adjusted exposure images. It can be understood that since the reference exposure image and the multiple adjusted exposure images are obtained based on different exposure times, the brightness values ​​of the reference exposure image and the multiple adjusted exposure images are different, and therefore, the brightness values ​​of the reference license plate information and the multiple adjusted license plate information are also different.

[0096] For example, Figure 4 As shown, Figure 4 It is another optional monitoring area schematic diagram of the license plate image fusion processing method provided in an embodiment of the present application, wherein a certain monitoring area S includes a sub-monitoring area E and a sub-monitoring area F, the sub-monitoring area E includes a target vehicle e, and the sub-monitoring area F includes a target vehicle f; then in this example, the reference exposure image can respectively identify the reference license plate information e1 corresponding to the target vehicle e, and the reference license plate information f1 corresponding to the target vehicle f from different sub-monitoring areas (sub-monitoring area E and sub-monitoring area F); then, multiple adjusted license plate information corresponding to the target vehicle e (such as adjusted license plate information e2, adjusted license plate information e3, etc.) and adjusted license plate information corresponding to the target vehicle f (such as adjusted license plate information f2, adjusted license plate information f3, etc.) are identified from the same sub-monitoring areas (sub-monitoring area E and sub-monitoring area F) in multiple different adjusted exposure images; it can be understood that the reference license plate information and the multiple adjusted license plate information indicate the same license plate content of the target vehicle, but the brightness values ​​of each license plate information are different.

[0097] In some embodiments, identifying and obtaining corresponding multiple adjusted license plate information from the same sub-monitoring area in multiple different adjusted exposure images includes the following steps 401 to 402:

[0098] Step 401, determining a first sub-monitoring area in the long exposure image that is the same as the sub-monitoring area where the reference license plate information is located, and identifying and obtaining the long exposure license plate information from the first sub-monitoring area.

[0099] Step 402, determine a second sub-monitoring area in the short-exposure image that is the same as the sub-monitoring area where the reference license plate information is located, and identify the short-exposure license plate information from the second sub-monitoring area, wherein the adjusted license plate information includes the long-exposure license plate information and the short-exposure license plate information, and the adjusted license plate information corresponds to the license plate content of the reference license plate information.

[0100] Steps 401 to 402 are described in detail below.

[0101] In some embodiments, when the ambient light is unstable, the reference exposure image captured by the camera is usually unevenly distributed in brightness. For example, at night, when the target vehicle turns on the headlights, the brightness of the license plate illuminated by the light emitted by the headlights will be high, while the brightness of the license plate not illuminated by the light emitted by the headlights will be low. If the overall brightness of the reference exposure image is adjusted by obtaining the long exposure image and the short exposure image corresponding to the reference exposure image, no matter how it is fused, there will always be problems of local overexposure or underexposure. Based on this, after obtaining the reference exposure image and the corresponding multiple adjusted exposure images, the embodiment of the present application fuses and splices the license plate information in each sub-monitoring area in the reference exposure image separately, so that the brightness value of each license plate information can be pixel-compensated based on its own brightness, ensuring that the brightness values ​​of all license plate information in the final target exposure image are bright and moderate, so that the target exposure image can present an appropriate contrast, thereby retaining the detail information in the image and improving the clarity of the target exposure image.

[0102] For example, firstly, the reference license plate information is identified from a sub-monitoring area of ​​the reference exposure image. Figure 4 For example, the reference license plate information e1 is identified in the sub-monitoring area E of the reference exposure image; then, the sub-monitoring area E2 (first sub-monitoring area) with the same position as the sub-monitoring area E is determined in the long exposure image. It can be understood that the sub-monitoring area E and the sub-monitoring area E2 are the same position of two different images, and the long exposure license plate information e2 is identified from the sub-monitoring area E2 of the long exposure image; similarly, the sub-monitoring area E3 with the same position as the sub-monitoring area E is determined in the short exposure image. It can be understood that the sub-monitoring area E and the sub-monitoring area E3 (second sub-monitoring area) are the same position of two different images, and the short exposure license plate information e3 is identified from the sub-monitoring area E3 of the short exposure image. It can be understood that the reference license plate information e1, the long exposure license plate information e2, and the short exposure license plate information e3 all identify the same license plate content, but the brightness value of each license plate content in each image is different.

[0103] Step 103, according to the reference brightness value corresponding to each reference license plate information, select the corresponding calibration license plate information from the multiple adjusted license plate information, fuse each reference license plate information and the corresponding calibration license plate information, and obtain the sub-exposure image under the sub-monitoring area.

[0104] The following is a detailed description of step 103.

[0105] In some embodiments, if the reference brightness value corresponding to the reference license plate information is bright, the adjusted license plate information with a lower brightness value is selected from the multiple adjusted license plate information as the calibration license plate information corresponding to the reference license plate information; if the reference brightness value corresponding to the reference license plate information is dark, the adjusted license plate information with a higher brightness value is selected from the multiple adjusted license plate information as the calibration license plate information corresponding to the reference license plate information. In this way, the brightness value of the reference license plate information in each sub-monitoring area of ​​the reference exposure image is selected from the multiple adjusted license plate information with different brightness values ​​to complete the subsequent image fusion operation, avoiding the problem of partial overexposure or underexposure of the image caused by the overall brightness adjustment of the reference exposure image.

[0106] In some embodiments, according to the reference brightness value corresponding to each reference license plate information, corresponding calibration license plate information is selected from a plurality of adjusted license plate information, including the following steps 501 to 502:

[0107] Step 501 : when the number of long-exposure license plate information is one and the reference brightness value is within a preset dim threshold, the long-exposure license plate information is selected as the calibration license plate information.

[0108] Step 502 : When the number of short-exposure license plate information is one and the reference brightness value is within a preset brightness threshold, the short-exposure license plate information is selected as the calibration license plate information.

[0109] Steps 501 to 502 are described in detail below.

[0110] In some embodiments, if the adjusted exposure image includes only one long exposure image and one short exposure image, then for the same sub-monitoring area, the number of long exposure license plate information and short exposure license plate information corresponding to the reference license plate information is both one; at this time, the range of the brightness value of the reference license plate information is determined, and if the reference brightness value is within a preset dim threshold, the long exposure license plate information is selected as the calibration license plate information, otherwise, the short exposure license plate information is selected as the calibration license plate information.

[0111] Furthermore, both the dim threshold and the bright threshold are preset. For example, in standard 8-bit color depth image processing, [0,65] can be determined as the preset dim threshold, and (190,255] can be determined as the preset bright threshold. In addition, if the reference brightness value corresponding to the reference license plate information is within the range of [65,190], it is considered that the brightness value of the reference license plate information is moderately bright, and there is no need to select its corresponding calibration license plate information for subsequent image fusion processing, so as to further speed up the efficiency of generating the target exposure image based on the processing method proposed in the embodiment of the present application.

[0112] It should be noted that the dim threshold and the bright threshold can be adaptively adjusted according to actual conditions, and the embodiments of the present application do not limit this.

[0113] In some embodiments, according to the reference brightness value corresponding to each reference license plate information, corresponding calibration license plate information is selected from a plurality of adjusted license plate information, and the following steps 601 to 604 are also included:

[0114] Step 601: When there are multiple long-exposure license plate information and multiple short-exposure license plate information, the multiple long-exposure license plate information are divided into different long exposure levels based on the long exposure duration, and the multiple short-exposure license plate information are divided into different short exposure levels based on the short exposure duration.

[0115] Step 602: Determine the brightness level corresponding to the reference brightness value.

[0116] Step 603 , if the reference brightness value is within the preset dim threshold, a target long exposure level matching the brightness level is determined from a plurality of long exposure levels, and long exposure license plate information corresponding to the target long exposure level is selected as the calibration license plate information.

[0117] Step 604 , if the reference brightness value is within the preset brightness threshold, a target short exposure level matching the brightness level is determined from a plurality of short exposure levels, and short exposure license plate information corresponding to the target short exposure level is selected as calibration license plate information.

[0118] Steps 601 to 604 are described in detail below.

[0119] In some embodiments, if the adjusted exposure image includes multiple long-exposure images and multiple short-exposure images, then for the same sub-monitoring area, the number of long-exposure license plate information and short-exposure license plate information corresponding to the reference license plate information is multiple; in this case, if the brightness value of the reference license plate information is brighter, it is necessary to select a more suitable one from the multiple long-exposure license plate information, otherwise it is necessary to select a more suitable one from the multiple short-exposure license plate information. In this way, the granularity of the selection of the calibration license plate information is improved, thereby improving the clarity of the sub-exposure image obtained by the subsequent fusion of each reference license plate information and the corresponding calibration license plate information.

[0120] Further, in order to better select the calibration license plate information from the multiple long exposure images and the multiple short exposure images, the multiple long exposure license plate information is divided into different long exposure levels in advance, and the basis for the division may be the long exposure time; specifically, the longer the long exposure time, the higher the brightness value of the corresponding long exposure license plate information, so the long exposure license plate information obtained under different long exposure times may be set as different long exposure levels. Exemplarily, the long exposure license plate information A1 obtained under the long exposure time T1 is determined to be the first long exposure level, and the long exposure license plate information A2 obtained under the long exposure time T2 is determined to be the second long exposure level, wherein the long exposure time T1 is greater than the long exposure time T2; the short exposure license plate information B1 obtained under the short exposure time T3 is determined to be the first short exposure level, and the short exposure license plate information B2 obtained under the short exposure time T4 is determined to be the second short exposure level, wherein the short exposure time T3 is greater than the short exposure time T4.

[0121] Further, determine the brightness level to which the reference brightness value belongs. For example, the brightness levels include a first dim level, a second dim level, a moderate level, a second bright level, and a first bright level (brightness values ​​are from low to high), and the first dim level and the second dim level belong to the dim threshold, and the first bright level and the second bright level belong to the bright threshold.

[0122] Exemplarily, if the reference brightness value is 50, it is determined that the brightness level of the reference brightness value is the first dim level and is within the dim threshold, so the first long exposure level is selected as the target long exposure level, and the long exposure license plate information corresponding to the target long exposure level (first long exposure level) is determined to be the calibration license plate information; if the reference brightness value is 190, it is determined that the brightness level of the reference brightness value is the first bright level and is within the bright threshold, so the first short exposure level is selected as the target short exposure level, and the short exposure license plate information corresponding to the target short exposure level (first short exposure level) is determined to be the calibration license plate information.

[0123] It should be noted that the specific division rules of the multiple long exposure levels and the multiple short exposure levels can be set according to actual conditions, and the embodiments of the present application do not impose specific limitations thereon.

[0124] In some embodiments, fusing each reference license plate information with the corresponding calibration license plate information to obtain a sub-exposure image under the sub-monitoring area includes the following steps 701 to 703:

[0125] Step 701: extract multiple reference license plate features from reference license plate information based on preset reference weights.

[0126] Step 702: extract multiple calibration license plate features from the calibration license plate information based on preset calibration weights.

[0127] Step 703: Align the reference license plate features and the calibration license plate features that match in spatial position one by one, and determine that the aligned image is the sub-exposure image of the sub-monitoring area.

[0128] Steps 701 to 703 are described in detail below.

[0129] The preset reference weight is used to indicate the proportion of features extracted from the reference license plate information, and the preset calibration weight is used to indicate the proportion of features extracted from the calibration license plate information. Further, based on the preset reference weight, a feature extraction operation is performed on the reference license plate information to obtain a plurality of reference license plate features; based on the preset calibration weight, a feature extraction operation is performed on the calibration license plate information to obtain a plurality of calibration license plate features.

[0130] It should be noted that the reference weight and the calibration weight can be set according to actual conditions, and the embodiments of the present application do not limit this.

[0131] Furthermore, due to different exposure times, there will be slight deviations in the position of the target vehicle's license plate information in the reference exposure image and multiple calibration exposure images. In order to improve the clarity of the final output target exposure image, the reference license plate features and the calibration license plate features need to be aligned one by one. This operation ensures the consistency of key features of the license plate images taken under different exposure conditions. The alignment operation eliminates image displacement or deformation caused by differences in exposure time, and obtains a sub-exposure image with higher clarity after alignment.

[0132] Step 104 , stitching a plurality of sub-exposure images from different sub-monitoring areas to obtain a target exposure image after brightness adjustment of the monitoring area.

[0133] Step 104 is described in detail below.

[0134] In some embodiments, after the corresponding sub-exposure images of each sub-monitoring area are obtained by fusion, all sub-exposure images are spliced ​​to obtain a target exposure image after the brightness of the monitoring area is adjusted. It can be understood that by selecting appropriate calibration license plate information according to the actual brightness value of each sub-monitoring area, it is ensured that the target exposure image finally spliced ​​is more uniform in brightness and has clearer details. That is, the processing method proposed in the present application effectively overcomes the overexposure or underexposure problem that may occur under a single exposure setting, is more adaptable to the complex light scenes encountered by the target vehicle during actual driving, and improves the overall quality of the target exposure image obtained under different light scenes.

[0135] like Figure 5 As shown, Figure 5: is an optional functional module diagram of a license plate image fusion processing device provided in an embodiment of the present application, wherein the license plate image fusion processing device may include:

[0136] The acquisition module 801 is used to acquire, within the same monitoring area, a reference exposure image under a preset reference exposure time and a plurality of adjusted exposure images corresponding to a plurality of different adjusted exposure times, wherein the adjusted exposure time is different from the reference exposure time, and the monitoring area includes a plurality of sub-monitoring areas.

[0137] The identification module 802 is used to identify reference license plate information from different sub-monitoring areas in the reference exposure image, and to identify corresponding multiple adjusted license plate information from the same sub-monitoring areas in multiple different adjusted exposure images.

[0138] The fusion module 803 is used to select corresponding calibration license plate information from multiple adjusted license plate information according to the reference brightness value corresponding to each reference license plate information, fuse each reference license plate information and the corresponding calibration license plate information, and obtain a sub-exposure image under the sub-monitoring area.

[0139] The stitching module 804 is used to stitch multiple sub-exposure images from different sub-monitoring areas to obtain a target exposure image after brightness adjustment of the monitoring area. In the same monitoring area, a reference exposure image under a preset reference exposure time and multiple adjusted exposure images corresponding to multiple different adjusted exposure times are obtained, wherein the adjusted exposure time is obtained by dynamically adjusting the reference exposure time, and the monitoring area includes multiple sub-monitoring areas.

[0140] The fusion processing method, device, equipment and storage medium of the license plate image proposed in the present application obtains a reference exposure image under a preset reference exposure time and multiple corresponding adjusted exposure images under multiple different adjusted exposure time in the same monitoring area, wherein the adjusted exposure time is different from the reference exposure time, and the monitoring area includes multiple sub-monitoring areas; identifies reference license plate information from different sub-monitoring areas of the reference exposure image, and identifies corresponding multiple adjusted license plate information from the same sub-monitoring area in multiple different adjusted exposure images; selects corresponding calibration license plate information from multiple adjusted license plate information according to the reference brightness value corresponding to each reference license plate information, fuses each reference license plate information and the corresponding calibration license plate information, and obtains the sub-exposure image under the sub-monitoring area; splices multiple sub-exposure images from different sub-monitoring areas to obtain the target exposure image after the brightness of the monitoring area is adjusted. It can be understood that when the ambient light is unstable, the reference exposure image captured by the camera is usually unevenly distributed in brightness. For example, at night, if the target vehicle turns on its headlights, the brightness of the license plate illuminated by the headlights will be higher, while the brightness of the license plate not illuminated by the headlights will be lower. If the overall brightness of the reference exposure image is adjusted by obtaining the corresponding long exposure image and short exposure image of the reference exposure image, no matter how they are fused, there will always be problems of local overexposure or underexposure. Based on this, after obtaining the reference exposure image and the corresponding multiple adjusted exposure images, the embodiment of the present application fuses and splices the license plate information in each sub-monitoring area in the reference exposure image, so that the brightness value of each license plate information can be pixel-compensated based on its own brightness, ensuring that the brightness values ​​of all license plate information in the final target exposure image are bright and moderate, so that the target exposure image can present an appropriate contrast, thereby retaining the detail information in the image, improving the clarity of the target exposure image, and improving the image quality of the output target exposure image.

[0141] The specific implementation of the license plate image fusion processing device is basically the same as the specific implementation of the license plate image fusion processing method mentioned above, and will not be repeated here.

[0142] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above license plate image fusion processing method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0143] like Figure 6 As shown, Figure 6 : is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application, the electronic device includes:

[0144] The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0145] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 calls and executes the license plate image fusion processing method of the embodiment of this application;

[0146] Input / output interface 903, used to implement information input and output;

[0147] Communication interface 904, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WI FI, Bluetooth, etc.);

[0148] A bus 905 that transmits information between the various components of the device (e.g., the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0149] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0150] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned license plate image fusion processing method.

[0151] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory 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 embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor 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.

[0152] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0153] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0154] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0156] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0157] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0158] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0159] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0160] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0161] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0162] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A fusion processing method for license plate images, characterized in that: The method comprises: In the same monitoring area, a reference exposure image under a preset reference exposure time and a plurality of adjusted exposure images corresponding to a plurality of different adjusted exposure time are obtained, wherein the adjusted exposure time is different from the reference exposure time, and the monitoring area includes a plurality of sub-monitoring areas; Identify reference license plate information from different sub-monitoring areas of the reference exposure image, and identify corresponding multiple adjusted license plate information from the same sub-monitoring areas in multiple different adjusted exposure images; According to the reference brightness value corresponding to each of the reference license plate information, corresponding calibration license plate information is selected from the plurality of adjusted license plate information, and each of the reference license plate information and the corresponding calibration license plate information are fused to obtain a sub-exposure image under the sub-monitoring area; The plurality of sub-exposure images from different sub-monitoring areas are stitched together to obtain a target exposure image after brightness adjustment of the monitoring area.

2. The method according to claim 1, characterized in that The plurality of adjusted exposure durations are obtained by the following steps, which include: According to the current recording time, a target time period is determined from a plurality of preset time periods; Selecting a first dynamic adjustment value from a plurality of preset dynamic adjustment values ​​based on the target time period, and multiplying the first dynamic adjustment value by a preset length value to obtain a long exposure duration, wherein the long exposure duration is greater than the reference exposure duration; A second dynamic adjustment value is selected from a plurality of preset dynamic adjustment values ​​based on the target time period, and the second dynamic adjustment value is multiplied by a preset short value to obtain a short exposure duration, wherein the short exposure duration is less than the reference exposure duration, and the plurality of adjusted exposure durations include at least one of the long exposure durations and at least one of the short exposure durations.

3. The method according to claim 1, characterized in that The plurality of adjusted exposure durations are obtained by the following steps, which include: If the current recording time is the preset interval correction time, determining the average exposure value of the reference exposure image based on the grayscale values ​​of all pixels in the reference exposure image; Selecting a third dynamic adjustment value from a plurality of preset dynamic adjustment values ​​based on the average exposure value, and multiplying the third dynamic adjustment value by a preset long value to obtain a long exposure duration, wherein the long exposure duration is greater than the reference exposure duration; A fourth dynamic adjustment value is selected from a plurality of preset dynamic adjustment values ​​based on the average exposure value, and a short exposure duration is obtained by multiplying the fourth dynamic adjustment value by a preset short value, wherein the short exposure duration is less than the reference exposure duration, and the plurality of adjusted exposure durations include at least one of the long exposure durations and at least one of the short exposure durations.

4. The method according to claim 2, characterized in that: The adjusted exposure image includes at least one long exposure image and at least one short exposure image, wherein the long exposure image is obtained by shooting at the long exposure time, and the short exposure image is obtained by shooting at the short exposure time; The step of identifying and obtaining corresponding multiple adjusted license plate information from the same sub-monitoring area in multiple different adjusted exposure images includes: Determine a first sub-monitoring area in the long-exposure image that is the same as the sub-monitoring area where the reference license plate information is located, and identify and obtain the long-exposure license plate information in the first sub-monitoring area; Determine a second sub-monitoring area in the short-exposure image that is the same as the sub-monitoring area where the reference license plate information is located, and identify short-exposure license plate information from the second sub-monitoring area, wherein the adjusted license plate information includes the long-exposure license plate information and the short-exposure license plate information, and the adjusted license plate information corresponds to the license plate content of the reference license plate information.

5. The method according to claim 4, characterized in that The step of selecting corresponding calibration license plate information from the plurality of adjusted license plate information according to the reference brightness value corresponding to each reference license plate information comprises: When the number of the long-exposure license plate information is one and the reference brightness value is within a preset dim threshold, selecting the long-exposure license plate information as the calibration license plate information; When the number of the short-exposure license plate information is one and the reference brightness value is within a preset brightness threshold, the short-exposure license plate information is selected as the calibration license plate information.

6. The method according to claim 4, characterized in that The selecting corresponding calibration license plate information from the plurality of adjustment license plate information respectively according to the reference brightness value corresponding to each reference license plate information also includes: When there are multiple long-exposure license plate information and multiple short-exposure license plate information, the multiple long-exposure license plate information are divided into different long exposure levels based on the long exposure duration, and the multiple short-exposure license plate information are divided into different short exposure levels based on the short exposure duration; Determining a brightness level corresponding to the reference brightness value; If the reference brightness value is within a preset dim threshold, determining a target long exposure level that matches the brightness level from the plurality of long exposure levels, and selecting the long exposure license plate information corresponding to the target long exposure level as the calibration license plate information; If the reference brightness value is within a preset brightness threshold, a target short exposure level matching the brightness level is determined from the multiple short exposure levels, and short exposure license plate information corresponding to the target short exposure level is selected as calibration license plate information.

7. The method according to claim 1, characterized in that The fusing each of the reference license plate information and the corresponding calibration license plate information to obtain a sub-exposure image under the sub-monitoring area includes: Extracting a plurality of reference license plate features from the reference license plate information based on preset reference weights; Extracting a plurality of calibration license plate features from the calibration license plate information based on preset calibration weights; The reference license plate features and the calibration license plate features that match in spatial position are aligned one by one, and the image after alignment is determined to be the sub-exposure image under the sub-monitoring area.

8. A fusion processing device for license plate images, characterized in that: The device comprises: an acquisition module, configured to acquire, within the same monitoring area, a reference exposure image under a preset reference exposure duration and a plurality of adjusted exposure images corresponding to a plurality of different adjusted exposure durations, wherein the adjusted exposure duration is different from the reference exposure duration, and the monitoring area includes a plurality of sub-monitoring areas; an identification module, configured to identify reference license plate information from different sub-monitoring areas of the reference exposure image, and to identify corresponding multiple adjusted license plate information from the same sub-monitoring areas in multiple different adjusted exposure images; A fusion module, configured to select corresponding calibration license plate information from the plurality of adjusted license plate information according to a reference brightness value corresponding to each of the reference license plate information, and fuse each of the reference license plate information with the corresponding calibration license plate information to obtain a sub-exposure image under the sub-monitoring area; A splicing module is used to splice multiple sub-exposure images from different sub-monitoring areas to obtain a target exposure image after brightness adjustment of the monitoring area. In the same monitoring area, a reference exposure image under a preset reference exposure time and multiple adjusted exposure images corresponding to multiple different adjusted exposure time are obtained, wherein the adjusted exposure time is obtained by dynamic adjustment based on the reference exposure time, and the monitoring area includes multiple sub-monitoring areas.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the license plate image fusion processing method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the license plate image fusion processing method according to any one of claims 1 to 7 is implemented.

Images