Computer image processing system adopting intelligent identification technology

Abstract

The invention relates to the technical field of image processing, in particular to a computer image processing system adopting an intelligent recognition technology, which comprises the following steps: when a target moves, acquiring each frame of image of a video stream containing features, and extracting quality data of each frame of image; identifying and classifying all the frame images according to the quality evaluation value to obtain a high-quality image or a low-quality image; and determining whether image acquisition is qualified or not according to the identified high-quality image magnitude. When it is determined that the image acquisition is qualified, the image with the maximum quality evaluation value in the video stream is identified; based on an unqualified image acquisition signal, obtaining the generation time of a high-quality image, carrying out time continuity identification, and judging an image processing related signal; determining an acquisition angle corresponding to a high-quality time period as image data of subsequent image processing based on the equipment regulation and control signal and according to the moving speed of the target; according to the method, the optimization capability of image quantity processing is realized, and the optimization capability of image quality processing is also realized.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a computer image processing system adopting intelligent recognition technology. Background Art

[0002] In the existing field of image technology, when processing images using computer processing technology, firstly, an image sensor is used to sense and collect the image, and then a subsequent processing circuit is used to process the collected image signal, and then the collected image signal is restored into an image in the computer and saved; At present, images are usually collected from a certain perspective without considering the impact of speed on image quality for high-speed moving targets. How to determine the collection time based on the computer's image recognition results to enhance the computer's image processing capabilities is an urgent problem that needs to be solved. Summary of the invention

[0003] The purpose of the present invention is to provide a computer image processing system using intelligent recognition technology. The technical problem solved by the present invention is: how to determine the acquisition time according to the computer's image recognition results to enhance the computer's image processing capabilities.

[0004] The purpose of the present invention can be achieved through the following technical solutions: A computer image processing system using intelligent recognition technology includes the following modules: Image data acquisition module: When the target moves, each frame of the video stream containing features is acquired, and the quality data of each frame is extracted; Image data processing module: perform data analysis based on the quality data of each frame of image extracted, output the quality evaluation value of each frame of image, identify and classify all frame images according to the quality evaluation value to obtain high-quality images or low-quality images; and determine whether the image acquisition is qualified based on the level of the identified high-quality image; Image data recognition module: when the image acquisition qualified signal is determined, the image with the maximum quality evaluation value in the video stream is identified; Related impact identification module: Based on the unqualified image acquisition signal, obtain the generation time of high-quality images, perform time continuity identification, and determine the image processing related signals; Among them, the image processing related signals include device control signals; Optimization control module: Based on the device control signal and the speed of the target movement, the acquisition angle corresponding to the high-quality period is determined as the image data for subsequent image processing.

[0005] As a technical solution of the present invention: the quality data of each frame of image includes: an angle deviation value for measuring the degree of image distortion, a font deformation value for measuring the degree of feature deformation, and a regional blur value for measuring the degree of image blur.

[0006] As a technical solution of the present invention: all frame images are identified and classified according to the quality evaluation value, including: The angle deviation value, the font deformation value and the area blur value are processed to obtain the quality evaluation value of each frame of the image; Analyze the quality assessment value of each frame image with the quality assessment threshold: If the quality assessment value is greater than or equal to the quality assessment threshold, a high-quality image is generated; If the quality assessment value is less than the quality assessment threshold, a high-quality image is generated.

[0007] As a technical solution of the present invention: the process of determining whether the image acquisition is qualified is as follows: Get the ratio of the total number of high-quality image frames in the video stream and obtain the magnitude of high-quality images; comparing the high-quality image magnitude to a high-quality image magnitude threshold; If the high-quality image level is greater than or equal to the high-quality image level threshold, an image acquisition qualified signal is generated; If the high-quality image level is less than the high-quality image level threshold, an image acquisition failure signal is generated.

[0008] As a technical solution of the present invention: the image data recognition module specifically includes: When the image acquisition is determined to be qualified, the images of all frames in the video stream are compared according to the quality evaluation value, the image with the maximum quality evaluation value is extracted, marked as the detection image, and the key information in the detection image is extracted.

[0009] As a technical solution of the present invention: the relevant impact identification module includes: When a signal based on image acquisition failure is obtained, the generation time of the high-quality image is obtained; and it is determined whether the generation time of the high-quality image is continuously generated in the video stream; If the generation time of high-quality images appears continuously in the video stream, the time period during which high-quality images are continuously generated will be marked as a high-quality time period, and a device control signal will be generated at the same time.

[0010] As a technical solution of the present invention: if the generation time of the high-quality image does not appear to be continuously generated in the video stream, a device detection signal is generated.

[0011] As a technical solution of the present invention: the optimization control module includes: When the device control signal is obtained, the high-quality image area where the target moves is determined according to the movement of the target in the high-quality time period, the acquisition time before the high-quality time period, and the acquisition time after the high-quality time period, and then the acquisition viewing angle of the high-quality image area is used as image data for subsequent image processing.

[0012] As a technical solution of the present invention: the process of determining the acquisition angle corresponding to the high-quality time period includes: Get the start time and end time of the high-quality time period; The start time of the high-quality time period is calculated by difference with the start time of the snapshot time to obtain the high opening time difference; the start time of the high-quality time period is calculated by difference with the end time of the snapshot time to obtain the high closing time difference; Then, the average speed in the high opening time difference, high quality time period and high closing time difference is obtained, and the average speed is multiplied with the corresponding high opening time difference, high quality time period and high closing time difference respectively to obtain the first distance L1, the second distance L2 and the third distance L3; the triangular areas constructed with the first distance L1, the second distance L2 and the third distance L3 as the base are marked as the front low-quality image area, the high-quality image area and the rear low-quality image area respectively; And, obtaining the height at which the camera device is installed, which is recorded as H, the current viewing angle of the camera device is recorded as J1, and the angle between the current viewing angle of the camera device and the vertical plane is recorded as J2; By formula , the camera device adjustment angle T2 is calculated; wherein the camera device adjustment angle T2 is the top angle of the high-quality image area.

[0013] As the technical solution of the present invention: by formula , the front side reduced viewing angle T3 of the camera device is calculated; wherein the front side reduced viewing angle T3 of the camera device is the top angle of the rear side low-quality image area; By formula , the reduced viewing angle T1 of the rear side of the camera device is calculated; wherein the reduced viewing angle T3 of the front side of the camera device is the top angle of the front low-quality image area.

[0014] Beneficial effects of the present invention: The present invention takes the moving target as the identification object, comprehensively identifies the quality of the image in the video stream through the angle deviation value, the font deformation value and the regional fuzzy value, and then feeds back the image acquisition to identify the acquisition quality; further, the best image can be identified to facilitate feature analysis for the best image; The present invention determines the factors that cause unqualified image acquisition through the impact results of image processing, and then determines the subsequent acquisition time of the moving target based on the image quality distribution using trigonometric functions. Therefore, the present invention uses intelligent recognition technology to identify the quality of the acquired image, and then determines the acquisition time based on the recognition result, thereby optimizing the computer image processing capability, not only realizing the optimization capability of image quantity processing, but also realizing the optimization capability of image quality processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below in conjunction with the accompanying drawings.

[0016] Figure 1 is a system block diagram of a computer image processing system using intelligent recognition technology in Embodiment 1 of the present invention; Figure 2 It is a principle diagram of viewing angle control of the camera device of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0018] See also Figure 1 As shown, the present invention is a computer image processing system using intelligent recognition technology, comprising the following modules: Image data acquisition module: When the target moves, each frame of the video stream containing features is acquired, and the quality data of each frame is extracted; In some embodiments, when the target is moving, a video stream containing features is collected through a video collector, and the image is divided according to the number of frames to obtain each frame of the image, and then the image quality assessment data is extracted, including an angle deviation value for measuring the degree of image distortion, a font deformation value for measuring the degree of feature deformation, and a regional blur value for measuring the degree of image blur; For example, the target may be a vehicle, and the feature may be a license plate. When the target moves, each frame of the video stream containing the feature is acquired, and the quality data of each frame is extracted. The specific process may be: On the highway, obtain the video of the license plate, divide it according to the number of frames, obtain the license plate image of each frame, and extract the angle deviation value, font deformation value and regional blur value of the license plate image; The process of extracting the angle deviation value is as follows: Get the angle between the top border of the license plate and the horizontal line, marked as the angle deviation value; The process of extracting font deformation value is: Get the number of deformed fonts in the license plate, marked as the font deformation value; The extraction process of regional fuzzy value is: Get the total area of ​​the license plate where the area is blurred, marked as the area blur value; It should be noted that the division of regional blur is as follows: the license plate image is divided into grid-type regions to obtain the contrast of each region; The contrast of each area is compared to the contrast of the standard; If the contrast is greater than or equal to the standard contrast, the area is marked as a clear area; If the contrast is less than the standard contrast, the area is marked as a blurred area; Image data processing module: perform data analysis based on the quality data of each frame of image extracted, output the quality evaluation value of each frame of image, identify and classify all frame images according to the quality evaluation value to obtain high-quality images or low-quality images; and determine whether the image acquisition is qualified based on the level of the identified high-quality image; In some embodiments, image quality data including an angle deviation value for measuring the degree of image distortion, a font deformation value for measuring the degree of feature deformation, and a regional blur value for measuring the degree of image blur are obtained, and the angle deviation value, the font deformation value, and the regional blur value are processed to obtain a quality evaluation value for each frame of the image; Analyze the quality assessment value of each frame image with the quality assessment threshold: If the quality assessment value is greater than or equal to the quality assessment threshold, a high-quality image is generated; If the quality assessment value is less than the quality assessment threshold, a high-quality image is generated; Then obtain the ratio of the total number of frames of high-quality images in the video stream to obtain the magnitude of high-quality images; comparing the high-quality image magnitude to a high-quality image magnitude threshold; If the high-quality image level is greater than or equal to the high-quality image level threshold, an image acquisition qualified signal is generated; If the high-quality image magnitude is less than the high-quality image magnitude threshold, an image acquisition failure signal is generated; For example, the angle deviation value, font deformation value and area blur value of each frame of the license plate image are obtained, which are marked as ZJ, ZB, and ZM respectively through the formula , calculate the quality value ZZi of each frame of image; where i represents the number of image frames in the video stream, a1, a2, and a3 are weight ratio coefficients, a1+a2+a3=1, the value of a1 is 0.17, the value of a2 is 0.48, and the value of a3 is 0.35; ZBz is the total number of fonts in the license plate, and ZMz is the total area of ​​the license plate; Compare the quality value ZZi of each frame image with the quality threshold of each frame image; If the quality value ZZi of each frame image is greater than or equal to the quality threshold, it means that the license plate captured by the camera on the highway has a large degree of license plate angle deviation, font deformation and image blur, that is, the license plate image quality is high, and the image is marked as a high-quality image; If the quality value ZZi of each frame image is less than the quality threshold, it means that the license plate captured by the camera on the highway has a large degree of license plate angle deviation, font deformation and image blur, that is, the license plate image quality is low, and the image is marked as a low-quality image; Based on the high-quality images, the proportion of high-quality images in the capture process is obtained, marked as a license plate capture evaluation value, and the license plate capture evaluation value is compared with the license plate capture evaluation threshold; If the license plate capture evaluation value is greater than or equal to the license plate capture evaluation threshold, it means that the number of high-quality images generated during the camera capture process on the highway accounts for a large proportion, and a high-speed camera capture qualified signal is generated; If the license plate capture evaluation value is less than the license plate capture evaluation threshold, it means that the number of high-quality images generated during the camera capture process on the highway is small, and a high-speed camera capture failure signal is generated; Specifically, in the process of obtaining the proportion of high-quality images: Obtain the total number of frames in the video capturing the license plate and the total number of frames generating high-quality images, calculate the ratio of the total number of frames of high-quality images to the total number of frames in the video capturing the license plate, and obtain the proportion of high-quality images; Image data recognition module: when the image acquisition qualified signal is determined, the image with the maximum quality evaluation value in the video stream is identified; In some embodiments, when determining that the image acquisition is qualified, images of all frames in the video stream are compared according to the quality evaluation values, an image with the maximum quality evaluation value is extracted, marked as a detection image, and key information in the detection image is extracted; Exemplarily, when a qualified signal of high-speed camera capture is obtained, the maximum quality value in the high-quality image is marked as a detection image, and then the license plate number in the detection image is extracted; The technical solution of the embodiment of the present invention is as follows: when the target moves, each frame image of the video stream containing the feature is obtained, and the quality data of each frame image is extracted; data analysis is performed based on the quality data of each frame image extracted, and a quality evaluation value of each frame image is outputted, and all frame images are identified and classified according to the quality evaluation value to obtain high-quality images or low-quality images; and according to the magnitude of the identified high-quality image, it is determined whether the image acquisition is a qualified signal, and when the image acquisition is determined to be a qualified signal, the image with the maximum quality evaluation value in the video stream is identified; the present invention takes the moving target as the identification object, comprehensively identifies the quality of the image in the video stream through the angle deviation value, the font deformation value and the regional blur value, and then feeds back the image acquisition to identify the quality of the acquisition; further, it will also be possible to identify The best image can be obtained, which is convenient for feature analysis of the best image. The present invention specifically uses a moving vehicle as a moving target and a license plate as a feature to illustrate: that is, by capturing a video of the license plate, the quality of the license plate image is detected from three aspects: angle deviation, font deformation and regional blur, and then the quality of the video in the entire capturing process is detected, thereby achieving the effect of dual detection of the license plate quality and the capturing quality, and can also output a license plate image with the best quality to ensure the accuracy of the license plate output. The problem in the prior art that, during the process of capturing the license plate of a moving vehicle by a camera on a highway, the captured license plate and the capturing process cannot be detected, resulting in the problem that the captured license plate has low quality. If an image with severe deformation and low clarity is encountered, it is difficult to distinguish the information of the vehicle license plate. Example

[0019] See also Figure 2 As shown, the present invention is a computer image processing system using intelligent recognition technology, which also includes the following steps: Related impact identification module: Based on the unqualified image acquisition signal, obtain the generation time of high-quality images, perform time continuity identification, and determine the image processing related signals; Among them, the image processing related signals include device detection signals or device control signals; In some implementation schemes: when a signal based on image acquisition failure is obtained, the generation time of the high-quality image is obtained; and it is determined whether the generation time of the high-quality image is continuously generated in the video stream; If the generation time of high-quality images appears to be continuously generated in the video stream, the time period in which high-quality images are continuously generated is marked as a high-quality time period, and a device control signal is generated at the same time; If the generation time of the high-quality image does not appear to be continuously generated in the video stream, a device detection signal is generated; For example, the overall acquisition time of the video stream is 2 seconds, and high-quality images are continuously generated in the time period of 0.22 seconds to 0.38 seconds, so the time period of 0.22 seconds to 0.38 seconds is recorded as the high-quality time period; It should be explained that the device detection signal indicates that during the highway capture process, the time when high-quality images appear is unevenly distributed during the entire capture time, which is likely caused by the unstable operation of the high-speed camera during the capture process. When the device detection signal is obtained, the high-speed camera is fault-detected; The device control signal indicates that during the highway capture process, the time when high-quality images appear is specifically distributed in a certain period of the entire capture time, which is likely caused by the poor shooting distance setting of the high-speed camera during the capture process; Optimization control module: Based on the device control signal and the target moving speed, the acquisition angle corresponding to the high-quality period is determined as the image data for subsequent image processing; In some embodiments, when a device control signal is obtained, a high-quality image area where the target moves is determined according to the movement of the target in the high-quality time period, the acquisition time before the high-quality time period, and the acquisition time after the high-quality time period, and then the acquisition angle of the high-quality image area is used as image data for subsequent image processing; Exemplarily, based on the device control signal, the viewing angle of the camera device is controlled, and the output is the reduced viewing angle T3 of the front side of the camera device, the camera device control viewing angle T2, and the reduced viewing angle T1 of the rear side of the camera device; In some embodiments, when the device control signal is obtained, the start time and the end time of the high-quality time period are obtained; The start time of the high-quality time period is calculated by difference with the start time of the snapshot time to obtain the high opening time difference; the start time of the high-quality time period is calculated by difference with the end time of the snapshot time to obtain the high closing time difference; Then, the average speed in the high opening time difference, high quality time period and high closing time difference is obtained, and the average speed is multiplied with the corresponding high opening time difference, high quality time period and high closing time difference respectively to obtain the first distance L1, the second distance L2 and the third distance L3; the triangular areas constructed with the first distance L1, the second distance L2 and the third distance L3 as the base are marked as the front low-quality image area, the high-quality image area and the rear low-quality image area respectively; And, obtaining the height at which the camera device is installed, which is recorded as H, the current viewing angle of the camera device is recorded as J1, and the angle between the current viewing angle of the camera device and the vertical plane is recorded as J2; By formula , the front side reduced viewing angle T3 of the camera device is calculated; wherein the front side reduced viewing angle T3 of the camera device is the top angle of the rear low-quality image area; the front side reduced viewing angle T3 of the camera device means the acquisition angle corresponding to the time after the high-quality time period; By formula , the camera device control angle T2 is calculated; wherein the camera device control angle T2 is the top angle of the high-quality image area; the camera device control angle T2 means the acquisition angle corresponding to the high-quality time period; By formula , the reduced viewing angle T1 of the rear side of the camera device is calculated; wherein the reduced viewing angle T3 of the front side of the camera device is the top angle of the front low-quality image area; the reduced viewing angle T1 of the front side of the camera device means the acquisition angle corresponding to the time before the high-quality time period; The sum of the reduced viewing angle T3 of the front side of the camera device, the camera device adjustment viewing angle T2 and the reduced viewing angle T1 of the rear side of the camera device is the current viewing angle J1 of the camera device. The current viewing angle J1 of the camera device is adjusted to the viewing angle T2 of the camera device, and the vehicle is captured according to the viewing angle T2 of the camera device; According to the reduced viewing angle T3 on one side of the camera device and the reduced viewing angle T1 on the other side of the camera device, the viewing angles on both sides of the current camera device are regulated, and the regulated viewing angle T2 of the camera device is the license plate capture working angle of the subsequent camera device; The technical solution of the embodiment of the present invention is as follows: based on the image acquisition failure signal, the generation time of the high-quality image is obtained, the time continuity recognition is performed, and the image processing related signal is judged; wherein the image processing related signal includes the device detection signal or the device control signal; based on the device control signal, according to the speed of the target movement, the acquisition angle corresponding to the high-quality time period is determined as the image data for subsequent image processing; the present invention judges the factors causing the image acquisition failure through the influence results of image processing, and then determines the subsequent acquisition time of the moving target based on the image quality distribution by using trigonometric functions. Therefore, the present invention uses intelligent recognition technology to identify the quality of the acquired image, and then determines the acquisition time according to the recognition result, so that the computer image processing capability can not only realize the optimization capability of image quantity processing, but also realize the optimization capability of image quality processing; in a specific example, In the case of unqualified snapshots, the performance of the camera equipment is tested to determine whether there is a fault or whether the camera capture angle is set unreasonably, so as to solve the current problem of low quality of high-speed camera license plate capture based on the results of the detection and analysis. Furthermore, in the case of unreasonable camera capture angle setting, the capture angle of the camera equipment is controlled in combination with the actual capture situation, which can not only narrow the capture angle and reduce the working time of the camera equipment, but also improve the overall quality of the camera equipment capture.

[0020] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0021] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A computer image processing system using intelligent recognition technology, characterized in that: Includes the following modules: Image data acquisition module: When the target moves, each frame of the video stream containing features is acquired and the quality data of each frame is extracted; Image data processing module: perform data analysis based on the quality data of each frame of image extracted, output the quality evaluation value of each frame of image, identify and classify all frame images according to the quality evaluation value, and obtain high-quality images or low-quality images; and determining whether the image acquisition is a qualified signal based on the magnitude of the high-quality image obtained by identification; Image data recognition module: when the image acquisition qualified signal is determined, the image with the maximum quality evaluation value in the video stream is identified; Related impact identification module: Based on the unqualified image acquisition signal, obtain the generation time of high-quality images, perform time continuity identification, and determine the image processing related signals; Among them, the image processing related signals include device control signals; Optimization control module: Based on the device control signal and the speed of the target movement, the acquisition angle corresponding to the high-quality period is determined as the image data for subsequent image processing.

2. A computer image processing system using intelligent recognition technology according to claim 1, characterized in that: The quality data of each frame of image includes: an angle deviation value used to measure the degree of image distortion, a font deformation value used to measure the degree of feature deformation, and an area blur value used to measure the degree of image blur.

3. A computer image processing system using intelligent recognition technology according to claim 2, characterized in that: Identify and classify all frame images according to the quality evaluation values, including: The angle deviation value, the font deformation value and the area blur value are processed to obtain the quality evaluation value of each frame of the image; Analyze the quality assessment value of each frame image with the quality assessment threshold: If the quality assessment value is greater than or equal to the quality assessment threshold, a high-quality image is generated; If the quality assessment value is less than the quality assessment threshold, a high-quality image is generated.

4. A computer image processing system using intelligent recognition technology according to claim 3, characterized in that: The process of determining whether the image acquisition is qualified is as follows: Get the ratio of the total number of high-quality image frames in the video stream and obtain the magnitude of high-quality images; comparing the high-quality image magnitude to a high-quality image magnitude threshold; If the high-quality image level is greater than or equal to the high-quality image level threshold, an image acquisition qualified signal is generated; If the high-quality image level is less than the high-quality image level threshold, an image acquisition failure signal is generated.

5. The computer image processing system using intelligent recognition technology according to claim 1, characterized in that: The image data recognition module specifically includes: When the image acquisition is determined to be qualified, the images of all frames in the video stream are compared according to the quality evaluation value, the image with the maximum quality evaluation value is extracted, marked as the detection image, and the key information in the detection image is extracted.

6. The computer image processing system using intelligent recognition technology according to claim 1, characterized in that: Relevant impact identification modules include: When a signal based on image acquisition failure is obtained, the generation time of the high-quality image is obtained; and it is determined whether the generation time of the high-quality image is continuously generated in the video stream; If the generation time of high-quality images appears continuously in the video stream, the time period during which high-quality images are continuously generated will be marked as a high-quality time period, and a device control signal will be generated at the same time.

7. A computer image processing system using intelligent recognition technology according to claim 6, characterized in that: If the generation time of the high-quality image does not appear to be continuously generated in the video stream, a device detection signal is generated.

8. The computer image processing system using intelligent recognition technology according to claim 1, characterized in that: The optimization control module includes: When the device control signal is obtained, the high-quality image area where the target moves is determined according to the movement of the target in the high-quality time period, the acquisition time before the high-quality time period, and the acquisition time after the high-quality time period, and then the acquisition viewing angle of the high-quality image area is used as image data for subsequent image processing.

9. A computer image processing system using intelligent recognition technology according to claim 8, characterized in that: The process of determining the acquisition angle corresponding to the high-quality period includes: Get the start time and end time of the high-quality time period; The start time of the high-quality time period is calculated by difference with the start time of the snapshot time to obtain the high opening time difference; the start time of the high-quality time period is calculated by difference with the end time of the snapshot time to obtain the high closing time difference; Then, the average speed in the high opening time difference, high quality time period and high closing time difference is obtained, and the average speed is multiplied with the corresponding high opening time difference, high quality time period and high closing time difference respectively to obtain the first distance L1, the second distance L2 and the third distance L3; the triangular areas constructed with the first distance L1, the second distance L2 and the third distance L3 as the base are marked as the front low-quality image area, the high-quality image area and the rear low-quality image area respectively; And, obtaining the height at which the camera device is installed, which is recorded as H, the current viewing angle of the camera device is recorded as J1, and the angle between the current viewing angle of the camera device and the vertical plane is recorded as J2; By formula , the camera device adjustment angle T2 is calculated; wherein the camera device adjustment angle T2 is the top angle of the high-quality image area.

10. A computer image processing system using intelligent recognition technology according to claim 9, characterized in that: By formula , the front side reduced viewing angle T3 of the camera device is calculated; wherein the front side reduced viewing angle T3 of the camera device is the top angle of the rear side low-quality image area; By formula , the reduced viewing angle T1 of the rear side of the camera device is calculated; wherein the reduced viewing angle T3 of the front side of the camera device is the top angle of the front low-quality image area.

Images