Method for improving image quality of video call fused with scheduling system

Abstract

The invention belongs to the technical field of video communication processing, and particularly relates to an image quality improvement method for a video call of a fusion scheduling system, which comprises the following steps: performing quality evaluation on collected video frames, determining image quality information according to a quality evaluation value, a preset threshold value and statistical historical video frame quality, and sending the image quality information to a server; and then the code rate and the resolution used by the current video coding are obtained, and the video coding parameters are dynamically adjusted based on the image quality information, the code rate and the resolution, so that the self-adaptive video coding parameter adjustment based on the video content is realized, and the optimal video quality and transmission efficiency are achieved. According to the invention, the video data in the video call of the converged communication scheduling system is processed, and the problems that the image quality is reduced and the jamming is obvious are eliminated, so that high-definition and smooth video image quality is provided, the user experience is improved, and the use requirements are met.

Description

Technical Field

[0001] The present invention belongs to the technical field of video communication processing, and in particular relates to a method for improving the image quality of a video call in a fusion scheduling system. Background Art

[0002] The integrated communication dispatching system is an important system that meets the daily production dispatching needs of coal mines. However, the underground environment of coal mines is complex, and there are many networks and hardware devices involved in command and dispatch, which leads to reduced image quality and obvious freezes in terminal video calls, posing a great challenge to video processing. Therefore, necessary intelligent video encoding parameter adjustments should be made in the video calls of the integrated dispatching system to improve video quality, eliminate problems such as screen freezes, provide a good channel for video information transmission, adapt to complex and changeable video scenes, and greatly improve user experience, thereby providing high-definition and smooth video quality for the video calls of the integrated dispatching system. Summary of the invention

[0003] In response to the technical problems existing in the video quality in the above-mentioned converged communication scheduling system video calls, the present invention proposes a method for improving the image quality of the converged communication scheduling system video calls, which is reasonably designed and can process the video data in the converged communication scheduling system video calls, eliminate the problems of image quality degradation and obvious freezes, so as to provide high-definition and smooth video quality and improve the user experience.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is a method for improving the image quality of a video call in a fusion scheduling system, comprising the following steps:

[0005] S1: Acquire multiple collected video frames;

[0006] S2: Use operator template to calculate space complexity KI;

[0007] S3: Calculate the time complexity TI using the residual pixel values ​​of two image frames;

[0008] S4: Obtain the image quality evaluation value and quality information of the current video encoding, and make adaptive judgment and adjustment.

[0009] In step S2, when calculating the spatial complexity, the pixel gradient is first used to represent the pixel information, and the horizontal gradient and vertical gradient of each pixel are calculated using the Sobel operator template. The step S2 further includes:

[0010] S21: Perform convolution operation using the Sobel operator template, multiply each pixel in the video image and the matrix composed of its surrounding pixels by the Sobel operator template to obtain the horizontal gradient Hg and the vertical gradient Vg;

[0011] S22: Use the root mean square of two directions to characterize the information volume pix of the pixel. The calculation formula is:

[0012]

[0013] Where pix represents the amount of information in a pixel. In a frame of image, w represents the frame width, h represents the frame height, and the number of all pixels in the frame is: n = w*h;

[0014] S23: Calculate the space complexity KI, and the calculation formula is expressed as:

[0015]

[0016] Preferably, when performing time complexity calculation, the average value is calculated based on the residual pixel values ​​of two image frames in a selected group, and the step S3 further includes: using Rf to represent the residual frame composed of all residual pixels, calculating the pixel average value of the residual frame to obtain the time domain information TI between the two frames of images, and the calculation formula is:

[0017]

[0018] As a preferred method, the spatial complexity and the temporal complexity are comprehensively calculated to obtain the image quality assessment value AI, and the calculation formula is expressed as:

[0019] Preferably, the videos collected in step S1 are 10 groups, and 30 frames are taken from each group.

[0020] Compared with the prior art, the advantages and positive effects of the present invention are:

[0021] 1. The present invention provides a method for improving the image quality of a video call in a fusion scheduling system. The method performs quality evaluation on the collected video frames, determines the image quality information according to the quality evaluation value, a preset threshold value and the statistical historical video frame quality, and then obtains the bit rate and resolution used for the current video encoding. The video encoding parameters are dynamically adjusted based on the image quality information, bit rate and resolution to achieve the adjustment of adaptive video encoding parameters based on the video content to achieve the best video quality and transmission efficiency. The video data in the video call of the fusion communication scheduling system can be processed to eliminate the problems of reduced image quality and obvious freezes, so as to provide high-definition and smooth video quality, greatly improve the user experience and meet the use requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A schematic diagram of a method for improving the image quality of a video call in a fusion scheduling system;

[0024] Figure 2 A schematic diagram of a Sobel operator template for a method for improving the image quality of a video call in a fusion scheduling system;

[0025] Figure 3 This is a schematic diagram of the video quality before the video call quality is enhanced;

[0026] Figure 4 This is a schematic diagram of video quality after improving the video call quality. DETAILED DESCRIPTION

[0027] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described below in conjunction with the accompanying drawings and embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0028] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways than those described herein. Therefore, the present invention is not limited to the specific embodiments of the following disclosure.

[0029] Examples, such as Figure 1 As shown, a method for improving the image quality of a video call in a fusion scheduling system mainly involves an adaptive video encoding parameter adjustment method, that is, performing quality assessment on the collected video frames, determining image quality information according to the quality assessment value, a preset threshold value, and the statistical historical video frame quality; then obtaining the bit rate and resolution used for the current video encoding, dynamically adjusting the video encoding parameters based on the image quality information, bit rate, and resolution, and realizing the adjustment of adaptive video encoding parameters based on video content to achieve the best video quality and transmission efficiency, specifically comprising the following steps:

[0030] S1: Acquire multiple collected video frames;

[0031] S2: Use operator template to calculate space complexity KI;

[0032] S3: Calculate the time complexity TI using the residual pixel values ​​of two image frames;

[0033] S4: obtaining the image quality evaluation value and quality information of the current video encoding, and making adaptive judgment and adjustment;

[0034] Further: in step S1, multiple captured video frames are obtained and video quality assessment is performed. The assessment can be performed in combination with the current network conditions, light conditions, complexity conditions or video quality assessment algorithm. Different video frames have different quality assessment values, and a comprehensive average value is taken to reflect the video quality. This embodiment aims to provide an algorithm for calculating spatial complexity and temporal complexity for evaluation, wherein the captured video can include 10 groups, each group has 30 frames, and the pixel values ​​of each group of random image frames are obtained for quality assessment.

[0035] In order to effectively complete the calculation of spatial complexity, the pixel gradient is first used to represent the pixel information, and the Sobel operator template is used to calculate the horizontal gradient and vertical gradient of each pixel; the Sobel operator template is as follows Figure 2 As shown, in the image processing, step S2 further includes:

[0036] S21: Perform convolution operation using the Sobel operator template, multiply each pixel in the video image and the matrix composed of its surrounding pixels by the Sobel operator template to obtain the horizontal gradient Hg and the vertical gradient Vg;

[0037] That is to say, in the Sobel operator template, it is defined how to use two 3x3 matrices (used to calculate the gradients in the horizontal and vertical directions respectively) to perform convolution operations with each pixel of the image. The matrix composed of each pixel in the video image and its surrounding pixels is multiplied by the above operator template to obtain the horizontal gradient (Hg) and the vertical gradient (Vg).

[0038] S22: Use the root mean square of two directions to characterize the information volume pix of the pixel. The calculation formula is:

[0039]

[0040] Where pix represents the amount of information in a pixel. In a frame of image, w represents the frame width, h represents the frame height, and the number of all pixels in the frame is: n = w*h;

[0041] S23: Finally, the space complexity KI is calculated, and the calculation formula is expressed as:

[0042]

[0043] In order to effectively complete the calculation of time complexity, the average value is calculated based on the residual pixel values ​​of the two image frames in the selected group. Step S3 further includes: using Rf to represent the residual frame composed of all residual pixels, calculating the pixel average value of the residual frame to obtain the time domain information TI between the two frames of image, and the calculation formula is:

[0044]

[0045] In order to effectively obtain the evaluation value of image quality, the spatial complexity and time complexity are comprehensively calculated to obtain the image quality evaluation value AI. The calculation formula is expressed as:

[0046] In addition, there are three main types of frames in the video: I frame (key frame), P frame (predicted frame) and B frame (bidirectional predicted frame). During encoding, I frame, P frame and B frame achieve efficient compression of the video through prediction and storage of the variation, thereby improving the transmission efficiency and storage efficiency of the video. During decoding, the decoder decodes the content according to the type of the current frame (I, P, B) and uses prediction or bidirectional prediction to generate a complete image. Frame Rate: refers to the number of frames played per second, which affects the smoothness and picture quality of the video. The higher the frame rate, the smoother the video playback, but it will also increase the file size and transmission bandwidth requirements. Resolution: refers to the number of pixels contained in a frame of image, which affects the clarity and file size of the image. The higher the resolution, the clearer the image, but the larger the file. Bit Rate: refers to the network bandwidth, measured in kbps, which refers to the number of data bits transmitted per second, which affects the quality and file size of the video. The higher the bit rate, the better the video quality, but the larger the file.

[0047] Therefore, in step S4, the bit rate, frame rate and resolution used in the current video encoding are obtained, and the video encoding parameters are adjusted based on the parameters and the image quality information; further, it determines an optimal evaluation value of excellent image quality according to actual needs, and lists all image quality information under the image quality, and compares it with the image quality evaluation value. When the optimal evaluation value is less than the image quality evaluation value, the image quality information is determined to be excellent, and when the optimal evaluation value is greater than the image quality evaluation value, the image quality information is determined to be poor. Automatic adjustment is performed according to the current image quality information according to a predefined judgment method, such as increasing the frame rate, reducing the frame rate, increasing the resolution, reducing the resolution, increasing the bit rate, reducing the bit rate and other adjustment strategies.

[0048] For example: when the resolution is high and the image quality is good, the frame rate corresponding to the bit rate is increased (for example, it can be increased if it is below 18fps); when the resolution is high and the image quality is poor, the frame rate corresponding to the bit rate is reduced (for example, it can be reduced to improve the image quality if it is above 21fps); when the resolution is low and the image quality is good, the bit rate corresponding to the resolution up-scaling is reduced; when the resolution is low and the image quality is good, it is considered that the current video quality is very good but the resolution is insufficient. At this time, the main problem of the video is blurring. A reasonable solution is to appropriately increase the video resolution to increase clarity, or to reduce the bit rate threshold when the resolution is up-scaling to a higher resolution, such as Figure 3 and Figure 4 The video shown is a comparison before and after the quality improvement.

[0049] In the above process: the quality of the collected video frames is evaluated, the picture quality information is determined according to the quality evaluation value and the preset threshold as well as the statistical historical video frame quality, and then the bit rate and resolution used for the current video encoding are obtained, and the video encoding parameters are dynamically adjusted based on the picture quality information, bit rate and resolution, so as to realize the adjustment of adaptive video encoding parameters based on the video content, so as to achieve the best video quality and transmission efficiency, and provide good support for the quality of video calls in the coal mine dispatching system, and then process the video data in the video calls of the converged communication dispatching system, and eliminate the problems of reduced picture quality and obvious freezes, so as to provide high-definition and smooth video quality, which greatly improves the user experience and meets the usage requirements.

[0050] The above description is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for improving the image quality of a video call in a fusion scheduling system, characterized in that: The following steps are involved: S1: Acquire multiple collected video frames; S2: Use operator template to calculate space complexity KI; S3: Calculate the time complexity TI using the residual pixel values ​​of two image frames; S4: Obtain the image quality evaluation value and quality information of the current video encoding, and make adaptive judgment and adjustment. In step S2, when calculating the spatial complexity, the pixel gradient is first used to represent the pixel information, and the horizontal gradient and vertical gradient of each pixel are calculated using the Sobel operator template. The step S2 further includes: S21: Perform convolution operation using the Sobel operator template, multiply each pixel in the video image and the matrix composed of its surrounding pixels by the Sobel operator template to obtain the horizontal gradient Hg and the vertical gradient Vg; S22: Use the root mean square of two directions to characterize the information volume pix of the pixel. The calculation formula is: Where pix represents the amount of information in a pixel. In a frame of image, w represents the frame width, h represents the frame height, and the number of all pixels in the frame is: n = w*h; S23: Calculate the space complexity KI, and the calculation formula is expressed as:

2. According to claim 1, a method for improving the image quality of a video call in a fusion scheduling system is characterized in that: When performing time complexity calculation, the average value is calculated based on the residual pixel values ​​of the two image frames in the selected group. The step S3 further includes: using Rf to represent the residual frame composed of all residual pixels, calculating the pixel average value of the residual frame to obtain the time domain information TI between the two frames of image, and the calculation formula is:

3. The method for improving the image quality of a video call in a fusion scheduling system according to claim 2, characterized in that: The spatial complexity and time complexity are calculated comprehensively to obtain the image quality assessment value AI.

4. The method for improving the image quality of a video call in a fusion scheduling system according to claim 1, characterized in that: The videos collected in step S1 are 10 groups, and 30 frames are taken from each group.

Images