Method for partial reference evaluation of wireless videos based on space-time domain feature extraction

Abstract

The invention discloses a method for partial reference evaluation of wireless videos based on space-time domain feature extraction, which relates to a method for evaluating video quality. On the basis of performing profound understanding and detailed analysis on the existing video objective quality evaluation model, by combining visual characteristics of human eyes, the invention provides the method for the partial reference evaluation of the wireless videos based on the space-time domain feature extraction to improve the conventional SSIM model. The method takes the fluency of the time domain and the structural similarity and the definition of the space domain of the videos as main evaluation indexes, and under the condition of ensuring the evaluation accuracy, the method extracts characteristic parameters of ST domains (the space domain and the time domain), establishes a new evaluation model, reduces the reference data needed by the evaluation and lowers the computational complexity to ensure that the evaluation model is suitable for evaluating the quality of wireless transmission videos in real time.

Description

technical field [0001] The present invention relates to a video quality evaluation method, in particular to a video part reference evaluation method based on space-time domain feature extraction and improvement of the traditional SSIM algorithm, with a small amount of data, and is especially suitable for video quality evaluation in wireless video services Real-time evaluation. Background technique [0002] With the increase of mobile communication services, wireless communication has been widely used. The characteristics of the wireless communication environment (wireless channels, mobile terminals, etc.) and mobile multimedia application services are more and more support and optimization for image services and video services. With the diversification of wireless networks and the diversification and complexity of wireless environments, the signal will be lost during the video transmission process, so the intuitive quality of video images has become an important indicator t...

AI Technical Summary

Problems solved by technology

[0005] (1) The currently widely used algorithm is based on the mean square signal-to-noise ratio, and the representative methods MSE (Mean Squared Error), PSNR (peak-signal-to-noise ratio), etc., are based on the error between corresponding pixels , that is, image quality evaluation based on error sensitivity, ignoring the special properties of the human visual system, may have deviations between the quality evaluation of video image content and human subjective evaluation;

[0006] (2) Based on the need to transmit complete material to be tested in the wireless transmission of the full reference model, the amount of data required for evaluation is large;

[0007] (3) The evaluation delay is large, the occupied bandwidth is large, and it is not suitable for real-time evaluation of wireless applications;

[0012] (3) Some references The current international research is not mature enough, and people's research on HVS is not yet thorough, and it is still difficult to establish an accurate and unified model so that some references can maintain the same effect as subjective evaluations

Images