| With the rapid development of IP network, 3g network and LTE, the audio and video on demand business which mainly contains sports service is becoming increasingly popular.For example, the Hupu sports and CCTV5(CCTV sports sites), and other professional sports sites develop rapidly, providing Internet users with a lot of sports broadcast and video. In the application of sports video on demand technology, it has been unable to meet the requirements of users for sports video quality just by monitoring the video protocol and the video transmission. Sports video suppliers still need to solve the further problem of specific sports video quality analysis, so as to provide better personalized and characteristic network sports video service for different users.In the present sports video quality assessment applications, the traditional whole reference evaluation occupies very important position. It usually need to compare each frame of video between the original video and distortion video. Although this way of evaluating every frame is accurate, the original video are always high-definition video, which occupy larger storage space, therefore in the process of actual operation, the extraction of the original video frame and operation is difficult.Considering that in sports videos the adjacent frames tend to have great similarity, this paper mainly extracted and analyzed the video frames which are most important for the user to perceive quality as a test sequence and put forward a fully reference evaluation method which is based on the temporal features and spatial features. Sports videos contain more details, and pictures change sharply. According to this characteristic, this method mainly used the SI(Spatial perceptual Information) and TI(Temporal perceptual Information) which are mentioned in ITU- R BT. 1788 to analyze the feature of every frame of CNTV/ESPN sports videos. Through the analysis of SI and TI, this paper extracted frames with high temporal perceptual Information and high spatial perceptual information as a test sequence. Then every frame in the sequence would be test referring to its original corresponding frame to calculate PSNR(Peak signal-to-noise ratio).Finally this paper calculated the average PSNR as the video quality assessment standards.In the experiment, this paper took football, basketball, hockey and the ultimate fighting four kinds of sports as experimental subjects. Through analysis the PSNR of videos corresponding to different quality levels(better quality, general quality and poor quality), this paper determined the PSNR scopes of different quality levels that can be used in practical(PSNR>20:videoqualityis good; 20>PSNR>15:video quality is general, PSNR<15:video quality is poor).The experimental results showed that the analysis method put forward in this paper based on the characteristics of SI and TI could be used on CNTV, ESPN sports video network platforms and the like. It automatic analyzed and judged sports video quality of different bit rates effectively and in real time. And it has a high Spearman rank order correlation coefficient(SROCC) with the subjective quality assessment. |
PDF Full Text Request