Video Compression Performance Evaluation Method in Transmission via a Low-Speed Channel

The paper presents an overview of the works devoted to video compression algorithms based on artificial intelligence methods. Two main directions for development such are identified - these modules post-processing results work classical and that completely replace existing codecs. problems performance evaluation criteria considered. It was found calculation standard deviation, as PSNR, cannot be used assess quality data when operating under influence radio interference, due strong result artifacts inevitably arise a effects this kind interference. An alternative assessment method semantic analysis frames is proposed, which can noise immunity transmission algorithms. presented estimation uses frame-by-frame comparison original restored sequence, similar PSNR. However, unlike latter, it ignores occur during exposure use frame analysis, consists in searching objects image using approaches intelligence. To compare reconstructed frames, estimate geometric position image. After that, indicator averaged all sequence order obtain resulting similarity original.