发明名称 VIDEO CONTENT CLASSIFICATION
摘要 Methods, systems and apparatus, including computer programs encoded on computer storage media, for video content classification. A video content classification system classifies input video data frame by frame. The video content classification system performs customized discrete cosine transform (DCT) operations on each frame. The video content classification system then determines, based on results of the DCT operations, how much image information in the frame may be lost due to compression. If the loss is estimated to be below a threshold value, the video content classification system applies a high data compression ratio algorithm to compress the frame. Otherwise, the video content classification system applies a low data compression ratio algorithm to compress the frame. The video content classification system may generate output video data that is compressed differently frame by frame.
申请公布号 US2017104995(A1) 申请公布日期 2017.04.13
申请号 US201415128183 申请日期 2014.03.25
申请人 Owtware Holdings Limited, BVI 发明人 Lunesu Lionello Giuseppe Giovanna;Walter Douglas Allen
分类号 H04N19/12;H04N19/15;H04N19/154;H04N19/625 主分类号 H04N19/12
代理机构 代理人
主权项 1. A method comprising: receiving, by one or more computers, video data, the video data comprising a sequence of frames, each frame including an image comprising a plurality of pixels; selecting a plurality of blocks of pixels from each frame; computing a respective information loss score of each frame, the information loss score indicating an estimated degree of loss of information in the image in a respective frame upon compressing the respective frame using a first compression algorithm; determining that an information loss score of a first frame in the sequence of frames satisfies a compression threshold and that an information loss score of a second frame in the sequence of frames does not satisfy the compression threshold; in response, compressing the first frame using the first compression algorithm and compressing the second frame using a second compression algorithm that is different from the first compression algorithm; and submitting the compressed first frame and the compressed second frame for rendering as a sequence of continuous frames in an output video for display on a display device.
地址 Shanghai CN
您可能感兴趣的专利