A multimodal lossless coding method for skeletons in videos
This addresses the need for efficient compression of skeleton data in video analysis, which is incremental as it applies existing coding techniques to a new domain.
The paper tackles the problem of coding massive skeleton information in videos for human-centric analysis by proposing a multimodal lossless coding tool with three schemes that switch based on skeleton type, achieving 74.4% and 54.7% size reductions on surveillance and overall test sequences.
Nowadays, skeleton information in videos plays an important role in human-centric video analysis but effective coding such massive skeleton information has never been addressed in previous work. In this paper, we make the first attempt to solve this problem by proposing a multimodal skeleton coding tool containing three different coding schemes, namely, spatial differential-coding scheme, motionvector-based differential-coding scheme and inter prediction scheme, thus utilizing both spatial and temporal redundancy to losslessly compress skeleton data. More importantly, these schemes are switched properly for different types of skeletons in video frames, hence achieving further improvement of compression rate. Experimental results show that our approach leads to 74.4% and 54.7% size reduction on our surveillance sequences and overall test sequences respectively, which demonstrates the effectiveness of our skeleton coding tool.