Content-Based Management of Human Motion Data: Survey and Challenges

Digitization of human motion using skeleton representations offers exciting possibilities for a large number applications but, at the same time, requires innovative techniques their effective and efficient processing. Content-based processing data has developed rapidly in recent years, focusing mainly on specialized prototypes with limited consideration generic management possibilities. In this survey article, we synthesize categorize existing approaches outline future research challenges brought by increasing availability data. particular, first discuss problems suitable representation segmentation continuous obtained from various sources. Then, concentrate comparison models assessing similarity time-restricted pieces motions, as required any content-based operation. Next, review evaluating queries over collections sequences filtering query-relevant parts streams. Finally, summarize usability perspective application domains new related to current technological infrastructural developments. We especially assess scalability propose directions dealing diverse volumes