Feature Based Digital Video Indexing
Arun Hampapur, Ramesh Chandra Jain, Terry E. Weymouth · 1995
Indexing video data is essential for providing content based access. Indexing has typically been viewed either from a manual annotation perspective or from an image sequence processing perspective. This work proposes a methodology for designing video indexing schemes which use low level machine derivable indices to map into the set of application specific desired video indices . The indexing procedure uses image sequence processing and application requirements analysis to arrive at the low level and desired indices. The mapping is created based on the domain constraints. A mapping efficacy measure is presented. Experimental results of indexing video using image motion features are presented.