An Efficient Indexing for Content-based Video Search on Peer-to-Peer Networks

In the past few years, videos become an ordinary communication mean for both personal and business activities. Not only the keyword search that have been utilized widely, but also the video content-based search, i.e. given a query video, the similar video sequences can be retrieved. Meanwhile, the increasing of the video utilization has posed both the computational and communication problem since the quality of service should be considered. In this paper, we address the efficiency issue of content-based video indexing over Peer-to-Peer (P2P) networks. The traditional video index is improved to suit with the P2P computational model. The algorithms to perform the video query based on the content similarity, increase the efficiency when new P2P nodes are to be joined with the network, manage the departure of nodes, and insert the videos, are proposed based on a well-known P2P overlay network. From the experiment results, our proposed approach outperforms a naive approach, which directly applies the P2P model with fully-replication, when a number of P2P nodes to be joined, as well as a number of videos to be inserted, is increased. Meanwhile, the efficiency of our approach in terms of the query answering is bounded by linear complexity.