Video Retrieval Based on Tracked Features Quantization

Abstract

In this paper, we present an image retrieval method based on feature tracking. Feature tracks are summarized into a compact discreet value and used for video indexing purpose. As opposed to existing space-time features, we do not make any assumption on the motion visible on the indexed videos. As a result, given an example query, our system is able to retrieve related videos from a large database. We evaluated our system with the copy detection benchmark MUSCLEVCD-2007. We also ran retrieval experiment on hours of TV broadcast. Keywords-Video retrieval, Content based retrieval, Descriptor, Quantization.

DOI: 10.1109/ICPR.2010.794

Extracted Key Phrases

2 Figures and Tables

Cite this paper

@inproceedings{Kubo2010VideoRB, title={Video Retrieval Based on Tracked Features Quantization}, author={Hiroaki Kubo and Julien Pilet and Hideo Saito and Shin'ichi Satoh}, booktitle={ICPR}, year={2010} }