Share Email Print

Proceedings Paper

A clustering based similarity measure and its application to human action recognition
Author(s): Qin Jiang; Yang Chen
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Computing the similarity between videos is a challenging problem in many applications of video processing such as video retrieval and video-based action recognition. The main difficulty in evaluating similarity between videos is the lack of an effective distance measure. In this paper, we propose a clustering based distance measure to solve this problem. In our approach, a video sequence is represented by a set of spatiotemporal descriptors. Therefore computing the similarity between two video sequences can be achieved by estimating the distance between two sets of descriptors extracted from the videos. To compute the distance measure, we use clustering to obtain distributions and "constrained distributions" of the two sets of descriptors, and use Kullback-Leibler (KL) divergence [6] with the distributions. We apply our distance measure to the problems of distinguishing different human actions and content-based video retrieval. Our experimental results show that the proposed distance measure is an effective metric for these applications.

Paper Details

Date Published: 28 April 2010
PDF: 9 pages
Proc. SPIE 7708, Mobile Multimedia/Image Processing, Security, and Applications 2010, 77080I (28 April 2010); doi: 10.1117/12.849846
Show Author Affiliations
Qin Jiang, HRL Labs., LLC (United States)
Yang Chen, HRL Labs., LLC (United States)

Published in SPIE Proceedings Vol. 7708:
Mobile Multimedia/Image Processing, Security, and Applications 2010
Sos S. Agaian; Sabah A. Jassim, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?