Behavior recognition via sparse spatio-temporal features-英文文献.pdf

Behavior Recognition via Sparse Spatio-Temporal Features ´ Piotr Dollar Vincent Rabaud Garrison Cottrell Serge Belongie Department of Computer Science and Engineering University of California, San Diego La Jolla, CA 92093 USA Abstract A common trend in object recognition is to detect and lever- age the use of sparse, informative feature points. The use of such features makes the problem more manageable while providing increased robustness to noise and pose variation. In this work we develop an extension of these ideas to the spatio-temporal case. For this purpose, we show that the direct 3D counterparts to commonly used 2D interest point detectors are inadequate, and we propose an alternative. Anchoring off of these interest points, we devise a recogni- tion algorithm based on spatio-temporally windowed data. We present recognition results on a variety of datasets in- cluding both human and rodent behavior. 1. Introduction Figure 1: Visualization of cuboid based behavior recognition. Spatio- temporal volume of mouse footage shown at top. We apply a spatio- temporal interest point detector to find local regions of interest in space In this work we develop a general framework for detecting and time (cuboids) which serve as the substrate for behavior recognition. and characterizing behavior from video sequences, making few underlying assumptions about t