Dense saliency-based spatiotemporal feature points for action recognition

Several spatiotemporal feature point detectors have been recently used in video analysis for action recognition. Feature points are detected using a number of measures, namely saliency, cornerness, periodicity, motion activity etc. Each of these measures is usually intensity-based and provides a different trade-off between density and informativeness. In this paper, we use saliency for feature point detection in videos and incorporate color and motion apart from intensity. Our method uses a multi-scale volumetric representation of the video and involves spatiotemporal operations at the voxel level. Saliency is computed by a global minimization process constrained by pure volumetric constraints, each of them being related to an informative visual aspect, namely spatial proximity, scale and feature similarity (intensity, color, motion). Points are selected as the extrema of the saliency response and prove to balance well between density and informativeness. We provide an intuitive view o...

• Type: Conference
• Year: 2009
• Where: CVPR
• Authors: Konstantinos Rapantzikos, Stefanos D. Kollias, Yannis S. Avrithis
• Keywords: Action Recognition, Computer Vision, CVPR 2009, Spatiotemporal Feature Points