For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
A Fast Sub-Volume Search Method for Human Action Detection
Ping GUO Zhenjiang MIAO Xiao-Ping ZHANG Zhe WANG
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/01/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
action detection, graph representation, Minimum Cycle detection, sub-volume search,
Full Text: PDF(1.4MB)>>
This paper discusses the task of human action detection. It requires not only classifying what type the action of interest is, but also finding actions' spatial-temporal locations in a video. The novelty of this paper lies on two significant aspects. One is to introduce a new graph based representation for the search space in a video. The other is to propose a novel sub-volume search method by Minimum Cycle detection. The proposed method has a low computation complexity while maintaining a high action detection accuracy. It is evaluated on two challenging datasets which are captured in cluttered backgrounds. The proposed approach outperforms other state-of-the-art methods in most situations in terms of both Precision-Recall values and running speeds.