Name
Abstract | ||
|---|---|---|
The reliable extraction of characteristic gait features from image sequences is an important issue in gait re cognition. In this paper we propose a simple, but efficient approach to extract gait feature. In view of the spatio-temporal motion characteristic of gait, we adopt the shape variation information between successive frames to denote gait information, called Interframe Variation Vector- IVV. Different with other features, IVV doesn't condense a gait sequence into single image, which ignores the spatial attribute, but records the whole moving process in a IVV sequence. This signature not only preserves all the movements of limbs of the body, above all it maintains the order of movement which is the nature of gait. Compared with other gait signatures, it can fully capture the essential feature of gait. Experimental result on CASIA gait database shows that our proposed method has an encouraging recognition performance. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1109/ISKE.2008.4731022 | 2008 3RD INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEM AND KNOWLEDGE ENGINEERING, VOLS 1 AND 2 |
Keywords | DocType | Volume |
shape,image recognition,feature extraction,vectors,gait analysis,hidden markov models,databases | Conference | null |
Issue | ISSN | Citations |
null | null | 0 |
PageRank | References | Authors |
0.34 | 19 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Song-zhi Su | 1 | 61 | 8.53 |
| Li Wang | 2 | 0 | 0.34 |
| Shaozi Li | 3 | 403 | 54.27 |