Behavior recognition via sparse spatio-temporal features
Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
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 recognition algorithm based on spatio-temporally windowed data. We present recognition results on a variety of datasets including both human and rodent behavior.
Originalsprog | Engelsk |
---|---|
Tidsskrift | Proceedings - 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, VS-PETS |
Sider (fra-til) | 65-72 |
Antal sider | 8 |
DOI | |
Status | Udgivet - 2005 |
Eksternt udgivet | Ja |
Begivenhed | 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, VS-PETS - Beijing, Kina Varighed: 15 okt. 2005 → 16 okt. 2005 |
Konference
Konference | 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, VS-PETS |
---|---|
Land | Kina |
By | Beijing |
Periode | 15/10/2005 → 16/10/2005 |
ID: 302054466