Behavior recognition via sparse spatio-temporal features
Research output: Contribution to journal › Conference article › Research › peer-review
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.
Original language | English |
---|---|
Journal | Proceedings - 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, VS-PETS |
Pages (from-to) | 65-72 |
Number of pages | 8 |
DOIs | |
Publication status | Published - 2005 |
Externally published | Yes |
Event | 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, VS-PETS - Beijing, China Duration: 15 Oct 2005 → 16 Oct 2005 |
Conference
Conference | 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, VS-PETS |
---|---|
Country | China |
City | Beijing |
Period | 15/10/2005 → 16/10/2005 |
ID: 302054466