Abstract
We present results on the PETS 2009 dataset using surveillance systems based on holistic properties of the video. In particular, we evaluate a crowd counting system, based on regression of holistic (global) features, on the PETS 2009 dataset. We also present experimental results on crowd event detection when using the dynamic texture model to represent holistic motion flow in the video
| Original language | English |
|---|---|
| Publication status | Published - Jun 2009 |
| Externally published | Yes |
| Event | 11th IEEE Intl. Workshop on Performance Evaluation of Tracking and Surveillance (PETS 2009) - Duration: 6 Aug 2010 → … |
Workshop
| Workshop | 11th IEEE Intl. Workshop on Performance Evaluation of Tracking and Surveillance (PETS 2009) |
|---|---|
| Period | 6/08/10 → … |