Analysis of Crowded Scenes using Holistic Properties
Research output: Conference Papers › RGC 32 - Refereed conference paper (without host publication) › peer-review
Author(s)
Detail(s)
Original language | English |
---|---|
Publication status | Published - Jun 2009 |
Externally published | Yes |
Workshop
Title | 11th IEEE Intl. Workshop on Performance Evaluation of Tracking and Surveillance (PETS 2009) |
---|---|
Location | |
City | |
Period | 6 August 2010 |
Link(s)
Document Link | Links
|
---|---|
Permanent Link | https://scholars.cityu.edu.hk/en/publications/publication(35721432-33d8-4e05-948a-c7ecbbe86c37).html |
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
Citation Format(s)
Analysis of Crowded Scenes using Holistic Properties. / CHAN, Antoni Bert; Morrow, Mulloy; Vasconcelos, Nuno.
2009. Paper presented at 11th IEEE Intl. Workshop on Performance Evaluation of Tracking and Surveillance (PETS 2009).
2009. Paper presented at 11th IEEE Intl. Workshop on Performance Evaluation of Tracking and Surveillance (PETS 2009).
Research output: Conference Papers › RGC 32 - Refereed conference paper (without host publication) › peer-review