Presentation | 2010-05-14 Surveillance Event Detection Using Local and Global Features Yusuke YOSHIZAWA, Koichi SHINODA, Sadaoki FURUI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper describes an event detection method from surveillance video data using the combination of local features and global features. Most previous methods tracked a person first, then extracted local features around him/her. These methods, however, might fail to detect events where many people are moving, since the tracking is erroneous in such crowded environments. To overcome this problem, we propose a robust event detection method combining a detector using local features and that using global features. The trajectories of persons obtained by using the particle filter are used as the local features, and the optical flow vectors in the whole image frame are used as the global features. We evaluated our method for three events, PersonRuns, PeopleMeet, and PeopleSplitUp, using the TRECVID2009 data set. A detection measure, ANDCR, was improved for these events by controlling the weight between the two detectors. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | surveillance / event detection / particle filter / optical flow |
Paper # | IE2010-43,PRMU2010-31,MI2010-31 |
Date of Issue |
Conference Information | |
Committee | MI |
---|---|
Conference Date | 2010/5/6(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Medical Imaging (MI) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Surveillance Event Detection Using Local and Global Features |
Sub Title (in English) | |
Keyword(1) | surveillance |
Keyword(2) | event detection |
Keyword(3) | particle filter |
Keyword(4) | optical flow |
1st Author's Name | Yusuke YOSHIZAWA |
1st Author's Affiliation | Department of Computer Science, Tokyo Institute of technology() |
2nd Author's Name | Koichi SHINODA |
2nd Author's Affiliation | Department of Computer Science, Tokyo Institute of technology |
3rd Author's Name | Sadaoki FURUI |
3rd Author's Affiliation | Department of Computer Science, Tokyo Institute of technology |
Date | 2010-05-14 |
Paper # | IE2010-43,PRMU2010-31,MI2010-31 |
Volume (vol) | vol.110 |
Number (no) | 28 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |