Surveillance event detection

Dikmen, Mert, Ning, Huazhong, Lin, Dennis J., Cao, Liangliang, Le, Vuong, Tsai, Shen-Fu, Lin, Kai-Hsiang, Li, Zhen, Yang, Jianchao, Huang, Thomas S, Lv, Fengjun, Xu, Wei, Yang, Ming, Yu, Kai, Zhao, Zhao, Zhu, Guangyu and Gong, Yihong 2008, Surveillance event detection, in 2008 TREC Video Retrieval Evaluation Notebook Papers, [The Conference], [Unknown], pp. 1-10.

Attached Files
Name Description MIMEType Size Downloads

Title Surveillance event detection
Author(s) Dikmen, Mert
Ning, Huazhong
Lin, Dennis J.
Cao, Liangliang
Le, VuongORCID iD for Le, Vuong orcid.org/0000-0003-1582-1269
Tsai, Shen-Fu
Lin, Kai-Hsiang
Li, Zhen
Yang, Jianchao
Huang, Thomas S
Lv, Fengjun
Xu, Wei
Yang, Ming
Yu, Kai
Zhao, Zhao
Zhu, Guangyu
Gong, Yihong
Conference name Text REtrieval Evaluation. Conference (2008)
Conference location [Unknown]
Conference dates 2008/01/01 - 2008/12/31
Title of proceedings 2008 TREC Video Retrieval Evaluation Notebook Papers
Publication date 2008
Start page 1
End page 10
Total pages 10
Publisher [The Conference]
Place of publication [Unknown]
Summary We have developed and evaluated three generalized systems for event detection. The first system is a simple brute force search method, where each space-time location in the video is evaluated by a binary decision rule on whether it contains the event or not. The second system is build on top of a head tracker to avoid costly brute force searching. The decision stage is a combination of state of the art feature extractors and classifiers. Our third system has a probabilistic framework. From the observations, the pose of the people are estimated and used to determine the presence of event. Finally we introduce two ad-hoc methods that were designed to specifically detect OpposingFlow and TakePicture events. The results are promising as we are able to get good results on several event categories, while for all events we have gained valuable insights and experience.
Notes Dates of conference unknown
Language eng
Indigenous content off
HERDC Research category EN.1 Other conference paper
Persistent URL http://hdl.handle.net/10536/DRO/DU:30138355

Document type: Conference Paper
Collection: A2I2 (Applied Artificial Intelligence Institute)
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 13 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 5 Abstract Views, 0 File Downloads  -  Detailed Statistics
Created: Mon, 08 Jun 2020, 14:19:30 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.