DocumentCode
3296901
Title
Multi-camera person tracking in crowded environments
Author
Krahnstoever, N. ; Yu, T. ; Patwardhan, K.A. ; Gao, D.
Author_Institution
GE Global Res., Niskayuna, NY, USA
fYear
2009
fDate
7-9 Dec. 2009
Firstpage
1
Lastpage
7
Abstract
Reliably tracking people throughout a camera network is an important capability in areas such as law enforcement, homeland protection, and healthcare. In this paper we will provide an overview of GE Global Research´s tracking system and evaluate it against a subset of the PETS 2009 dataset. The tasks of counting, density estimation, multiperson tracking as well as the tracking of selected individuals will be addressed. Qualitative and quantitative performance results will be reported.
Keywords
cameras; computer vision; health care; GE global research; PETS dataset; counting; crowded environments; density estimation; healthcare; homeland protection; law enforcement; multicamera person tracking; Cameras; Cities and towns; Law enforcement; Medical services; Pixel; Positron emission tomography; Protection; Real time systems; Solid modeling; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Performance Evaluation of Tracking and Surveillance (PETS-Winter), 2009 Twelfth IEEE International Workshop on
Conference_Location
Snowbird, UT
Print_ISBN
978-1-4244-5503-4
Type
conf
DOI
10.1109/PETS-WINTER.2009.5399731
Filename
5399731
Link To Document