We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Detection of object abandonment using temporal logic.
- Authors
Bhargava, Medha; Chia-Chih Chen; Ryoo, M. S.; Aggarwal, J. K.
- Abstract
This paper describes a novel framework for a smart threat detection system that uses computer vision to capture, exploit and interpret the temporal flow of events related to the abandonment of an object. Our approach uses contextual information along with an analysis of the causal progression of events to decide whether or not an alarm should be raised. When an unattended object is detected, the system traces it back in time to determine and record who its most likely owner(s) may be. Through subsequent frames, the system searches the scene for the owner and issues an alert if no match is found for the owner over a given period of time. Our algorithm has been successfully tested on two benchmark datasets (PETS 2006 Benchmark Data, 2006; i-LIDS Dataset for AVSS, 2007), and yielded results that are substantially more accurate than similar systems developed by other academic and industrial research groups.
- Subjects
INDUSTRIAL research; RESEARCH teams; PATTERN recognition systems; IMAGE processing; COMPUTER vision
- Publication
Machine Vision & Applications, 2009, Vol 20, Issue 5, p271
- ISSN
0932-8092
- Publication type
Article
- DOI
10.1007/s00138-008-0181-8