Detection of object abandonment using temporal logic

Authors:
Medha Bhargava;Chia-Chih Chen;M. S. Ryoo;J. K. Aggarwal
Affiliations:
The University of Texas at Austin, Department of Electrical and Computer Engineering, Computer and Vision Research Center, 78712-0240, Austin, TX, USA and CGGVeritas, Brentford, UK;The University of Texas at Austin, Department of Electrical and Computer Engineering, Computer and Vision Research Center, 78712-0240, Austin, TX, USA;The University of Texas at Austin, Department of Electrical and Computer Engineering, Computer and Vision Research Center, 78712-0240, Austin, TX, USA;The University of Texas at Austin, Department of Electrical and Computer Engineering, Computer and Vision Research Center, 78712-0240, Austin, TX, USA
Venue:
Machine Vision and Applications
Year:
2009

Citing 0
Cited 1

Towards feature-based situation assessment for airport apron video surveillance

Proceedings of the 15th international conference on Theoretical Foundations of Computer Vision: outdoor and large-scale real-world scene analysis

Quantified Score

Hi-index	0.00

Visualization

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.