Share Email Print

Proceedings Paper

Activity and function recognition for moving and static objects in urban environments from wide-area persistent surveillance inputs
Author(s): Georgiy Levchuk; Aaron Bobick; Eric Jones
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper, we describe results from experimental analysis of a model designed to recognize activities and functions of moving and static objects from low-resolution wide-area video inputs. Our model is based on representing the activities and functions using three variables: (i) time; (ii) space; and (iii) structures. The activity and function recognition is achieved by imposing lexical, syntactic, and semantic constraints on the lower-level event sequences. In the reported research, we have evaluated the utility and sensitivity of several algorithms derived from natural language processing and pattern recognition domains. We achieved high recognition accuracy for a wide range of activity and function types in the experiments using Electro-Optical (EO) imagery collected by Wide Area Airborne Surveillance (WAAS) platform.

Paper Details

Date Published: 15 April 2010
PDF: 14 pages
Proc. SPIE 7704, Evolutionary and Bio-Inspired Computation: Theory and Applications IV, 77040P (15 April 2010); doi: 10.1117/12.849492
Show Author Affiliations
Georgiy Levchuk, Aptima, Inc. (United States)
Aaron Bobick, Georgia Institute of Technology (United States)
Eric Jones, Aptima, Inc. (United States)

Published in SPIE Proceedings Vol. 7704:
Evolutionary and Bio-Inspired Computation: Theory and Applications IV
Teresa H. O'Donnell; Misty Blowers; Kevin L. Priddy, Editor(s)

© SPIE. Terms of Use
Back to Top