30 March 2009 Surveillance of pedestrian bridge traffic using neural networks
Author Affiliations +
Abstract
A computer-vision monitoring system is demonstrated that automatically detects the presence and location of people. The approach investigated the potential for real-time, automated surveillance and tracking in a realistic environment. Economy was obtained by the use of gray-scale, fixed perspective images and efficiency was obtained by the use of selected object features and a neural-network-processing algorithm. The system was applied to pedestrian traffic on an outdoor bridge and consequently had to handle complex images. Image sequences of single and multiple people were used with differences in clothing, position, lighting, season, etc. A two-stage algorithm was implemented in which (1) new objects were identified in a highly variable scene and (2) the objects were classified with a back-propagation neural network. The image processing techniques included segmentation and filtering and the neural network used fourteen object features as inputs. The implementation had excellent people-discrimination accuracy despite the noise in the images and had low computational complexity with respect to alternative techniques.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Steve E. Watkins, Steve E. Watkins, R. Joe Stanley, R. Joe Stanley, Anand Gopal, Anand Gopal, Randy H. Moss, Randy H. Moss, } "Surveillance of pedestrian bridge traffic using neural networks", Proc. SPIE 7292, Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2009, 72922Q (30 March 2009); doi: 10.1117/12.815523; https://doi.org/10.1117/12.815523
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Remote image segmentation based on color information
Proceedings of SPIE (December 14 1999)
Accelerating sub-pixel marker segmentation using GPU
Proceedings of SPIE (February 04 2009)
Iconic-symbolic interfaces
Proceedings of SPIE (April 30 1992)

Back to Top