Performance of optical flow techniques
International Journal of Computer Vision
W4: Real-Time Surveillance of People and Their Activities
IEEE Transactions on Pattern Analysis and Machine Intelligence
Video Surveillance of Interactions
VS '99 Proceedings of the Second IEEE Workshop on Visual Surveillance
ACM Computing Surveys (CSUR)
The OBSERVER: an intelligent and automated video surveillance system
ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part I
A survey on visual surveillance of object motion and behaviors
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
A real-time system for video surveillance of unattended outdoor environments
IEEE Transactions on Circuits and Systems for Video Technology
A new approach for adaptive background object tracking based on Kalman filter and mean shift
Proceedings of the 2013 Research in Adaptive and Convergent Systems
| Hi-index | 0.00 |
Autonomous video surveillance systems typically consist of several functional modules working in concert. These modules perform specialized tasks including motion detection, separation of the foreground and background, depth estimation, object tracking, feature estimation, and behavioral analysis. Computational overhead and redundancy may result from designing each module individually, as each module may incorporate different variety of techniques and algorithms. This paper presents the design of a surveillance system that uses an optical flow algorithm throughout. We consider the capabilities, solutions, and limitations of this design. Additionally, an evaluation of the performance of optical flow in specific situations, such as depth estimation, rigid and non-rigid classification, segmentation, and tracking, is provided. The main contribution of this work is a new system-level architecture based on a single key algorithm (optical flow) for the entire video surveillance system.