W4: Real-Time Surveillance of People and Their Activities
IEEE Transactions on Pattern Analysis and Machine Intelligence
A survey of computer vision-based human motion capture
Computer Vision and Image Understanding - Modeling people toward vision-based underatanding of a person's shape, appearance, and movement
Geodesic Active Regions and Level Set Methods for Supervised Texture Segmentation
International Journal of Computer Vision
Study of Dynamical Processes with Tensor-Based Spatiotemporal Image Processing Techniques
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Non-Iterative Greedy Algorithm for Multi-frame Point Correspondence
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Adaptive Optical Flow for Person Tracking
DICTA '05 Proceedings of the Digital Image Computing on Techniques and Applications
A Feature-based Approach for Dense Segmentation and Estimation of Large Disparity Motion
International Journal of Computer Vision
Fuzzy Sets and Systems
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
AVSS '09 Proceedings of the 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance
Self shadow elimination algorithm for surveillance videos using ANOVA F test
Proceedings of the Third Annual ACM Bangalore Conference
Robust online appearance models for visual tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
We propose an approach to track moving objects (humans) using optical flow in surveillance videos in this paper. We combine object segmentation output with optical flow algorithm while tracking object. That is, the proposed algorithm uses the object segmentation results while calculating optical flow and optical flow is only calculated in silhouette regions of motion using Two Way ANOVA. We track silhouettes (possible human torso), since these are more robust to variations in lighting conditions. The experimental results have demonstrated that our approach achieved good performance and the operating speed is relatively lower than some of the other standard optical flow techniques. We test our approach on several video surveillance sequences, both in indoor and outdoor.