Active vision
Region-based strategies for active contour models
International Journal of Computer Vision
CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
Fast Approximate Energy Minimization via Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Region Tracking via Level Set PDEs without Motion Computation
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Moving Object Tracking in Video
AIPR '00 Proceedings of the 29th Applied Imagery Pattern Recognition Workshop
Contour-Based Object Tracking with Occlusion Handling in Video Acquired Using Mobile Cameras
IEEE Transactions on Pattern Analysis and Machine Intelligence
Illumination-Invariant Tracking via Graph Cuts
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Effciently Solving Dynamic Markov Random Fields Using Graph Cuts
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
ACM Computing Surveys (CSUR)
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
Diminished reality for landscape video sequences with homographies
KES'10 Proceedings of the 14th international conference on Knowledge-based and intelligent information and engineering systems: Part III
Hi-index | 0.01 |
This paper presents a new method to both track and segment objects in videos. It includes predictions and observations inside an energy function that is minimized with graph cuts. The min-cut/max-flow algorithm provides a segmentation as the global minimum of the energy function, at a modest computational cost. Simultaneously, our algorithm associates the tracked objects to the observations during the tracking. It thus combines "detect-before-track" tracking algorithms and segmentation methods based on color/motion distributions and/or temporal consistency. Results on real sequences are presented in which the robustness to partial occlusions and to missing observations is shown.