Motion Layer Extraction in the Presence of Occlusion Using Graph Cuts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiview segmentation and tracking of dynamic occluding layers
Image and Vision Computing
An ease-of-use stereo-based particle filter for tracking under occlusion
Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Multiple objects tracking in the presence of long-term occlusions
Computer Vision and Image Understanding
Closed-loop adaptation for robust tracking
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Motion layer extraction in the presence of occlusion using graph cut
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Multimedia Tools and Applications
Recovery and Reasoning About Occlusions in 3D Using Few Cameras with Applications to 3D Tracking
International Journal of Computer Vision
Background updating with the use of intrinsic curves
ICIAR'06 Proceedings of the Third international conference on Image Analysis and Recognition - Volume Part I
Background updating for visual surveillance
ISVC'05 Proceedings of the First international conference on Advances in Visual Computing
A graph-based, multi-resolution algorithm for tracking objects in presence of occlusions
GbRPR'05 Proceedings of the 5th IAPR international conference on Graph-Based Representations in Pattern Recognition
A generative model of dense optical flow in layers
SCVMA'04 Proceedings of the First international conference on Spatial Coherence for Visual Motion Analysis
Hi-index | 0.00 |
Motion layer estimation has recently emerged as apromising object tracking method. In this paper, we extendprevious research on layer-based tracker by introducingthe concept of background occluding layers and explicitlyinferring depth ordering of foreground layers. Thebackground occluding layers lie in front of, behind, and inbetween foreground layers. Each pixel in the backgroundregions belongs to one of these layers and occludes all theforeground layers behind it. Together with the foregroundordering, the complete information necessary for reliablytracking objects through occlusion is included in ourrepresentation. An MAP estimation framework isdeveloped to simultaneously update the motion layerparameters, the ordering parameters, and the backgroundoccluding layers. Experimental results show that undervarious conditions with occlusion, including situationswith moving objects undergoing complex motions orhaving complex interactions, our tracking algorithm isable to handle many difficult tracking tasks reliably.