Appearance models for occlusion handling

346 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Tracking Multiple Occluding People by Localizing on Multiple Scene Planes (2009, methodology): “For a detailed review of the state of the art in tracking research, the reader is referred to the recent survey by Yilmaz et al. [61].”
Unsupervised Detection and Tracking of Arbitrary Objects with Dependent Dirichlet Process Mixtures (2012, methodology): “There has been a particular emphasis on developing ways to deal with problems such as object occlusion (where one object blocks another from the view of a video camera) [54, 18, 66], complex object interactions [38, 44, 19], objects with similar appearances [42, 36], variable (and potentially high) ”
A Protocol for Evaluating Video Trackers Under Real-World Conditions (2013, background): “Distance-based criteria use the concept of distance minimization between estimation and ground truth to evaluate performance.”
Multi-Object Tracking Through Simultaneous Long Occlusions and Split-Merge Conditions (2006, methodology): “To associate generated tracks T i with ground truth tracks G j , we used the following track distance measure [6]: where O ( T i , G j ) denotes the frames where T i and G j overlap, |·| denotes cardinality, and (cid:11)·(cid:11) denotes the L2-norm.”
Respectful cameras: detecting visual markers in real-time to address privacy concerns (2007, methodology): “[47] uses object models as a post-processing step to disambiguate between objects and compensate for occlusions.”