Many successful feature detectors and descriptors exist for 2D intensity images. However, obtaining the same effectiveness in the domain of 3D objects has proven to be a more elusi...
Linear subspace methods that provide sufficient reconstruction of the data, such as PCA, offer an efficient way of dealing with missing pixels, outliers, and occlusions that often ...
A reliable system for visual learning and recognition should enable a selective treatment of individual parts of input data and should successfully deal with noise and occlusions....
This paper presents a bottom-up tracking algorithm for surveillance applications where speed and reliability in the case of multiple matches and occlusions are major concerns. The...
This paper deals with motion estimation and segmentation in video sequences. Some methods of motion computation between two consecutive frames of a video sequence are based on the...
Ariane Herbulot, Sylvain Boltz, Eric Debreuve, Mic...