Two novel computational techniques, harmonic cut and regularized centroid transform, are developed for segmentation of cells and their corresponding substructures observed with an...
Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations....
We propose a method for trajectory classification based on trajectory voting in Moving Object Databases (MOD). Trajectory voting is performed based on local trajectory similarity. ...
Costas Panagiotakis, Nikos Pelekis, Ioannis Kopana...
This paper presents a new structure-based interest region detector called Principal Curvature-Based Regions (PCBR) which we use for object class recognition. The PCBR interest ope...
Hongli Deng, Wei Zhang, Eric N. Mortensen, Thomas ...
We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...