This paper investigates the design of a system for recognizing
objects in 3D point clouds of urban environments.
The system is decomposed into four steps: locating, segmenting,
...
Aleksey Golovinskiy, Vladimir G. Kim, Thomas Funkh...
It is widely conjectured that the excellent ROC performance of biological vision systems is due in large part to the exploitation of context at each of many levels in a part/whole...
`Invariant regions' are image patches that automatically deform with changing viewpoint as to keep on covering identical physical parts of a scene. Such regions are then desc...
This paper builds on a novel framework of hybrid matching constraints for estimation of structure and recovery of camera focal length and motion, combining the advantages of both ...
MONNET is a visual surveillance system for tracking pedestrians over extended premises. The MONNET system is composed of intelligent nodes, which exchange information on the indiv...