Range Imaging (RIM) is a new suitable choice for measurement and modelling in many different applications. The ability to describe scenes in three dimensions opens new scenarios, providing new opportunities in different fields, including visual monitoring and security. Active range sensors provide depth information allowing to develop algorithms much less complex and allows problems to be approached in a new, robust and efficient way. The paper presents a wide dataset for indoor surveillance applications acquired by a state-of-the art range camera. The main issue is the definition of a common basis for the comparative evaluation of the performance of vision algorithms.
1 Dec 2010
Volume: 2 Pages: 1-16
Proc. of British Machine Vision Conference (BMVC), BMVA Press