Showing papers by "Rajeev Sharma published in 2014"
••
24 Aug 2014
TL;DR: Neovision2 neuromorphic-vision systems' performance in detecting objects in video was measured using a set of annotated clips and a comparison with computer vision based baseline algorithms is described.
Abstract: The U.S. Defense Advanced Research Projects Agency's (DARPA) Neovision2 program aims to develop artificial vision systems based on the design principles employed by mammalian vision systems. Three such algorithms are briefly described in this paper. These neuromorphic-vision systems' performance in detecting objects in video was measured using a set of annotated clips. This paper describes the results of these evaluations including the data domains, metrics, methodologies, performance over a range of operating points and a comparison with computer vision based baseline algorithms.
18 citations