Robust extraction of moving objects through grouping edges along with optical flow
Asaka Yamane, Noboru Ohnishi, Noboru Sugie · 2005
A robust network system is proposed for segmenting and extracting multiple moving objects. The system uses an interconnected neural network in which grouping factors, such as edge proximity and smoothness of edge orientation, and smoothness of motion component perpendicular to an edge, are embedded. Experimental results are provided to indicate performance and noise robustness of the system in extracting objects in synthesized images.