Contour motion estimation for address-event data

Abstract

Current motion estimation methods use very sophisticated techniques that require high computational complexity, with low time performance, and large resources. The current framework is considered exhausted. DVSs (Dynamic Visual Sensors) efficiently encode and transmit motion signals. They are valuable to study the early visual motion providing motion boundaries that are salient.

Publication
IX Workshop on Perceptual Organization in Computer Vision at IEEE CVPR 2014
Francisco Barranco
Francisco Barranco
Associate Professor

Associate Professor at the Department of Computer Engineering, Automation and Robotics, Principal Investigator at the Applied Computational Neuroscience Group and the Computer Vision and Robotics Lab of the University of Granada.