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
In IX Workshop on Perceptual Organization in Computer Vision at IEEE CVPR 2014
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.

Supplementary notes can be added here, including code and math.

Francisco Barranco
Francisco Barranco
Associate Professor of Computer Engineering

Neuromorph, Hardware, CPS, Graná, Tellurider, UMD & DC.

Related