In this section
@inproceedings{Goncalves:2020:10.1007/978-3-030-58558-7_10,
author = {Goncalves, Nunes UM and Demiris, Y},
doi = {10.1007/978-3-030-58558-7_10},
pages = {161--176},
publisher = {Springer},
title = {Entropy minimisation framework for event-based vision model estimation},
url = {http://dx.doi.org/10.1007/978-3-030-58558-7_10},
year = {2020}
}
TY - CPAPER
AB - We propose a novel Entropy Minimisation (EMin) frame-work for event-based vision model estimation. The framework extendsprevious event-based motion compensation algorithms to handle modelswhose outputs have arbitrary dimensions. The main motivation comesfrom estimating motion from events directly in 3D space (e.g.eventsaugmented with depth), without projecting them onto an image plane.This is achieved by modelling the event alignment according to candidateparameters and minimising the resultant dispersion. We provide a familyof suitable entropy loss functions and an efficient approximation whosecomplexity is only linear with the number of events (e.g.the complexitydoes not depend on the number of image pixels). The framework is eval-uated on several motion estimation problems, including optical flow androtational motion. As proof of concept, we also test our framework on6-DOF estimation by performing the optimisation directly in 3D space.
AU - Goncalves,Nunes UM
AU - Demiris,Y
DO - 10.1007/978-3-030-58558-7_10
EP - 176
PB - Springer
PY - 2020///
SP - 161
TI - Entropy minimisation framework for event-based vision model estimation
UR - http://dx.doi.org/10.1007/978-3-030-58558-7_10
UR - https://link.springer.com/chapter/10.1007/978-3-030-58558-7_10
UR - http://hdl.handle.net/10044/1/81881
ER -
