Efficient Egocentric Visual Perception Combining Eye-tracking, a Software Retina and Deep Learning

Autor: Hristozova, Nina, Ozimek, Piotr, Siebert, Jan Paul

We present ongoing work to harness biological approaches to achieving highly efficient egocentric perception by combining the space-variant imaging architecture of the mammalian retina with Deep Learning methods. By pre-processing images collected by

Externí odkaz: http://arxiv.org/abs/1809.01633

Smart Visual Sensing Using a Software Retina Model

Autor: Siebert, Jan Paul, Ozimek, Piotr, Balog, Lorinc, Hristozova, Nina, Aragon-Camarasa, Gerardo

Publikováno v: IROS2018 Workshop: Unconventional Sensing and Processing for Robotic Visual Perception, at 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems

We present an approach to efficient visual sensing and perception based on a non-uniformly sampled, biologically inspired, software retina that when combined with a DCNN classifier has enabled megapixel-sized camera input images to be processed in a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=core_ac_uk__::a0c5cc72da27002616e605e36d6f1205
https://eprints.gla.ac.uk/183359/1/183359.pdf

Egocentric Perception using a Biologically Inspired Software Retina Integrated\ud with a Deep CNN

Autor: Ozimek, Piotr, Balog, Lorinc, Wong, Ryan, Esparon, Tom, Siebert, J. Paul

Publikováno v: International Conference on Computer Vision 2017, ICCV 2017, Second International Workshop on Egocentric Perception, Interaction and Computing

We presented the concept of of a software retina, capable\ud of significant visual data reduction in combination with\ud scale and rotation invariance, for applications in egocentric\ud and robot vision at the first EPIC workshop in Amsterdam\ud [9].

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=core_ac_uk__::b8425695d314c69609e6ec3eb2b8f51a
https://eprints.gla.ac.uk/148802/13/148802.pdf

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Determination of Radial Segmentation of Point Clouds Using K-D Trees with the Algorithm Rejecting Subtrees.

Autor: Orlof, Jerzy¹ (AUTHOR) jerzy.orlof@pk.edu.pl, Ozimek, Paweł¹ (AUTHOR), Łabędź, Piotr¹ (AUTHOR), Widłak, Adrian¹ (AUTHOR), Nytko, Mateusz¹ (AUTHOR)

Publikováno v: Symmetry (20738994). Dec2019, Vol. 11 Issue 12, p1451-1451. 1p.