dc.creator | Pérez Carrasco, José Antonio | es |
dc.creator | Zhao, Bo | es |
dc.creator | Serrano Gotarredona, María del Carmen | es |
dc.creator | Acha Piñero, Begoña | es |
dc.creator | Serrano Gotarredona, María Teresa | es |
dc.creator | Cheng, Shouchun | es |
dc.creator | Linares Barranco, Bernabé | es |
dc.date.accessioned | 2018-10-25T15:32:44Z | |
dc.date.available | 2018-10-25T15:32:44Z | |
dc.date.issued | 2013 | |
dc.identifier.citation | Pérez Carrasco, J.A., Zhao, B., Serrano Gotarredona, M.d.C., Acha, B., Serrano Gotarredona, T., Cheng, S. y Linares Barranco, B. (2013). Mapping from Frame-Driven to Frame-Free Event-Driven Vision Systems by Low-Rate Rate-Coding and Coincidence Processing. Application to Feed-Forward ConvNets. IEEE transactions on pattern analysis and machine intelligence, 35 (11), 2706-2719. | |
dc.identifier.issn | 0162-8828 | es |
dc.identifier.uri | https://hdl.handle.net/11441/79657 | |
dc.description.abstract | Event-driven visual sensors have attracted interest
from a number of different research communities. They provide
visual information in quite a different way from conventional
video systems consisting of sequences of still images rendered at a
given “frame rate”. Event-driven vision sensors take inspiration
from biology. Each pixel sends out an event (spike) when it senses
something meaningful is happening, without any notion of a frame.
A special type of Event-driven sensor is the so called
Dynamic-Vision-Sensor (DVS) where each pixel computes relative
changes of light, or “temporal contrast”. The sensor output
consists of a continuous flow of pixel events which represent the
moving objects in the scene. Pixel events become available with
micro second delays with respect to “reality”. These events can be
processed “as they flow” by a cascade of event (convolution)
processors. As a result, input and output event flows are
practically coincident in time, and objects can be recognized as
soon as the sensor provides enough meaningful events. In this
paper we present a methodology for mapping from a properly
trained neural network in a conventional Frame-driven
representation, to an Event-driven representation. The method is
illustrated by studying Event-driven Convolutional Neural
Networks (ConvNet) trained to recognize rotating human
silhouettes or high speed poker card symbols. The Event-driven
ConvNet is fed with recordings obtained from a real DVS camera.
The Event-driven ConvNet is simulated with a dedicated
Event-driven simulator, and consists of a number of Event-driven
processing modules the characteristics of which are obtained from
individually manufactured hardware modules. | es |
dc.format | application/pdf | es |
dc.language.iso | spa | es |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | es |
dc.relation.ispartof | IEEE transactions on pattern analysis and machine intelligence, 35 (11), 2706-2719. | |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internacional | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | * |
dc.subject | Feature Extraction | es |
dc.subject | Convolutional Neural Networks | es |
dc.subject | Object Recognition | es |
dc.title | Mapping from Frame-Driven to Frame-Free Event-Driven Vision Systems by Low-Rate Rate-Coding and Coincidence Processing. Application to Feed-Forward ConvNets | es |
dc.type | info:eu-repo/semantics/article | es |
dc.type.version | info:eu-repo/semantics/submittedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Teoría de la Señal y Comunicaciones | es |
dc.relation.publisherversion | https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6497055 | es |
dc.identifier.doi | 10.1109/TPAMI.2013.71 | es |
idus.format.extent | 14 p. | es |
dc.journaltitle | IEEE transactions on pattern analysis and machine intelligence | es |
dc.publication.volumen | 35 | es |
dc.publication.issue | 11 | es |
dc.publication.initialPage | 2706 | es |
dc.publication.endPage | 2719 | es |
dc.identifier.sisius | 20530392 | es |