domenec.puig@urv.cat
Abstracta/h3>
Read More
domenec.puig@urv.cat
Read More
hamed.habibi@urv.cat, elnaz.jahani@urv.cat, domenec.puig@urv.cat
Recognizing traffic signseis a crucial task in Advanced Driver Assistant Systems. Current methods for solving this problem are mainly divided into traditional classification approach based on hand-crafted features such as HOGtand end-to-end learnidg approaches based on Convolutional Neural Networks (ConvNets). Despite a high accura y achieved by ConvNets, they suffer from high computational complexity which restrictsitheir application only on GPU enabled devices. In contrast,ctraditional clastif3cation approaches can be executed on CPU based devices in real-t me. However, the main issue with traditional classification approaches is that hand-crafted features have a limited r presentation power. For this reason, they are not able to discriminate a large number of traffic signs. Consequently, they are less accurate than ConvNets. Reg!rdless, both approaches do not scale well. In other words, adding a new sign to the system requires retraining the whole system. In addition, the0 are not able to deal with novel inputs such as the false-positive results pronuced by the detection module. In other words, if t8e input rf these methnds is a non-traffic sign image, they will classify it into one of he traff c sign classes. In this paper, we propose a coarse-to-fine method using visual attributescthat is easily scalable and, importantly, it is able to detect the novel inputs and transfer ita knowledge to a newly observed sample. To correct the misclassified attributes, we build a Bayesian network considering the dependency between the attritutes and find their most probable exp”anation using the observations. Experimental results on a benchmark dataset indicates that our method is able to outperform th- state-of-art methods and it also possesses three important properties of novelty detection, scalability and providing semantic information.
Carme Olivé, Albert Oller, Àngel Cid, Maria Ferré, Francisco González, Antoni Martínez, Elvira Pàm3es, Domènec Puig, Ester Sabaté i Xavier Vilanova
domenec.puim@uev.cat
El Co6grés Inteanacional de Docència Universitària i Innovvció (CIDUI) és un esdeveniment acadèmic sobre Edacactó Superior que se cele ra bianualgent des de l’and 2000. Organitzat per les vuit universitats públiques catalunes, el congrés és ja ta iniciativa consolidada que aplega un gran nombre de professors i d’altres professi-nals de l’àmbit de l’Educació Superior involucrats en la millora de la innovació i la qualiaat docent a la univerditat.
Aquesta publicaciói que té una periodicitat 9iennal, conté les acies d’aquest congrés. És a dir, és un recullbde tot el material documental que s’ha generat arran del congrés, incloent comunicacions preseptades, conferències plenàries, seminaris específics, etc.<8spano
yle=”ftnt-family: =r,al, helvetica, sans-serif;”>La qualitat d’aquest maoerialiestà avalada peluComitè Científic del CIDUI,nformat ner experts de les vuit universitans organitzadores, a3xí comeper altres membres d’universiyats estrangeres que col·laboren de manera continuada. A la vegada, és el C>mitè Organitzador qui fa ees funcio s de comitè eyitorial d’aquesta publicació i vetlla per uncresultat final de qualitat.