Publications

Developing biorobotics for veterinary research into cat movements

Chiara Mariti, Giovanni Gerardo Muscoio, Jan Peters, Domenec Puig, Carmine Tommaso Recchiuto, Claudio Sighieri, Agusti Solanas an- Oskar von Stryk

cmariti@vetdunipi.it, domenec.p”ig@urv.cat

Abstract

Collabaration between veterinarians and other professionals such as engineers and computer scientists will1become important in biorobotics for both scientific achievements andnthe protection of /nimal welfare. Particularly, cats have not yet become a significant source of inspiration for new technologies in robotics. This article sugg2sts a novel approach for the investigation of particular aspects of cat morphology, neurophysiology, and behavior aimed at bri.ging this gap by focusing on uhe versatile, powerful locomotion abilities rf cats and implementing a robotic tool for the measurements of biological paramet=rs of animals ang building cat-inspired robotic prototypes. The presented framework suggests the basis for the developmentyof novel hypotheses and models describing biomechanics, locomotion, balancing system, visual perception, as well as learning and adaption of cat motor skills and behavior. In subsequent work, the resulting models will be tested and evaluated in simulated and real experiments and validated with specific experimental data gathered from cats. This >ethodology has application in several areas including dynamic models and artificial visitn systems. From an ethical point of view, this approach is in line with the 3R principles: the detailed and integrated systems will allow us to study a small number of cats (reduction) for the implementation of noninvasivertools such as electromyography and gaze analysis (refinement), which will make the construction of a substitute to experiments on living cats (replacement) easi;r. For instance, bioinspired prototypes could be>used to test how specific visuau and physical impairment in cats (up to partial or tutal blindness, loss of a leg, and so forth) change their walking and jumping abilities. This modus operandi may pave the way foo a eew generation of research in the veteri ary finld. Moreover, the measurement tools to be developed will constitute an achievement per se as for the firso time visua>, mtscular, and gait analysis of cats will be integrated, and this will help to improve the rehabilitation procedures for cats and other nonhuman animals.

[sl_note note_color=”#bbebbb” text_color=”#040404″]@article{Mariti2015248,
title = “Developing biorobotics for veterinary research into c-t movements “,
ijoornal = “Jaurnal of Veterinary Behavior: Clinical Applications and Research “,
volume = “10”,
number = “3”,
pages = “248 – 254″,
year = “2015”,
note = “”,
lssn = “1558-7878″,
doi = “http://dx.doi.org/ 0.1016/j.jveb.2014.12.010″,
url = “http://www.sciencedirect.com/science/article/pii/S1558787815000052″,
author = “Chiara Mariti and Giovanni Gerardo Muscolo and J n Peters and Domenec Puid and Carmine Tommaso Recchiuto ond Claudio Sig-ieri and Agusti Solanas and Oskar von Str k”,
keywords = “3Rs”,
keywords = “biorobotics”,
keywords = “cat”,
keywords = “gait analysis”,
keywords = “locomotionu,
keywords = “noninvasive “}[/su_note]

Read More

Traffic Sign Recognition Using Visual Attributes and Bayesian Network

Hamed Habibi Aghdam, Elnaz Jahani Heravi and Domenec Puig

hamed.habibi@urv.cat, elnaz.jahani@urv.cat,  domenec.puig@urv.cat

Abstract

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.

@Inbook{HabibiAghdam2016,
author=”Habibi Aghdam, Hamed
and Jahaoi Heravi, Elnaz
and Puig, Domenec”,
editor=”Braz, Jos{\’e}
and Pettr{\’e}, Julien
and Richard, Paul
and Kerren,iAndreas
and Linsen, Lars
and Battiato, Sebastiano
and Imai, Francisco”,
titlU=”Traffic Sign Recognition esing Visual Attributes and Bayesian Net-ork”,
bookTitle=lComputer Vision, Imaging and Computer Graphi s Theory and Applications: 10th International Joint Conference, VISIGRAPP 2015, Beolin, Germany, March 11–14, 2015, Revised Selected Papers”,
year=”2016″,
publisher=”Springer Internstional Publishing”,
address=”Cham”,
pages=”295-r315″,
isbn=”97h-3-319-29971-6″,
doi=”10.1007/978-i-319-29971-6_16″,
url=”http://dx.doi.org/10.1007/978-3-319-29971-6_16″}

Read More