Multi-target Tracking with Sparse Group Features and Position Using Discrete-Continuous Optimization

Simple item page
datacite.alternateIdentifier.citationCOMPUTER VISION - ACCV 2014 WORKSHOPS, PT III,Vol.9010,680-694,2015
datacite.alternateIdentifier.doi10.1007/978-3-319-16634-6_49
datacite.creatorPeralta Márquez, Billy
datacite.creatorSoto, Alvaro
datacite.creatorJawahar, CV
datacite.creatorShan, S
datacite.date2015
datacite.titleMulti-target Tracking with Sparse Group Features and Position Using Discrete-Continuous Optimization
dc.date.accessioned2021-04-30T16:35:20Z
dc.date.available2021-04-30T16:35:20Z
dc.description.abstractMulti-target tracking of pedestrians is a challenging task due to uncertainty about targets, caused mainly by similarity between pedestrians, occlusion over a relatively long time and a cluttered background. A usual scheme for tackling multi-target tracking is to divide it into two sub-problems: data association and trajectory estimation. A reasonable approach is based on joint optimization of a discrete model for data association and a continuous model for trajectory estimation in a Markov Random Field framework. Nonetheless, usual solutions of the data association problem are based only on location information, while the visual information in the images is ignored. Visual features can be useful for associating detections with true targets more reliably, because the targets usually have discriminative features. In this work, we propose a combination of position and visual feature information in a discrete data association model. Moreover, we propose the use of group Lasso regularization in order to improve the identification of particular pedestrians, given that the discriminative regions are associated with particular visual blocks in the image. We find promising results for our approach in terms of precision and robustness when compared with a state-of-the-art method in standard datasets for multi-target pedestrian tracking.
dc.identifier.urihttp://repositoriodigital.uct.cl/handle/10925/3104
dc.language.isoen
dc.publisherSPRINGER-VERLAG BERLIN
dc.sourceCOMPUTER VISION - ACCV 2014 WORKSHOPS, PT III
oaire.resourceTypeMeeting
uct.catalogadorWOS
uct.indizacionISTP
Files
Collections
Migración Web of Science