Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/127513
COMPARTIR / EXPORTAR:
SHARE CORE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Campo DC | Valor | Lengua/Idioma |
---|---|---|
dc.contributor.author | Huerta, Iván | - |
dc.contributor.author | Pedersoli, Marco | - |
dc.contributor.author | Gonzàlez, Jordi | - |
dc.contributor.author | Sanfeliu, Alberto | - |
dc.date.accessioned | 2016-01-12T13:59:03Z | - |
dc.date.available | 2016-01-12T13:59:03Z | - |
dc.date.issued | 2015 | - |
dc.identifier | issn: 0031-3203 | - |
dc.identifier.citation | Pattern Recognition 48(3): 709-719 (2015) | - |
dc.identifier.uri | http://hdl.handle.net/10261/127513 | - |
dc.description.abstract | Change detection is the most important task for video surveillance analytics such as foreground and anomaly detection. Current foreground detectors learn models from annotated images since the goal is to generate a robust foreground model able to detect changes in all possible scenarios. Unfortunately, manual labelling is very expensive. Most advanced supervised learning techniques based on generic object detection datasets currently exhibit very poor performance when applied to surveillance datasets because of the unconstrained nature of such environments in terms of types and appearances of objects. In this paper, we take advantage of change detection for training multiple foreground detectors in an unsupervised manner. We use statistical learning techniques which exploit the use of latent parameters for selecting the best foreground model parameters for a given scenario. In essence, the main novelty of our proposed approach is to combine the where (motion segmentation) and what (learning procedure) in change detection in an unsupervised way for improving the specificity and generalization power of foreground detectors at the same time. We propose a framework based on latent support vector machines that, given a noisy initialization based on motion cues, learns the correct position, aspect ratio, and appearance of all moving objects in a particular scene. Specificity is achieved by learning the particular change detections of a given scenario, and generalization is guaranteed since our method can be applied to any possible scene and foreground object, as demonstrated in the experimental results outperforming the state-of-the-art. | - |
dc.description.sponsorship | This work was partially funded by the DPI2013-42458-P and TIN2012-39051. | - |
dc.publisher | Elsevier | - |
dc.relation | info:eu-repo/grantAgreement/MINECO/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/DPI2013-42458-P | - |
dc.relation.isversionof | Preprint | - |
dc.rights | openAccess | - |
dc.subject | Multiple appearance models | - |
dc.subject | Video surveillance | - |
dc.subject | Support vector machine | - |
dc.subject | Latent variables | - |
dc.subject | Motion segmentation | - |
dc.subject | Object detection | - |
dc.subject | Unsupervised learning | - |
dc.title | Combining where and what in change detection for unsupervised foreground learning in surveillance | - |
dc.type | artículo | - |
dc.identifier.doi | 10.1016/j.patcog.2014.09.023 | - |
dc.relation.publisherversion | http://dx.doi.org/10.1016/j.patcog.2014.09.023 | - |
dc.date.updated | 2016-01-12T13:59:04Z | - |
dc.description.version | Peer Reviewed | - |
dc.language.rfc3066 | eng | - |
dc.contributor.funder | Ministerio de Ciencia e Innovación (España) | - |
dc.contributor.funder | Ministerio de Economía y Competitividad (España) | - |
dc.relation.csic | Sí | - |
dc.identifier.funder | http://dx.doi.org/10.13039/501100004837 | es_ES |
dc.identifier.funder | http://dx.doi.org/10.13039/501100003329 | es_ES |
dc.type.coar | http://purl.org/coar/resource_type/c_6501 | es_ES |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.fulltext | With Fulltext | - |
item.cerifentitytype | Publications | - |
item.openairetype | artículo | - |
item.grantfulltext | open | - |
Aparece en las colecciones: | (IRII) Artículos |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
surveillance.pdf | 6,13 MB | Adobe PDF | Visualizar/Abrir |
CORE Recommender
SCOPUSTM
Citations
15
checked on 12-abr-2024
WEB OF SCIENCETM
Citations
15
checked on 26-feb-2024
Page view(s)
226
checked on 18-abr-2024
Download(s)
290
checked on 18-abr-2024
Google ScholarTM
Check
Altmetric
Altmetric
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.