Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Ariel Amato"'
Autor:
Ariel Amato
Publikováno v:
ELCVIA Electronic Letters on Computer Vision and Image Analysis, Vol 13, Iss 2 (2014)
Motion perception is an amazing innate ability of the creatures on the planet. This adroitness entails a functional advantage that enables species to compete better in the wild. The motion perception ability is usually employed at different levels, a
Externí odkaz:
https://doaj.org/article/2a82f36a1020469fa3db421c77be31c1
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2010 (2010)
This paper describes an efficient background subtraction technique for detecting moving objects. The proposed approach is able to overcome difficulties like illumination changes and moving shadows. Our method introduces two discriminative features ba
Externí odkaz:
https://doaj.org/article/f9ac56fda04944cda4466c958d7902b7
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8add8f1550a90bc28fa623a6e0647cb4
https://doi.org/10.1109/cvprw56347.2022.00318
https://doi.org/10.1109/cvprw56347.2022.00318
Publikováno v:
Pattern Recognition. 112:107795
Deep metric learning methods aim to measure similarity of data points (e.g. images) by calculating their distance in a high dimensional embedding space. These methods are usually trained by optimizing a ranking loss function, which is designed to bri
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::562aee515f6e3dc8eeb4aad22b6598fb
https://doi.org/10.1016/j.patcog.2020.107795
https://doi.org/10.1016/j.patcog.2020.107795
Publikováno v:
IEEE Transactions on Image Processing. 20:2954-2966
This paper describes a novel framework for detection and suppression of properly shadowed regions for most possible scenarios occurring in real video sequences. Our approach requires no prior knowledge about the scene, nor is it restricted to specifi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a3fc255ddce9789f82b5f1a281c86bc7
https://doi.org/10.1109/tip.2011.2132728
https://doi.org/10.1109/tip.2011.2132728
Publikováno v:
Pattern Recognition and Image Analysis. 19:165-171
An efficient method to overcome adverse effects of occlusion upon object tracking is presented. The method is based on matching paths of objects in time and solves a complex occlusion-caused problem of merging separate segments of the same path.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fb5abf12af8c3c45dd63aeb406137b0d
https://doi.org/10.1134/s105466180901026x
https://doi.org/10.1134/s105466180901026x
Publikováno v:
CrowdMM@ACM Multimedia
In this paper we present some conclusions about the advantages of having an efficient task formulation when a crowdsourcing platform is used. In particular we show how the task atomization and distribution can help to obtain results in an efficient w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e9cf96a8f11cbc6f6ae04205cf6d86bf
https://doi.org/10.1145/2506364.2506371
https://doi.org/10.1145/2506364.2506371
Autor:
Carles Fernández, Jordi Gonzàlez, Josep M. Gonfaus, Ramón A. Mollineda, Marc Castelló, Nicolás Pérez de la Blanca, Ariel Amato, Pau Baiget, Marco Pedersoli, F. Xavier Roca
Publikováno v:
Multimodal Interaction in Image and Video Applications ISBN: 9783642359316
Multimodal Interaction in Image and Video Applications
Multimodal Interaction in Image and Video Applications
In this paper we present an example of a video surveillance application that exploits Multimodal Interactive (MI) technologies. The main objective of the so-called VID-Hum prototype was to develop a cognitive artificial system for both the detection
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6ae3630b0e0b4755abc566f1283d8007
https://doi.org/10.1007/978-3-642-35932-3_8
https://doi.org/10.1007/978-3-642-35932-3_8
Publikováno v:
Universitat Autònoma de Barcelona
Recercat. Dipósit de la Recerca de Catalunya
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Digital.CSIC. Repositorio Institucional del CSIC
Recercat. Dipósit de la Recerca de Catalunya
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Digital.CSIC. Repositorio Institucional del CSIC
This paper presents a novel algorithm for mobile-object segmentation from static background scenes, which is both robust and accurate under most of the common problems found in motion segmentation. In our first contribution, a case analysis of motion
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::61dccb94fe190b4cb7e8bc752987144c
http://hdl.handle.net/10261/96387
http://hdl.handle.net/10261/96387
Publikováno v:
EURASIP Journal on Advances in Signal Processing, Vol 2010 (2010)
EURASIP Journal on Advances in Signal Processing, Vol 2010, Iss 1, p 901205 (2010)
EURASIP Journal on Advances in Signal Processing, Vol 2010, Iss 1, p 901205 (2010)
This paper describes an efficient background subtraction technique for detecting moving objects. The proposed approach is able to overcome difficulties like illumination changes and moving shadows. Our method introduces two discriminative features ba
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c23c438698db9b8e437531d251a5e66d
https://doaj.org/article/f9ac56fda04944cda4466c958d7902b7
https://doaj.org/article/f9ac56fda04944cda4466c958d7902b7