Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Georg Nebehay"'
Autor:
Ales Leonardis, Fatih Porikli, Matej Kristan, Gustavo Fernandez, Georg Nebehay, Roman Pflugfelder, Luka Cehovin, Tomas Vojir, Jiri Matas
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 38:2137-2155
This paper addresses the problem of single-target tracker performance evaluation. We consider the performance measures, the dataset and the evaluation system to be the most important components of tracker evaluation and propose requirements for each
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ab98ceb0c600ba2758c0ee17385422d2
https://doi.org/10.1109/tpami.2016.2516982
https://doi.org/10.1109/tpami.2016.2516982
Autor:
Georg Nebehay, Roman Pflugfelder, Bernhard Rinner, Jennifer Simonjan, Gustavo Fernández Domínguez, Peter R. Lewis, Lukas Esterle
Publikováno v:
Computer. 48:21-28
Smart cameras perform on-board image analysis, adapt their algorithms to changes in their environment, and collaborate with other networked cameras to analyze the dynamic behavior of objects. A proposed computational framework adopts the concepts of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4b0160153cb87f74a440a6234322eb7d
https://doi.org/10.1109/mc.2015.209
https://doi.org/10.1109/mc.2015.209
Publikováno v:
Natural Computing Series ISBN: 9783319396743
Self-aware Computing Systems
Self-aware Computing Systems
As explained in Chapter 5, self-aware and self-expressive systems can be designed based on a number of patterns and primitives. In this chapter, we discuss issues to be considered when developing such systems, especially when going through phases 3 (
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4e2f1e2adffe7ca750ef2b8221eb16ea
https://doi.org/10.1007/978-3-319-39675-0_6
https://doi.org/10.1007/978-3-319-39675-0_6
Publikováno v:
Natural Computing Series ISBN: 9783319396743
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c460f5da951756e2c5f7a60e6439aaba
https://doi.org/10.1007/978-3-319-39675-0_7
https://doi.org/10.1007/978-3-319-39675-0_7
Autor:
Michael Felsberg, Amanda Berg, Gustav Hager, Jorgen Ahlberg, Matej Kristan, Jiri Matas, Ales Leonardis, Luka Cehovin, Gustavo Fernandez, Tomas Vojır, Georg Nebehay, Roman Pflugfelder, Alan Lukezic, Alvaro Garcia-Martin, Amir Saffari, Ang Li, Andres Solıs Montero, Baojun Zhao, Cordelia Schmid, Dapeng Chen, Dawei Du, Fahad Shahbaz Khan, Fatih Porikli, Gao Zhu, Guibo Zhu, Hanqing Lu, Hilke Kieritz, Hongdong Li, Honggang Qi, Jae-chan Jeong, Jae-il Cho, Jae-Yeong Lee, Jianke Zhu, Jiatong Li, Jiayi Feng, Jinqiao Wang, Ji-Wan Kim, Jochen Lang, Jose M. Martinez, Kai Xue, Karteek Alahari, Liang Ma, Lipeng Ke, Longyin Wen, Luca Bertinetto, Martin Danelljan, Michael Arens, Ming Tang, Ming-Ching Chang, Ondrej Miksik, Philip H. S. Torr, Rafael Martin-Nieto, Robert Laganiere, Sam Hare, Siwei Lyu, Song-Chun Zhu, Stefan Becker, Stephen L. Hicks, Stuart Golodetz, Sunglok Choi, Tianfu Wu, Wolfgang Hubner, Xu Zhao, Yang Hua, Yang Li, Yang Lu, Yuezun Li, Zejian Yuan, Zhibin Hong
Publikováno v:
ICCV Workshops
The Thermal Infrared Visual Object Tracking challenge 2015, VOT-TIR2015, aims at comparing short-term single-object visual trackers that work on thermal infrared (TIR) sequences and do not apply pre-learned models of object appearance. VOT-TIR2015 is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1a5112225d2aeb0382a66fc9a1ba3343
https://doi.org/10.1109/iccvw.2015.86
https://doi.org/10.1109/iccvw.2015.86
Autor:
Georg Nebehay, Roman Pflugfelder
Publikováno v:
CVPR
We propose a novel method for establishing correspondences on deformable objects for single-target object tracking. The key ingredient is a dissimilarity measure between correspondences that takes into account their geometric compatibility, allowing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d1d92f6d7039b5428cbe9d3dd5d02672
https://doi.org/10.1109/cvpr.2015.7298895
https://doi.org/10.1109/cvpr.2015.7298895
Autor:
Kristoffer Öfjäll, Zhen Lei, Fahad Shahbaz Khan, Karel Lebeda, Tomas Vojir, Ming-Ming Cheng, Jorge Batista, Georg Nebehay, Dominik Pangersic, Bohyung Han, Ales Leonardis, Jin-Woo Choi, Lei Qin, Seunghoon Hong, Yuankai Qi, Cherkeng Heng, Amir Saffari, Jiri Matas, Jijia Li, Gustav Häger, Weiyao Lin, Christophe Garcia, Stan Z. Li, Alfredo Petrosino, Martin Danelljan, Michael Felsberg, Kwang Moo Yi, Sam Hare, Mario Edoardo Maresca, Joost van de Weijer, Bo Li, Hyeonseob Nam, Aleksandar Dimitriev, Horst Bischof, Matej Kristan, Simon Hadfield, Vibhav Vineet, Philip H. S. Torr, Zhiheng Niu, Luka Cehovin, Jianke Zhu, Richard Bowden, Horst Possegger, Longyin Wen, Alan Lukezic, Stuart Golodetz, Thomas Mauthner, Gustavo Fernandez, Jin-Young Choi, Samantha Yueying Lim, Qingming Huang, João F. Henriques, Yang Li, Stefan Duffner, Roman Pflugfelder, Franci Oven, Shengcai Liao
Publikováno v:
Computer Vision-ECCV 2014 Workshops ISBN: 9783319161808
ECCV Workshops (2)
Workshop on Visual Object Tracking Challenge (VOT2014)-ECCV
Workshop on Visual Object Tracking Challenge (VOT2014)-ECCV, Sep 2014, Zurich, Switzerland. pp.1-27
ECCV Workshops (2)
Workshop on Visual Object Tracking Challenge (VOT2014)-ECCV
Workshop on Visual Object Tracking Challenge (VOT2014)-ECCV, Sep 2014, Zurich, Switzerland. pp.1-27
The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 38 trackers are presented. The number of tested trackers makes VOT 20
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7ec65e47dd03dfe9e0bfab5419a98ce2
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-121006
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-121006
Autor:
Georg Nebehay, Gustavo Fernández Domínguez, Lukas Esterle, Jennifer Simonjan, Bernhard Rinner
Publikováno v:
ICDSC
We have developed a self-aware multi-camera multi-object tracking application for distributed heterogeneous smart camera networks. This application is able to track multiple persons through the network whereby the cameras are able to transfer the tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d52b884894061f7630a4ca0c0dbed9d8
https://doi.org/10.1145/2659021.2669474
https://doi.org/10.1145/2659021.2669474
Autor:
Georg Nebehay, Roman Pflugfelder
Publikováno v:
WACV
We propose a novel keypoint-based method for long-term model-free object tracking in a combined matching-and-tracking framework. In order to localise the object in every frame, each keypoint casts votes for the object center. As erroneous keypoints a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::31ffe9b1fbbb9ac2fa065903afdaa922
https://doi.org/10.1109/wacv.2014.6836013
https://doi.org/10.1109/wacv.2014.6836013
Autor:
Bernhard Rinner, Jennifer Simonjan, Gustavo Fernandez, Georg Nebehay, Lukas Esterle, Bernhard Dieber, Roman Pflugfelder
Publikováno v:
ICDSC
Despite significant interest in the research community, the development of multi-camera applications is still quite challenging. This paper presents Ella - a dedicated publish/subscribe middleware system that facilitates distribution, component reuse
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a9595c7ea140a51f17756a760f9ee76
https://doi.org/10.1109/icdsc.2013.6778223
https://doi.org/10.1109/icdsc.2013.6778223