Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Sabine Sternig"'
Publikováno v:
Pattern Recognition Letters
Highlights ► Classifier grids showed excellent detection results for stationary cameras. ► On-line adaptive classifiers reduce the complexity of the classification task. ► Fixed update strategies allow long-term stability. ► Short-term stabil
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0a5b89567a4cc0a9650a4e7100fec84f
http://europepmc.org/articles/PMC3320709
http://europepmc.org/articles/PMC3320709
Publikováno v:
CVPR
Combining foreground images from multiple views by projecting them onto a common ground-plane has been recently applied within many multi-object tracking approaches. These planar projections introduce severe artifacts and constrain most approaches to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d767630eea308cb1855e54315db8da69
https://doi.org/10.1109/cvpr.2013.310
https://doi.org/10.1109/cvpr.2013.310
Publikováno v:
Lecture Notes in Computer Science
Computer Vision – ECCV 2012 ISBN: 9783642337116
ECCV (3)
Computer Vision – ECCV 2012 ISBN: 9783642337116
ECCV (3)
Object detection and segmentation are two challenging tasks in computer vision, which are usually considered as independent steps. In this paper, we propose a framework which jointly optimizes for both tasks and implicitly provides detection hypothes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c16dff960efab30c2869498328663403
Publikováno v:
ICCV Workshops
Recently, several approaches have been introduced for incorporating the information from multiple cameras to increase the robustness of tracking. This allows to handle problems of mutually occluding objects - a reasonable scenario for many tasks such
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::48c6bf2e9963524dc9afd4d3e2f5fa6a
https://doi.org/10.1109/iccvw.2011.6130453
https://doi.org/10.1109/iccvw.2011.6130453
Autor:
Dietmar Schabus, Bernhard Schalko, Harald Rainer, Yuriy Lypetskyy, Josef Alois Birchbauer, Sabine Sternig, Franz Graf, Michael Pucher, Wolfgang Schneider, Peter Schallauer, Michael Stadtschnitzer
Publikováno v:
ITSC
We present detection and tracking methods for highway monitoring based on video and audio sensors, and the combination of these two modalities. We evaluate the performance of the different systems on realistic data sets that have been recorded on Aus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9bb9b8b8dd487c8d37b91a6b07634c7e
https://doi.org/10.1109/itsc.2010.5625035
https://doi.org/10.1109/itsc.2010.5625035
Publikováno v:
ICPR
Recently, classifier grids have shown to be a considerable alternative for object detection from static cameras. However, one drawback of such approaches is drifting if an object is not moving over a long period of time. Thus, the goal of this work i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::80e40ca2769aed0ff508cf926b0e6f64
https://doi.org/10.1109/icpr.2010.194
https://doi.org/10.1109/icpr.2010.194
Publikováno v:
AVSS
Recently, classifier grids have shown to be a considerablealternative to sliding window approaches for objectdetection from static cameras. The main drawback of suchmethods is that they are biased by the initial model. In fact,the classifiers can be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3188cda2681340fc3323cb806b24c67d
https://doi.org/10.1109/avss.2010.10
https://doi.org/10.1109/avss.2010.10
Publikováno v:
CVPR Workshops
For on-line learning algorithms, which are applied in many vision tasks such as detection or tracking, robust integration of unlabeled samples is a crucial point. Various strategies such as self-training, semi-supervised learning and multiple-instanc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::736dd260b013646a203bf67b214e22dd
https://doi.org/10.1109/cvprw.2010.5543880
https://doi.org/10.1109/cvprw.2010.5543880
Publikováno v:
CVPR Workshops
Tracking and detection of objects often require to apply complex models to cope with the large intra-class variability of the foreground as well as the background class. In this work, we reduce the complexity of a binary classification problem by a c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eb7a85d006fb11c9ac300e524724d5c8
https://doi.org/10.1109/cvprw.2010.5543886
https://doi.org/10.1109/cvprw.2010.5543886
Publikováno v:
TU Graz
Lecture Notes in Computer Science ISBN: 9783319117515
GCPR
Lecture Notes in Computer Science ISBN: 9783319117515
GCPR
Tracking multiple objects in parallel is a difficult task, especially if instances are interacting and occluding each other. To alleviate the arising problems multiple camera views can be taken into account, which, however, increases the computationa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0c7d7081b2fbe533cf1065bf29e860a9
https://graz.pure.elsevier.com/en/publications/hough-forests-revisited-an-approach-to-multiple-instance-tracking-from-multiple-cameras(238ada9b-98f0-4085-9f84-5e387aa43f7c).html
https://graz.pure.elsevier.com/en/publications/hough-forests-revisited-an-approach-to-multiple-instance-tracking-from-multiple-cameras(238ada9b-98f0-4085-9f84-5e387aa43f7c).html
