archive-at.com » AT » T » TUGRAZ.AT

Total: 196

Choose link from "Titles, links and description words view":

Or switch to "Titles and links view".
  • Learning, Recognition, and Surveillance @ ICG
    3D Hand Pose Estimation by Exploiting Uncertainties bib project Georg Poier Konstantinos Roditakis Samuel Schulter Damien Michel Horst Bischof and Antonis A Argyros In Proc British Machine Vision Conference BMVC 2015 oral presentation Interactive Segmentation of Rock Art in High Resolution 3D Reconstructions bib Matthias Zeppelzauer Georg Poier Markus Seidl Christian Reinbacher Christian Breiteneder Horst Bischof and Samuel Schulter In Proc Digital Heritage Conference DH 2015 oral presentation winner of the best paper price You Should Use Regression to Detect Cells bib Philipp Kainz Martin Urschler Samuel Schulter Paul Wohlhart and Vincent Lepetit In Proceedings of the Conference on Medical Image Computing and Computer Assisted Intervention MICCAI 2015 Fast and Accurate Image Upscaling with Super Resolution Forests bib Samuel Schulter Christian Leistner and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2015 Supplemental Material Code 2014 Hough Forests Revisited An Approach to Multiple Instance Tracking from Multiple Cameras bib Georg Poier Samuel Schulter Sabine Sternig Peter M Roth and Horst Bischof In Proc German Conference on Pattern Recognition GCPR DAGM 2014 The original publication is available at www springer com Accurate Object Detection with Joint Classification Regression Random Forests bib Samuel Schulter Christian Leistner Paul Wohlhart Peter M Roth and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2014 2013 Alternating Regression Forests for Object Detection and Pose Estimation bib Samuel Schulter Christian Leistner Paul Wohlhart Peter M Roth and Horst Bischof In Proc International Conference on Computer Vision ICCV 2013 Unsupervised Object Discovery and Segmentation in Videos bib Samuel Schulter Christian Leistner Peter M Roth and Horst Bischof In Proc British Machine Vision Conference BMVC 2013 Ordinal Random Forests for Object Detection bib Samuel Schulter Peter M Roth and Horst Bischof In Proc German Conference on Pattern Recognition GCPR DAGM 2013 Alternating Decision Forests bib Samuel Schulter Paul Wohlhart Christian Leistner Amir Saffari Peter M Roth and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2013 2012 Discriminative Hough Forests for Object Detection bib Paul Wohlhart Samuel Schulter Martin Koestinger Peter M Roth and Horst Bischof In Proc British Machine Vision Conference BMVC 2012 2011 OUTLIER Online Learning and Visualization of Unusual Events bib Josef Birchbauer Samuel Schulter Rene Schuster Georg Poier Martin Winter Peter Schallauer and Peter M Roth and Horst Bischof In Proc IEEE International Conference on Advanced Video and Signal Based Surveillance AVSS Demo Session 2011 Improving Classifiers with Unlabeled Weakly Related Videos bib Christian Leistner Martin Godec Samuel Schulter Amir Saffari Manuel Werlberger and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2011 On line Hough Forests bib Samuel Schulter Christian Leistner Peter M Roth Luc Van Gool and Horst Bischof In Proc British Machine Vision Conference BMVC 2011 Multi Cue Learning and Visualization of Unusual Events bib Rene Schuster Samuel Schulter Georg Poier Martin Hirzer Josef Birchbauer Peter M Roth Horst Bischof Martin Winter and Peter Schallauer In Proc 11th IEEE Workshop on Visual

    Original URL path: http://lrs.icg.tugraz.at/members/schulter (2016-02-14)
    Open archived version from archive


  • Learning, Recognition, and Surveillance @ ICG
    Weiming Hu Wolfgang Hübner Xiaomeng Wang Xin Li Xinchu Shi Xu Zhao Xue Mei Yao Shizeng Yang Hua Yang Li Yang Lu Yuezun Li Zhaoyun Chen Zehua Huang Zhe Chen Zhe Zhang Zhenyu He and Zhibin Hong In Proc Workshop on the Visual Object Tracking Challenge VOT in conjunction with ICCV 2015 Pairwise Linear Regression An Efficient and Fast Multi view Facial Expression Recognition bib Mahdi Jampour Thomas Mauthner and Horst Bischof In Proc IEEE International Conference on Automatic Face and Gesture Recognition FG 2015 Multi view Facial Expressions Recognition using Local Linear Regression of Sparse Codes bib Mahdi Jampour Thomas Mauthner and Horst Bischof In Proc Computer Vision Winter Workshop CVWW 2015 2014 Improved Sport Activity Recognition using Spatio temporal Context bib Georg Waltner Thomas Mauthner and Horst Bischof In Proc DVS Conference on Computer Science in Sport DVS GSSS 2014 Indoor Activity Detection and Recognition for Automated Sport Games Analysis bib Georg Waltner Thomas Mauthner and Horst Bischof In Proc Workshop of the Austrian Association for Pattern Recognition AAPR OAGM 2014 Occlusion Geodesics for Online Multi Object Tracking bib code Horst Possegger Thomas Mauthner Peter M Roth and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2014 A novel method for the analysis of sequential actions in team handball bib Paul Rudelsdorfer Norbert Schrapf Horst Possegger Thomas Mauthner Horst Bischof and Markus Tilp International Journal of Computer Science in Sport IJCSS 13 1 69 84 2014 The original publication is available at iacss org The Visual Object Tracking VOT2014 challenge results bib Matej Kristan Roman Pflugfelder Aleš Leonardis Ji i Matas Luka Čehovin Georg Nebehay Tomáš Vojí Gustavo Fernández Alan Lukežič Aleksandar Dimitriev Alfredo Petrosino Amir Saffari Bo Li Bohyung Han Cherkeng Heng Christophe Garcia Dominik Pangeršič Gustav Häger Fahad Shahbaz Khan Franci Oven Horst Possegger Horst Bischof Hyeonseob Nam Jianke Zhu JiJia Li Jin Young Choi Jin Woo Choi João F Henriques Joost van de Weijer Jorge Batista Karel Lebeda Kristoffer Öfjäll Kwang Moo Yi Lei Quin Longyin Wen Mario Edoardo Maresca Martin Danelljan Michael Felsberg Ming Ming Cheng Philip Torr Quingming Huang Richard Bowden Sam Hare Samantha YueYing Lim Seunghoon Hong Shengcai Liao Simon Hadfield Stan Z Li Stefan Duffner Stuart Golodetz Thomas Mauthner Vibhav Vineet Weiyao Lin Yang Li Yuankai Qui Zhen Lei and Zhiheng Niu In Proc Workshop on the Visual Object Tracking Challenge VOT in conjunction with ECCV 2014 The publication and additional resources are available at votchallenge net 2013 Robust Real Time Tracking of Multiple Objects by Volumetric Mass Densities bib data Horst Possegger Sabine Sternig Thomas Mauthner Peter M Roth and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2013 2012 Learn to Move Activity Specific Motion Models for Tracking by Detection bib Thomas Mauthner Peter M Roth and Horst Bischof In IEEE International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams ARTEMIS in conjunction with ECCV 2012 SkiTracker Robust Outdoor PTZ Tracking bib Thomas Mauthner

    Original URL path: http://lrs.icg.tugraz.at/members/mauthner (2016-02-14)
    Open archived version from archive

  • Learning, Recognition, and Surveillance @ ICG
    of an occupancy volume exploiting the full geometry and the objects center of mass and develop an efficient algorithm for 3D object tracking Individual objects are tracked using the local mass density scores within a particle filter based approach constrained by a Voronoi partitioning between nearby trackers We benefit from the geometric knowledge given by the occupancy volume to robustly extract features and train classifiers on demand when volumetric information becomes unreliable We evaluate our approach on several challenging real world scenarios including the public APIDIS dataset Experimental evaluations demonstrate significant improvements compared to state of the art methods while achieving real time performance See also Download the ICG Lab 6 dataset 614 MB Download the ICG Lab 6 evaluation code protocol 32 KB MATLAB View the short summary video results vimeo Selected publications Robust Real Time Tracking of Multiple Objects by Volumetric Mass Densities bib data Horst Possegger Sabine Sternig Thomas Mauthner Peter M Roth and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2013 Short summary additional tracking results Unsupervised Calibration of Camera Networks and Virtual PTZ Cameras CVWW 12 Authors Possegger Rüther Sternig Mauthner Klopschitz Roth and Bischof Pan Tilt Zoom PTZ cameras are widely used in video surveillance tasks In particular they can be used in combination with static cameras to provide high resolution imagery of interesting events in a scene on demand Nevertheless PTZ cameras only provide a single trajectory at a time Hence engineering algorithms for common computer vision tasks such as automatic calibration or tracking for camera networks including PTZ cameras is difficult Therefore we implemented a virtual PTZ vPTZ camera to simplify the algorithm development for such camera networks The vPTZ camera is built on a cylindrical panoramic view of the scene and allows to reposition its field of view arbitrarily to provide several trajectories The vPTZ camera has been used to develop an unsupervised extrinsic self calibration method for a network of static cameras and PTZ cameras solely based on correspondences between tracks of a walking human Our experimental results show that we can obtain accurate estimates of the extrinsic camera parameters in both outdoor and indoor scenarios See also Download the sample vPTZ implementation C Download the multi camera vPTZ datasets View the short summary video results vimeo Selected publications Unsupervised Calibration of Camera Networks and Virtual PTZ Cameras bib code data Horst Possegger Matthias Rüther Sabine Sternig Thomas Mauthner Manfred Klopschitz Peter M Roth and Horst Bischof In Proc Computer Vision Winter Workshop CVWW 2012 Short summary calibration results Downloads Code Generic Distractor Aware Object Tracking CVPR 15 We provide a MATLAB reimplementation for our paper In Defense of Color based Model free Tracking The provided package also contains a short test sequence to test it out of the box Download here 5 4 MB MATLAB Selected publications In Defense of Color based Model free Tracking bib code Horst Possegger Thomas Mauthner and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2015 Code Multi Object Tracking Occlusion Geodesics CVPR 14 We provide the MATLAB implementation for our paper Occlusion Geodesics for Online Multi Object Tracking The provided package also contains a short test sequence to demonstrate the capabilities of the multi object tracker Download here 31 MB MATLAB Selected publications Occlusion Geodesics for Online Multi Object Tracking bib code Horst Possegger Thomas Mauthner Peter M Roth and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2014 Dataset Multi Camera Scenarios ICG Lab 6 CVPR 13 This dataset contains 6 indoor people tracking scenarios recorded at our laboratory using 4 static Axis P1347 cameras Changing appearance Chap This sequence depicts a standard surveillance scenario where 5 people move unconstrained within the laboratory Throughout the scene the people change their visual appearance by putting on jackets with significantly different colors than their sweaters Leapfrogs Leaf 1 2 These scenarios depict leapfrog games where players leap over each other s stooped backs Specific challenges of these sequences are the spatial proximity of players out of plane motion and difficult poses Musical chairs Much This sequence shows 4 people playing musical chairs and a non playing moderator who starts and stops the recorded music Due to the nature of this game this sequence exhibits fast motion as well as crowded situations e g when all players race to the available chairs Furthermore sitting on the chairs is a rather unusual pose for typical surveillance scenarios and violates the commonly used constraint of standing persons Pose This sequence shows up to 6 people in various poses such as standing walking kneeling crouching crawling sitting and stepping on ladders Table This scenario exhibits significant out of plane motion as up to 5 people walk and jump over a table For each scenario we provide the synchronized video streams the full extrinsic intrinsic camera calibration manually annotated groundtruth for every 10th frame as well as a top view model of the ground plane Furthermore we provide MATLAB evaluation scripts for comparison using the CLEAR MOT performance metrics Download the ICG Lab 6 dataset 614 MB and the corresponding evaluation code protocol 32 KB MATLAB Selected publications Robust Real Time Tracking of Multiple Objects by Volumetric Mass Densities bib data Horst Possegger Sabine Sternig Thomas Mauthner Peter M Roth and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2013 Dataset Multi Camera Virtual PTZ Scenarios CVWW 12 This dataset contains the video streams and calibrations of several static Axis P1347 cameras and one panoramic video from a spherical Point Grey Ladybug3 camera for two scenarios The first scenario outdoor shows a crowded campus of our university while the second sequence indoor was recorded during the preparations of a handball training game at a sports hall in Graz The panoramic imagery can be used to simulate a PTZ camera with the provided implementation of the virtual PTZ vPTZ camera Available for download here Selected publications Unsupervised Calibration of

    Original URL path: http://lrs.icg.tugraz.at/members/possegger (2016-02-14)
    Open archived version from archive

  • Learning, Recognition, and Surveillance @ ICG
    face pairs also for face identification Second we show how to learn and combine person specific metrics for face identification improving the classification power We demonstrate the method for different face recognition tasks where we are able to match or slightly outperform state of the art multi task learning approaches The work was supported by the Austrian Science Foundation FWF project Advanced Learning for Tracking and Detection in Medical Workflow Analysis I535 N23 and by the Austrian Research Promotion Agency FFG project SHARE in the IV2Splus program Full text pdf Robust Face Detection by Simple Means CVAW DAGM OEAGM 2012 Koestinger Wohlhart Roth Bischof Face detection is still one of the core problems in computer vision especially in unconstrained real world situations where variations in face pose or bad imaging conditions have to be handled These problems are covered by recent benchmarks such as Face Detection Dataset and Benchmark FDDB Jain and Learned Miller 2010 which reveals that established methods e g Viola and Jones Viola and Jones 2001 suffer a drop in performance More effctive approaches exist but are closed source and not publicly available Thus we propose a simple but effective detector that is available to the public It combines Histograms of Orientated Gradient HOG Dalal and Triggs 2005 features with linear Support Vector Machine SVM classiffication The work was supported by the Austrian Science Foundation FWF project Advanced Learning for Tracking and Detection in Medical Workflow Analysis I535 N23 and by the Austrian Research Promotion Agency FFG project SHARE in the IV2Splus program Full text pdf Code available soon C Videos Face Recognition media player from Videos only using Weakly Related Information Cues media player Visual Speaker Identification media player Face Detection media player Optical Character Recognition in Videos VideoOCR and Natural Images Source Image with inpainted text Student Projects TBA Publications 2014 Mahalanobis Distance Learning for Person Re Identification bib Peter M Roth Martin Hirzer Martin Koestinger Csaba Beleznai and Horst Bischof In Person Re Identification pages 247 267 Springer 2014 The original publication is available at www springer com 2013 Joint Learning of Discriminative Prototypes and Large Margin Nearest Neighbor Classifiers bib Martin Koestinger Paul Wohlhart Peter M Roth and Horst Bischof In Proc International Conference on Computer Vision ICCV 2013 Efficient Retrieval for Large Scale Metric Learning bib Martin Koestinger Peter M Roth and Horst Bischof In Proc German Conference on Pattern Recognition GCPR DAGM 2013 Optimizing 1 Nearest Prototype Classifiers bib Paul Wohlhart Martin Koestinger Michael Donoser Peter M Roth and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2013 2012 Dense Appearance Modeling and Efficient Learning of Camera Transitions for Person Re Identification bib Martin Hirzer Csaba Beleznai Martin Koestinger Peter M Roth and Horst Bischof In Proc IEEE International Conference on Image Processing ICIP 2012 Relaxed Pairwise Learned Metric for Person Re Identification bib Martin Hirzer Peter M Roth Martin Koestinger and Horst Bischof In Proc European Conference on Computer Vision ECCV 2012 The original publication

    Original URL path: http://lrs.icg.tugraz.at/members/koestinger (2016-02-14)
    Open archived version from archive

  • Learning, Recognition, and Surveillance @ ICG
    bib Samuel Schulter Christian Leistner Paul Wohlhart Peter M Roth and Horst Bischof In Proc International Conference on Computer Vision ICCV 2013 Joint Learning of Discriminative Prototypes and Large Margin Nearest Neighbor Classifiers bib Martin Koestinger Paul Wohlhart Peter M Roth and Horst Bischof In Proc International Conference on Computer Vision ICCV 2013 Alternating Decision Forests bib Samuel Schulter Paul Wohlhart Christian Leistner Amir Saffari Peter M Roth and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2013 Optimizing 1 Nearest Prototype Classifiers bib Paul Wohlhart Martin Koestinger Michael Donoser Peter M Roth and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2013 2012 Large Scale Metric Learning from Equivalence Constraints bib Martin Koestinger Martin Hirzer Paul Wohlhart Peter M Roth and Horst Bischof In Proc IEEE Conference on Computer Vision and Pattern Recognition CVPR 2012 Robust Face Detection by Simple Means bib Martin Koestinger Paul Wohlhart Peter M Roth and Horst Bischof In Computer Vision in Applications Workshop DAGM 2012 Detecting Partially Occluded Objects with an Implicit Shape Model Random Field bib Paul Wohlhart Michael Donoser Peter M Roth and Horst Bischof In Proc Asian Conference on Computer Vision ACCV 2012 Winner of the Best Paper Award Discriminative Hough Forests for Object Detection bib Paul Wohlhart Samuel Schulter Martin Koestinger Peter M Roth and Horst Bischof In Proc British Machine Vision Conference BMVC 2012 2011 Open Source Intelligence am Beispiel von KIRAS MDL Multimedia Documentation Lab bib Gerhard Backfried Dorothea Aniola Gerald Quirchmayr Werner Winiwarter Klaus Mak H C Pilles Christian Meurers Martin Koestinger Paul Wohlhart and Peter M Roth In Proceedings of 9 Sicherheitskonferenz Krems Donau Universitaet Krems 2011 Learning to Recognize Faces from Videos and Weakly Related Information Cues bib Martin Koestinger Paul Wohlhart Peter M Roth

    Original URL path: http://lrs.icg.tugraz.at/members/wohlhart (2016-02-14)
    Open archived version from archive

  • Learning, Recognition, and Surveillance @ ICG
    about 25k annotated faces in real world images Of these faces 59 are tagged as female 41 are tagged as male updated some images contain multiple faces No rescaling or cropping has been performed Most of the images are color although some of them gray scale In total AFLW contains roughly 380k manually annotated facial landmarks of a 21 point markup The facial landmarks are annotated upon visibility So no annotation is present if a facial landmark e g left ear lobe is not visible A wide range of natural face poses is captured The database is not limited to frontal or near frontal faces Additional to the landmark annotation the database provides face rectangles and ellipses The ellipses are compatible with the FDDB protocol Further we include the coarse head pose obtained by fitting a mean 3D face with the POSIT algorithm A rich set of tools to work with the annotations is provided e g a database backend that enables to import other face collections and annotation types Also a graphical user interface is provided that enables to view and manipulate the annotations Due to the nature of the database and the comprehensive annotation we think it is well suited to train and test algorithms for facial feature localization multi view face detection coarse head pose estimation License agreement By downloading the database you agree to the following restrictions The AFLW database is available for non commercial research purposes only The AFLW database includes images obtained from FlickR which are not property of Graz University of Technology Graz University of Technology is not responsible for the content nor the meaning of these images Any use of the images must be negociated with the respective picture owners according to the Yahoo terms of use In particular you agree not to reproduce duplicate copy sell trade resell or exploit for any commercial purposes any portion of the images and any portion of derived data You agree not to further copy publish or distribute any portion of the AFLW database Except for internal use at a single site within the same organization it is allowed to make copies of the database All submitted papers or any publicly available text using the AFLW database must cite the following paper Annotated Facial Landmarks in the Wild A Large scale Real world Database for Facial Landmark Localization pdf bibtex Martin Koestinger Paul Wohlhart Peter M Roth and Horst Bischof In First IEEE International Workshop on Benchmarking Facial Image Analysis Technologies 2011 The organization represented by you will be listed as users of the AFLW database Download instructions If you agree with the terms of the license agreement contact Michael Opitz michael opitz at icg tugraz at to obtain download instructions Please send the email from your official account so we can verify your affiliation and include your Name Position job title Organization and the intended use If you already received your login credentials you can proceed to the download section Additional notes Unfortunately some

    Original URL path: http://lrs.icg.tugraz.at/research/aflw/ (2016-02-14)
    Open archived version from archive

  • Learning, Recognition, and Surveillance @ ICG
    the experiments If you want to use the original extracted features before PCA compression download the kissme features full zip 887 11 MB archive Installing other competing metric learning methods The experiments described in the paper benchmark our method KISSME to other metric learning methods LMNN ITML LDML SVMs Due to different licenses these are not pre installed by default If you agree to these install the code with the following matlab snipet For details click on the link below run fullfile BASE DIR KISSME toolbox install3dpartylibs m Quick Start Running Experiments Change the directory to KISSME workflows CVPR cd fullfile BASE DIR KISSME workflows CVPR Pick the experiment of your choice and run the according script i e demo viper m To run all experiments ToyCars VIPeR run fullfile cd demo toycars m run fullfile cd demo viper m PubFig LFW run fullfile cd demo pubfig m run fullfile cd demo lfw sift m run fullfile cd demo lfw attributes m Note For LFW and PubFig only KISSME is enabled per default For some of the other algorithms it takes quite long to complete If you want to train all installed learning algorithms uncomment the respective code Check the inline comments for details e g in demo lfw sift m License The toolbox code is licensed under the BSD 3 Clause License modified BSD license If you use the code i e our algorithm in a scientific publication please cite this paper For the provided data please check the included copyright notice as it is partly based on other data References 1 L M Bregman The Relaxation Method of Finding the Common Point of Convex Sets and Its Application to the Solution of Problems in Convex Programming USSR Computational Mathematics and Mathematical Physics 7 200 217 1967 2 C C Chang and C J Lin LIBSVM A library for support vector machines ACM Trans on Intelligent Systems and Technology 2 27 1 27 27 2011 3 J V Davis B Kulis P Jain S Sra and I S Dhillon Information theoretic metric learning In Proc IEEE Intern Conf on Machine Learning 2007 4 M Dikmen E Akbas T S Huang and N Ahuja Pedestrian recognition with a learned metric In Proc Asian Conf on Computer Vision 2010 5 M Farenzena L Bazzani A Perina V Murino and M Cristani Person re identification by symmetry driven accumulation of local features In Proc IEEE Intern Conf on Computer Vision and Pattern Recognition 2010 6 D Gray S Brennan and H Tao Evaluating appearance models for recongnition reacquisition and tracking In Proc IEEE Intern Workshop on Performance Evaluation of Tracking and Surveillance 2007 7 D Gray and H Tao Viewpoint invariant pedestrian recognition with an ensemble of localized features In Proc European Conf on Computer Vision 2008 8 M Guillaumin J Verbeek and C Schmid Is that you Metric learning approaches for face identification In Proc IEEE Intern Conf on Computer Vision 2009 9 M Guillaumin J Verbeek and C Schmid Multiple

    Original URL path: http://lrs.icg.tugraz.at/research/kissme/ (2016-02-14)
    Open archived version from archive

  • Learning, Recognition, and Surveillance @ ICG
    a negative label providing the required stability The experimental results demonstrate that using the proposed approach state of the art detection results can by obtained however showing superior classification results in presence of non moving objects TransientBoost Sternig Godec Roth Bischof 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 instance learning have been proposed However these methods are either too adaptive which causes drifting or biased by a prior which hinders incorporation of new orthogonal information Therefore we propose a new boosting based on line learning algorithm TransientBoost which is highly adaptive but still robust This is realized by using an internal multi class representation and modeling reliable and unreliable data in separate classes Unreliable data is considered transient hence we use highly adaptive learning parameters to adapt to fast changes in the scene while errors fade out fast In contrast the reliable data is preserved completely and not harmed by wrong updates We demonstrate our algorithm on two different representative tasks ie object detection and object tracking showing that we can handle typical problems considerable better than existing approaches In addition to demonstrate the stability and the robustness we show long term experiments for both tasks media player Longterm Tracking Results Robust Adaptive Real time Object Detection based on Classifier Grids We introduce classifier grids in order to develop an adaptive but still robust real time object detector for static cameras Instead of using a sliding window for object detection we propose to train a separate classifier for each image location obtaining a very specific object detector with a low false alarm rate For each classifier corresponding to a grid element we estimate two generative representations in parallel one describing the object s class and one describing the background These are combined in order to obtain a discriminative model To enable to adapt to changing environments these classifiers are learned on line i e boosting Continuously learning 24 hours a day 7 days a week requires a stable system In our method this is ensured by a fixed object representation while updating only the representation of the background We demonstrate the stability in a long term experiment by running the system for a whole week which shows a stable performance over time In addition we compare the proposed approach to state of the art methods in the field of person and car detection In both cases we obtain competitive results Download the ICVSS 2009 Poster Datasets Longterm dataset used in Classifier Grids for Robust Adaptive Object Detection CVPR 09 Download Downloads media player Download Results Caviar Sequence video download Download Results Pets Sequence free media player Download Results Highway Sequence media player Download Results Corridor Sequence Publications 2014 Hough Forests Revisited An Approach to Multiple Instance Tracking from Multiple Cameras bib Georg Poier Samuel Schulter Sabine Sternig Peter M Roth

    Original URL path: http://lrs.icg.tugraz.at/members/sternig (2016-02-14)
    Open archived version from archive