Navigation

Horst Possegger


H. Possegger E-Mail possegger(at)icg.tugraz.at
Phone +43 316 873-5033
Office Room E3.09 (IE02112)

Google Scholar ResearchGate DBLP

Short CV

I received the BSc and MSc degrees in Software Development and Business Management from Graz University of Technology in 2011 and 2013, respectively. Currently, I am a PhD student at the Institute for Computer Graphics and Vision at Graz University of Technology, Austria.

Contents

On this web page you can find:

News

October 2016

Looking forward to attend the Google Computer Vision PhD Summit in Zürich.

June 2016

I will be interning at X, the moonshot factory (formerly Google[x], CA) this summer.

May 2015

I will be giving a Featured Talk (Distractor-aware Model-free Tracking) at OAGM'15

March 2015

Our papers In Defense of Color-based Model-free Tracking and Encoding based Saliency Detection for Videos and Images got accepted at CVPR'15.

April 2014

I will be giving a Featured Talk (Geometric Cues for Online Multi-Object Tracking) at OAGM'14 and got accepted at ICVSS'14.

March 2014

Our paper Occlusion Geodesics for Online Multi-Object Tracking got accepted at CVPR'14.

March 2013

I received my MSc degree from Graz University of Technology.

February 2013

Our paper Robust Real-Time Tracking of Multiple Objects by Volumetric Mass Densities was accepted at CVPR'13.

We won the OCG Best Student Paper Award at CVWW'13.

Student Opportunities

I'm currently offering several bachelor and master projects!

The topics are typically in the field of machine learning, with computer vision applications to object tracking, learning from videos, etc.

You can find a list of current topics here.

Exemplary student projects (click teaser image for details):

Tracking for Nanomedicine Pedestrian intent

Projects

In Defense of Color-based Model-free Tracking (CVPR'15)

Authors: Possegger*, Mauthner*, and Bischof
(* Both authors contributed equally)

In this work, we address the problem of model-free online object tracking based on color representations. According to the findings of recent benchmark evaluations, such trackers often tend to drift towards regions which exhibit similar appearance compared to the object of interest. To overcome this limitation, we propose an efficient discriminative object model which allows to identify potentially distracting regions in advance. Furthermore, we exploit this knowledge to adapt the object representation beforehand such that distractors are suppressed and the risk of drifting is significantly reduced.

We evaluate our approach on recent online tracking benchmark datasets demonstrating state-of-the-art results. In particular, our approach performs favorably both in terms of accuracy and robustness compared to recent tracking algorithms. Moreover, the proposed approach allows for an efficient implementation to enable online object tracking in real-time.

See also:
Selected publications:
  1. 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

Short summary & additional tracking results

Encoding based Saliency Detection for Videos and Images (CVPR'15)

Authors: Mauthner, Possegger, Waltner, and Bischof

We present a novel video saliency detection method to support human activity recognition and weakly supervised training of activity detection algorithms. Recent research has emphasized the need for saliency analysis to minimize dataset bias or to supervise weakly labeled training of activity detectors. In contrast to previous methods we do not rely on training information given by either eye-gaze or annotation data, but propose a fully unsupervised algorithm to find salient regions within videos. In general, we enforce the Gestalt principle of figure-ground segregation for both appearance and motion cues. We introduce an encoding approach that allows for efficient computation of saliency by approximating joint feature distributions. We evaluate our approach on several datasets, including challenging scenarios with cluttered background and camera motion, as well as salient object detection in images. Overall, we demonstrate favorable performance compared to state-of-the-art methods in estimating both ground-truth eye-gaze and activity annotations.

See also:
Selected publications:
  1. Encoding based Saliency Detection for Videos and Images (bib) (supp) Thomas Mauthner, Horst Possegger, Georg Waltner, and Horst Bischof In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015

Short summary & additional results

Occlusion Geodesics for Online Multi-Object Tracking (CVPR'14)

Authors: Possegger, Mauthner, Roth, and Bischof

Robust multi-object tracking-by-detection requires the correct assignment of noisy detection results to object trajectories. We address this problem by proposing an online approach based on the observation that object detectors primarily fail if objects are significantly occluded. In contrast to most existing work, we only rely on geometric information to efficiently overcome detection failures. In particular, we exploit the spatio-temporal evolution of occlusion regions, detector reliability, and target motion prediction to robustly handle missed detections. In combination with a conservative association scheme for visible objects, this allows for real-time tracking of multiple objects from a single static camera, even in complex scenarios. Our evaluations on publicly available multi-object tracking benchmark datasets demonstrate favorable performance compared to the state-of-the-art in online and offline multi-object tracking.

See also:
Selected publications:
  1. 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

Short summary & additional tracking results

Robust Real-Time Tracking of Multiple Objects by Volumetric Mass Densities (CVPR'13)

Authors: Possegger, Sternig, Mauthner, Roth, and Bischof

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 objects moving on a common 2D ground-plane. To overcome these limitations, we introduce the concept 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:
Selected publications:
  1. 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:
Selected publications:
  1. 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:
  1. 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
DAT thumb

[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:
  1. 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
Occlusion geodesics thumb

[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:
  1. 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
R2T2 Thumbnails

[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:
  1. 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
vPTZ Dataset Thumbnails

[Code] Virtual PTZ (CVWW'12)

This sample C++ implementation of the virtual PTZ (vPTZ) camera allows to simulate a real PTZ camera from panoramic imagery.

Available for download here!

Selected publications:
  1. 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
vPTZ Thumbnail

Conference & Journal Publications

2017

  1. Pedestrian Detection in RGB-D Images from an Elevated Viewpoint (bib)Christian Ertler, Horst Possegger, Michael Opitz, and Horst Bischof In Proc. Computer Vision Winter Workshop (CVWW), 2017

2016

  1. Efficient Model Averaging for Deep Neural Networks (bib)Michael Opitz, Horst Possegger, and Horst Bischof In Proc. Asian Conference on Computer Vision (ACCV), 2016
  2. Grid Loss: Detecting Occluded Faces (bib) (supp)Michael Opitz, Georg Waltner, Georg Poier, Horst Possegger, and Horst Bischof In Proc. European Conference on Computer Vision (ECCV), 2016
  3. The Visual Object Tracking VOT2016 challenge results (bib)Matej Kristan, Aleš Leonardis, Jiři Matas, Michael Felsberg, Roman Pflugfelder, Luka Čehovin, Tomáš Vojiř, Gustav Häger, Alan Lukežič, Gustavo Fernández, Abhinav Gupta, Alfredo Petrosino, Alireza Memarmoghadam, Alvaro Garcia-Martin, Andrés Solís Montero, Andrea Vedaldi, Andreas Robinson, Andy J. Ma, Anton Varfolomieiev, Aydin Alatan, Aykut Erdem, Bernard Ghanem, Bin Liu, Bohyung Han, Brais Martinez, Chang-Ming Chang, Changsheng Xu, Chong Sun, Chong Sun, Daijin Kim, Dapeng Chen, Dawei Du, Dawei Du, Deepak Mishra, Dit-Yan Yeung, Erhan Gundogdu, Erkut Erdem, Fahad Khan, Fahad Shahbaz Khan, Fatih Porikli, Fei Zhao, Filiz Bunyak, Francesco Battistone, Gao Zhu, Giorgio Roffo, Gorthi R K Sai Subrahmanyam, Guilherme Bastos, Guna Seetharaman, Henry Medeiros, Hongdong Li, Honggang Qi, Horst Bischof, Horst Possegger, Huchuan Lu, Huchuan Lu, Hyemin Lee, Hyeonseob Nam, Hyung Jin Chang, Isabela Drummond, Jack Valmadre, Jae-chan Jeong, Jae-il Cho, Jae-Yeong Lee, Jianke Zhu, Jiayi Feng, Jin Gao, Jin Young Choi, Jingjing Xiao, Ji-Wan Kim, Jiyeoup Jeong, Joao F. Henriques, Jochen Lang, Jongwon Choi, Jose M. Martinez, Junliang Xing, Junyu Gao, Kannappan Palaniappan, Karel Lebeda, Ke Gao, Krystian Mikolajczyk, Lei Qin, Lijun Wang, Lijun Wang, Longyin Wen, Longyin Wen, Luca Bertinetto, Madan kumar Rapuru, Mahdieh Poostchi, Mario Maresca, Martin Danelljan, Matthias Mueller, Mengdan Zhang, Michael Arens, Michel Valstar, Ming Tang, Mooyeol Baek, Muhammad Haris Khan, Naiyan Wang, Nana Fan, Noor Al-Shakarji, Ondrej Miksik, Osman Akin, Payman Moallem, Pedro Senna, Philip H. S. Torr, Pong C. Yuen, Qingming Huang, Qingming Huang, Rafael Martin-Nieto, Rengarajan Pelapur, Richard Bowden, Robert Laganiere, Rustam Stolkin, Ryan Walsh, Sebastian B. Krah, Shengkun Li, Shengping Zhang, Shizeng Yao, Simon Hadfield, Simone Melzi, Siwei Lyu, Siwei Lyu, Siyi Li, Stefan Becker, Stuart Golodetz, Sumithra Kakanuru, Sunglok Choi, Tao Hu, Thomas Mauthner, Tianzhu Zhang, Tony Pridmore, Vincenzo Santopietro, Weiming Hu, Wenbo Li, Wolfgang Hübner, Xiangyuan Lan, Xiaomeng Wang, Xin Li, Yang Li, Yiannis Demiris, Yifan Wang, Yuankai Qi, Zejian Yuan, Zexiong Cai, Zhan Xu, Zhenyu He, and Zhizhen Chi In Proc. Workshop on the Visual Object Tracking Challenge (VOT, in conjunction with ECCV), 2016
  4. The Thermal Infrared Visual Object Tracking VOT-TIR2016 Challenge Results (bib)Michael Felsberg, Matej Kristan, Jiři Matas, Aleš Leonardis, Roman Pflugfelder, Gustav Häger, Amanda Berg, Abdelrahman Eldesokey, Jörgen Ahlberg, Luka Čehovin, Tomáš Vojiř, Alan Lukežič, Gustavo Fernández, Alfredo Petrosino, Alvaro Garcia-Martin, Andrés Solís Montero, Anton Varfolomieiev, Aykut Erdem, Bohyung Han, Chang-Ming Chang, Dawei Du, Erkut Erdem, Fahad Shahbaz Khan, Fatih Porikli, Fei Zhao, Filiz Bunyak, Francesco Battistone, Gao Zhu, Guna Seetharaman, Hongdong Li, Honggang Qi, Horst Bischof, Horst Possegger, Hyeonseob Nam, Jack Valmadre, Jianke Zhu, Jiayi Feng, Jochen Lang, Jose M. Martinez, Kannappan Palaniappan, Karel Lebeda, Ke Gao, Krystian Mikolajczyk, Longyin Wen, Luca Bertinetto, Mahdieh Poostchi, Mario Maresca, Martin Danelljan, Michael Arens, Ming Tang, Mooyeol Baek, Nana Fan, Noor Al-Shakarji, Ondrej Miksik, Osman Akin, Philip H. S. Torr, Qingming Huang, Rafael Martin-Nieto, Rengarajan Pelapur, Richard Bowden, Robert Laganiere, Sebastian B. Krah, Shengkun Li, Shizeng Yao, Simon Hadfield, Siwei Lyu, Stefan Becker, Stuart Golodetz, Tao Hu, Thomas Mauthner, Vincenzo Santopietro, Wenbo Li, Wolfgang Hübner, Xin Li, Yang Li, Zhan Xu, and Zhenyu He In Proc. Workshop on the Visual Object Tracking Challenge (VOT, in conjunction with ECCV), 2016

2015

  1. Encoding based Saliency Detection for Videos and Images (bib) (supp) Thomas Mauthner, Horst Possegger, Georg Waltner, and Horst Bischof In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015
  2. 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
  3. The Visual Object Tracking VOT2015 challenge results (bib)Matej Kristan, Jiři Matas, Aleš Leonardis, Michael Felsberg, Luka Čehovin, Gustavo Fernández, Tomáš Vojíř, Gustav Häger, Georg Nebehay, Roman Pflugfelder, Abhinav Gupta, Adel Bibi, Alan Lukežič, Alvaro Garcia-Martin, Alfredo Petrosino, Amir Saffari, Andrés Solís Montero, Anton Varfolomieiev, Atilla Baskurt, Baojun Zhao, Bernard Ghanem, Brais Martinez, Byeong Ju Lee, Bohyung Han, Chaohui Wang, Christophe Garcia, Chunyuan Zhang, Cordelia Schmid, Dacheng Tao, Daijin Kim, Dafei Huang, Danil Prokhorov, Dawei Du, Dit-Yan Yeung, Eraldo Ribeiro, Fahad Shahbaz Khan, Fatih Porikli, Filiz Bunyak, Gao Zhu, Guna Seetharaman, Hilke Kieritz, Hing Tuen Yau, Hongdong Li, Honggang Qi, Horst Bischof, Horst Possegger, Hyemin Lee, Hyeonseob Nam, Ivan Bogun, Jae-chan Jeong, Jae-il Cho, Jae-Yeong Lee, Jianke Zhu, Jianping Shi, Jiatong Li, Jiaya Jia, Jiayi Feng, Jin Gao, Jin Young Choi, Ji-Wan Kim, Jochen Lang, Jose M. Martinez, Jongwon Choi, Junliang Xing, Kai Xue, Kannappan Palaniappan, Karel Lebeda, Karteek Alahari, Ke Gao, Kimin Yun, Kin Hong Wong, Lei Luo, Liang Ma, Lipeng Ke, Longyin Wen, Luca Bertinetto, Mahdieh Pootschi, Mario Maresca, Martin Danelljan, Mei Wen, Mengdan Zhang, Michael Arens, Michel Valstar, Ming Tang, Ming-Ching Chang, Muhammad Haris Khan, Nana Fan, Naiyan Wang, Ondrej Miksik, Philip Torr, Qiang Wang, Rafael Martin-Nieto, Rengarajan Pelapur, Richard Bowden, Robert Laganière, Salma Moujtahid, Sam Hare, Simon Hadfield, Siwei Lyu, Siyi Li, Song-Chun Zhu, Stefan Becker, Stefan Duffner, Stephen L Hicks, Stuart Golodetz, Sunglok Choi, Tianfu Wu, Thomas Mauthner, Tony Pridmore, 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

2014

  1. 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
  2. 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)
  3. The Visual Object Tracking VOT2014 challenge results (bib)Matej Kristan, Roman Pflugfelder, Aleš Leonardis, Jiři Matas, Luka Čehovin, Georg Nebehay, Tomáš Vojíř, 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

  1. 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

  1. 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

Theses

2013

  1. Exploiting 3D Information for Robust Real-Time Tracking of Multiple Objects in Complex Scenarios (bib)Horst Possegger MSc. Thesis, Graz University of Technology, Faculty of Computer Science, 2013

2011

  1. Evaluation of Feature Representations for Object Detection with Boosted Classifiers Horst Possegger BSc. Thesis, Graz University of Technology, Faculty of Computer Science, 2011

Oral Presentations

  1. Distractor-Aware Model-free Tracking
    Featured talk at the Workshop of the Austrian Association for Pattern Recognition (AAPR/OAGM)
    Salzburg, Austria
    May, 2015
  2. Geometric Cues for Online Multi-Object Tracking
    Featured talk (invited) at the Workshop of the Austrian Association for Pattern Recognition (AAPR/OAGM)
    Maria Gugging, Austria
    May, 2014
  3. Multi-Camera Multi-Object Tracking from Visual Hulls
    Oral presentation (peer-reviewed) at the Computer Vision Winter Workshop (CVWW)
    Hernstein, Austria
    February, 2013
    Winner of the OCG Best Student Paper Award
  4. Unsupervised Calibration of Camera Networks and Virtual PTZ Cameras
    Oral presentation at Computer Vision Winter Workshop (CVWW)
    Mala Nedelja, Slovenia
    February, 2012

Professional Services

Journal Reviewer for:
  • Elsevier Computer Vision and Image Understanding (CVIU)
  • Elsevier Pattern Recognition (PR)
  • Elsevier Pattern Recognition Letters (PR LETTERS)
  • Elsevier Journal of Visual Communication and Image Representation (JVCI)
  • IEEE Transactions on Image Processing (TIP)
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
  • IEEE Signal Processing Letters (SP LETTERS)
  • International Journal of Distributed Sensor Networks (IJDSN)
  • Systems Science and Control Engineering (SSCE)
  • IET Computer Vision
Conference Reviewer for:
  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
  • European Conference on Computer Vision (ECCV), 2016
  • ACM SIGGRAPH Asia, 2016

Copyright 2010 ICG

Valid XHTML 1.1 Valid CSS