Search For:

Displaying 1-28 out of 28 total
Coupled Detection and Trajectory Estimation for Multi-Object Tracking
Found in: Computer Vision, IEEE International Conference on
By Bastian Leibe, Konrad Schindler, Luc Van Gool
Issue Date:October 2007
pp. 1-8
We present a novel approach for multi-object tracking which considers object detection and spacetime trajectory estimation as a coupled optimization problem. It is formulated in a hypothesis selection framework and builds upon a state-of-the-art pedestrian...
 
A mobile vision system for robust multi-person tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Andreas Ess, Bastian Leibe, Konrad Schindler, Luc Van Gool
Issue Date:June 2008
pp. 1-8
We present a mobile vision system for multi-person tracking in busy environments. Specifically, the system integrates continuous visual odometry computation with tracking-by-detection in order to track pedestrians in spite of frequent occlusions and egomot...
 
Action snippets: How many frames does human action recognition require?
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Konrad Schindler, Luc van Gool
Issue Date:June 2008
pp. 1-8
Visual recognition of human actions in video clips has been an active field of research in recent years. However, most published methods either analyse an entire video and assign it a single action label, or use relatively large look-ahead to classify each...
 
Are Cars Just 3D Boxes? Jointly Estimating the 3D Shape of Multiple Objects
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Muhammad Zeeshan Zia,Michael Stark,Konrad Schindler
Issue Date:June 2014
pp. 3678-3685
Current systems for scene understanding typically represent objects as 2D or 3D bounding boxes. While these representations have proven robust in a variety of applications, they provide only coarse approximations to the true 2D and 3D extent of objects. As...
 
Predicting Matchability
Found in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Wilfried Hartmann,Michal Havlena,Konrad Schindler
Issue Date:June 2014
pp. 9-16
The initial steps of many computer vision algorithms are interest point extraction and matching. In larger image sets the pairwise matching of interest point descriptors between images is an important bottleneck. For each descriptor in one image the (appro...
 
Optimal Reduction of Large Image Databases for Location Recognition
Found in: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW)
By Michal Havlena,Wilfried Hartmann,Konrad Schindler
Issue Date:December 2013
pp. 676-683
For some computer vision tasks, such as location recognition on mobile devices or Structure from Motion (SfM) computation from Internet photo collections, one wants to reduce a large set of images to a compact, representative subset, sometimes called ``key...
 
Learning People Detectors for Tracking in Crowded Scenes
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Siyu Tang,Mykhaylo Andriluka,Anton Milan,Konrad Schindler,Stefan Roth,Bernt Schiele
Issue Date:December 2013
pp. 1049-1056
People tracking in crowded real-world scenes is challenging due to frequent and long-term occlusions. Recent tracking methods obtain the image evidence from object (people) detectors, but typically use off-the-shelf detectors and treat them as black box co...
 
Piecewise Rigid Scene Flow
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Christoph Vogel,Konrad Schindler,Stefan Roth
Issue Date:December 2013
pp. 1377-1384
Estimating dense 3D scene flow from stereo sequences remains a challenging task, despite much progress in both classical disparity and 2D optical flow estimation. To overcome the limitations of existing techniques, we introduce a novel model that represent...
 
Semantic tie points
Found in: 2013 IEEE Workshop on Applications of Computer Vision (WACV)
By Javier A. Montoya-Zegarra,Christian Leistner,Konrad Schindler
Issue Date:January 2013
pp. 377-384
Images for 3D mapping are always recorded in such a way that relevant scene parts are seen from multiple viewpoints, so as to facilitate camera orientation and 3D point triangulation. Beyond geometric reconstruction, automatic mapping also requires the sem...
 
3D scene flow estimation with a rigid motion prior
Found in: Computer Vision, IEEE International Conference on
By Christoph Vogel,Konrad Schindler,Stefan Roth
Issue Date:November 2011
pp. 1291-1298
We present an approach to 3D scene flow estimation, which exploits that in realistic scenarios image motion is frequently dominated by observer motion and independent, but rigid object motion. We cast the dense estimation of both scene structure and 3D mot...
 
New features and insights for pedestrian detection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Stefan Walk, Nikodem Majer, Konrad Schindler, Bernt Schiele
Issue Date:June 2010
pp. 1030-1037
Despite impressive progress in people detection the performance on challenging datasets like Caltech Pedestrians or TUD-Brussels is still unsatisfactory. In this work we show that motion features derived from optic flow yield substantial improvements on im...
 
Multibody Structure-from-Motion in Practice
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Kemal Egemen Ozden, Konrad Schindler, Luc Van Gool
Issue Date:June 2010
pp. 1134-1141
Multibody structure from motion (SfM) is the extension of classical SfM to dynamic scenes with multiple rigidly moving objects. Recent research has unveiled some of the mathematical foundations of the problem, but a practical algorithm which can handle rea...
 
Robust Multiperson Tracking from a Mobile Platform
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Andreas Ess, Bastian Leibe, Konrad Schindler, Luc van Gool
Issue Date:October 2009
pp. 1831-1846
In this paper, we address the problem of multiperson tracking in busy pedestrian zones using a stereo rig mounted on a mobile platform. The complexity of the problem calls for an integrated solution that extracts as much visual information as possible and ...
 
Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Bastian Leibe, Konrad Schindler, Nico Cornelis, Luc Van Gool
Issue Date:October 2008
pp. 1683-1698
We present a novel approach for multi-object tracking which considers object detection and spacetime trajectory estimation as a coupled optimization problem. Our approach is formulated in an MDL hypothesis selection framework, which allows it to recover fr...
 
Simultaneous Segmentation and 3D Reconstruction of Monocular Image Sequences
Found in: Computer Vision, IEEE International Conference on
By Kemal Egemen Ozden, Konrad Schindler, L. van Gool
Issue Date:October 2007
pp. 1-8
When trying to extract 3D scene information and camera motion from an image sequence alone, it is often necessary to cope with independently moving objects. Recent research has unveiled some of the mathematical foundations of the problem, but a general and...
 
Adaptive Object Tracking Based on an Effective Appearance Filter
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Hanzi Wang, David Suter, Konrad Schindler, Chunhua Shen
Issue Date:September 2007
pp. 1661-1667
We propose a similarity measure based on a Spatial-color Mixture of Gaussians (SMOG) appearance model for particle filters. This improves on the popular similarity measure based on color histograms because it considers not only the colors in a region but a...
 
Two-View Multibody Structure-and-Motion with Outliers through Model Selection
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Konrad Schindler, David Suter
Issue Date:June 2006
pp. 983-995
Multibody structure-and-motion (MSaM) is the problem to establish the multiple-view geometry of several views of a 3D scene taken at different times, where the scene consists of multiple rigid objects moving relative to each other. We examine the case of t...
 
Incremental Kernel SVD for Face Recognition with Image Sets
Found in: Automatic Face and Gesture Recognition, IEEE International Conference on
By Tat-Jun Chin, Konrad Schindler, David Suter
Issue Date:April 2006
pp. 461-466
Non-linear subspaces derived using kernel methods have been found to be superior compared to linear subspaces in modeling or classification tasks of several visual phenomena. Such kernel methods include Kernel PCA, Kernel DA, Kernel SVD and Kernel QR. Sinc...
 
Face Recognition from Video by Matching Image Sets
Found in: Digital Image Computing: Techniques and Applications
By Tat-Jun Chin, James U, Konrad Schindler, David Suter
Issue Date:December 2005
pp. 28
As opposed to still-image based paradigms, video-based face recognition involves identifying a person from a video input. In video-based approaches, face detection and tracking are performed together with recognition, as usually the background is included ...
 
Two-View Multibody Structure-and-Motion with Outliers
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Konrad Schindler, David Suter
Issue Date:June 2005
pp. 676-683
Multi-body structure-and-motion (MSaM) is the problem to establish the multiple-view geometry of several views of a 3D scene taken at different times, where the scene consists of multiple rigid objects moving relative to each other. We examine the case of ...
 
A Model-Based Method For Building Reconstruction
Found in: Higher-Level Knowledge in 3D Modeling and Motion Analysis, IEEE International Workshop on
By Konrad Schindler, Joachim Bauer
Issue Date:October 2003
pp. 74
In this paper model-based reconstruction methods are applied to the detailed reconstruction of buildings from close-range images. The 3D points obtained through image matching are segmented into a coarse polyhedral model with a robust regression algorithm,...
 
Continuous Energy Minimization for Multitarget Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Anton Milan,Stefan Roth,Konrad Schindler
Issue Date:January 2014
pp. 58-72
Many recent advances in multiple target tracking aim at finding a (nearly) optimal set of trajectories within a temporal window. To handle the large space of possible trajectory hypotheses, it is typically reduced to a finite set by some form of data-drive...
 
Detection- and Trajectory-Level Exclusion in Multiple Object Tracking
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Anton Milan,Konrad Schindler,Stefan Roth
Issue Date:June 2013
pp. 3682-3689
When tracking multiple targets in crowded scenarios, modeling mutual exclusion between distinct targets becomes important at two levels: (1) in data association, each target observation should support at most one trajectory and each trajectory should be as...
 
A Higher-Order CRF Model for Road Network Extraction
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Jan D. Wegner,Javier A. Montoya-Zegarra,Konrad Schindler
Issue Date:June 2013
pp. 1698-1705
The aim of this work is to extract the road network from aerial images. What makes the problem challenging is the complex structure of the prior: roads form a connected network of smooth, thin segments which meet at junctions and crossings. This type of a-...
 
Explicit Occlusion Modeling for 3D Object Class Representations
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By M. Zeeshan Zia,Michael Stark,Konrad Schindler
Issue Date:June 2013
pp. 3326-3333
Despite the success of current state-of-the-art object class detectors, severe occlusion remains a major challenge. This is particularly true for more geometrically expressive 3D object class representations. While these representations have attracted rene...
 
The Epipolar Geometry of the Log-Polar Image Plane
Found in: Pattern Recognition, International Conference on
By Konrad Schindler, Horst Bischof
Issue Date:August 2004
pp. 40-43
This paper presents an explicit formulation of the epipolar geometry of two oriented log-polar images. A method is derived for efficient pixel-by-pixel computation of epipolar lines in the log-polar plane, which are complicated non-linear functions. As an ...
 
3D MURALE: a multimedia system for archaeology
Found in: Proceedings of the 2001 conference on Virtual reality, archeology, and cultural heritage (VAST '01)
By Alexy Zalesny, Damian Green, Desi Vanrintel, Edward Grabczewski, Franz Leberl, Fred Weimer, John Cosmas, Konrad Karner, Konrad Schindler, Luc Van Gool, Marc Pollefeys, Marc Waelkens, Markus Grabner, Martin Kampel, Michael Gervautz, Robert Sablatnig, Roland DeGeest, Stefan Hynst, Take Itegaki
Issue Date:November 2001
pp. 297-306
This paper introduces the 3D Measurement and Virtual Reconstruction of Ancient Lost Worlds of Europe system (3D MURALE). It consists of a set of tools for recording, reconstructing, encoding, visualising and database searching/querying that operate on buil...
     
A work-flow and data model for reconstruction, management, and visualization of archaeological sites
Found in: Proceedings of the 2001 conference on Virtual reality, archeology, and cultural heritage (VAST '01)
By Konrad Schindler, Markus Grabner, Michael Gervautz, Stefan Hynst
Issue Date:November 2001
pp. 43-52
We propose a framework for a complex visualization environment suitable for archaelogical applications. Given 2D and 3D data derived from appropriate acquisition processes, the scene is organized in a structure that can easily be incorporated into a databa...
     
 1