Wide-baseline Stereo from Multiple Views: a Probabilistic Account (2008)
Strecha, Christoph, Fransen, Rik, Van Gool, Luc
This paper describes a method for dense depth reconstruction from a small set of wide-baseline images. In a widebaseline setting an inherent difficulty which complicates the stereo-correspondence...
Dense Matching of Multiple Wide-baseline Views (2008)
Strecha, Christoph, Tuytelaars, Tinne, Van Gool, Luc
This paper describes a PDE-based method for dense depth extraction from multiple wide-baseline images. Emphasis lies on the usage of only a small amount of images. The integration of these multiple...
Combined Depth and Outlier Estimation in Multi-View Stereo (2008)
Strecha, Christoph, Fransens, Rik, Van Gool, Luc
In this paper, we present a generative model based approach to solve the multi-view stereo problem. The input images are considered to be generated by either one of two processes: (i) an inlier...
A GENERATIVE MODEL FOR TRUE ORTHORECTIFICATION (2008)
Strecha, Christoph, Van Gool, Luc, Fua, Pascal
Orthographic images compose an efficient and economic way to represent aerial images. This kind of information allows to measure two-dimensional objects and relate these to Geographic Information...
On Benchmarking Camera Calibration and Multi-View Stereo for High Resolution Imagery (2008)
Strecha, Christoph, Von Hansen, Wolfgang, Van Gool, Luc, Fua, Pascal, Thoennessen, Ulrich
In this paper we want to start the discussion on whether image based 3-D modelling techniques can possibly be used to replace LIDAR systems for outdoor 3D data acquisition. Two main issues have to be...
A Generative Model for True Orthorectification (2008)
Strecha, Christoph, Van Gool, Luc, Fua, Pascal
Orthographic images compose an efficient and economic way to represent aerial images. This kind of information allows to measure two-dimensional objects and relate these to Geographic Information...
Populating Ancient Pompeii with Crowds of Virtual Romans (2008)
Maïm, Jonathan, Haegler, Simon, Yersin, Barbara, Müller, Pascal, Van Gool, Luc
Pompeii was a Roman city, destroyed and completely buried during an eruption of the volcano Mount Vesuvius. We have revived its past by creating a 3D model of its previous appearance and populated it...
Learning Generative Models for Monocular Body Pose Estimation (2007)
Jaeggli, Tobias, Koller-Meier, Esther, Van Gool, Luc, Van Gool, Luc
We consider the problem of monocular 3d body pose tracking from video sequences. This task is inherently ambiguous.We propose to learn a generative model of the relationship of body pose and image...
Multi-Activity Tracking in LLE Body Pose Space (2007)
Jaeggli, Tobias, Koller-Meier, Esther, Van Gool, Luc, Van Gool, Luc
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a low-dimensional embedding of the pose manifolds using Locally...
Smart Particle Filtering for High-Dimensional Tracking (2007)
Bray, Matthieu, Koller-Meier, Esther, Van Gool, Luc, Van Gool, Luc
Tracking articulated structures like a hand or body within a reasonable time is challenging because of the high dimensionality of the state space. Recently, a new optimization method, called...
Fast Stochastic Optimization for Articulated Structure Tracking (2007)
Bray, Matthieu, Koller-Meier, Esther, Schraudolph, Nicol, Van Gool, Luc
Recently, an optimization approach for fast visual tracking of articulated structures based on stochastic meta-descent (SMD) has been presented. SMD is a gradient descent with local step size...
Omnidirectional Vision based Topological Navigation (2007)
Goedeme, Toon, Nuttin, Marnix, Tuytelaars, Tinne, Van Gool, Luc, Van Gool, Luc
In this work we present a novel system for autonomous mobile robot navigation. With only an omnidirectional camera as sensor, this system is able to build automatically and robustly accurate...
Range determination for mobile robots using an omnidirectional camera (2007)
Millnert, Ola, Goedeme, Toon, Tuytelaars, Tinne, Van Gool, Luc, Van Gool, Luc, Huntemann, Alexander, ...
We propose a method for computing the absolute distances to static obstacles using a single omnidirectional camera. The method is applied to mobile robots. We achieve this without restricting the...
Speeded-up Robust Features (SURF) (2007)
Bay, Herbert, Ess, Andreas, Tuytelaars, Tinne, Van Gool, Luc, Van Gool, Luc
This article presents a novel scale- and rotation-invariant detector and descriptor, coined SURF (Speeded-Up Robust Features). SURF approximates or even outperforms previously proposed schemes with...
Depth and Appearance for Mobile Scene Analysis (2007)
Ess, Andreas, Leibe, Bastian, Van Gool, Luc
In this paper, we address the challenging problem of simultaneous pedestrian detection and ground-plane estimation from video while walking through a busy pedestrian zone. Our proposed system...
Dynamic 3D Scene Analysis from a Moving Vehicle (2007)
Leibe, Bastian, Cornelis, Nico, Cornelis, Kurt, Van Gool, Luc
In this paper, we present a system that integrates fully automatic scene geometry estimation, 2D object detection, 3D localization, trajectory estimation, and tracking for dynamic scene...
Coupled Detection and Trajectory Estimation for Multi-Object Tracking (2007)
Leibe, Bastian, Schindler, Konrad, Van Gool, Luc
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...
Simultaneous Segmentation and 3D Reconstruction of Monocular Image Sequences (2007)
Ozden, K. E., Schindler, Konrad, Van Gool, Luc
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...
Efficient Mining of Frequent and Distinctive Feature Configurations (2007)
Quack, Till, Ferrari, Vittorio, Leibe, Bastian, Van Gool, Luc
We present a novel approach to automatically find spatial configurations of local features occurring frequently on instances of a given object class, and rarely on the background. The approach is...
Generalised Linear Pose Estimation (2007)
Ess, Andreas, Neubeck, Alexander, Van Gool, Luc
This paper investigates several aspects of 3D-2D camera pose estimation, aimed at robot navigation in poorly-textured scenes. The major contribution is a fast, linear algorithm for the general case...
Fast stochastic optimization for articulated structure tracking (2006)
Bray, Matthieu, Koller-Meier, Esther, Schraudolph, Nicol, Van Gool, Luc, Van Gool, Luc
Recently, an optimization approach for fast visual tracking of articulated structures based on Stochastic Meta-Descent (SMD) has been presented. SMD is a gradient descent with local step size...
The PASCAL Visual Object Classes Challenge 2006 (VOC 2006) Results (2006)
Everingham, Mark, Zisserman, Andrew, Williams, Christopher, Van Gool, Luc
This report presents the results of the 2006 PASCAL Visual Object Classes Challenge (VOC2006). Details of the challenge, data, and evaluation are presented. Participants in the challenge submitted...
Efficient, simultaneous detection of multiple object classes (2006)
Zehnder, Philipp, Koller-Meier, Esther, Van Gool, Luc
At present, the object categorisation literature is still dominated by the use of individual class detectors. Detecting multiple classes then implies the subsequent application of multiple such...
Efficient, Simultaneous Detection of Multiple Object Classes (2006)
Zehnder, Philipp, Koller-Meier, Esther, Van Gool, Luc, Van Gool, Luc
At present, the object categorisation literature is still dominated by the use of individual class detectors. Detect- ing multiple classes then implies the subsequent application of multiple such...
Monocular tracking with a mixture of view-dependent learned models (2006)
Jaeggli, Tobias, Koller-Meier, Esther, Van Gool, Luc
This paper considers the problem of monocular human body tracking using learned models. We propose to learn the joint probability distribution of appearance and body pose using a mixture of...
Video Mining with Frequent Itemset Configurations (2006)
Quack, Till, Ferrari, Vittorio, Van Gool, Luc
We present a method for mining frequently occurring objects and scenes from videos. Object candidates are detected by finding recurring spatial arrangements of affine covariant regions. Our mining...
Combining sample-based and analytical density propagation for monocular tracking (2006)
Van Gool, Luc, Jaeggli, Tobias, Koller-Meier, Esther
For image based body pose estimation, the relationship of body pose and image appearance has often been captured by the means of a geometric body model. In contrast to such handcrafted models, a...
Combined Depth and Outlier Estimation in Multi-View Stereo (2006)
Strecha, Christoph, Fransens, Rik, Van Gool, Luc, Van Gool, Luc
In this paper, we present a generative model based approach to solve the multi-view stereo problem. The input images are considered to be generated by either one of two processes: (i) an inlier...
A Generalized EM Approach for 3D Model Based Face Recognition under Occlusions (2006)
De Smet, Michael, Fransens, Rik, Van Gool, Luc, Van Gool, Luc
This paper describes an algorithm for pose and illumination invariant face recognition from a single image under occlusions. The method iteratively estimates the parameters of a 3D morphable face...
A Mean Field EM-algorithm for Coherent Occlusion Handling in MAP-Estimation Problems (2006)
Fransens, Rik, Strecha, Christoph, Van Gool, Luc, Van Gool, Luc
This paper presents a generative model based approach to deal with occlusions in vision problems which can be formulated as MAP-estimation problems. The approach is generic and targets applications...
Robust Estimation in the Presence of Spatially Coherent Outliers (2006)
Fransens, Rik, Strecha, Christoph, Van Gool, Luc, Van Gool, Luc
We present a generative model based approach to deal with spatially coherent outliers. The model assumes that image pixels are generated by either one of two distinct processes: an inlier process...
Towards Multi-View Object Class Detection (2006)
Thomas, Alexander, Ferrari, Vittorio, Leibe, Bastian, Tuytelaars, Tinne, Schiele, Bernt, Van Gool, Luc, ...
We present a novel system for generic object class detection. In contrast to most existing systems which focus on a single viewpoint or aspect, our approach can detect object instances from arbitrary...
Automatic Interactive Calibration of Multi-Projector-Camera Systems (2006)
Griesser, Andreas, Van Gool, Luc, Van Gool, Luc
This paper presents a novel interactive Projector Calibration for arbitrary Multi-Projector-Camera environments. The method does not require any calibration rig and is not restricted to any special...
Fast Compact City Modeling for Navigation Pre-Visualization (2006)
Cornelis, Nico, Cornelis, Kurt, Van Gool, Luc, Van Gool, Luc
Nowadays, GPS-based car navigation systems mainly use speech and aerial views of simplified road maps to guide drivers to their destination. However, drivers often experience difficulties in linking...
Towards Multi-View Object Class Detection (2006)
Thomas, Alexander, Ferrari, Vittorio, Leibe, Bastian, Tuytelaars, Tinne, Schiele, Bernt, Van Gool, Luc
We present a novel system for generic object class detection. In contrast to most existing systems which focus on a single viewpoint or aspect, our approach can detect object instances fr om...
A generalized EM approach for 3D model based face recognition under occlusions (2006)
De Smet, Michael, Fransens, Rik, Van Gool, Luc, Van Gool, Luc
This paper describes an algorithm for pose and illumination invariant face recognition from a single image under occlusions. The method iteratively estimates the parameters of a 3D morphable face...
Combined depth and outlier estimation in multi-view stereo (2006)
Strecha, Christoph, Fransens, Rik, Van Gool, Luc, Van Gool, Luc
In this paper, we present a generative model based approach to solve the multi-view stereo problem. The input images are considered to be generated by either one of two processes: (i) an inlier...
A mean field EM-algorithm for coherent occlusion handling in MAP-estimation problems (2006)
Fransens, Rik, Strecha, Christoph, Van Gool, Luc, Van Gool, Luc
This paper presents a generative model based approach to deal with occlusions in vision problems which can be formulated as MAP-estimation problems. The approach is generic and targets applications...
Robust estimation in the presence of spatially coherent outliers (2006)
Fransens, Rik, Strecha, Christoph, Van Gool, Luc, Van Gool, Luc
We present a generative model based approach to deal with spatially coherent outliers. The model assumes that image pixels are generated by either one of two distinct processes: an inlier process...
3D from Line Segments in Two Poorly-Textured, Uncalibrated Images (2006)
Bay, Herbert, Ess, Andreas, Neubeck, Alexander, Van Gool, Luc, Van Gool, Luc
This paper addresses the problem of camera selfcalibration, bundle adjustment and 3D reconstruction from line segments in two images of poorly-textured indoor scenes. First, we generate line segment...
Combining Sample-Based and Analytical Density Propagation for Monocular Tracking (2006)
Van Gool, Luc, Van Gool, Luc, Jaeggli, Tobias, Koller-Meier, Esther
For image based body pose estimation, the relationship of body pose and image appearance has often been captured by the means of a geometric body model. In contrast to such handcrafted models, a...
SURF: Speeded Up Robust Features (2006)
Bay, Herbert, Tuytelaars, Tinne, Van Gool, Luc, Van Gool, Luc
In this paper, we present a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features). It approximates or even outperforms previously...
Object Detection by Contour Segment Networks (2006)
Ferrari, Vittorio, Tuytelaars, Tinne, Van Gool, Luc, Van Gool, Luc
We propose a method for object detection in cluttered real images, given a single hand-drawn example as model. The image edges are partitioned into contour segments and organized in an image...
Space-Time-Scale Registration of Dynamic Scene Reconstructions (2006)
Ozden, Kemal Egemen, Cornelis, Kurt, Van Gool, Luc, Van Gool, Luc
The paper presents a method for multi-dimensional registration of two video streams. The sequences are captured by two hand-held cameras moving independently with respect to each other, both...
Interactive Museum Guide: Fast and Robust Recognition of Museum Objects (2006)
Bay, Herbert, Fasel, Beat, Van Gool, Luc
In this paper, we describe the application of the novel SURF (Speeded Up Robust Features) algorithm [Bay2006] for the recognition of objects of art. For this purpose, we developed a prototype of a...
Object Detection by Contour Segment Networks (2006)
Ferrari, Vittorio, Tuytelaars, Tinne, Van Gool, Luc
We propose a method for object detection in cluttered real images, given a single hand-drawn example as model. The image edges are partitioned into contour segments and organized in an image...
Localization with omnidirectional images using the radial trifocal tensor (2006)
Sagues, C., Murillo, A., Guerrero, J., Goedeme, T., Tuytelaars, Tinne, Van Gool, Luc, ...
In this paper we present a technique to linearly recover 2D structure and motion in man made environments from three uncalibrated omnidirectional views. We use vertical lines from the scene which are...
Simultaneous Object Recognition and Segmentation from Single or Multiple Model Views (2006)
Ferrari, Vittorio, Tuytelaars, Tinne, Van Gool, Luc
We present a novel Object Recognition approach based on affine invariant regions. It actively counters the problems related to the limited repeatability of the region detectors, and the difficulty of...
Modeling Scenes with Local Descriptors and Latent Aspects (2006)
Quelhas, Pedro, Monay, Florent, Odobez, Jean-Marc, Gatica-Perez, Daniel, Tuytelaars, Tinne, Van Gool, Luc
We present a new approach to model visual scenes in image collections, based on local invariant features and probabilistic latent space models. Our formulation provides answers to three open...
Modeling Scenes with Local Descriptors and Latent Aspects (2006)
Quelhas, Pedro, Monay, Florent, Odobez, Jean-Marc, Gatica-Perez, Daniel, Tuytelaars, Tinne, Van Gool, Luc
We present a new approach to model visual scenes in image collections, based on local invariant features and probabilistic latent space models. Our formulation provides answers to three open...
Fast stochastic optimization for articulated structure tracking (2006)
Bray, Matthieu, Koller-Meier, Esther, Schraudolph, Nicol, Van Gool, Luc
Recently, an optimization approach for fast visual tracking of articulated structures based on Stochastic Meta-Descent (SMD) has been presented. SMD is a gradient descent with local step size...
The 2005 PASCAL Visual Object Classes Challenge (2006)
Everingham, Mark, Zisserman, Andrew, Williams, Christopher, Van Gool, Luc, Allan, Moray, Bishop, Chris, ...
The PASCAL Visual Object Classes Challenge ran from February to March 2005. The goal of the challenge was to recognize objects from a number of visual object classes in realistic scenes (i.e. not...
Range determination for mobile robots using one omnidirectional camera (2006)
Millnert, Ola, Goedeme, Toon, Tuytelaars, Tinne, Van Gool, Luc, Van Gool, Luc, Huntemann, Alexander, ...
We propose a method for computing the absolute distances to obstacles using only one omnidirectional camera. The method is applied to mobile robots. We achieve this without restricting the...
Visual topological map building in self-similar environments (2006)
Goedeme, Toon, Tuytelaars, Tinne, Van Gool, Luc, Van Gool, Luc
This paper describes a method to automatically build topological maps for robot navigation out of a sequence of visual observations taken from a camera mounted on the robot. This direct non-metrical...
Omnidirectional vision based topological navigation (2005)
Goedeme, Toon, Nuttin, Marnix, Tuytelaars, Tinne, Van Gool, Luc, Van Gool, Luc
This work presents a unique system for autonomous mobile robot navigation. The main sensor is an omnidirectional camera. The proposed system is capable to build automatically a topological map...
Monocular Tracking with a Mixture of View-Dependent Learned Models (2005)
Jaeggli, Tobias, Koller-Meier, Esther, Van Gool, Luc
This paper considers the problem of monocular human body tracking using learned models. We propose to learn the joint probability distribution of appearance and body pose using a mixture of...
Modeling Scenes with Local Descriptors and Latent Aspects (2005)
Quelhas, Pedro, Monay, Florent, Odobez, Jean-Marc, Gatica-Perez, Daniel, Tuytelaars, Tinne, Van Gool, Luc
We present a new approach to model visual scenes in image collections, based on the use of local invariant features and probabilistic latent space models. Our formulation provides answers to three...
Omnidirectional Sparse Visual Path Following with Occlusion-Robust Feature Tracking (2005)
Goedeme, T., Tuytelaars, Tinne, Vanacker, G., Nuttin, M., Van Gool, Luc, Van Gool, Luc
Omnidirectional vision sensors are very attractive for autonomous robots because they offer a rich source of environment information. The main challenge in using these for mobile robots is managing...
Parametric Stereo for Multi-Pose Face Recognition and 3D-Face Modeling (2005)
Fransens, Rik, Strecha, Christoph, Van Gool, Luc, Van Gool, Luc
This paper presents a new method for face modeling and face recognition from a pair of calibrated stereo cameras. In a first step, the algorithm builds a stereo reconstruction of the face by...
Markerless Full Body Tracking by Integrating Multiple Cues (2005)
Kehl, Roland, Bray, Matthieu, Van Gool, Luc
This work proposes a novel markerless solution to full body pose tracking by integrating multiple cues such as edges, color information and volumetric reconstruction. A model built from...
Interactive Museum Guide (2005)
Bay, Herbert, Fasel, Beat, Van Gool, Luc
In this paper, we describe the prototype of an interactive museum guide. It runs on a tablet PC that features a touchscreen, a webcam and a Bluetooth receiver. This guide recognises objects on...
Feature based omnidirectional sparse visual path following (2005)
Goedeme, Toon, Tuytelaars, Tinne, Vanacker, G., Nuttin, Marnix, Van Gool, Luc, Van Gool, Luc
Vision sensors are attractive for autonomous robots because they are a rich source of environment information. The main challenge in using images for mobile robots is managing this wealth of...
Wide-baseline Stereo Matching with Line Segments (2005)
Bay, Herbert, Ferrari, Vittorio, Van Gool, Luc
This paper presents a new method for matching line segments between two uncalibrated wide baseline images. Most current techniques for wide baseline matching are based on viewpoint invariant regions....
Is structure needed for omnidirectional visual homing? (2005)
Goedeme, Toon, Vanhooydonck, D., Demeester, E., Nuttin, M., Tuytelaars, Tinne, Van Gool, Luc, ...
Upcoming fast vision techniques for finding image correspondences enable reliable real-time visual homing, i.e. the guidance of a mobile robot from a arbitrary start pose towards a goal pose defined...
Full Body Tracking from Multiple Views Using Stochastic Sampling (2005)
Kehl, Roland, Bray, Matthieu, Van Gool, Luc
We present a novel approach for full body pose tracking using stochastic sampling. A volumetric reconstruction of a person is extracted from silhouettes in multiple video images. Then, an articulated...
Composite Texture Synthesis (2005)
Zalesny, Alexey, Ferrari, Vittorio, Caenen, Gert, Van Gool, Luc
Many textures require complex models to describe their intricate structures. Their modeling can be simplified if they are considered composites of simpler subtextures. After an initial, unsupervised...
Composite texture synthesis (2005)
Zalesny, A., Ferrari, Vittorio, Caenen, Geert, Van Gool, Luc, Van Gool, Luc
Many textures require complex models to describe their intricate structures. Their modeling can be simplified if they are considered composites of simpler subtextures. After an initial, unsupervised...
Analysis of human locomotion based on partial measurements (2005)
Jaeggli, Tobias, Caenen, Geert, Fransens, Rik, Van Gool, Luc
A lot of computer vision applications have to deal with occlusions. In such settings only a subset of the features of interest can be observed, i.e. only incomplete or partial measurements are...
Analysis of human locomotion based on partial measurements (2005)
Jaeggli, Tobias, Caenen, Geert, Fransens, Rik, Van Gool, Luc, Van Gool, Luc
A lot of computer vision applications have to deal with occlusions. In such settings only a subset of the features of interest can be observed, i.e.~only incomplete or partial measurements are...
A Hierarchical System for Recognition, Tracking and Pose Estimation (2005)
Zehnder, Philipp, Koller-Meier, Esther, Van Gool, Luc
This paper presents a new system for recognition, tracking and pose estimation of people in video sequences. It is based on the wavelet transform from the upper body part and uses Support Vector...