Calibration of Real Scenes for the Reconstruction of Dynamic Light (2009)
Ingo Scholz, Joachim Denzler, Heinrich Niemann
The classic light field and lumigraph are two well-known approaches to image-based rendering, and subsequently many new rendering techniques and representations have been proposed based on them....
Automated Evaluation of 3D Reconstruction Results for Benchmarking View Planning (2009)
Munkelt, Christoph, Denzler, Joachim
To obtain complete 3D object reconstructions using optical measurements, several views of the object are necessary. The task of determining good sensor positions to achieve a 3D reconstruction with...
Model-based Surface Defect Detection and Condition Monitoring in Wire Ropes (2009)
Platzer, Esther, Denzler, Joachim
Wire ropes are exposed to huge external powers everyday. Therefore strict rules for a regular visual inspection exist. Many approaches for textural defect detection in textiles or other materials...
Theory of Learning with Few Examples and Object Localization (2009)
Rodner, Erik, Denzler, Joachim
Visual object localization and categorization is still a big challenge for current research and gets even more difficult when confronted with few training examples. Therefore we will present a...
Evaluating Guided KLT Tracking for Next Best View Planning in 3D Reconstruction (2009)
Trummer, Michael, Denzler, Joachim
This report considers the task of 3D reconstruction within a Next Best View (NBV) planning approach. Particular attention is given to the possibilities of extending the well-known Kanade-Lucas-Tomasi...
Minimum Uncertainty Triangle Paths for Multi Camera Calibration (2009)
Bajramovic, Ferid, Denzler, Joachim
Multi camera systems become increasingly important in computer vision. For many applications, however, the system has to be calibrated, i.e. the intrinsic and extrinsic parameters of the cameras have...
Active Self Calibration of a Multi Sensor System (2009)
Brückner, Marcel, Denzler, Joachim
The combination of a multi camera system with different sensor types like PMD cameras or motion sensors is called multi sensor system. Such systems offer many different application scenarios, e.g....
Computer Vision in Camera Networks for Analyzing Complex Dynamic Natural Scenes (2009)
Sensor or camera networks will play an important role in future applications, from surveillance tasks for workplace safety or security in general, over driver assisting systems in automotive and last...
Generic Object Recognition (2009)
Hegazy, Doaa, Denzler, Joachim
The object recognition problem has challenged the computer vision community for long time due to the huge change in the scale, occlusion and lighting conditions which have a great effect on the...
3-D Reconstruction in Piecewise Planar Environments (2009)
Kähler, Olaf, Denzler, Joachim
The structure-from-motion problem is central in applications like visual robot navigation and visual 3d modeling. Typical solutions split the problem into feature tracking and geometric...
Universal Image Statistics as a Basis for Esthetic Perception (2009)
Koch, Michael, Denzler, Joachim, Redies, Christoph
In the last decades many neuroscientists have started to investigate the perception of nature and art by the human visual system. Natural scenes lead to an esthetically pleasing perception, therefore...
Denzler, Joachim, Koch, Michael
From 12.10. to 15.10.2008, the Dagstuhl Event 08422 was held in Schloss Dagstuhl~--~Leibniz Center for Informatics. During the seminar, several participants presented their current research, and...
Self-Calibration with Partially Known Rotations (2008)
Ferid Bajramovic, Joachim Denzler
Abstract. Self-calibration methods allow estimating the intrinsic camera parameters without using a known calibration object. However, such methods are very sensitive to noise, even in the simple...
Using Graph-Cut for Planar Patch Segmentation (2008)
Olaf Kähler, Erik Rodner, Joachim Denzler
Planar patch detection aims at simplifying data from 3-D imaging sensors to a more compact scene description. We propose a fusion of intensity and depth information using Graph-Cut methods for this...
Torsten Rohlfing, Joachim Denzler, Christoph Gräßl, Daniel B. Russakoff, Calvin R. Maurer
Abstract—Accurate and fast localization of a predefined target region inside the patient is an important component of many image-guided therapy procedures. This problem is commonly solved by...
An Efficient Shortest Triangle Paths Algorithm for Uncertainty-based Multi Camera Calibration (2008)
Bajramovic, Ferid, Denzler, Joachim
Extrinsically calibrating a multi camera system based on scene images only is in general a very difficult problem. One promising approach computes the extrinsic parameters from sufficiently many...
An Efficient Shortest Triangle Paths Algorithm for Uncertainty-based Multi Camera Calibration (2008)
Bajramovic, Ferid, Denzler, Joachim
Extrinsically calibrating a multi camera system based on scene images only is in general a very difficult problem. One promising approach computes the extrinsic parameters from sufficiently many...
Binocular 3-D Object Tracking with Varying Focal Lengths (2007)
Matthias Zobel, Matthias Zobel, Joachim Denzler, Joachim Denzler, Heinrich Niemann, Heinrich Niemann
appeared in:
Calibration of Real Scenes for the Reconstruction of Dynamic Light (2007)
Ingo Scholz, Ingo Scholz, Joachim Denzler, Joachim Denzler, Heinrich Niemann, Heinrich Niemann
The classic light field and lumigraph are two well-known approaches to image-based rendering, and subsequently many new rendering techniques and representations have been proposed based on them....
Abstract Tracking of Probabilistically Coupled Features (2007)
Matthias Zobel, Joachim Denzler, Heinrich Niemann, M. Zobel, J. Denzler, H. Niemann
In this paper an approach on tracking objects consisting of multiple parts is presented. Instead of tracking each part independently, all features are tracked simultaneously. Therefore, the spatial...
Coupling Rays – Probabilistic Modeling of Spatial Dependencies (2007)
Matthias Zobel, Joachim Denzler, Heinrich Niemann, M. Zobel, J. Denzler, H. Niemann
Abstract In this paper we show, how modeling of spatial dependencies between single parts can be used to improve the robustness of the localization of multi– part objects. Spatial dependencies are...
Chair for pattern recognition (2007)
Rainer Deventer, Joachim Denzler, Heinrich Niemann
Abstract. Due to shorter life cycles and more complex production processes the automatic generation of models for control purposes is of great importance. Even though Bayesian networks have proven...
On Optimal Camera Parameter Selection in Kalman Filter Based Object Tracking (2007)
Joachim Denzler, Matthias Zobel, Heinrich Niemann
Abstract In this paper we present an information theoretic framework that provides an optimality criterion for the selection of the best sensor data regarding state estimation of dynamic system. One...
Tracking of Probabilistically Coupled Features (2007)
Matthias Zobel, Joachim Denzler, Heinrich Niemann, M. Zobel, J. Denzler, H. Niemann
In this paper an approach on tracking objects consisting of multiple parts is presented. Instead of tracking each part independently, all features are tracked simultaneously. Therefore, the spatial...
Coupling Rays-- Probabilistic Modeling of Spatial Dependencies (2007)
Matthias Zobel, Joachim Denzler, Heinrich Niemann, M. Zobel, J. Denzler, H. Niemann
Abstract In this paper we show, how modeling of spatial dependencies between single parts can be used to improve the robustness of the localization of multi--part objects. Spatial dependencies are...
Control of Dynamic Systems Using Bayesian Networks (2007)
Rainer Deventer, Joachim Denzler, Heinrich Niemann
Abstract. Bayesian networks for the static as well as for the dynamic case have gained an enormous interest in the research community of artificial intelligence, machine learning and pattern...
Progressive Attenuation Fields: Fast 2D-3D Image Registration Without Precomputation (2007)
Torsten Rohlfing, Daniel B. Russakoff, Joachim Denzler, Calvin R. Maurer
Abstract. This paper introduces the progressive attenuation field (PAF), a method to speed up computation of digitally reconstructed radiograph (DRR) images during intensity-based 2D-3D registration....
Detecting coplanar feature points in handheld image sequences (2007)
Abstract: 3D reconstruction applications can benefit greatly from knowledge about coplanar feature points. Extracting this knowledge from images alone is a difficult task, however. The typical...
PLEASE SCROLL DOWN FOR ARTICLE (2007)
Publisher Informa Healthcare, Christoph Redies, Jan Hänisch, Marko Blickhan, Joachim Denzler
Publication details, including instructions for authors and subscription information:
06311 Executive Summary -- Sensor Data and Information Fusion in Computer Vision and Medicine (2007)
Denzler, Joachim, Hornegger, Joachim, Kittler, Josef, Maurer JR., Calvin R.
Today many technical systems are equipped with multiple sensors and information sources, like cameras, ultrasound sensors or web data bases. It is no problem to generate an exorbitantly large amount...
Denzler, Joachim, Hornegger, Joachim, Kittler, Josef, Maurer JR., Calvin R.
From 30.07.06 to 04.08.06, the Dagstuhl Seminar 06311 ``Sensor Data and Information Fusion in Computer Vision and Medicine'' was held in the International Conference and Research Center (IBFI),...
Viewpoint selection - planning optimal sequences of views for object recognition (2003)
Frank Deinzer, Joachim Denzler, Heinrich Niemann
Abstract. In the past decades most object recognition systems were based on passive approaches. But in the last few years a lot of research was done in the field of active object recognition. In this...
Plenoptic Models in Robot Vision (2003)
Joachim Denzler, Benno Heigl, Matthias Zobel, Heinrich Niemann
this article, we propose a new kind of model for robot vision, the so called plenoptic model, a model that can be acquired fully automatically. This is regarded in this article as learning. The key...
Machine Vision and Applications manuscript No. (2003)
Will Be Inserted, Matthias Zobel, Joachim Denzler, Benno Heigl, Elmar Nöth, Dietrich Paulus, ...
This contribution introduces MOBSY, a fully integrated autonomous mobile service robot system. It acts as an automatic dialogue based receptionist for visitors of our institute. MOBSY incorporates...
Viewpoint Selection - Planning Optimal Sequences of Views for Object Recognition (2003)
Frank Deinzer, Joachim Denzler, Heinrich Niemann
In the past decades most object recognition systems were based on passive approaches. But in the last few years a lot of research was done in the field of active object recognition. In this context...
Probabilistische Zustandsschätzung und Aktionsauswahl im Rechnersehen / (2003)
Zugl.: Erlangen, Nürnberg, Universiẗat, Habil.-Schr.
Improving Object Recognition By Fusion Of Multiple Views (2002)
Frank Deinzer, Joachim Denzler, Heinrich Niemann
In the past decades most object recognition systems were based on passive approaches. But in the last few years a lot of research was done in the field of active approaches for object recognition. In...
Entropy based camera control for visual object tracking (2002)
Matthias Zobel, Matthias Zobel, Joachim Denzler, Joachim Denzler, Heinrich Niemann, Heinrich Niemann
In active visual 3-D object tracking one goal is to control the pan and tilt axes of the involved cameras to keep the tracked object in the centers of the fields of view. In this paper we present a...
Christopher Drexler, Frank Mattern, Joachim Denzler
Abstract Classifying unknown objects in familiar, general categories rather than trying to classify them into a certain known, but only similar class, or rejecting them at all is an important aspect...
Entropy based camera control for visual object tracking (2002)
Matthias Zobel, Matthias Zobel, Joachim Denzler, Joachim Denzler, Heinrich Niemann, Heinrich Niemann
In active visual 3-D object tracking one goal is to control the pan and tilt axes of the involved cameras to keep the tracked object in the centers of the fields of view. In this paper we present a...
Hierarchic object models and classification based on probabilistic (2002)
Christopher Drexler, Frank Mattern, Joachim Denzler
In this paper we tackle the problem of classifying objects, which are not known to the system but similar to some of the objects contained in the training set. This type of classification is referred...
Improving Object Recognition by Fusion of Multiple Views (2002)
Frank Deinzer Joachim, Joachim Denzler, Heinrich Niemann
In the past decades most object recognition systems were based on passive approaches. But in the last few years a lot of research was done in the field of active approaches for object recognition. In...
Hierarchic object models and classification based on probabilistic (2002)
Christopher Drexler, Frank Mattern, Joachim Denzler
In this paper we tackle the problem of classifying objects, which are not known to the system but similar to some of the objects contained in the training set. This type of classification is referred...
Bayesian Control of Dynamic Systems (2001)
Rainer Deventer, Joachim Denzler, Heinrich Niemann
Abstract. Bayesian networks for the static as well as for the dynamic case have gained an enormous interest in the research community of machine learning and pattern recognition. Although the...
Mobsy: Integration of vision and dialogue in service robots (2001)
Matthias Zobel, Matthias Zobel, Joachim Denzler, Joachim Denzler, Benno Heigl, Benno Heigl, ...
Abstract. MOBSY is a fully integrated autonomous mobile service robot system. It acts as an automatic dialogue based receptionist for visitors of our institute. MOBSY incorporates many techniques...
Mobsy: Integration of vision and dialogue in service robots (2001)
Matthias Zobel, Matthias Zobel, Joachim Denzler, Joachim Denzler, Benno Heigl, Benno Heigl, ...
Abstract. MOBSY is a fully integrated autonomous mobile service robot system. It acts as an automatic dialogue based receptionist for visitors of our institute. MOBSY incorporates many techniques...
MOBSY: Integration of Vision and Dialogue in Service (2001)
Robots Matthias Zobel, Matthias Zobel, Joachim Denzler, Benno Heigl, Elmar Nöth, Dietrich Paulus, ...
MOBSY is a fully integrated autonomous mobile service robot system.
Denzler, Joachim, Brown, Christopher M.
In this paper we introduce a formalism for optimal sensor parameter selection for iterative state estimation in static systems. In contrast to common approaches, where a certain metric---for example,...
Robust facial feature localization by coupled features (2000)
Matthias Zobel, Arnd Gebhard, Dietrich Paulus, Joachim Denzler, Heinrich Niemann, M. Zobel, ...
In this paper, we consider the problem of robust localization of faces and some of their facial features. The task arises e.g. in the medical field of visual analysis of facial paresis. We detect...
Viewpoint Selection - A Classifier Independent Learning Approach (2000)
Frank Deinzer, Joachim Denzler, Heinrich Niemann, F. Deinzer, J. Denzler, H. Niemann
This paper deals with an aspect of active object recognition for improving the classification and localization results by choosing optimal next views at an object. The knowledge of “good ” next...
Robust facial feature localization by coupled features (2000)
Matthias Zobel, Arnd Gebhard, Dietrich Paulus, Joachim Denzler, Heinrich Niemann, M. Zobel, ...
In this paper, we consider the problem of robust localization of faces and some of their facial features. The task arises e.g. in the medical field of visual analysis of facial paresis. We detect...
Viewpoint Selection - A Classifier Independent Learning Approach (2000)
Frank Deinzer, Joachim Denzler, Heinrich Niemann, F. Deinzer, J. Denzler, H. Niemann
This paper deals with an aspect of active object recognition for improving the classification and localization results by choosing optimal next views at an object. The knowledge of "good...
Non-linear modeling of a production process by hybrid Bayesian Networks (2000)
Rainer Deventer, Joachim Denzler, Heinrich Niemann
Abstract. This paper shows how non-linear functions can be approximated by hybrid Bayesian networks. The basic idea is to make a piecewise linear approximation with several base points. This approach...
Robust facial feature localization by coupled features (2000)
Matthias Zobel, Arnd Gebhard, Dietrich Paulus, Joachim Denzler, Heinrich Niemann, M. Zobel, ...
In this paper, we consider the problem of robust localization of faces and some of their facial features. The task arises e.g. in the medical field of visual analysis of facial paresis. We detect...
Real--time pedestrian tracking in natural scenes (1997)
Joachim Denzler, Heinrich Niemann, J. Denzler, H. Niemann
The following paper was published in the Proceedings on the 7 th International Conference
Model Based Extraction of Articulated Objects in Image Sequences for Gait Analysis (1997)
Dorthe Meyer, Joachim Denzler, Heinrich Niemann
This paper describes an approach to the extraction of articulated objects which will be used for gait analysis. In most medical applications markers are used to determine trajectories of different...
Aktives Sehen zur Echtzeitobjektverfolgung / (1997)
Zugl.: Erlangen, Nürnberg, Universiẗat, Diss., 1997.
Statistical approach to classification of flow patterns for motion detection (1996)
Joachim Denzler, Volker Schle, Dietrich Paulus, Heinrich Niemann
We present a new approach for egomotion computation and the detection of independent motion in the scene. In contrast to related work we apply statistical methods which are based on the normal...
3d data driven prediction for active contour models based on geometric bounding volumes (1996)
Joachim Denzler, Heinrich Niemann
In this paper we apply a new data driven 3D prediction step for active contour models to car tracking on highways. The so called 3D bounding volume (BV) is a coarse 3D representation of a moving...
3D Data Driven Prediction for Active Contour Models based on Geometric Bounding Volumes (1996)
Joachim Denzler, Heinrich Niemann
Active contour models have proven to be a promising approach for data driven object tracking without knowledge about the problem domain and the object. Problems arise in case of fast moving objects...
Combination of simple vision modules for robust real--time motion tracking (1995)
Joachim Denzler, Joachim Denzler, Heinrich Niemann, Heinrich Niemann
In this paper we describe a real time object tracking system consisting of three modules (motion detection, object tracking, robot control), each working with a moderate accuracy, implemented in...
Active Motion Detection and Object Tracking (1994)
Joachim Denzler, Joachim Denzler
In this paper we describe a two stage active vision system for tracking of a moving object which is detected in an overview image of the scene; a close--up view is then taken by changing the frame...