Heinrich Niemann

Improving Object Recognition by Fusion of Multiple Views (2004)

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...

Improving Children's Speech Recognition by (2004)

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...

Stefan Steidl, Georg Stemmer, Christian Hacker, Elmar Noth, Heinrich Niemann

In this paper we address the problem of building a good speech recognizer if there is only a small amount of training data available.

Viewpoint Selection -- Planning Optimal (2004)

Context-Dependent Output Densities for Hidden Markov Models in Speech Recognition (2004)

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...

Georg Stemmer, Viktor Zeissler, Christian Hacker, Elmar N Oth, Heinrich Niemann

In this paper we propose an efficient method to utilize context in the output densities of HMMs. State scores of a phone recognizer are integrated into the HMMs of a word recognizer which makes their...

A Phone Recognizer Helps To Recognize Words Better (2004)

Georg Stemmer, Viktor Zeissler, Christian Hacker, Elmar N Oth, Heinrich Niemann

For most speech recognition systems dynamic features are the only way to incorporate temporal context into the output distributions of the HMMs. In this paper we propose an efficient method to...

Plenoptic Models in Robot Vision (2004)

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...

Jochen Schmidt, Florian Vogt, and Heinrich Niemann (2003)

Jochen Schmidt, Florian Vogt, Heinrich Niemann

This paper presents an approach for applying a dual quaternion hand-- eye calibration algorithm on an endoscopic surgery robot. Special focus is on robustness, since the error of position and...

Florian Vogt, Sophie Kruger, Heinrich Niemann, Christoph Schick (2003)

Florian Vogt, Sophie Kruger, Heinrich Niemann, Christoph Schick

During endoscopic operations the surgeon works without direct visual contact to the operation area. The image of the operation situs is displayed on a monitor. Currently, only hardware based image...

Proc. Of The Speech Processing Workshop, (2003)

Christian Hacker, Georg Stemmer, Stefan Steidl, Elmar Noth, Heinrich Niemann

When semicontinuous HMM are used for acoustic modeling in speech recognition usually all states share a single codebook. In our investigations we split the feature set into independent subsets and...

Vision, Modeling, and Visualization 2003, Aka / IOS Press, pages 199--206 (2003)

A Refined Icp Algorithm For Robust 3-D Correspondence Estimation (2003)

There are many nearest neighbor algorithms tailormade for ICP, but most of them require special input data like range images or triangle meshes. We focus on efficient nearest neighbor algorithms that...

Performance Analysis of Nearest Neighbor Algorithms (2003)

Robust registration of two 3-D point sets is a common problem in computer vision. The Iterative Closest Point (ICP) algorithm is undoubtedly the most popular algorithm for solving this kind of...

Illumination Insensitive Template Matching with Hyperplanes (2003)

There are many nearest neighbor algorithms tailormade for ICP, but most of them require special input data like range images or triangle meshes. We focus on efficient nearest neighbor algorithms that...

Christoph Gral, Timo Ziner, Heinrich Niemann

Data-driven object tracking is very important for many vision based applications, because it does not require any previous knowledge about the object to be tracked. In the literature, template...

A Refined ICP Algorithm for Robust 3-D Correspondence Estimation (2003)

Matthias Zobel, Joachim Denzler, Heinrich Niemann (2003)

Robust registration of two 3-D point sets is a common problem in computer vision. The Iterative Closest Point (ICP) algorithm is undoubtedly the most popular algorithm for solving this kind of...

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...

Matthias Zobel, Joachim Denzler, Heinrich Niemann (2003)

Matthias Zobel, Joachim Denzler, Heinrich Niemann, M. Zobel, J. Denzler, H. Niemann

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 described...

Matthias Zobel, Arnd Gebhard, Dietrich Paulus, Joachim Denzler, Heinrich Niemann (2003)

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...

Frank Deinzer, Joachim Denzler, Heinrich Niemann (2003)

Frank Deinzer, Joachim Denzler, Heinrich Niemann, Austin Texas Usa, F. Deinzer, J. Denzler, ...

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 views...

Dense Disparity Maps in Real-Time with an Application to . . . (2003)

Jochen Schmidt, Heinrich Niemann, Lehrstuhl Fur Mustererkennung, Sebastian Vogt

This work presents a technique for computing dense disparity maps from a binocular stereo camera system. The methods are applied in an Augmented Reality setting for combining real and virtual worlds...

Dense Disparity Maps in Real-Time with an Application to . . . (2003)

Jochen Schmidt, Heinrich Niemann, Sebastian Vogt

This work presents' a technique for computing dense disparity maps from a binocular stereo camera system. The methods' are applied in an Augmented Reality setting for combining real and virtual...

? (2003)

Jochen Schmidt, Florian Vogt, Heinrich Niemann

We present an approach for nonlinear optimization of the parameters of an endoscopic camera mounted on a surgery robot. The goal is to generate a depth map for each image in order to enhance the...

Improved Hardware-Accelerated Visual Hull Rendering (2003)

Li, Ming, Magnor, Marcus, Seidel, Hans-Peter, Ertl, Thomas, Girod, Bernd, Greiner, Günther, ...

The visual hull is an efficient shape approximation for the purpose of reconstructing and visualizing dynamic objects. Recently, rapid progress in graphics hardware development has made it possible...

Improved Hardware-Accelerated Visual Hull Rendering (2003)

Li, Ming, Magnor, Marcus, Seidel, Hans-Peter, Ertl, Thomas, Girod, Bernd, Greiner, Günther, ...

The visual hull is an efficient shape approximation for the purpose of reconstructing and visualizing dynamic objects. Recently, rapid progress in graphics hardware development has made it possible...

A Parallel Framework for Silhouette-based Human Motion Capture (2003)

Theobalt, Christian, Carranza, Joel, Magnor, Marcus, Seidel, Hans-Peter, Ertl, Thomas, Girod, Bernd, ...

A Parallel Framework for Silhouette-based Human Motion Capture (2003)

Theobalt, Christian, Carranza, Joel, Magnor, Marcus, Seidel, Hans-Peter, Ertl, Thomas, Girod, Bernd, ...

Using Feature Flow Fields for Topological Comparison of Vector Fields (2003)

Theisel, Holger, Rössl, Christian, Seidel, Hans-Peter, Ertl, Thomas, Girod, Bernd, Greiner, Günther, ...

In this paper we propose a new topology based metric for 2D vector fields. This metric is based on the concept of feature flow fields. We show that it incorporates both the characteristics and the...

Convex Boundary Angle Based Flattening (2003)

Zayer, Rhaleb, Rössl, Christian, Seidel, Hans-Peter, Ertl, Thomas, Girod, Bernd, Greiner, Günther, ...

A Solid-State, Simultaneous Wide Angle-Detailed View Video Surveillance Camera (2003)

Oi, R., Magnor, Marcus, Aizawa, K., Ertl, Thomas, Girod, Bernd, Greiner, Günther, ...

Improving Object Recognition by Fusion of Multiple Views (2002)

Computational analysis of core promoters in the Drosophilagenome (2002)

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...

Ohler, Uwe, Liao, Guo-chun, Niemann, Heinrich, Rubin, Gerald M

Abstract Background The core promoter, a region of about 100 base-pairs flanking the transcription start site (TSS), serves as the recognition site for the basal transcription apparatus. Drosophila...

Calibration of Real Scenes for the Reconstruction of Dynamic Light Fields (2002)

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....

Matthias Zobel, Joachim Denzler, Heinrich Niemann (2002)

Matthias Zobel, Joachim Denzler, Heinrich Niemann

In this paper we discuss some practical facets of active camera control during 3-D object tracking. The basis of our investigation is an active binocular camera system looking onto a scene to track a...

Application of Bayesian controllers to dynamic systems * (2002)

Highlight Substitution in Light Fields (2002)

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 parallels between...

Florian Vogt, Dietrich Paulus, Heinrich Niemann

Highlights occur especially when recording medical (color) images during micro-invasive operations. They disturb the physicians who can sometimes only guess the tissue at the position of the...

Making the Invisible Visible: Highlight Substitution by Color Light Fields (2002)

Florian Vogt, Dietrich Paulus, Benno Heigl, Christian Vogelgsang, Heinrich Niemann, G Unther Greiner, ...

In this contribution we present a new technique of highlight substitution. From a color image sequence, acquired with a hand-held camera, a so-called light field is generated. Additionally, a...

lgf3 - A Versatile Framework for Vision and Image-Based Rendering Applications (2002)

Christian Vogelgsang, Ingo Scholz, Gunther Greiner, Heinrich Niemann

Applications of computer vision and image-based rendering techniques nowadays often share ideas and algorithms. Thus the components required for implementation show a high degree of similarity....

Prosodic Classification of Offtalk: First Experiments (2002)

Anton Batliner, Viktor Zeier, Elmar Noth, Heinrich Niemann

SmartKom is a multi-modal dialogue system which combines speech with gesture and facial expression. In this paper, we want to deal with one of those phenomena which can be observed in such elaborated...

Comparison and Combination of Confidence Measures (2002)

Georg Stemmer, Stefan Steidl, Elmar Noth, Heinrich Niemann

A set of features for word-level confidence estimation is developed. The features should be easy to implement and should require no additional knowledge beyond the information which is available from...

Using Non-Markov models for the Control of Dynamic Systems (2002)

On Optimal Camera Parameter Selection in Kalman Filter Based Object Tracking (2002)

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 their...

Joachim Denzler, Matthias Zobel, Heinrich Niemann

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 relevant...

The Prosody Module (2002)

Anton Batliner, Jan Buckow, Heinrich Niemann, Elmar Noth, Volker Warnke

We describe the acoustic-prosodic and syntactic-prosodic annotation and classification of boundaries, accents and sentence mood integrated in the Verbmobil system for the three languages German,...

Prosodic Feature Evaluation: Brute Force Or Well Designed? (2002)

Anton Batliner, Jan Buckow, Richard Huber, Volker Warnke, Elmar Noth, Heinrich Niemann

In this paper we want to bridge the gap between phonetic /phonological theory on the one hand and automatic speech processing on the other hand. As material, we use a subset of the German VERBMOBIL...

Using Quaternions for Parametrizing 3-D Rotations in Unconstrained Nonlinear Optimization (2002)

Jochen Schmidt, Heinrich Niemann, J. Schmidt, H. Niemann

In this paper we address the problem of using quaternions in unconstrained nonlinear optimization of 3-D rotations. Quaternions representing rotations have four elements but only three degrees of...

Semantigrams --- Polygrams Detecting Meaning Jurgen Haas and Elmar Noth and Heinrich Niemann (2002)

Jurgen Haas, Elmar Noth, Heinrich Niemann

In this paper we present a statistical approach to shallow linguistic analysis of word chains modeled with probabilistic methods. We reduce the linguistic analysis to the problem of extracting pairs...

Combination of Simple Vision Modules for Robust (2002)

Joachim Denzler, 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...

Interpolated Markov Chains for Eukaryotic Promoter Recognition (2002)

Uwe Ohler, Stefan Harbeck, Heinrich Niemann, Elmar Noth, Martin G. Reese

Motivation: We describe a new content based approach for the detection of promoter regions of eukaryotic protein encoding genes. Our system is based on three interpolated Markov chains (IMCs) of...

Joint modeling of DNA sequence and physical properties to improve eukaryotic promoter recognition (2002)

Uwe Ohler, Heinrich Niemann, Guo-chun Liao

We present an approach to integrate physical properties of DNA, such as DNA bendability or GC content, into our probabilistic promoter recognition system MCPROMOTER. In the new model, a promoter is...

Jochen Schmidt, Ingo Scholz, and Heinrich Niemann (2002)

Jochen Schmidt, Ingo Scholz, Heinrich Niemann

We describe an Augmented Reality system using the corners of a color cube for camera calibration. In the augmented image the cube is replaced by a computer generated virtual object. The cube is...

Whence and Whither Prosody in Automatic Speech Understanding: A Case Study. (2002)

Anton Batliner, Elmar N Oth, Jan Buckow, Richard Huber, Volker Warnke, Heinrich Niemann

The `case' this paper is dealing with is prosody research at the Chair for Pattern Recognition at the University of Erlangen-- Nuremberg during the last fifteen years. We want to show how this...

Discriminative Training Of Language Model Classifiers (2002)

Uwe Ohler, Stefan Harbeck, Heinrich Niemann

We show how discriminative training methods, namely the Maximum Mutual Information and Maximum Discrimination approach, can be adopted for the training of N-gram language models used as classifiers...

Information Theoretic Based Segments for Language Identification (2002)

Stefan Harbeck, Uwe Ohler, Heinrich Niemann

In our paper we present two new approaches for language identification. Both of them are based on the use of so-called multigrams, an information theoretic based observation representation. In the...

Robust Facial Feature Localization by Coupled Features (2002)

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...

D Data Driven Prediction for Active Contour (2002)

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...

VERBMOBIL: The Use of Prosody in the Linguistic Components of a Speech Understanding System (2002)

Elmar Ntth, Anton Batliner, Andreas Kiegling, Ralf Kompe, Heinrich Niemann

In this paper, we show how prosody can be used in speech understanding systems. This is demonstrated with the VERBMOBIL speech-to-speech translation system which, to our knowledge, is the first...

Sebastian Meller Matthias Wolf Dietrich Paulus Matthias Pelka Peter Weierich Heinrich Niemann (2002)

Sebastian Meller, Matthias Wolf, Dietrich Paulus, Matthias Pelka, Peter Weierich, Heinrich Niemann, ...

this paper can use the calculated surface data to prepare the grinding of the inlay (Figure 5c) or onlay by an NC--machine

Camera Calibration from Extended Image Sequences for Lightfield Reconstruction (2002)

Benno Heigl, Heinrich Niemann

calibration of extended image sequences with the goal to generate light elds. Our method is mainly based on the factorization method by Sturm and Triggs which provides a closed{form solution if all...

Process modelling using Bayesian Networks (2002)

Rainer Deventer, Bernhard Kahles, Heinrich Niemann

Introduction We used Bayesian networks for process modelling. The main advantage of such a process model is a deeper comprehension of the process, the usage of the model to search optimal input for...

Non-linear modeling of a production process by hybrid Bayesian Networks (2002)

Statistical 3-D Object Localization Without Segmentation Using Wavelet Analysis (2002)

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 is...

Josef P Osl, Heinrich Niemann

This paper presents a new approach for statistical object localization.

Computational Identification and Analysis of Eukaryotic Promoters: New Algorithms on the Traces of Gene Regulation (2002)

Uwe Ohler, Heinrich Niemann

With the information of the complete DNA sequence of several higher eukaryotes as well as expression patterns of thousands of genes under a variety of conditions in our hands, we now have the...

Duration Features in Prosodic Classification: Why Normalization Comes Second, and what they Really Encode. (2002)

Anton Batliner, Elmar N Oth, Jan Buckow, Richard Huber, Volker Warnke, Heinrich Niemann

For the classification of boundaries and accents in German and English spontaneous speech in the VERBMOBIL project (speech to speech translation system), we use a large prosodic feature vector;...

Feature Extraction from Interferograms for Phase Distribution Analysis (2002)

Torsten Merz, Dietrich Paulus, Heinrich Niemann

In several applications of interferogram analysis, e.g. automated nondestructive testing, it is necessary to detect irregular interference phase distributions or to compare interference phase...

Tracking of Probabilistically Coupled Features (2002)

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...

Multilingual Speech Recognition in the Context (2002)

Stefan Harbeck, Elmar Noth, Heinrich Niemann

The multilingual speech recognizer implemented inside the SQEL Copernicus project is based on a combination of several monolingual recognizer within one recognizer using a special bigram grammar.

Coupling Rays - Probabilistic Modeling of Spatial Dependencies (2002)

Matthias Zobel, Joachim Denzler, Heinrich Niemann, M. Zobel, J. Denzler, H. Niemann

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 described...

Statistical Approach to Classification of Flow Patterns for Motion Detection (2002)

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...

Automatic Labeling Of Phrase Accents In German (2002)

Andreas Kieling, Ralf Kompe, Anton Batliner, Heinrich Niemann, Elmar Noth

In this paper a method for the automatic labeling of phrase accents is described, based on a large text corpus that has been generated automatically and read by 100 speakers. Perception experiments...

Control of Dynamic Systems Using Bayesian Networks (2002)