Search our Publications

Results

Stefan Menzel, Markus Olhofer, Bernhard Sendhoff, "A Metamodel-driven Interactive Framework for a Designer Assistance System", Proceedings of the 11th International Design Conference – Design 2010, pp. 1371–1380, 2010.

Abstract

The design of innovative products in the automotive industry is influenced by multiple criteria dominated by both human creativity and technical requirements. Thus the generation of a prototype is an adaptive process which iteratively integrates the needs of various disciplines, working on different timescales. This paper proposes and evaluates a styling design framework which introduces the application of neural networks for fast estimation of t...



Download Bibtex file Download PDF

Martin Heckmann, "Supervised vs. Unsupervised Learning of Spectro Temporal Speech Features", Statistical And Perceptual Audition (SAPA), 2010.

Abstract

To overcome limitations of purely spectral speech features we previously introduced Hierarchical Spectro-Temporal (HIST) features. We could show that a combination of HIST and standard features does reduce recognition errors in clean and in noise. The HIST features consist of two hierarchical layers where the corresponding filter functions are learned in a data driven way. In this paper we investigate how different learning methodologies applied ...



Download Bibtex file Download PDF

Robert Kastner, Thomas Michalke, Thomas Burbach, Jannik Fritsch, Christian Goerick, "Attention-Based Traffic Sign Recognition with an Array of Weak Classifiers", IEEE Intelligent Vehicles Symposium (IV), 2010.

Abstract

Currently available traffic sign recognition systems typically focus on a single class of traffic sign and therefore, the algorithms are optimized to find only this specific class. To this end, a number of approaches for real time capable classification of mostly circular signs exist. Nevertheless, to simultaneously recognize a number of classes a different way has to be taken. This paper presents a real-time capable approach, which uses a two-ti...



Download Bibtex file Download PDF

Sven Rebhan and Julian Eggert, "Dynamic, Task-Related and Demand-Driven Scene Representation", Cognitive Computation, 2010.

Abstract

Humans selectively process and store details about the vicinity based on their knowledge about the scene, the world and their current task. In doing so, only those pieces of information are extracted from the visual scene that is required for solving a given task. In this paper, we present a flexible system architecture along with a control mechanism that allows for a task-dependent representation of a visual scene. Contrary to existing approache...



Download Bibtex file Download PDF

Volker Willert and Julian Eggert, "Belief Propagation in Spatiotemporal Graph Topologies for the Analysis of Image Sequences", Proceedings of the VISAPP, 2010.

Abstract

Belief Propagation (BP) is an efficient approximate inference technique both for Markov Random Fields (MRF) and Dynamic Bayesian Networks (DBN). 2DMRFs provide a unified framework for early vision problems that are based on static image observations. 3D MRFs are suggested to cope with dynamic image data. To the contrary, DBNs are far less used for dynamic low level vision problems even though they represent sequences of state variables and hence ...



Download Bibtex file Download PDF

Martin Heckmann, Claudius Gläser, Frank Joublin, Kazuhiro Nakadai, "Applying Geometric Source Separation for Improved Pitch Extraction in Human-Robot Interaction", Proc. INTERSPEECH, 2010.

Abstract

We present a system for robust pitch extraction in noisy and echoic environments consisting of a multi-channel signal enhancement, a pitch extraction algorithm inspired by the processing in the mammalian auditory system and a pitch tracking based on a Bayesian filter. For the multi-channel signal enhancement we deploy an 8 channel Geometric Source Separation (GSS). During pitch extraction we first apply a Gammatone filter bank and then calculate ...



Download Bibtex file Download PDF

Michael Gienger, Mark Toussaint, Christian Goerick, "Whole-body Motion Planning – Building Blocks for Intelligent Systems", Motion Planning for Humanoid Robots, Springer, issue 1st Edition, 2010.

Abstract

Humanoid robots have become increasingly sophisticated, both in terms of their movement as well as their sensorial capabilities. This allows one to target for more challenging problems, eventually leading to robotic systems that can perform useful tasks in everyday environments. In this paper, we review some elements we consider to be important for a movement control and planning architecture. We first explain the whole-body control concept, whic...



Download Bibtex file Download PDF

Stephan Hasler, "Learning Features for Robust Object Recognition", Honda Research Institute Europe GmbH / Bielefeld University, 2010.

Abstract

Humans can easily recognize a very large number of previously seen objects. Despite extensive efforts in recent years, the principles underlying this capability are hardly understood and modern object recognition systems are far from reaching human performance. The main reason for this is that the visual appearance of an object is strongly influenced by various conditions. So depending on the viewing angle different parts of an object are vis...



Download Bibtex file Per Mail Request

Andreas Knoblauch, "Bimodal structural plasticity can explain the spacing effect in long-term memory tasks.", Frontiers in Systems Neuroscience. Conference Abstract: Computational and Systems Neuroscience, 2010.



Download Bibtex file Download PDF

Matthias Rolf, Jochen Steil, Michael Gienger, "Goal Babbling permits direct learning of inverse kinematics", IEEE Transactions on Autonomous Mental Development, vol. 2, no. 3, pp. 216 - 229, 2010.

Abstract

We present an approach to learn inverse kinematics of redundant systems without prior- or expert-knowledge. The method allows for an iterative bootstrapping and refinement of the inverse kinematics estimate. The essential novelty lies in a path based sampling approach: we generate trainig data along pathes, which result from execution of the currently learned estimate along a desired path towards a goal. The information structure thereby induced ...



Download Bibtex file Download PDF

1 ... 92 93 94 95 96 97 ... 146

Search