Bram Bolder, Mark Dunn, Michael Gienger, Herbert Janßen, Hisashi Sugiura, Christian Goerick,
"Visually Guided Whole Body Interaction",
IEEE International Conference on Robotics and Automation (ICRA 2007), 2007.
Abstract
We describe a system for visual interaction developed for humanoid robots. It enables the robot to interact with its environment using a smooth whole body motion control driven by stabilized visual targets. Targets are defined as visually extracted "proto-objects" and behavior-relevant object hypotheses and are stabilized by means of a short-term sensory memory. Selection mechanisms are used to switch between behavior alternatives for searching o...
Download Bibtex file
Download PDF
Bernd Schneiders,
"Objektdetektion mit einem hierarchischen Modell der Verarbeitung im visuellen Kortex",
Univ. Applied Sciences Trier (Birkenfeld), 2007.
Download Bibtex file
Per Mail Request
Julian Eggert, Sven Rebhan, Edgar Körner,
"First steps towards an intentional vision system",
Proceedings of the 5th International Conference on Computer Vision Systems, ICVS, 2007.
Abstract
Contrary to many standard vision systems which proceed in a cascaded feedforward manner, imposing a fixed order in the sequence of visual operations like detection preceding segmentation and classification, we develop here the idea of a vision system that flexibly controls the order and accessibility of visual processes during operation. Vision is hereby understood as the dynamic process of adaptation of visual parameters and modules as a functio...
Download Bibtex file
Martin Heckmann, Frank Joublin, Christian Goerick,
"Combining Rate and Place Information for Robust Pitch Extraction",
Proc. INTERSPEECH 2007, pp. 2765-2768, 2007.
Abstract
In this paper we propose an algorithm for the robust extraction of pitch combining both temporal (rate) and pattern matching (place) techniques. Following a transformation into the spectral domain via the application of a Gammatone filter bank the rate information is extracted in each band via the zero crossing distances in that band. Next a comb filter with teeth at the harmonics of the current fundamental frequency hypothesis is set up, reflect...
Download Bibtex file
Xavier Domont, Martin Heckmann, Heiko Wersing, Frank Joublin, Stefan Menzel, Bernhard Sendhoff, Christian Goerick,
"Word Recognition with a Hierarchical Neural Network",
Advances in Nonlinear Speech Processing, pp. 142-151, 2007.
Abstract
In this paper we propose a feedforward neural network for syllable recognition. The core of the recognition system is based on a hierarchical architecture initially developed for visual object recognition. We show that, given the similarities between the primary auditory and visual cortexes, such a system can successfully be used for speech recognition. Syllables are used as basic units for the recognition. Their spectrograms, computed using a Ga...
Download Bibtex file
Download PDF
Nils Einecke, Julian Eggert, Sven Hellbach, Edgar Körner,
"Walking the manifold without falling off",
Proceedings of the 14th International Conference on Neual Information Processing (ICONIP), pp. 653-662, 2007.
Abstract
Having a good description of an object’s appearance is crucial for good object tracking. However, modeling the whole appearance of an object is difficult because of the high dimensional and nonlinear character of the appearance. To tackle the first problem we apply nonlinear dimensionality reduction approaches on multiple views of an object in order to extract the appearance manifold of the object and to embed it into a lower dimensional space....
Download Bibtex file
Download PDF
Marc-Oliver Gewaltig,
"Simulation Technologie for large neural systems.",
Recent developments, chances and limitations of modern brain research., Technologie Ausschuss des Deutschen Bundestags, 2006.
Abstract
In computational neuroscience, simulations are an important tool to investigate and answer questions which are not tractable by experimental methods. They allow us to explicitly test models of information processing, by constructing models according to the hypothesized principles. Most computer models of neural systems focus on the properties of single neurons or small networks of neurons (see 2.2.2). However, in order to understand the fundament...
Download Bibtex file
Hans-Georg Beyer and Bernhard Sendhoff,
"Functions with Noise-Induced Multi-Modality: A Test for Evolutionary Robust Optimization – Properties and Performance Analysis",
IEEE Transactions on Evolutionary Computation, vol. 10, no. 5, pp. 507-526, 2006.
Download Bibtex file
Jochen Steil and Heiko Wersing,
"Recent trends in online learning for cognitive robotics",
Proceedings of the European Symposium on Neural Networks, pp. 77-88, 2006.
Download Bibtex file
Download PDF
Inna Mikhailova, Werner von Seelen, Christian Goerick,
"Usage of General Developmental Principles for Adaptation of Reactive Behavior",
Proceedings of the Sixth International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems, pp. 63-70, 2006.
Abstract
We propose a design of a self-motivational system which would be suitable for both adaptation and development scenarios. The core features of our design are: the usage of general rewards and building up on a reactive system. As a test case for our design we use the human-robot interaction via shared attention. We show that with addition of a general-purpose self-motivational mechanism the system can aquire a behavior for distinguishing between ob...
Download Bibtex file
Download PDF
1 ...
127 128 129 130
131 132 ...
151
