Search our Publications
Latest Publications
Qiang Li, Robert Haschke, Helge Ritter, Bram Bolder , "Grasp Point Optimization by Online Exploration of Unknown Object Surface", 12th IEEE-RAS Intl Conf on Humanoid Robots, 2012.
Download Bibtex file
Nils Einecke , "Stereoscopic Depth Estimation for Online Vision Systems", Uni Ilmenau, TU Ilmenau, 2012.
AbstractThe human visual perception heavily depends on stereoscopic vision. By fusing the two views that our eyes provide, a 3-D sensation of the surrounding is generated. It is therefore natural to assume that machine vision systems also benefit from a comparable sense. A lot of work has been done in the area of machine stereo vision, but a severe drawback of today’s algorithms is that they either achieve high accuracy and robustness by sacrificing real...
Download Bibtex file Per Mail Request
Morimichi Nishigaki, Sven Rebhan, Nils Einecke , "Vision-based Lateral Position Improvement of RADAR Detections", ITSC, pp. 90–97, 2012.
AbstractDetecting vehicles ahead by sensors mounted on an ego-vehicle is an essential element of Advanced Driver Assistance Systems (ADAS). Although millimeter-wave radar sensors are very robust at detecting vehicles, the lateral position resolution is very low. However, a more precise lateral position would not only improve the performance of existing ADAS, but it would also enable a wide range of additional applications. In this paper, we propose a met...
Download Bibtex file
Nikola Aulig and Ingolf Lepenies , "A Topology Optimization Interface for LS-Dyna", LS-Dyna Forum 2012, 2012.
Download Bibtex file
Thomas Guthier, Adrian Sosic, Julian Eggert, Volker Willert , "Finding a tradeoff between compression and loss in motion compensated video coding", SIGMAP 2012, pp. 81-84, 2012.
AbstractIn video coding, affine motion models combined with a quadtree decomposition have often been suggested as an extension to the mostly used translational models combined with a blockwise decomposition. What is missing so far is a thorough analysis to judge the tradeoff between using more complex motion models or more elaborate decomposition methods in terms of data compression and information loss. In this paper, we compare different polynomial...
Download Bibtex file
Christian Vollmer, Julian Eggert, Horst-Michael Groß , "Generating Motion Trajectories by Sparse Activation of Learned Motion Primitives", Int. Conf. on Artificial Neural Networks (ICANN), vol. 1, pp. 637-644, 2012.
AbstractWe interpret biological motion trajectories as composed of sequences of sub-blocks or motion primitives. Such primitives, together with the information, when they occur during a motion, provide a compact representation of movement.We present a two-layer model for movement generation, where the higher level consists of a number of spiking neurons that trigger motion primitives in the lower level. Given a set of handwritten character trajectories, ...
Download Bibtex file
Christian Vollmer, Julian Eggert, Horst-Michael Groß , "Modeling Human Motion Trajectories by Sparse Activation of Motion Primitives Learned from Unpartitioned Data", German Conf. on Artificial Intelligence (KI), pp. 168-179, 2012.
AbstractWe interpret biological motion trajectories as being composed of sequences of sub-blocks or motion primitives. Such primitives, together with the information, when they occur during an observed trajectory, provide a compact representation of movement in terms of events that is invariant to temporal shifts. Based on this representation, we present a model for the generation of motion trajectories that consists of two layers. In the lower lay...
Download Bibtex file
Benjamin Inden, Yaochu Jin, Robert Haschke, Helge Ritter , "Evolving neural fields for problems with large input and output spaces", Neural Networks, vol. 28, pp. 24-39, 2012.
AbstractWe have developed an extension of the NEAT neuroevolution method, called NEATfields, to solve problems with large input and output spaces. The NEATfields method is a multilevel neuroevolution method using externally specified design patterns. Its networks have three levels of architecture. The highest level is a NEAT-like network of neural fields. The intermediate level is a field of identical subnetworks, called field elements, with a two-dimens...
Download Bibtex file
Benjamin Inden, Yaochu Jin, Robert Haschke, Helge Ritter , "Evolution of multisensory integration in large neural fields", Lecture Notes in Computer Science, vol. 7401, pp. 181-192, 2012.
AbstractWe show that by evolving neural fields it is possible to study the evolution of neural networks that perform multisensory integration of high dimensional input data. In particular, four simple tasks for the integration of visual and tactile input are introduced. Neural networks evolve that can use these senses in a cost-optimal way, enhance the accuracy of classifying noisy input images, or enhance spatial accuracy of perception. An evolved neura...
Download Bibtex file
Nikolas Hemion, Frank Joublin, Katharina Rohlfing , "Integration of Sensorimotor Mappings by Making Use of Redundancies", Int. Joint Conf. on Neural Networks, pp. 1-8, 2012.
AbstractWe present a novel approach to learn and combine multiple input to output mappings. Our system can employ the mappings to find solutions that satisfy multiple task constraints simultaneously. This is done by training a network for each mapping independently and maintaining all solutions to multivalued mappings. Redundancies are resolved online through dynamic competitions in neural fields. The performance of the approach is demonstrated in the ex...
Download Bibtex file
1 ... 113 114 115 116 117 118 ... 183
Follow us
