Navigationsweiche Anfang

Navigationsweiche Ende

Lehrstuhl für Allgemeine Elektrotechnik und Theoretische Nachrichtentechnik

Prof. Dr.- Ing. Anton Kummert


  • Organisation der Vorlesung „Signale und Systeme“ bzgl. Uni@Home
    Aktuelle Informationen zur Organisation der Vorlesung „Signale und Systeme“ bzgl. Uni@Home finden... [mehr]
zum Archiv ->

Prof. Dr.-Ing. Anton Kummert


Raum: FE 1.01
Telefon: +49 (0)202 439 1961
E-Mail: kummert{at}



Jessica Malerczyk; Sabine Lerch; Bernd Tibken; Anton Kummert
Impact of intelligent agents on the avoidance of spontaneous traffic jams on two-lane motorways
MATEC Web of Conferences Band 308 , Seite 05003.
EDP Sciences
Jan-Christoph Schmitz; Stephan Tilgner; Kathrin Kalischewski; Daniel Wagner; Anton Kummert
Hands on Wheel Classification Based on Depth Images and Neural Networks
MATEC Web of Conferences Band 308 , Seite 06003.
EDP Sciences
Lukas Hahn; Lutz Roese-Koerner; Klaus Friedrichs; Anton Kummert
Fast and Reliable Architecture Selection for Convolutional Neural Networks Proceedings of the 27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), pages 179-184, Bruges 2019
ArXiv, abs/1905.01924

Schlüsselwörter: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

Zusammenfassung: The performance of a Convolutional Neural Network (CNN) depends on its hyperparameters, like the number of layers, kernel sizes, or the learning rate for example. Especially in smaller networks and applications with limited computational resources, optimisation is key. We present a fast and efficient approach for CNN architecture selection. Taking into account time consumption, precision and robustness, we develop a heuristic to quickly and reliably assess a network's performance. In combination with Bayesian optimisation (BO), to effectively cover the vast parameter space, our contribution offers a plain and powerful architecture search for this machine learning technique.

Matthias Buß; Stephan Benen; D Kraus; Anton Kummert
False Alarm Reduction for Active Sonars using Deep Learning Architectures
2019 UDT, Stockholm
Patrick Weyers; Alexander Barth; Anton Kummert
Driver State Monitoring with Hierarchical Classification
2018 IEEE International Conference on Intelligent Transportation Systems (ITSC)
November 2018
Bartlomiej Sulikowski; Krzysztof Galkowski; Anton Kummert; Eric Rogers
Two-dimensional (2D) systems approach to feedforward/feedback control of a class of spatially interconnected systems
International Journal of Control, 91:1-23
September 2018

Zusammenfassung: Electrical ladder circuits, consisting of a series, or cascade, connection of cells are a class of spatially interconnected systems. These circuits can be modeled as 2D systems, i.e., there exist two directions of information propagation, where one indeterminate is time and the other the number of the current cell (node). In this paper, the recently developed direct (2D) approach to stability analysis and stabilization of these systems is extended to the presence of uncertainty in the models described by the norm bounded structure. The analysis is then further extended to the design of feedforward/feedback control action to track a spatially distributed time invariant reference signal in the presence of disturbances.

Zhu Weimeng; J. Siegemund; Anton Kummert
Dense Spatial Translation Network
2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)
September 2018
Matthias Buß; Yannik Steiniger; Stephan Benen; Dietmar Stiller; Dieter Kraus; Anton Kummert
Evaluation un terschiedlicher Klassifikationsalgorithmen zur Falschalarmreduktion in der Aktiv-Sonarortung
Jahrestagung für Akustik DAGA 2018
Juli 2018
Farzin Ghorban; Narges Milani; Daniel Schugk; Lutz Roese-Koerner; Yu Su; Dennis M; Anton Kummert
Conditional multichannel generative adversarial networks with an application to traffic signs representation learning
Progress in Artificial Intelligence, 8
April 2018

Zusammenfassung: Generative adversarial networks (GANs) are known to produce photorealistic representations. However, we show in this study that this is only valid when the input channels come from a regular RGB camera sensor. In order to alleviate this shortcoming, we propose a general solution to which we refer to as multichannel GANs (MCGANs). In contrast to the existing approaches, MCGANs can process multiple channels with different textures and resolutions. This is achieved by using known concepts in deep learning such as weight sharing and specially separated convolutions. The proposed pipeline enables particular kernels to learn low-level characteristics from the different channels without the need for exhaustive hyper-parameter tuning. We demonstrate the improved representational ability of the framework on traffic sign samples that are captured by a camera with a so-called red-clear-clear-clear pixel topology. Furthermore, we extend our solution by applying the concept of conditions, that offers a whole spectrum of new features, especially for the generation of traffic signs. Throughout this paper, we further discuss relevant applications for the generated synthetic data.

Farzin Ghorban; Javier Marin; Yu Su; Alessandro Colombo; Anton Kummert
Aggregated channels network for real-time pedestrian detection
, Seite 54.
April 2018
Cao Jiuwen; Anton Kummert; Lin Zhiping; Jörg Velten
Recent Advances in Machine Learning for Signal Analysis and Processing
Journal of The Franklin Institute, Special Issue, 355(4):1513-2066
März 2018
Jörg Velten; Anton Kummert; D. Wagner; K. Galkowski
A k-D Stability Measure for Discrete Roesser-Like System Implementations
Januar 2018
Zurück | 1, 2, 3, 4, 5, 6, ... , 28 | Weiter