2018

Aquaplaning - a potential hazard also for Automated Driving
Bernd Hartmann and Thomas Raste and Matthias Kretschmann and Manuel Amthor and Felix Schneider and Joachim Denzler.
ITS automotive nord e.V. (Hrsg.), Braunschweig. 2018.
[bibtex]

2016

Impatient DNNs - Deep Neural Networks with Dynamic Time Budgets
Manuel Amthor and Erik Rodner and Joachim Denzler.
British Machine Vision Conference (BMVC). 2016.
[bibtex] [pdf]

2015

Road Condition Estimation based on Spatio-Temporal Reflection Models
Manuel Amthor and Bernd Hartmann and Joachim Denzler.
DAGM German Conference on Pattern Recognition (DAGM-GCPR). Pages 3-15. 2015.
[bibtex] [pdf] []

Abstract: Automated road condition estimation is a crucial basis for Advanced Driver Assistance Systems (ADAS) and even more for highly and fully automated driving functions in future. In order to improve vehicle safety relevant vehicle dynamics parameters, e.g. last-point-to-brake (LPB), last-point-to-steer (LPS), or vehicle curve speed should be adapted depending on the current weather-related road surface conditions. As vision-based systems are already integrated in many of today’s vehicles they constitute a beneficial resource for such a task. As a first contribution, we present a novel approach for reflection modeling which is a reliable and robust indicator for wet road surface conditions. We then extend our method by texture description features since local structures enable for the distinction of snow-covered and bare road surfaces. Based on a large real-life dataset we evaluate the performance of our approach and achieve results which clearly outperform other established vision-based methods while ensuring real-time capability.
Fahrbahnzustandserkennung als grundlegender Baustein für das Umfeldmodell
Bernd Hartmann and Manuel Amthor and Waldemar Jarisa.
VDI-Fachkonferenz - Innovative Bremstechnik. 2015.
[bibtex] []

Abstract: Der Wunsch, den Fahrbahnzustand oder gar den zwischen Reifen und Fahrbahn zur Verfügung stehenden Reibbeiwert vorausschauend, robust und möglichst präzise zu erfassen, ist nicht neu und beschäftigt seit mehreren Jahrzehnten aber spätestens seit dem EUREKA-Prometheus-Projekt (PROgraMme for a European Traffic of Highest Efficiency and Unprecedented Safety, 1986–1994) die weltweite Automobil- und Zulieferindustrie. Das Haftungspotenzial zwischen Reifen und Fahrbahn bestimmt die physikalischen Grenzen der Fahrdynamik und ist somit ausschlaggebender Faktor für die aktive Sicherheit von Kraftfahrzeugen. Erfreulicherweise haben sich die Rahmenbedingungen zur Entwicklung solcher Systeme in den letzten Jahren stark zum Positiven verändert. Einerseits steigt der Vernetzungsgrad der Fahrzeuge stetig und die Sensorentwicklung macht gerade im Bereich der Umfeldsensorik große Fortschritte. Die Evolution der Fahrdynamik- und Fahrerassistenzsysteme fordert neben einer deutlich steigenden Rechenleistung für Integrationsplattformen immer genauere und teilweise auch redundante Umfeldsensoren bei gleichzeitig größeren Erfassungsbereichen für das Sensor-Setup. Andererseits ergeben sich gerade durch die Fahrerassistenz neue Anwendungsfälle, die schon bei reduzierten Anforderungen funktional einen Mehrwert durch Einbeziehung von Informationen zum Fahrbahnzustand versprechen. Der hier beschriebene Ansatz zielt darauf ab, über die Fusion bereits existierender Fahrzeugsensoren, wie beispielsweise Wetter-, Inertial- und Umfeldsensorik ergänzt um digitale Wetterkarten und Backendinformationen, den Fahrbahnzustand zu bestimmen und daraus eine Reibwertklasse abzuleiten, die nutzbringend für die Adaption von Fahrerassistenzsystemen genutzt werden kann. Wo die Kenntnis des Fahrbahnzustands für manuelles, assistiertes oder teilautomatisiertes Fahren noch einen nützlichen funktionalen Mehrwert verspricht, ist sie für Systeme des Hoch- und Vollautomatisierten Fahrens eine zwingende Voraussetzung.

2014

Robust Pictorial Structures for X-ray Animal Skeleton Tracking
Manuel Amthor and Daniel Haase and Joachim Denzler.
International Conference on Computer Vision Theory and Applications (VISAPP). Pages 351-359. 2014.
[bibtex] [pdf] []

Abstract: The detailed understanding of animals in locomotion is a relevant field of research in biology, biomechanics and robotics. To examine the locomotor system of birds in vivo and in a surgically non-invasive manner, high-speed X-ray acquisition is the state of the art. For a biological evaluation, it is crucial to locate relevant anatomical structures of the locomotor system. There is an urgent need for automating this task, as vast amounts of data exist and a manual annotation is extremely time-consuming. We present a biologically motivated skeleton model tracking framework based on a pictorial structure approach which is extended by robust sub-template matching. This combination makes it possible to deal with severe self-occlusions and challenging ambiguities. As opposed to model-driven methods which require a substantial amount of labeled training samples, our approach is entirely data-driven and can easily handle unseen cases. Thus, it is well suited for large scale biological applications at a minimum of manual interaction. We validate the performance of our approach based on 24 real-world X-ray locomotion datasets, and achieve results which are comparable to established methods while clearly outperforming more general approaches.

2012

Fast and Robust Landmark Tracking in X-ray Locomotion Sequences Containing Severe Occlusions
Manuel Amthor and Daniel Haase and Joachim Denzler.
International Workshop on Vision, Modelling, and Visualization (VMV). Pages 15-22. 2012.
[bibtex] []

Abstract: Recent advances in the understanding of animal locomotion have proven it to be a key element of many fields in biology, motion science, and robotics. For the analysis of walking animals, high-speed x-ray videography is employed. For a biological evaluation of these x-ray sequences, anatomical landmarks have to be located in each frame. However, due to the motion of the animals, severe occlusions complicate this task and standard tracking methods can not be applied. We present a robust tracking approach which is based on the idea of dividing a template into sub-templates to overcome occlusions. The difference to other sub-template approaches is that we allow soft decisions for the fusion of the single hypotheses, which greatly benefits tracking stability. Also, we show how anatomical knowledge can be included into the tracking process to further improve the performance. Experiments on real datasets show that our method achieves results superior to those of existing robust approaches.