3 papers
cs.CV2019
Combining Deep Learning and Model-Based Methods for Robust Real-Time Semantic Landmark Detection
Benjamin Naujoks, Patrick Burger, Hans-Joachim Wuensche
Compared to abstract features, significant objects, so-called landmarks, are a more natural means for vehicle localization and navigation, especially in challenging unstructured en…
eess.SP2019
Fast 3D Extended Target Tracking using NURBS Surfaces
Benjamin Naujoks, Patrick Burger, Hans-Joachim Wuensche
This paper proposes fast and novel methods to jointly estimate the target's unknown 3D shape and dynamics. Measurements are noisy and sparsely distributed 3D points from a light de…
cs.CV2018
The Greedy Dirichlet Process Filter - An Online Clustering Multi-Target Tracker
Benjamin Naujoks, Patrick Burger, Hans-Joachim Wuensche
Reliable collision avoidance is one of the main requirements for autonomous driving. Hence, it is important to correctly estimate the states of an unknown number of static and dyna…