no code implementations • 13 Jul 2022 • Hao Xing, Yifan Cao, Maximilian Biber, Mingchuan Zhou, Darius Burschka
Supervised learning depth estimation methods can achieve good performance when trained on high-quality ground-truth, like LiDAR data.
no code implementations • 12 Jul 2022 • Hao Xing, Darius Burschka
However, in most existing Graph Convolutional Networks, the local attention mask is defined based on natural connections of human skeleton joints and ignores the dynamic relations for example between head, hands and feet joints.
no code implementations • 6 Sep 2021 • Hao Xing, Yuxuan Xue, Mingchuan Zhou, Darius Burschka
Our approach achieves the bestperformance on precision and accuracy of human fall event detection, compared with other existing dictionary learning methods.
no code implementations • 7 Jul 2020 • Darius Burschka, Christian Robl, Sebastian Ohrendorf-Weiss
We present an approach for optical navigation in unstructured, dynamic railroad environments.
no code implementations • 20 Jun 2018 • Kartik Gupta, Darius Burschka, Arnav Bhavsar
Due to the variations in geometrical and motion constraints, there are different manipulations actions possible to perform different sets of actions with an object.
no code implementations • 27 Apr 2018 • Jens Schulz, Constantin Hubmann, Julian Löchner, Darius Burschka
Planning for autonomous driving in complex, urban scenarios requires accurate prediction of the trajectories of surrounding traffic participants.
no code implementations • 18 Sep 2017 • Darius Burschka, Elmar Mair
We present a direct method to calculate a 6DoF pose change of a monocular camera for mobile navigation.
no code implementations • 7 Sep 2017 • Darius Burschka
We present a processing technique for a robust reconstruction of motion properties for single points in large scale, dynamic environments.
no code implementations • 15 Nov 2016 • Aurelien Bustin, Anne Menini, Martin A. Janich, Darius Burschka, Jacques Felblinger, Anja C. S. Brau, Freddy Odille
The proposed method is a joint image reconstruction and motion correction method consisting of several steps, including a non-rigid motion extraction and a motion-compensated reconstruction.