Tobias Bolten
18 Papers
17 Citations
Tobias Bolten is an academic researcher. The author has contributed to research in topics: Computer science & Neuromorphic engineering. The author has an hindex of 3, co-authored 9 publications.
Chat about Author
Papers
DVS-OUTLAB: A Neuromorphic Event-Based Long Time Monitoring Dataset for Real-World Outdoor Scenarios
Tobias Bolten,Regina Pohle-Fröhlich,Klaus D. Tönnies +2 more
- 01 Jun 2021
TL;DR: In this article, the authors describe a recording setting of a DVS-based long time monitoring of an urban public area and provide labeled DVS data that also contain effects of environmental outdoor influences recorded in this process.
Empowering People with Disabilities Using Urban Public Transport
TL;DR: This paper shows an approach developed within the project “mobile” funded by The German Federal Ministry of economy and energy (BMWi) that supports this kind of users while traveling by public transport that takes their personal constraints into account and provides them with timely information about their trip.
13
•Proceedings Article
Detection of Symmetry Points in Images
Christoph Dalitz,Regina Pohle-Fröhlich,Tobias Bolten +2 more
- 01 Jan 2013
TL;DR: This article proposes a new method for detecting symmetry points in images that assigns a "symmetry score" to each image point and yields the size of the symmetry region without additional computational effort.
An HMM-based averaging approach for creating mean motion data from a full-body Motion Capture system to support the development of a biomechanical model
Andreas Kitzig,Julia Demmer,Tobias Bolten,Edwin Naroska,Gudrun Stockmanns,Reinhard Viga,Anton Grabmaier,Anton Grabmaier +7 more
TL;DR: A Hidden Markov Model (HMM) based approach is presented for the averaging of individual movement sequences of different persons in the field of biomechanical modeling and simulation.
N-MuPeTS: Event Camera Dataset for Multi-Person Tracking and Instance Segmentation
Tobias Bolten,Christian Neumann,Regina Pohle-Fröhlich,Klaus D. Tönnies +3 more
- 01 Jan 2023
TL;DR: This work presents a technical recording setup as well as a software processing pipeline for generating event-based recordings in the context of multi-person tracking and enables the automatic generation of highly accurate instance labels for each individual output event using color features in the scene.
4