Abstract
Automated monitoring and analysis of passenger movement in safety-critical parts of transport infrastructures represent a relevant visual surveillance task. Recent breakthroughs in visual representation learning and spatial sensing opened up new possibilities for detecting and tracking humans and objects within a 3D spatial context. This paper proposes a flexible analysis scheme and a thorough evaluation of various processing pipelines to detect and track humans on a ground plane, calibrated automatically via stereo depth and pedestrian detection. We consider multiple combinations within a set of RGB- and depth-based detection and tracking modalities. We exploit the modular concepts of Meshroom and demonstrate its use as a generic vision processing pipeline and scalable evaluation framework. Furthermore, we introduce a novel open RGB-D railway platform dataset with annotations to support research activities in automated RGB-D surveillance. We present quantitative results for multiple object detection and tracking for various algorithmic combinations on our dataset. Results indicate that the combined use of depth-based spatial information and learned representations yields substantially enhanced detection and tracking accuracies. As demonstrated, these enhancements are especially pronounced in adverse situations when occlusions and objects not captured by learned representations are present.
Originalsprache | Englisch |
---|---|
Titel | Pattern Recognition. ICPR International Workshops and Challenges |
Herausgeber (Verlag) | Springer Nature |
Seiten | 656-671 |
Seitenumfang | 16 |
Band | 12667 |
ISBN (elektronisch) | 978-3-030-68787-8 |
ISBN (Print) | 978-3-030-68786-1 |
DOIs | |
Publikationsstatus | Veröffentlicht - 2021 |
Veranstaltung | International Workshop on Research & Innovation for Secure Societies at the International Conference on Pattern Recognition ICPR 2020 - Dauer: 10 Jan. 2021 → 15 Jan. 2021 |
Publikationsreihe
Name | Lecture Notes in Computer Science |
---|---|
Herausgeber (Verlag) | Springer Nature |
Band | 12667 |
ISSN (Print) | 0302-9743 |
ISSN (elektronisch) | 161-3349 |
Konferenz
Konferenz | International Workshop on Research & Innovation for Secure Societies at the International Conference on Pattern Recognition ICPR 2020 |
---|---|
Zeitraum | 10/01/21 → 15/01/21 |
Research Field
- Assistive and Autonomous Systems
Fingerprint
Untersuchen Sie die Forschungsthemen von „RGB-D Railway Platform Monitoring and Scene Understanding for Enhanced Passenger Safety“. Zusammen bilden sie einen einzigartigen Fingerprint.Forschungsdatensätze
-
RailEye3D Dataset
Wallner, M. (Urheber:in), Steininger, D. (Mitwirkende:r), Widhalm, V. (Datenmanager:in), Schörghuber, M. (Mitwirkende:r) & Beleznai, C. (Mitwirkende:r), 2021
https://github.com/raileye3d/raileye3d_dataset und noch ein Link, https://paperswithcode.com/dataset/raileye3d-dataset (weniger anzeigen)
Datensatz