3D localization of persons from a single image is a challenging problem, where advances are largely data-driven. In this paper, we enhance the recently released EuroCity Persons detection dataset, a large and diverse automotive dataset covering pedestrians and riders. Previously, only 2D annotations and image data were provided. We introduce an automatic 3D lifting procedure by using additional LiDAR distance measurements, to augment a large part of the reasonable subset of 2D box annotations with their corresponding 3D point positions (136K persons in 46K frames of day- and night-time). The resulting dataset (coined ECP2.5D), now including Li-DAR data as well as the generated annotations, is made publicly available for (non-commercial) benchmarking of camera-based and/or LiDAR 3D object detection methods. We provide baseline results for 3D localization from single images by extending the YOLOv3 2D object detector with a distance regression including uncertainty estimation.
ECP2.5D - Person Localization in Traffic Scenes
2020 IEEE Intelligent Vehicles Symposium (IV) ; 1694-1701
2020-10-19
4047205 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
ECP2.5D - PERSON LOCALIZATION IN TRAFFIC SCENES
British Library Conference Proceedings | 2020
|AN EXPERIMENTAL STUDY ON 3D PERSON LOCALIZATION IN TRAFFIC SCENES
British Library Conference Proceedings | 2020
|Monitoring crowded traffic scenes
IEEE | 2002
|Study on Detection and Localization Algorithm of Traffic Signs from Natural Scenes
Tema Archiv | 2014
|