Prof. Dr. Didier Stricker

Dr. Alain Pagani

Keonna Cunningham

Dr. Jason Raphael Rambach

Dr. Oliver Wasenmüller

Dr. Gabriele Bleser

Dr. Bertram Taetz

Rashed Al Koutayni

Jilliam Maria Diaz Barros

Mahdi Chamseddine

Steve Dias da Cruz

Christiano Couto Gava

Tewodros Amberbir Habtegebrial

Jigyasa Singh Katrolia

Andreas Kölsch

Onorina Kovalenko

Muhammad Jameel Nawaz Malik

Nareg Minaskan Karabid

Manthan Pancholi

María Alejandra Sánchez Marín

Dr. Kripasindhu Sarkar

Alexander Schäfer

Ahmet Firintepe

Dr. Vladislav Golyanik

Dr. Aditya Tewari

André Luiz Brandão

LRPD: Long Range 3D Pedestrian Detection Leveraging Specific Strengths of LiDAR and RGB

LRPD: Long Range 3D Pedestrian Detection Leveraging Specific Strengths of LiDAR and RGB
David Michael Fürst, Oliver Wasenmüller, Didier Stricker
IEEE International Conference on Intelligent Transportation Systems (ITSC). IEEE Intelligent Transportation Systems Conference (IEEE ITSC-2020) September 20-23 Virtual Conference Greece IEEE 2020 .

Abstract:: While short range 3D pedestrian detection is sufficient for emergency breaking, long range detections are required for smooth breaking and gaining trust in autonomous vehicles. The current state-of-the-art on the KITTI benchmark performs suboptimal in detecting the position of pedestrians at long range. Thus, we propose an approach specifically targeting long range 3D pedestrian detection (LRPD), leveraging the density of RGB and the precision of LiDAR. Therefore, for proposals, RGB instance segmentation and LiDAR point based proposal generation are combined, followed by a second stage using both sensor modalities symmetrically. This leads to a significant improvement in mAP on long range compared to the current state-of-the art. The evaluation of our LRPD approach was done on the pedestrians from the KITTI benchmark.

Back to the overview