We present a multi-camera 3D pedestrian detection method that does not need to train using data from the target scene. We estimate pedestrian location on the ground plane using a novel heuristic based on human body poses and person's bounding boxes from an off-the-shelf monocular detector. We then project these locations onto the world ground plane and fuse them with a new formulation of a clique cover problem. We also propose an optional step for exploiting pedestrian appearance during fusion by using a domain-generalizable person re-identification model. We evaluated the proposed approach on the challenging WILDTRACK dataset. It obtained a MODA of 0.569 and an F-score of 0.78, superior to state-of-the-art generalizable detection techniques.
@article{arxiv.2104.05813,
title = {Generalizable Multi-Camera 3D Pedestrian Detection},
author = {João Paulo Lima and Rafael Roberto and Lucas Figueiredo and Francisco Simões and Veronica Teichrieb},
journal= {arXiv preprint arXiv:2104.05813},
year = {2021}
}
Comments
Accepted to CVPRW 2021, LatinX in Computer Vision (LXCV) Workshop