@inproceedings{13f7f8cbe1a444b2aeff6a6ed7f16bdc,
title = "Generalizable multi-camera 3D pedestrian detection",
abstract = "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.",
author = "Lima, {Joao Paulo} and Rafael Roberto and Lucas Figueiredo and Francisco Simoes and Veronica Teichrieb",
year = "2021",
month = sep,
day = "1",
doi = "10.1109/CVPRW53098.2021.00135",
language = "English",
series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",
publisher = "IEEE",
pages = "1232--1240",
booktitle = "Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021",
address = "USA United States",
note = "2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 ; Conference date: 19-06-2021 Through 25-06-2021",
}