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.

提出了一种多相机 3D 行人检测方法，该方法不需要使用目标场景的数据进行训练，通过基于人体姿势和来自现成单目检测器的人物包围框的新启发式方法在地面平面上估计行人位置，然后将这些位置投影到世界地面平面，并用新的团覆盖问题公式进行融合，同时还提出利用域通用的行人再识别模型在融合期间对行人外貌的选择性步骤，评估表明，在具有挑战性的 WILDTRACK 数据集上，所提出的方法获得了 0.569 的 MODA 和 0.78 的 F 分数，优于现有的最先进的通用检测技术。