Toward unlabeled multi-view 3D pedestrian detection by generalizable AI: techniques and performance analysis

TL;DR

This paper explores how generalizable AI techniques, specifically automatic labeling with untrained detectors, can enhance multi-view 3D pedestrian detection in unlabeled scenes, outperforming existing methods.

Contribution

It introduces a training framework utilizing automatic labeling with untrained detectors, demonstrating improved detection performance on public datasets.

Findings

Untrained detector-based labeling outperforms other automatic labeling methods.

Achieved 4% and 1% better MODA scores than existing unlabeled methods on WILDTRACK and MultiviewX.

Framework effectively enhances generalization in unlabeled multi-view 3D pedestrian detection.

Abstract

We unveil how generalizable AI can be used to improve multi-view 3D pedestrian detection in unlabeled target scenes. One way to increase generalization to new scenes is to automatically label target data, which can then be used for training a detector model. In this context, we investigate two approaches for automatically labeling target data: pseudo-labeling using a supervised detector and automatic labeling using an untrained detector (that can be applied out of the box without any training). We adopt a training framework for optimizing detector models using automatic labeling procedures. This framework encompasses different training sets/modes and multi-round automatic labeling strategies. We conduct our analyses on the publicly-available WILDTRACK and MultiviewX datasets. We show that, by using the automatic labeling approach based on an untrained detector, we can obtain superior results than directly using the untrained detector or a detector trained with an existing labeled source dataset. It achieved a MODA about 4% and 1% better than the best existing unlabeled method when using WILDTRACK and MultiviewX as target datasets, respectively.