Toward unlabeled multi-view 3D pedestrian detection by generalizable AI: techniques and performance analysis
This work addresses pedestrian detection for surveillance or autonomous systems in new, unlabeled environments, but it is incremental as it builds on existing labeling and training frameworks.
The paper tackles the problem of multi-view 3D pedestrian detection in unlabeled target scenes by using generalizable AI, specifically comparing pseudo-labeling and automatic labeling with an untrained detector, and shows that the untrained detector approach achieves a MODA about 4% better on WILDTRACK and 1% better on MultiviewX compared to existing unlabeled methods.
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.