home / centre for automotive safety research / Publications / List / Details
|Title||Weakly Supervised Training of Monocular 3D Object Detectors Using Wide Baseline Multi-view Traffic Camera Data|
|Authors||Howe M, Reid I, Mackenzie JRR|
|Abstract||Accurate 7DoF prediction of vehicles at an intersection is an important task for assessing potential conflicts between road users. In principle, this could be achieved by a single camera system that is capable of detecting the pose of each vehicle but this would require a large, accurately labelled dataset from which to train the detector. Although large vehicle pose datasets exist (ostensibly developed for autonomous vehicles), we find training on these datasets inadequate. These datasets contain images from a ground level viewpoint, whereas an ideal view for intersection observation would be elevated higher above the road surface. We develop an alternative approach using a weakly supervised method of fine tuning 3D object detectors for traffic observation cameras; showing in the process that large existing autonomous vehicle datasets can be leveraged for pre-training. To fine-tune the monocular 3D object detector, our method utilises multiple 2D detections from overlapping, wide-baseline views and a loss that encodes the subjacent geometric consistency. Our method achieves vehicle 7DoF pose prediction accuracy on our dataset comparable to the top performing monocular 3D object detectors on autonomous vehicle datasets. We present our training methodology, multi-view reprojection loss, and dataset.|
|Conference Name||The 32nd British Machine Vision Conference|
|Conference Abbreviation||BMVC 2021|
|Conference Date||22-25 November 2021|
|Notes||Available from Cornell University online: https://arxiv.org/abs/2110.10966
The copyright of this document resides with its authors.
It may be distributed unchanged freely in print or electronic forms.
|Howe M, Reid I, Mackenzie JRR (2021). Weakly Supervised Training of Monocular 3D Object Detectors Using Wide Baseline Multi-view Traffic Camera Data. The 32nd British Machine Vision Conference, 22-25 November 2021.|