Inferring Spatial Uncertainty in Object Detection
This work addresses the need for probabilistic evaluation in autonomous driving object detection, though it is incremental as it builds on existing uncertainty modeling methods.
The authors tackled the problem of deterministic bounding box annotations in object detection datasets by proposing a generative model to estimate label uncertainties from LiDAR point clouds, resulting in a new evaluation metric, JIoU, that outperforms IoU on KITTI and Waymo Open Datasets.
The availability of real-world datasets is the prerequisite for developing object detection methods for autonomous driving. While ambiguity exists in object labels due to error-prone annotation process or sensor observation noises, current object detection datasets only provide deterministic annotations without considering their uncertainty. This precludes an in-depth evaluation among different object detection methods, especially for those that explicitly model predictive probability. In this work, we propose a generative model to estimate bounding box label uncertainties from LiDAR point clouds, and define a new representation of the probabilistic bounding box through spatial distribution. Comprehensive experiments show that the proposed model represents uncertainties commonly seen in driving scenarios. Based on the spatial distribution, we further propose an extension of IoU, called the Jaccard IoU (JIoU), as a new evaluation metric that incorporates label uncertainty. Experiments on the KITTI and the Waymo Open Datasets show that JIoU is superior to IoU when evaluating probabilistic object detectors.