Inferring Spatial Uncertainty in Object Detection

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.

Authors

• Zining Wang
• Di Feng
• Yiyang Zhou
• Lars Rosenbaum
• Fabian Timm
• Klaus Dietmayer
• Masayoshi Tomizuka
• Wei Zhan

Keywords

• Uncertainty
• Graphical models
• Three-dimensional displays
• Annotations
• Object detection
• Probabilistic logic
• Distribution functions
• Spatial Uncertainty
• Deterministic
• Intersection Over Union
• Point Cloud
• Bounding Box
• Observation Noise
• Object Labels
• LiDAR Point
• LiDAR Point Clouds
• Object Detection Dataset
• Rich Information
• 3D Space
• Singular Value Decomposition
• Average Precision
• Object Size
• Gaussian Mixture Model
• Prediction Uncertainty
• Bird’s Eye
• Labeled Data Set
• KITTI Dataset
• Intersection Over Union Score
• Object Detection Network
• Label Noise
• Intersection Over Union Threshold
• Minimum Bounding Box
• Quality Labels
• Predicted Probability Distribution
• Predicted Bounding Box
• Intersection Over Union Value