# Inferring Spatial Uncertainty in Object Detection

arXiv: https://arxiv.org/abs/2003.03644 · HTML: https://mlsanity.com/paper/2003.03644/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2020.

## Built on by (most cited first, 10 of 10)

- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Uncertainty for Identifying Open-Set Errors in Visual Object Detection](https://mlsanity.com/paper/2104.01328/) (2021)
- [GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation](https://mlsanity.com/paper/2207.02466/) (2022)
- [Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection](https://mlsanity.com/paper/2106.06072/) (2021)
- [Generating Evidential BEV Maps in Continuous Driving Space](https://mlsanity.com/paper/2302.02928/) (2023)
- [A Review of Testing Object-Based Environment Perception for Safe Automated Driving](https://mlsanity.com/paper/2102.08460/) (2021)
- [Reducing Overconfidence Predictions for Autonomous Driving Perception](https://mlsanity.com/paper/2202.07825/) (2022)
- [Multi-Agent Active Search using Detection and Location Uncertainty](https://mlsanity.com/paper/2203.04524/) (2022)
- [Checklist to Define the Identification of TP, FP, and FN Object Detections in Automated Driving](https://mlsanity.com/paper/2308.07106/) (2023)
- [Sarus: Privacy-Preserving Multi-Vendor Perception Fusion via Homomorphic Encryption](https://mlsanity.com/paper/2607.19146/) (2026)

## Abstract (arXiv)

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.