Uncertainty Estimation in One-Stage Object Detection

Abstract

Environment perception is the task for intelligent vehicles on which all subsequent steps rely. A key part of perception is to safely detect other road users such as vehicles, pedestrians, and cyclists. With modern deep learning techniques huge progress was made over the last years in this field. However such deep learning based object detection models cannot predict how certain they are in their predictions, potentially hampering the performance of later steps such as tracking or sensor fusion. We present a viable approaches to estimate uncertainty in an one-stage object detector, while improving the detection performance of the baseline approach. The proposed model is evaluated on a large scale automotive pedestrian dataset. Experimental results show that the uncertainty outputted by our system is coupled with detection accuracy and the occlusion level of pedestrians.

References in corpus (2)

• SSD: Single Shot MultiBox Detector
• The EuroCity Persons Dataset: A Novel Benchmark for Object Detection

Cited by in corpus (10)

• A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving
• Multivariate Confidence Calibration for Object Detection
• A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications
• Building Extraction from Remote Sensing Images via an Uncertainty-Aware Network
• Uncertainty for Identifying Open-Set Errors in Visual Object Detection
• Trustworthy Multimodal Fusion for Sentiment Analysis in Ordinal Sentiment Space
• Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates
• A Trustworthiness Score to Evaluate DNN Predictions
• Prediction Accuracy & Reliability: Classification and Object Localization under Distribution Shift
• Overcoming the Limitations of Localization Uncertainty: Efficient & Exact Non-Linear Post-Processing and Calibration