A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving

Abstract

Capturing uncertainty in object detection is indispensable for safe autonomous driving. In recent years, deep learning has become the de-facto approach for object detection, and many probabilistic object detectors have been proposed. However, there is no summary on uncertainty estimation in deep object detection, and existing methods are not only built with different network architectures and uncertainty estimation methods, but also evaluated on different datasets with a wide range of evaluation metrics. As a result, a comparison among methods remains challenging, as does the selection of a model that best suits a particular application. This paper aims to alleviate this problem by providing a review and comparative study on existing probabilistic object detection methods for autonomous driving applications. First, we provide an overview of generic uncertainty estimation in deep learning, and then systematically survey existing methods and evaluation metrics for probabilistic object detection. Next, we present a strict comparative study for probabilistic object detection based on an image detector and three public autonomous driving datasets. Finally, we present a discussion of the remaining challenges and future works. Code has been made available at https://github.com/asharakeh/pod_compare.git

arXiv commentAccepted in the IEEE Transactions on Intelligent Transportation Systems

References in corpus (30)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• On Calibration of Modern Neural Networks
• Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
• Weight Uncertainty in Neural Networks
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• The ApolloScape Open Dataset for Autonomous Driving and its Application
• Evidential Deep Learning to Quantify Classification Uncertainty
• CrowdHuman: A Benchmark for Detecting Human in a Crowd
• Stochastic Gradient Hamiltonian Monte Carlo
• Accurate Uncertainties for Deep Learning Using Calibrated Regression
• Predictive Uncertainty Estimation via Prior Networks
• The EuroCity Persons Dataset: A Novel Benchmark for Object Detection
• A General Framework for Uncertainty Estimation in Deep Learning
• Scalability in Perception for Autonomous Driving: Waymo Open Dataset
• Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction
• Reliability, Sufficiency, and the Decomposition of Proper Scores
• Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
• SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving
• Verified Uncertainty Calibration
• Uncertainty Estimation in One-Stage Object Detection
• Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning
• A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
• Towards a Framework to Manage Perceptual Uncertainty for Safe Automated Driving
• SemanticVoxels: Sequential Fusion for 3D Pedestrian Detection using LiDAR Point Cloud and Semantic Segmentation
• Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving
• Large-Scale Visual Active Learning with Deep Probabilistic Ensembles
• Localization Uncertainty Estimation for Anchor-Free Object Detection
• Labels Are Not Perfect: Improving Probabilistic Object Detection via Label Uncertainty

Cited by in corpus (18)

• Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys
• Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review
• Choose Your Simulator Wisely: A Review on Open-source Simulators for Autonomous Driving
• Run-Time Monitoring of Machine Learning for Robotic Perception: A Survey of Emerging Trends
• Uncertainty for Identifying Open-Set Errors in Visual Object Detection
• Model-agnostic explainable artificial intelligence for object detection in image data
• Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks
• Probabilistic Metamodels for an Efficient Characterization of Complex Driving Scenarios
• LiDAR-MIMO: Efficient Uncertainty Estimation for LiDAR-based 3D Object Detection
• Rethinking Trajectory Forecasting Evaluation
• Object Detection as Probabilistic Set Prediction
• Prediction Accuracy & Reliability: Classification and Object Localization under Distribution Shift
• Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling
• Utilizing dataset affinity prediction in object detection to assess training data
• Probabilistic Approach for Road-Users Detection
• An Efficient Approach to Generate Safe Drivable Space by LiDAR-Camera-HDmap Fusion
• Overcoming the Limitations of Localization Uncertainty: Efficient & Exact Non-Linear Post-Processing and Calibration
• Calibrating the Full Predictive Class Distribution of 3D Object Detectors for Autonomous Driving