LiDARDustX: A LiDAR Dataset for Dusty Unstructured Road Environments

2025-05-28

AI Summary

Existing autonomous driving datasets primarily target structured urban environments and lack coverage of unstructured, adverse conditions—particularly high-dust scenarios prevalent in mining and off-road settings. Method: We introduce DustLIDAR, the first open-source LiDAR dataset specifically designed for high-dust environments, comprising 30,000 multi-sensor point cloud frames captured in real-world mining roads, with fine-grained 3D bounding box annotations and per-point semantic segmentation; over 80% of samples exhibit significant dust-induced interference. We further propose the first systematic physical model of dust-induced LiDAR signal degradation and establish a dust-robustness benchmark for 3D detection and segmentation. Contribution/Results: Evaluating 12 state-of-the-art models on DustLIDAR, we quantitatively demonstrate an average 27.4% drop in detection accuracy under dust interference. All data, annotations, degradation modeling framework, and evaluation tools are publicly released, addressing a critical gap in perception datasets and benchmarks for adverse environmental conditions.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: 3D Computer Vision
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Web Mining and Content Analysis: Web data integration and cleaning
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Autonomous driving datasets are essential for validating the progress of intelligent vehicle algorithms, which include localization, perception, and prediction. However, existing datasets are predominantly focused on structured urban environments, which limits the exploration of unstructured and specialized scenarios, particularly those characterized by significant dust levels. This paper introduces the LiDARDustX dataset, which is specifically designed for perception tasks under high-dust conditions, such as those encountered in mining areas. The LiDARDustX dataset consists of 30,000 LiDAR frames captured by six different LiDAR sensors, each accompanied by 3D bounding box annotations and point cloud semantic segmentation. Notably, over 80% of the dataset comprises dust-affected scenes. By utilizing this dataset, we have established a benchmark for evaluating the performance of state-of-the-art 3D detection and segmentation algorithms. Additionally, we have analyzed the impact of dust on perception accuracy and delved into the causes of these effects. The data and further information can be accessed at: https://github.com/vincentweikey/LiDARDustX.

Problem

• Lack of datasets for dusty unstructured road environments
• Need for perception tasks in high-dust conditions
• Impact of dust on 3D detection and segmentation accuracy

Innovation

• LiDAR dataset for dusty unstructured roads
• 30,000 frames with 3D annotations
• Benchmark for dust-impacted perception