提出高精度128通道激光雷达数据集与轻量分割架构，提升自动驾驶感知准确率与效率。
On Deep Learning for Geometric and Semantic Scene Understanding Using On-Vehicle 3D LiDAR
- 构建128通道全景红外与反射率图像激光雷达数据集DurLAR，支持高保真场景建模。
- 提出RAPiD-Seg架构，结合距离感知特征，在少量标注下实现更优分割精度。
- 轻量级设计兼顾效率与准确率，适合资源受限的自动驾驶系统部署。
3D LiDAR点云数据在计算机视觉、机器人及自动驾驶中对场景感知至关重要。几何与语义场景理解依赖于3D点云，是推动自动驾驶技术发展的关键。然而，系统在准确性（如分割精度、深度估计精度等）和效率方面仍面临重大挑战。为提升基于激光雷达任务的准确性，本文提出首个128通道高保真3D LiDAR数据集DurLAR，包含全景近红外与反射率图像。为提升3D分割效率并保持精度，提出新型轻量级流水线，所需人工标注更少，性能优于现有方法。为提高分割精度，引入范围感知点距离分布（RAPiD）特征及RAPiD-Seg架构。所有成果已通过同行评审会议接收，证实了在自动驾驶3D LiDAR应用中准确率与效率的双重提升。
原文摘要 · Abstract (English)
3D LiDAR point cloud data is crucial for scene perception in computer vision, robotics, and autonomous driving. Geometric and semantic scene understanding, involving 3D point clouds, is essential for advancing autonomous driving technologies. However, significant challenges remain, particularly in improving the overall accuracy (e.g., segmentation accuracy, depth estimation accuracy, etc.) and efficiency of these systems. To address the challenge in terms of accuracy related to LiDAR-based tasks, we present DurLAR, the first high-fidelity 128-channel 3D LiDAR dataset featuring panoramic ambient (near infrared) and reflectivity imagery. To improve efficiency in 3D segmentation while ensuring the accuracy, we propose a novel pipeline that employs a smaller architecture, requiring fewer ground-truth annotations while achieving superior segmentation accuracy compared to contemporary approaches. To improve the segmentation accuracy, we introduce Range-Aware Pointwise Distance Distribution (RAPiD) features and the associated RAPiD-Seg architecture. All contributions have been accepted by peer-reviewed conferences, underscoring the advancements in both accuracy and efficiency in 3D LiDAR applications for autonomous driving. Full abstract: https://etheses.dur.ac.uk/15738/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。