CurbNet: Curb Detection Framework Based on LiDAR Point Cloud Segmentation

TL;DR

This work tackles curb detection in autonomous driving using LiDAR by introducing CurbNet, a point-cloud segmentation framework, and the 3D-Curb dataset to provide 3D curb annotations. The authors design the Multi-Scale and Channel Attention (MSCA) module to capture both spatial and height-based features and pair it with an Adaptive Cross-Entropy plus Lovász-Softmax loss to address severe class imbalance, augmented by a multi-cluster curve fitting post-processing to reduce noise. On two diverse datasets, CurbNet achieves state-of-the-art results, with high precision, recall, and F1 scores, and demonstrates real-time performance on edge hardware, validating its practical viability. The combination of a new large-scale curb-specific dataset, advanced feature fusion, imbalance-aware losses, and robust post-processing establishes a strong foundation for curb detection in complex urban scenes and supports safer autonomous driving systems.

Abstract

Curb detection is a crucial function in intelligent driving, essential for determining drivable areas on the road. However, the complexity of road environments makes curb detection challenging. This paper introduces CurbNet, a novel framework for curb detection utilizing point cloud segmentation. To address the lack of comprehensive curb datasets with 3D annotations, we have developed the 3D-Curb dataset based on SemanticKITTI, currently the largest and most diverse collection of curb point clouds. Recognizing that the primary characteristic of curbs is height variation, our approach leverages spatially rich 3D point clouds for training. To tackle the challenges posed by the uneven distribution of curb features on the xy-plane and their dependence on high-frequency features along the z-axis, we introduce the Multi-Scale and Channel Attention (MSCA) module, a customized solution designed to optimize detection performance. Additionally, we propose an adaptive weighted loss function group specifically formulated to counteract the imbalance in the distribution of curb point clouds relative to other categories. Extensive experiments conducted on 2 major datasets demonstrate that our method surpasses existing benchmarks set by leading curb detection and point cloud segmentation models. Through the post-processing refinement of the detection results, we have significantly reduced noise in curb detection, thereby improving precision by 4.5 points. Similarly, our tolerance experiments also achieve state-of-the-art results. Furthermore, real-world experiments and dataset analyses mutually validate each other, reinforcing CurbNet's superior detection capability and robust generalizability. The project website is available at: https://github.com/guoyangzhao/CurbNet/.

Figures (11)

• Figure 1: Curb detection challenges and our proposed method. Three main challenges of curb detection are shown (a) height feature extraction (b) different density distribution of point clouds (c) Curb point cloud quantity proportion imbalance. Solution: First propose a 3D-Curb dataset. The MSCA module is designed for multi-scale spatial feature fusion and height feature extraction. The loss group is proposed to solve the imbalance problem. Finally, we use post-processing to further improve performance.
• Figure 2: 3D-Curb dataset construction process. Mainly developed based on the standard SemanticKITTI dataset.
• Figure 3: Overview of proposed CurbNet framework. From left to right, first is point cloud data input and voxelization. Then there is a 5-layer deep encoder-decoder structure. Next comes the feature aggregation and segmentation head. Finally, the post-processing refinement of the detection results.
• Figure 4: Structure of multi-scale and channel attention (MSCA) module. SConv means Sparse convolution layer. Multi-Scale Fusion is mainly used to fuse spatial features of different scales, and Channel Attention is used to dynamically extract height features of the z-axis.
• Figure 5: Process of multiple clustering and fitting to remove noise points.The left figure shows the effect of multiple clustering in discontinuous scenes. The right figure shows the method of curve fitting and setting distance to remove noise points.