PotholeGuard: A Pothole Detection Approach by Point Cloud Semantic Segmentation

TL;DR

PotholeGuard is a novel 3D point cloud segmentation method that improves pothole detection accuracy by addressing point cloud sparsity and local feature extraction challenges through innovative modules and a lightweight adaptive structure.

Contribution

The paper introduces a new point cloud-based architecture with local relationship learning and adaptive feature refinement, enhancing 3D pothole segmentation accuracy over existing methods.

Findings

Outperforms state-of-the-art methods on three public datasets

Effectively captures hidden features and local shape relationships

Addresses point cloud density variations with a lightweight adaptive structure

Abstract

Pothole detection is crucial for road safety and maintenance, traditionally relying on 2D image segmentation. However, existing 3D Semantic Pothole Segmentation research often overlooks point cloud sparsity, leading to suboptimal local feature capture and segmentation accuracy. Our research presents an innovative point cloud-based pothole segmentation architecture. Our model efficiently identifies hidden features and uses a feedback mechanism to enhance local characteristics, improving feature presentation. We introduce a local relationship learning module to understand local shape relationships, enhancing structural insights. Additionally, we propose a lightweight adaptive structure for refining local point features using the K nearest neighbor algorithm, addressing point cloud density differences and domain selection. Shared MLP Pooling is integrated to learn deep aggregation features, facilitating semantic data exploration and segmentation guidance. Extensive experiments on three public datasets confirm PotholeGuard's superior performance over state-of-the-art methods. Our approach offers a promising solution for robust and accurate 3D pothole segmentation, with applications in road maintenance and safety.