Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Survey

Abstract

In recent years, 3D point clouds (PCs) have gained significant attention due to their diverse applications across various fields, such as computer vision (CV), condition monitoring (CM), virtual reality, robotics, autonomous driving, etc. Deep learning (DL) has proven effective in leveraging 3D PCs to address various challenges encountered in 2D vision. However, applying deep neural networks (DNNs) to process 3D PCs presents unique challenges. This paper provides an in-depth review of recent advancements in DL-based industrial CM using 3D PCs, with a specific focus on defect shape classification and segmentation within industrial applications. Recognizing the crucial role of these aspects in industrial maintenance, the paper offers insightful observations on the strengths and limitations of the reviewed DL-based PC processing methods. This knowledge synthesis aims to contribute to understanding and enhancing CM processes, particularly within the framework of remaining useful life (RUL), in industrial systems.

27 pages, 13 figures, 3 tables, review paper

References in corpus (23)

• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• ShapeNet: An Information-Rich 3D Model Repository
• PCT: Point cloud transformer
• O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
• PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
• Deep Parametric Continuous Convolutional Neural Networks
• PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation
• Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
• FPNN: Field Probing Neural Networks for 3D Data
• Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook
• Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds
• Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds
• Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space
• Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection
• MASC: Multi-scale Affinity with Sparse Convolution for 3D Instance Segmentation
• GA-NET: Global Attention Network for Point Cloud Semantic Segmentation
• 3D Graph Embedding Learning with a Structure-aware Loss Function for Point Cloud Semantic Instance Segmentation
• Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
• Learning Gaussian Instance Segmentation in Point Clouds
• GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation
• LSANet: Feature Learning on Point Sets by Local Spatial Aware Layer
• 3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis
• ENSTRECT: A Stage-based Approach to 2.5D Structural Damage Detection