Point Cloud-Based Deep Learning in Industrial Production: A Survey
Open Access
- 20 February 2025
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 57 (7) , 1-36
Abstract
With the rapid development of 3D acquisition technology, point clouds have received increasing attention. In recent years, point cloud-based deep learning has been applied to various industrial scenarios, promoting industrial intelligence. However, there is still a lack of review on the application of point cloud-based deep learning in industrial production. To bridge this gap and inspire future research, this article provides a review of current point cloud-based deep learning methods applied to industrial production from the perspective of different application scenarios, including pose estimation, defect inspection, measurement and estimation, and so on. Considering the real-time requirement of industrial production, this article also summarizes real-time point cloud-based deep learning methods in each application scenario. Then, this article introduces commonly used evaluation metrics and public industrial point cloud datasets. Finally, from the aspects of the dataset, speed and industrial product specificity, the challenges faced by current point cloud-based deep learning methods in industrial production are discussed, and future research directions are prospected.Keywords
Funding Information
- General Project of Liaoning Provincial Department of Education (LJKMZ20220613)
- Key Project of National Natural Science Foundation of China (U1908212)
This publication has 124 references indexed in Scilit:
- The 3D narrow butt weld seam detection system based on the binocular consistency correctionJournal of Intelligent Manufacturing, 2022
- Automated surface defect detection framework using machine vision and convolutional neural networksJournal of Intelligent Manufacturing, 2022
- A novel parallel classification network for classifying three-dimensional surface with point cloud dataJournal of Intelligent Manufacturing, 2021
- Synthetic data augmentation for surface defect detection and classification using deep learningJournal of Intelligent Manufacturing, 2020
- End-to-End Object Detection with Transformers2020
- A pose estimation system based on deep neural network and ICP registration for robotic spray painting applicationThe International Journal of Advanced Manufacturing Technology, 2019
- Deep learning–based stress prediction for bottom-up SLA 3D printing processThe International Journal of Advanced Manufacturing Technology, 2019
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- Microsoft COCO: Common Objects in Context2014
- Technical Demonstration on Model Based Training, Detection and Pose Estimation of Texture-Less 3D Objects in Heavily Cluttered Scenes2012