Advancing Industrial Object Detection Through Domain Adaptation: A Solution for Industry 5.0
Open Access
Abstract
Domain adaptation (DA) is essential for developing robust machine learning models capable of operating across different domains with minimal retraining. This study explores the application of domain adaptation techniques to 3D datasets for industrial object detection, with a focus on short-range and long-range scenarios. While 3D data provide superior spatial information for detecting industrial parts, challenges arise due to domain shifts between training data (often clean or synthetic) and real-world conditions (noisy and occluded environments). Using the MVTec ITODD dataset, we propose a multi-level adaptation approach that leverages local and global feature alignment through PointNet-based architectures. We address sensor variability by aligning data from high-precision, long-range sensors with noisier short-range alternatives. Our results demonstrate an 85% accuracy with a minimal 0.02% performance drop, highlighting the resilience of the proposed methods. This work contributes to the emerging needs of Industry 5.0 by ensuring adaptable and scalable automation in manufacturing processes, empowering robotic systems to perform precise, reliable object detection and manipulation under challenging, real-world conditions, and supporting seamless human–robot collaboration.Keywords
This publication has 28 references indexed in Scilit:
- Performance and Challenges of 3D Object Detection Methods in Complex Scenes for Autonomous DrivingIEEE Transactions on Intelligent Vehicles, 2022
- A Compressed Unsupervised Deep Domain Adaptation Model for Efficient Cross-Domain Fault DiagnosisIEEE Transactions on Industrial Informatics, 2022
- Image Translation Based Synthetic Data Generation for Industrial Object Detection and Pose EstimationIEEE Robotics and Automation Letters, 2022
- Semi-supervised Ensemble Learning for Efficient Cancer Sample Classification from miRNA Gene Expression DataNew Generation Computing, 2021
- Point-cloud based 3D object detection and classification methods for self-driving applications: A survey and taxonomyInformation Fusion, 2021
- Recent advances in surface defect inspection of industrial products using deep learning techniquesThe International Journal of Advanced Manufacturing Technology, 2021
- Multistage GAN for Fabric Defect DetectionIEEE Transactions on Image Processing, 2019
- Symmetry Aware Evaluation of 3D Object Detection and Pose Estimation in Scenes of Many Parts in Bulk2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Robotic grasping recognition using multi-modal deep extreme learning machineMultidimensional Systems and Signal Processing, 2016