ERD-YOLO-DMS: A Multi-Domain Fusion Framework for High-Speed Real-Time Online Plywood Veneer Detection
Open Access
Abstract
Plywood has emerged as a key sustainable material in modern building. Yet, ensuring its consistent performance requires rigorous quality control of the rotary-cut veneers used in its manufacture. This task is complicated by the high-speed nature of industrial conveyors, where motion blur and the complex, varying textures of eucalyptus wood drastically reduce the effectiveness of real-time surface inspection. This study proposes an intelligent, real-time defect detection system specifically optimized for the diverse defect morphology of eucalyptus veneers. A lightweight model, YOLOv11-DMS-Veneers, was developed by integrating MobileNetV4 as the backbone, a Dynamic Head for multi-scale feature extraction, and a Shape-IoU loss function to precisely localize irregular defects like cracks and knots. Additionally, an ERD video enhancement framework (combining ESRGAN, RIFE, and DnCNN) was implemented to mitigate motion blur in dynamic environments. Experimental results demonstrate that the proposed model achieves a mean Average Precision (mAP@50) of 96.0% and a Precision of 95.7% with a low computational cost of only 4.5 GFlops, significantly outperforming traditional algorithms. Notably, the detection precision for challenging linear cracks reached 93.9%. In dynamic tests at conveyor speeds up to 24 m/min, the video enhancement strategy increased the average detection confidence by 0.288, maintaining a maximum confidence of 0.890. This technology offers a robust solution for the automated quality control of eucalyptus veneers, facilitating the production of high-performance plywood and advancing the efficient application of engineered wood in the building industry.Keywords
Funding Information
- Key R&D Program Project of Yunnan Provincial: Key Technology Research and Application Demonstration of Public Rail Intermodal Intelligent Logistics Park (202503AA080013)
- Yunnan Provincial Department of Education (2026Y0885)
- Research on Intelligent Perception and Mending Methods for Rotary-Cut Veneer in Plywood (YJS-KCJJ-2025-24)
- Yunnan Fundamental Research Projects (202501AT070245)
This publication has 33 references indexed in Scilit:
- Edge-glued wooden panel defect detection using deep learningWood Science and Technology, 2022
- Ultrasonic and thermal testing to non-destructively identify internal defects in plantation eucalyptsComputers and Electronics in Agriculture, 2020
- Air-coupled ultrasound detection of natural defects in wood using ferroelectret and piezoelectric sensorsWood Science and Technology, 2020
- Investigating face veneer check development in decorative plywood panels: the impact of four common manufacturing factorsEuropean Journal of Wood and Wood Products, 2019
- Recognition of wood surface defects with near infrared spectroscopy and machine visionJournal of Forestry Research, 2019
- Influence of site, storage and steaming on Eucalyptus nitens log-end splittingAnnals of Forest Science, 2015
- Automatic knot segmentation in CT images of wet softwood logs using a tangential approachComputers and Electronics in Agriculture, 2014
- Automated knot detection for high speed computed tomography on Pinus sylvestris L. and Picea abies (L.) Karst. using ellipse fitting in concentric surfacesComputers and Electronics in Agriculture, 2013
- Enhancement of flexural properties and dimensional stability of rice husk particleboard using wood strands in face layersComposites Part B: Engineering, 2013
- Automatic knot detection and measurements from X-ray CT images of wood: A review and validation of an improved algorithm on softwood samplesComputers and Electronics in Agriculture, 2012