Multimodal surface defect detection from wooden logs for sawing optimization

2025-03-27

AI Summary

Low accuracy in knot detection on rough-sawn lumber surfaces and reliance on costly X-ray CT imaging hinder industrial automation. Method: This paper proposes a dual-stream late-fusion detection framework integrating RGB imagery and laser point clouds for robust knot localization; it further introduces a novel real-time sawing-angle optimization strategy based on surface-knot geometric features and cross-correlation analysis to enable geometry-aware cutting planning. Contributions/Results: By abandoning single-modality constraints and leveraging complementary multimodal features, the method directly maps visual detection outputs to optimal sawing poses. Evaluated on real production-line data, it achieves significantly higher knot detection accuracy than unimodal baselines; moreover, the incidence of corner knots is reduced by over 40%, demonstrating strong trade-offs among precision, throughput, and engineering deployability.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

We propose a novel, good-quality, and less demanding method for detecting knots on the surface of wooden logs using multimodal data fusion. Knots are a primary factor affecting the quality of sawn timber, making their detection fundamental to any timber grading or cutting optimization system. While X-ray computed tomography provides accurate knot locations and internal structures, it is often too slow or expensive for practical use. An attractive alternative is to use fast and cost-effective log surface measurements, such as laser scanners or RGB cameras, to detect surface knots and estimate the internal structure of wood. However, due to the small size of knots and noise caused by factors, such as bark and other natural variations, detection accuracy often remains low when only one measurement modality is used. In this paper, we demonstrate that by using a data fusion pipeline consisting of separate streams for RGB and point cloud data, combined by a late fusion module, higher knot detection accuracy can be achieved compared to using either modality alone. We further propose a simple yet efficient sawing angle optimization method that utilizes surface knot detections and cross-correlation to minimize the amount of unwanted arris knots, demonstrating its benefits over randomized sawing angles.

Problem

• Detects surface knots on wooden logs using multimodal data fusion
• Improves knot detection accuracy with RGB and point cloud fusion
• Optimizes sawing angles to reduce unwanted arris knots

Innovation

• Multimodal data fusion for knot detection
• Late fusion module combining RGB and point cloud
• Sawing angle optimization using surface knots