SGN-YOLO: Detecting Wood Defects with Improved YOLOv5 Based on Semi-Global Network

Abstract

Object detection based on wood defects involves using bounding boxes to label defects in the surface image of the wood. This step is crucial before the transformation of wood products. Due to the small size and diverse shape of wood defects, most previous object detection models are unable to filter out critical features effectively. Consequently, they have faced challenges in generating adequate contextual information to detect defects accurately. In this paper, we proposed a YOLOv5 model based on a Semi-Global Network (SGN) to detect wood defects. Unlike previous models, firstly, a lightweight SGN is introduced in the backbone to model the global context, which can improve the accuracy and reduce the complexity of the network at the same time; the backbone is embedded with the Extended Efficient Layer Aggregation Network (E-ELAN), which continuously enhances the learning ability of the network; and finally, the Efficient Intersection and Merger (EIOU) loss is used to solve the problems of slow convergence speed and inaccurate regression results. Experimental results on public wood defect datasets demonstrated that our approach outperformed existing target detection models. The mAP value was 86.4%, a 3.1% improvement over the baseline network model, a 7.1% improvement over SSD, and a 13.6% improvement over Faster R-CNN. These results show the effectiveness of our proposed methodology.

A Multi-Source Data Fusion Network for Wood Surface Broken Defect Segmentation

“…To improve the detection accuracy, Tu et al [ 6 ] designed an improved Gaussian YOLOv3 by adding a complete intersection over union (CIoU) loss function to reduce repeated detection. Considering the complicated characteristics and various sizes of wood defects, Meng et al [ 22 ] proposed an improved YOLOv5 model based on a semi-global network (SGN) to generate adequate contextual information of wood defects; furthermore, Zhu et al [ 7 ] proposed an efficient multi-level-feature integration network (EMINet) to extract the discriminative features of defects. Focusing on the tiny cracks, Lin et al [ 8 ] proposed a data-driven semantic segmentation network to recognize cracks at the pixel-level.…”

Artificial Intelligence for Routine Heritage Monitoring and Sustainable Planning of the Conservation of Historic Districts: A Case Study on Fujian Earthen Houses (Tulou)

“…Lastly, although ultrasonic waves can reveal internal and external defects, they are sensitive to external conditions and easily interfered with. These methods have their own advantages and disadvantages, which affect the accuracy and efficiency of detection [56]. Therefore, visual judgment is widely used as a standard for early detection and damage judgment for wood materials, and these preliminary assessments provide an effective method professionals can use to conduct targeted inspections later with minimal impact on buildings.…”

High-Magnification Object Tracking with Ultra-Fast View Adjustment and Continuous Autofocus Based on Dynamic-Range Focal Sweep

“…Recently, methods based on convolutional neural networks (CNNs) have significantly enhanced object detection capabilities, greatly improving robust long-term object tracking. Several studies have successfully tracked specific objects such as defects [ 57 ] and vehicles [ 58 ] using CNN-based methods. Moreover, advancements in parallel computation hardware have effectively accelerated the computation speed of CNNs [ 59 ], making deep-learning-based tracking methods feasible for real-time tracking.…”