Wood Crack Detection Based on Data-Driven Semantic Segmentation Network

Lin, Yi; Xu, Zhezhuang; Chen, Dan; Ai, Zhijie; Qiu, Yang; Yuan, Yazhou

doi:10.1109/jas.2023.123357

Cited by 14 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To improve detection accuracy, Tu et al [12] utilized Gaussian YOLOv3 to detect wood defects and introduced complete intersection over union (CIoU) loss to reduce repeated detection. Aiming at segmentation of cracks in wood, Lin et al [13] designed a position attention mechanism and a feature enhancement mechanism to improve the detection accuracy. Although the deep learning-based methods have achieved good performance, the detection efficiency still needs further improvement.…”

Section: Wood Surface Defect Detection Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Surface defect detection of sawn timbers based on efficient multilevel feature integration

Zhu,

Xu,

Lin

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Surface defect detection of sawn timber is a critical task to ensure the quality of wooden products. Current methods have challenges in considering detection accuracy and speed simultaneously, due to the complexity of defects and the massive length of sawn timbers. Speciﬁcally, there are scale variation, large intraclass diﬀerence and high interclass similarity in the defects, which reduce the detection accuracy. To overcome these challenges, we propose an eﬃcient multilevel-feature integration network (EMINet) based on YOLOv5s. To obtain discriminative features of defects, the cross fusion module (CFM) is proposed to fully integrate the multilevel features of backbone. In the CFM, the local information aggregation (LIA) is designed to enrich the detailed information of high-level features, and the global information aggregation (GIA) is designed to enhance the semantic information of low-level features. Experimental results demonstrate that the proposed EMINet achieves better accuracy with fast speed compared with the state-of-the-art methods.

show abstract

Section: Wood Surface Defect Detection Methodsmentioning

confidence: 99%

“…The feature extracted by CNNs has excellent universality [8], which enables its application in various vision tasks [9][10][11]. For timber surface defect detection, object detection [12] and semantic segmentation [13] are widely used to estimate the classification and the localization of defects.…”

Section: Introductionmentioning

confidence: 99%

Surface defect detection of sawn timbers based on efficient multilevel feature integration

Zhu,

Xu,

Lin

et al. 2024

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…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. Due to the limitation of the receptive field of CNN, Ge et al [ 23 ] introduced a detection transformer (DETR) to improve the detection performance.…”

Section: Related Workmentioning

confidence: 99%

“…Initially, many non-destructive approaches were developed to identify a broken defect region, such as the ultrasonic [ 1 ], infrared [ 2 ], stress wave [ 3 ], and acoustic laser techniques [ 4 ], which are sensitive to the depth variation in the broken region, but ignore the appearance characteristic, leading to an incomplete detection of the broken defects. With the support of machine vision, which focuses on image data with high resolution and intuitiveness, the researchers proposed numerous deep-learning-based approaches, which utilize convolutional neural networks (CNN) with excellent feature representation capabilities [ 5 ] to perform wood defect detection in region level [ 6 , 7 ] or pixel level [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

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

Zhu,

Xu,

Lin

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

Wood surface broken defects seriously damage the structure of wooden products, these defects have to be detected and eliminated. However, current defect detection methods based on machine vision have difficulty distinguishing the interference, similar to the broken defects, such as stains and mineral lines, and can result in frequent false detections. To address this issue, a multi-source data fusion network based on U-Net is proposed for wood broken defect detection, combining image and depth data, to suppress the interference and achieve complete segmentation of the defects. To efficiently extract various semantic information of defects, an improved ResNet34 is designed to, respectively, generate multi-level features of the image and depth data, in which the depthwise separable convolution (DSC) and dilated convolution (DC) are introduced to decrease the computational expense and feature redundancy. To take full advantages of two types of data, an adaptive interacting fusion module (AIF) is designed to adaptively integrate them, thereby generating accurate feature representation of the broken defects. The experiments demonstrate that the multi-source data fusion network can effectively improve the detection accuracy of wood broken defects and reduce the false detections of interference, such as stains and mineral lines.

show abstract

A multi-task network for occluded meter reading with synthetic data generation technology

Lin,

Xu,

et al. 2025

Advanced Engineering Informatics

View full text Add to dashboard Cite

Wood Crack Detection Based on Data-Driven Semantic Segmentation Network

Cited by 14 publications

References 15 publications

Surface defect detection of sawn timbers based on efficient multilevel feature integration

Surface defect detection of sawn timbers based on efficient multilevel feature integration

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

A multi-task network for occluded meter reading with synthetic data generation technology

Contact Info

Product

Resources

About