GBCD-YOLO: A High-Precision and Real-Time Lightweight Model for Wood Defect Detection
With the advancement of the wood processing industry, the demand for the detection of surface defects in wood has become increasingly urgent. The application of automated production technology has enhanced the efficiency and precision of wood processing, which can significantly impact product qualit...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10409188/ |
| _version_ | 1827369219116761088 |
|---|---|
| author | Yunchang Zheng Mengfan Wang Bo Zhang Xiangnan Shi Qing Chang |
| author_facet | Yunchang Zheng Mengfan Wang Bo Zhang Xiangnan Shi Qing Chang |
| author_sort | Yunchang Zheng |
| collection | DOAJ |
| description | With the advancement of the wood processing industry, the demand for the detection of surface defects in wood has become increasingly urgent. The application of automated production technology has enhanced the efficiency and precision of wood processing, which can significantly impact product quality and competitiveness. However, current methods for detecting surface defects in wood suffer from issues such as low detection accuracy, high computational complexity, and poor real-time performance. In response to these challenges, this paper proposes a high-precision, lightweight, real-time wood surface defect detection method based on YOLO(GBCD-YOLO) model. Firstly, the Ghost Bottleneck is introduced to improve the computational efficiency and inference speed of deep neural networks. Furthermore, the BiFormer is incorporated in the neck to enhance the performance of natural language processing tasks. Simultaneously, CARAFE is utilized as an upsampling replacement to enhance perceptual and capture abilities for details. In addition, the Dynamic Head is introduced to enhance the method’s flexibility and generalization ability, and the loss function is replaced with complete intersection over union (CIoU). The proposed method was evaluated using an optimized dataset and the YOLOv5s model was chosen as the baseline. The experimental results show that compared with the original YOLOv5s, the mAP (0.5) has been improved by 13.45%, reaching 88.72%. The mAP (0.5:0.95) increased by 11.95%, and FPS increased by 6.25%. In addition, the parameter of the improved model has been reduced by 15.49%. These results indicate that the proposed GBCD-YOLO improves the real-time detection performance of wood surface defects. |
| first_indexed | 2024-03-08T09:43:02Z |
| format | Article |
| id | doaj.art-bc48f7098b68403eb484156463b5e8f0 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T09:43:02Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-bc48f7098b68403eb484156463b5e8f02024-01-30T00:04:14ZengIEEEIEEE Access2169-35362024-01-0112128531286810.1109/ACCESS.2024.335604810409188GBCD-YOLO: A High-Precision and Real-Time Lightweight Model for Wood Defect DetectionYunchang Zheng0https://orcid.org/0000-0003-4418-3518Mengfan Wang1Bo Zhang2https://orcid.org/0009-0000-8134-6326Xiangnan Shi3Qing Chang4Hebei University of Architecture, Zhangjiakou, ChinaHebei University of Architecture, Zhangjiakou, ChinaHebei University of Architecture, Zhangjiakou, ChinaHebei University of Architecture, Zhangjiakou, ChinaHebei University of Architecture, Zhangjiakou, ChinaWith the advancement of the wood processing industry, the demand for the detection of surface defects in wood has become increasingly urgent. The application of automated production technology has enhanced the efficiency and precision of wood processing, which can significantly impact product quality and competitiveness. However, current methods for detecting surface defects in wood suffer from issues such as low detection accuracy, high computational complexity, and poor real-time performance. In response to these challenges, this paper proposes a high-precision, lightweight, real-time wood surface defect detection method based on YOLO(GBCD-YOLO) model. Firstly, the Ghost Bottleneck is introduced to improve the computational efficiency and inference speed of deep neural networks. Furthermore, the BiFormer is incorporated in the neck to enhance the performance of natural language processing tasks. Simultaneously, CARAFE is utilized as an upsampling replacement to enhance perceptual and capture abilities for details. In addition, the Dynamic Head is introduced to enhance the method’s flexibility and generalization ability, and the loss function is replaced with complete intersection over union (CIoU). The proposed method was evaluated using an optimized dataset and the YOLOv5s model was chosen as the baseline. The experimental results show that compared with the original YOLOv5s, the mAP (0.5) has been improved by 13.45%, reaching 88.72%. The mAP (0.5:0.95) increased by 11.95%, and FPS increased by 6.25%. In addition, the parameter of the improved model has been reduced by 15.49%. These results indicate that the proposed GBCD-YOLO improves the real-time detection performance of wood surface defects.https://ieeexplore.ieee.org/document/10409188/Small target detectionwood defectdeep learningtransformerYOLOv5 |
| spellingShingle | Yunchang Zheng Mengfan Wang Bo Zhang Xiangnan Shi Qing Chang GBCD-YOLO: A High-Precision and Real-Time Lightweight Model for Wood Defect Detection IEEE Access Small target detection wood defect deep learning transformer YOLOv5 |
| title | GBCD-YOLO: A High-Precision and Real-Time Lightweight Model for Wood Defect Detection |
| title_full | GBCD-YOLO: A High-Precision and Real-Time Lightweight Model for Wood Defect Detection |
| title_fullStr | GBCD-YOLO: A High-Precision and Real-Time Lightweight Model for Wood Defect Detection |
| title_full_unstemmed | GBCD-YOLO: A High-Precision and Real-Time Lightweight Model for Wood Defect Detection |
| title_short | GBCD-YOLO: A High-Precision and Real-Time Lightweight Model for Wood Defect Detection |
| title_sort | gbcd yolo a high precision and real time lightweight model for wood defect detection |
| topic | Small target detection wood defect deep learning transformer YOLOv5 |
| url | https://ieeexplore.ieee.org/document/10409188/ |
| work_keys_str_mv | AT yunchangzheng gbcdyoloahighprecisionandrealtimelightweightmodelforwooddefectdetection AT mengfanwang gbcdyoloahighprecisionandrealtimelightweightmodelforwooddefectdetection AT bozhang gbcdyoloahighprecisionandrealtimelightweightmodelforwooddefectdetection AT xiangnanshi gbcdyoloahighprecisionandrealtimelightweightmodelforwooddefectdetection AT qingchang gbcdyoloahighprecisionandrealtimelightweightmodelforwooddefectdetection |