CCG-YOLOv7: A Wood Defect Detection Model for Small Targets Using Improved YOLOv7

被引：10

作者：

Cui, Wenqi ^{[1
]}

Li, Zhenye ^{[1
]}

Duanmu, Anning ^{[1
]}

Xue, Sheng ^{[1
]}

Guo, Yiren ^{[1
]}

Ni, Chao ^{[1
]}

Zhu, Tingting ^{[1
]}

Zhang, Yajun ^{[1
]}

机构：

[1] Nanjing Forestry Univ, Coll Mech & Elect Engn, Nanjing 210037, Jiangsu, Peoples R China

来源：

IEEE ACCESS | 2024年 / 12卷

基金：

美国国家科学基金会;

关键词：

Floors; Feature extraction; Production; Gravity; Testing; Shape; Convolutional neural networks; Deep learning; Surface cracks; small target; wood floor defect detection; YOLOv7; R-CNN; NETWORK;

D O I：

10.1109/ACCESS.2024.3352445

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The Chinese furniture market has a high demand for wood floors. Manual defect detection in wood floors is inefficient and lacks stability in accuracy. It is necessary to conduct research on automatic defect detection in wood floors. To improve the accuracy of detecting small defects in wood floors, this paper proposed a new network based on YOLOv7. The new network is called the cascade center of gravity YOLOv7 (CCG-YOLOv7). This paper designed cascade efficient layer aggregation networks (C-ELAN), streamlined the CBS, replaced the ELAN with the C-ELAN, introduced the rapid supervised attention module to connect the backbone and head layers, and simplified the head layer of the YOLOv7 network. These methods improved the detection accuracy and speed for detecting small defects on wood floor surfaces. The improved network can effectively detect small defects on the wooden board surfaces, including knots, scratches, and mildew. Compared to the original YOLOv7, CCG-YOLOv7 improves precision, recall, and mean average precision by 2.1%, 1.6%, and 1.2%, respectively.

引用

页码：10575 / 10585

页数：11

共 25 条

[1]

Ai Zhijie, 2022, 2022 China Automation Congress (CAC), P6513, DOI 10.1109/CAC57257.2022.10055249

[2] Relation R-CNN: A Graph Based Relation-Aware Network for Object Detection [J].

Chen, Shengjia ;

Li, Zhixin ;

Tang, Zhenjun .

IEEE SIGNAL PROCESSING LETTERS, 2020, 27 :1680-1684

[3]

Dawei Qi, 2008, 2008 IEEE Conference on Cybernetics and Intelligent Systems, P951, DOI 10.1109/ICCIS.2008.4670955

[4] Review of the use of air-coupled ultrasonic technologies for nondestructive testing of wood and wood products [J].

Fang, Yiming ;

Lin, Lujun ;

Feng, Hailin ;

Lu, Zhixiong ;

Emms, Grant W. .

COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2017, 137 :79-87

[5] Extraction and Exploratory Analysis of Texture Features on Images of Timber Defect [J].

Hashim, Ummi Raba'ah ;

Hashim, Siti Zaiton Mohd ;

Muda, Azah Kamilah ;

Kanchymalay, Kasturi ;

Jalil, Intan Ermahani A. ;

Anuar, Aznah Nor ;

Othman, Muhammad Hakim .

ADVANCED SCIENCE LETTERS, 2018, 24 (02) :1104-1108

[6] Application of deep convolutional neural network on feature extraction and detection of wood defects [J].

He, Ting ;

Liu, Ying ;

Yu, Yabin ;

Zhao, Qian ;

Hu, Zhongkang .

MEASUREMENT, 2020, 152

[7] Observation of interference effects in air-coupled ultrasonic inspection of wood-based panels [J].

Hilbers, Ulrich ;

Neuenschwander, Juerg ;

Hasener, Joerg ;

Sanabria, Sergio J. ;

Niemz, Peter ;

Thoemen, Heiko .

WOOD SCIENCE AND TECHNOLOGY, 2012, 46 (05) :979-990

[8] Defect Identification Method for Poplar Veneer Based on Progressive Growing Generated Adversarial Network and MASK R-CNN Model [J].

Hu, Kai ;

Wang, Baojin ;

Shen, Yi ;

Guan, Jieru ;

Cai, Yi .

BIORESOURCES, 2020, 15 (02) :3041-3052

[9] Causal-ViT: Robust Vision Transformer by causal intervention [J].

Li, Wei ;

Li, Zhixin ;

Yang, Xiwei ;

Ma, Huifang .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 126

[10] An Optimized Lightweight Model for Real-Time Wood Defects Detection based on YOLOv4-Tiny [J].

Lim, Wei-Han ;

Bonab, Mohammad Babrdel ;

Chua, Kein Huat .

2022 IEEE INTERNATIONAL CONFERENCE ON AUTOMATIC CONTROL AND INTELLIGENT SYSTEMS, I2CACIS, 2022, :186-191

← 1 2 3 →