Insulator-Defect Detection Algorithm Based on Improved YOLOv7
Existing detection methods face a huge challenge in identifying insulators with minor defects when targeting transmission line images with complex backgrounds. To ensure the safe operation of transmission lines, an improved YOLOv7 model is proposed to improve detection results. Firstly, the target b...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/22/8801 |
| _version_ | 1827643646396071936 |
|---|---|
| author | Jianfeng Zheng Hang Wu Han Zhang Zhaoqi Wang Weiyue Xu |
| author_facet | Jianfeng Zheng Hang Wu Han Zhang Zhaoqi Wang Weiyue Xu |
| author_sort | Jianfeng Zheng |
| collection | DOAJ |
| description | Existing detection methods face a huge challenge in identifying insulators with minor defects when targeting transmission line images with complex backgrounds. To ensure the safe operation of transmission lines, an improved YOLOv7 model is proposed to improve detection results. Firstly, the target boxes of the insulator dataset are clustered based on K-means++ to generate more suitable anchor boxes for detecting insulator-defect targets. Secondly, the Coordinate Attention (CoordAtt) module and HorBlock module are added to the network. Then, in the channel and spatial domains, the network can enhance the effective features of the feature-extraction process and weaken the ineffective features. Finally, the SCYLLA-IoU (SIoU) and focal loss functions are used to accelerate the convergence of the model and solve the imbalance of positive and negative samples. Furthermore, to optimize the overall performance of the model, the method of non-maximum suppression (NMS) is improved to reduce accidental deletion and false detection of defect targets. The experimental results show that the mean average precision of our model is 93.8%, higher than the Faster R-CNN model, the YOLOv7 model, and YOLOv5s model by 7.6%, 3.7%, and 4%, respectively. The proposed YOLOv7 model can effectively realize the accurate detection of small objects in complex backgrounds. |
| first_indexed | 2024-03-09T18:00:59Z |
| format | Article |
| id | doaj.art-65e126d29e784cbdbf0903f378c67cd9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:00:59Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-65e126d29e784cbdbf0903f378c67cd92023-11-24T09:56:00ZengMDPI AGSensors1424-82202022-11-012222880110.3390/s22228801Insulator-Defect Detection Algorithm Based on Improved YOLOv7Jianfeng Zheng0Hang Wu1Han Zhang2Zhaoqi Wang3Weiyue Xu4School of Mechanical Engineering and Rail Transit, Changzhou University, Changzhou 213164, ChinaSchool of Mechanical Engineering and Rail Transit, Changzhou University, Changzhou 213164, ChinaKey Laboratory of Noise and Vibration, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, ChinaSchool of Mechanical Engineering and Rail Transit, Changzhou University, Changzhou 213164, ChinaSchool of Mechanical Engineering and Rail Transit, Changzhou University, Changzhou 213164, ChinaExisting detection methods face a huge challenge in identifying insulators with minor defects when targeting transmission line images with complex backgrounds. To ensure the safe operation of transmission lines, an improved YOLOv7 model is proposed to improve detection results. Firstly, the target boxes of the insulator dataset are clustered based on K-means++ to generate more suitable anchor boxes for detecting insulator-defect targets. Secondly, the Coordinate Attention (CoordAtt) module and HorBlock module are added to the network. Then, in the channel and spatial domains, the network can enhance the effective features of the feature-extraction process and weaken the ineffective features. Finally, the SCYLLA-IoU (SIoU) and focal loss functions are used to accelerate the convergence of the model and solve the imbalance of positive and negative samples. Furthermore, to optimize the overall performance of the model, the method of non-maximum suppression (NMS) is improved to reduce accidental deletion and false detection of defect targets. The experimental results show that the mean average precision of our model is 93.8%, higher than the Faster R-CNN model, the YOLOv7 model, and YOLOv5s model by 7.6%, 3.7%, and 4%, respectively. The proposed YOLOv7 model can effectively realize the accurate detection of small objects in complex backgrounds.https://www.mdpi.com/1424-8220/22/22/8801YOLOv7insulator-defect detectionattention mechanismHorBlockSIoU |
| spellingShingle | Jianfeng Zheng Hang Wu Han Zhang Zhaoqi Wang Weiyue Xu Insulator-Defect Detection Algorithm Based on Improved YOLOv7 Sensors YOLOv7 insulator-defect detection attention mechanism HorBlock SIoU |
| title | Insulator-Defect Detection Algorithm Based on Improved YOLOv7 |
| title_full | Insulator-Defect Detection Algorithm Based on Improved YOLOv7 |
| title_fullStr | Insulator-Defect Detection Algorithm Based on Improved YOLOv7 |
| title_full_unstemmed | Insulator-Defect Detection Algorithm Based on Improved YOLOv7 |
| title_short | Insulator-Defect Detection Algorithm Based on Improved YOLOv7 |
| title_sort | insulator defect detection algorithm based on improved yolov7 |
| topic | YOLOv7 insulator-defect detection attention mechanism HorBlock SIoU |
| url | https://www.mdpi.com/1424-8220/22/22/8801 |
| work_keys_str_mv | AT jianfengzheng insulatordefectdetectionalgorithmbasedonimprovedyolov7 AT hangwu insulatordefectdetectionalgorithmbasedonimprovedyolov7 AT hanzhang insulatordefectdetectionalgorithmbasedonimprovedyolov7 AT zhaoqiwang insulatordefectdetectionalgorithmbasedonimprovedyolov7 AT weiyuexu insulatordefectdetectionalgorithmbasedonimprovedyolov7 |