Coal block detection method integrating lightweight network and dual attention mechanism
In order to solve the problems of low detection precision and slow detection speed of existing coal block detection methods on belt conveyor in underground coal mine, an improved YOLOv4 model integrating lightweight network and dual attention mechanism is proposed, and it is applied to coal block de...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Industry and Mine Automation
2021-12-01
|
| Series: | Gong-kuang zidonghua |
| Subjects: | |
| Online Access: | http://www.gkzdh.cn/jn-abD.aspx?ArticleID=16354 |
| _version_ | 1798025070435631104 |
|---|---|
| author | YE Ou1 DOU Xiaoyi1 FU Yan1 DENG Jun2 |
| author_facet | YE Ou1 DOU Xiaoyi1 FU Yan1 DENG Jun2 |
| author_sort | YE Ou1 |
| collection | DOAJ |
| description | In order to solve the problems of low detection precision and slow detection speed of existing coal block detection methods on belt conveyor in underground coal mine, an improved YOLOv4 model integrating lightweight network and dual attention mechanism is proposed, and it is applied to coal block detection of belt conveyor. The improved YOLOv4 model uses K-means clustering algorithm to re-cluster the prior frames, so that the prior frames are more suitable for the size of the detected target. The model improves the backbone network structure by introducing the MobileNet lightweight network model to reduce the amount of model parameters and calculations, and improve the detection speed. A convolution block attention module with dual attention mechanism is embedded to improve the sensitivity of the model to target characteristics, suppress interference information and improve the precision of target detection. The experimental results show that the improved YOLOv4 model can detect coal blocks of different sizes accurately. Compared with the YOLOv4 model, the improved YOLOv4 model weight file is reduced by 36.46%, the accuracy rate is increased by 2.16%, the recall rate is increased by 20.4%, the average accuracy is increased by 14.37%, the missed detection rate is decreased by 16%, the detection speed is increased by 19 frames/s, the processing time for a single image is reduced by 1.31 s, which improves the detection precision and speed of coal block detection. |
| first_indexed | 2024-04-11T18:12:49Z |
| format | Article |
| id | doaj.art-3f474e49f5554daca1eedcd43e29f056 |
| institution | Directory Open Access Journal |
| issn | 1671-251X |
| language | zho |
| last_indexed | 2024-04-11T18:12:49Z |
| publishDate | 2021-12-01 |
| publisher | Editorial Department of Industry and Mine Automation |
| record_format | Article |
| series | Gong-kuang zidonghua |
| spelling | doaj.art-3f474e49f5554daca1eedcd43e29f0562022-12-22T04:10:03ZzhoEditorial Department of Industry and Mine AutomationGong-kuang zidonghua1671-251X2021-12-014712758010.13272/j.issn.1671-251x.2021030075Coal block detection method integrating lightweight network and dual attention mechanism YE Ou10DOU Xiaoyi11FU Yan12DENG Jun231.College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an 710054,China; 1.College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an 710054,China; 1.College of Computer Science and Technology, Xi'an University of Science and Technology, Xi'an 710054,China; 2.College of Safety Science and Engineering, Xi'an University of Science and Technology, Xi'an 710054, ChinaIn order to solve the problems of low detection precision and slow detection speed of existing coal block detection methods on belt conveyor in underground coal mine, an improved YOLOv4 model integrating lightweight network and dual attention mechanism is proposed, and it is applied to coal block detection of belt conveyor. The improved YOLOv4 model uses K-means clustering algorithm to re-cluster the prior frames, so that the prior frames are more suitable for the size of the detected target. The model improves the backbone network structure by introducing the MobileNet lightweight network model to reduce the amount of model parameters and calculations, and improve the detection speed. A convolution block attention module with dual attention mechanism is embedded to improve the sensitivity of the model to target characteristics, suppress interference information and improve the precision of target detection. The experimental results show that the improved YOLOv4 model can detect coal blocks of different sizes accurately. Compared with the YOLOv4 model, the improved YOLOv4 model weight file is reduced by 36.46%, the accuracy rate is increased by 2.16%, the recall rate is increased by 20.4%, the average accuracy is increased by 14.37%, the missed detection rate is decreased by 16%, the detection speed is increased by 19 frames/s, the processing time for a single image is reduced by 1.31 s, which improves the detection precision and speed of coal block detection.http://www.gkzdh.cn/jn-abD.aspx?ArticleID=16354belt conveyor; coal block detection; target detection; lightweight network; dual attention mechanism; yolov4 |
| spellingShingle | YE Ou1 DOU Xiaoyi1 FU Yan1 DENG Jun2 Coal block detection method integrating lightweight network and dual attention mechanism Gong-kuang zidonghua belt conveyor; coal block detection; target detection; lightweight network; dual attention mechanism; yolov4 |
| title | Coal block detection method integrating lightweight network and dual attention mechanism |
| title_full | Coal block detection method integrating lightweight network and dual attention mechanism |
| title_fullStr | Coal block detection method integrating lightweight network and dual attention mechanism |
| title_full_unstemmed | Coal block detection method integrating lightweight network and dual attention mechanism |
| title_short | Coal block detection method integrating lightweight network and dual attention mechanism |
| title_sort | coal block detection method integrating lightweight network and dual attention mechanism |
| topic | belt conveyor; coal block detection; target detection; lightweight network; dual attention mechanism; yolov4 |
| url | http://www.gkzdh.cn/jn-abD.aspx?ArticleID=16354 |
| work_keys_str_mv | AT yeou1 coalblockdetectionmethodintegratinglightweightnetworkanddualattentionmechanism AT douxiaoyi1 coalblockdetectionmethodintegratinglightweightnetworkanddualattentionmechanism AT fuyan1 coalblockdetectionmethodintegratinglightweightnetworkanddualattentionmechanism AT dengjun2 coalblockdetectionmethodintegratinglightweightnetworkanddualattentionmechanism |