Improving YOLOv4-Tiny’s Construction Machinery and Material Identification Method by Incorporating Attention Mechanism
To facilitate the development of intelligent unmanned loaders and improve the recognition accuracy of loaders in complex scenes, we propose a construction machinery and material target detection algorithm incorporating an attention mechanism (AM) to improve YOLOv4-Tiny. First, to ensure the robustne...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/9/1453 |
| _version_ | 1797503884471566336 |
|---|---|
| author | Jiale Yao Dengsheng Cai Xiangsuo Fan Bing Li |
| author_facet | Jiale Yao Dengsheng Cai Xiangsuo Fan Bing Li |
| author_sort | Jiale Yao |
| collection | DOAJ |
| description | To facilitate the development of intelligent unmanned loaders and improve the recognition accuracy of loaders in complex scenes, we propose a construction machinery and material target detection algorithm incorporating an attention mechanism (AM) to improve YOLOv4-Tiny. First, to ensure the robustness of the proposed algorithm, we adopt style migration and sliding window segmentation to increase the underlying dataset’s diversity. Second, to address the problem that YOLOv4-Tiny’s (the base network) framework only adopts a layer-by-layer connection form, which demonstrates an insufficient feature extraction ability, we adopt a multilayer cascaded residual module to deeply connect low- and high-level information. Finally, to filter redundant feature information and make the proposed algorithm focus more on important feature information, a channel AM is added to the base network to perform a secondary screening of feature information in the region of interest, which effectively improves the detection accuracy. In addition, to achieve small-scale object detection, a multiscale feature pyramid network structure is employed in the prediction module of the proposed algorithm to output two prediction networks with different scale sizes. The experimental results show that, compared with the traditional network structure, the proposed algorithm fully incorporates the advantages of residual networks and AM, which effectively improves its feature extraction ability and recognition accuracy of targets at different scales. The final proposed algorithm exhibits the features of high recognition accuracy and fast recognition speed, with mean average precision and detection speed reaching 96.82% and 134.4 fps, respectively. |
| first_indexed | 2024-03-10T03:56:45Z |
| format | Article |
| id | doaj.art-940d76b669944ebdacde31cce798251a |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T03:56:45Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-940d76b669944ebdacde31cce798251a2023-11-23T08:44:33ZengMDPI AGMathematics2227-73902022-04-01109145310.3390/math10091453Improving YOLOv4-Tiny’s Construction Machinery and Material Identification Method by Incorporating Attention MechanismJiale Yao0Dengsheng Cai1Xiangsuo Fan2Bing Li3School of Electrical Electronic and Computer Science, Guangxi University of Science and Technology, Liuzhou 545006, ChinaSchool of Electrical Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Electrical Electronic and Computer Science, Guangxi University of Science and Technology, Liuzhou 545006, ChinaGuangxi Collaborative Innovation Centre for Earthmoving Machinery, Guangxi University of Science and Technology, Liuzhou 545006, ChinaTo facilitate the development of intelligent unmanned loaders and improve the recognition accuracy of loaders in complex scenes, we propose a construction machinery and material target detection algorithm incorporating an attention mechanism (AM) to improve YOLOv4-Tiny. First, to ensure the robustness of the proposed algorithm, we adopt style migration and sliding window segmentation to increase the underlying dataset’s diversity. Second, to address the problem that YOLOv4-Tiny’s (the base network) framework only adopts a layer-by-layer connection form, which demonstrates an insufficient feature extraction ability, we adopt a multilayer cascaded residual module to deeply connect low- and high-level information. Finally, to filter redundant feature information and make the proposed algorithm focus more on important feature information, a channel AM is added to the base network to perform a secondary screening of feature information in the region of interest, which effectively improves the detection accuracy. In addition, to achieve small-scale object detection, a multiscale feature pyramid network structure is employed in the prediction module of the proposed algorithm to output two prediction networks with different scale sizes. The experimental results show that, compared with the traditional network structure, the proposed algorithm fully incorporates the advantages of residual networks and AM, which effectively improves its feature extraction ability and recognition accuracy of targets at different scales. The final proposed algorithm exhibits the features of high recognition accuracy and fast recognition speed, with mean average precision and detection speed reaching 96.82% and 134.4 fps, respectively.https://www.mdpi.com/2227-7390/10/9/1453intelligent loaderstyle transfermachine visionCAMYOLOv4-Tiny |
| spellingShingle | Jiale Yao Dengsheng Cai Xiangsuo Fan Bing Li Improving YOLOv4-Tiny’s Construction Machinery and Material Identification Method by Incorporating Attention Mechanism Mathematics intelligent loader style transfer machine vision CAM YOLOv4-Tiny |
| title | Improving YOLOv4-Tiny’s Construction Machinery and Material Identification Method by Incorporating Attention Mechanism |
| title_full | Improving YOLOv4-Tiny’s Construction Machinery and Material Identification Method by Incorporating Attention Mechanism |
| title_fullStr | Improving YOLOv4-Tiny’s Construction Machinery and Material Identification Method by Incorporating Attention Mechanism |
| title_full_unstemmed | Improving YOLOv4-Tiny’s Construction Machinery and Material Identification Method by Incorporating Attention Mechanism |
| title_short | Improving YOLOv4-Tiny’s Construction Machinery and Material Identification Method by Incorporating Attention Mechanism |
| title_sort | improving yolov4 tiny s construction machinery and material identification method by incorporating attention mechanism |
| topic | intelligent loader style transfer machine vision CAM YOLOv4-Tiny |
| url | https://www.mdpi.com/2227-7390/10/9/1453 |
| work_keys_str_mv | AT jialeyao improvingyolov4tinysconstructionmachineryandmaterialidentificationmethodbyincorporatingattentionmechanism AT dengshengcai improvingyolov4tinysconstructionmachineryandmaterialidentificationmethodbyincorporatingattentionmechanism AT xiangsuofan improvingyolov4tinysconstructionmachineryandmaterialidentificationmethodbyincorporatingattentionmechanism AT bingli improvingyolov4tinysconstructionmachineryandmaterialidentificationmethodbyincorporatingattentionmechanism |