Real-Time Detection of Eichhornia crassipes Based on Efficient YOLOV5

被引:5
作者
Qian, Yukun [1 ]
Miao, Yalun [1 ]
Huang, Shuqin [1 ]
Qiao, Xi [2 ]
Wang, Minghui [1 ]
Li, Yanzhou [1 ]
Luo, Liuming [1 ]
Zhao, Xiyong [1 ,2 ]
Cao, Long [1 ]
机构
[1] Guangxi Univ, Sch Mech Engn, Nanning 530004, Peoples R China
[2] Chinese Acad Agr Sci, Agr Genom Inst Shenzhen, Shenzhen Branch,Minist Agr & Rural Affairs, Guangdong Lab Lingnan Modern Agr,Genome Anal Lab, Shenzhen 518120, Peoples R China
关键词
Eichhornia crassipes detection; YOLOV5; deep learning; EfficientNet; GROWTH; MODEL;
D O I
10.3390/machines10090754
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The rapid propagation of Eichhornia crassipes has a threatening impact on the aquatic environment. For most small water areas with good ecology, daily manual monitoring and salvage require considerable financial and material resources. Unmanned boats have important practical significance for the automatic monitoring and cleaning Eichhornia crassipes. To ensure that the target can be accurately detected, we solve the problems that exist in the lightweight model algorithm, such as low accuracy and poor detection effect on targets with small or unclear characteristics. Taking YOLOV5m 6.0 version as the baseline model, given the computational limit of real-time detection, this paper proposes to use EfficientNet-Lite0 as the backbone, use the ELU function as the activation function, modify the pooling mode in SPPF, embed the SA attention mechanism, and add the RFB module in the feature fusion network to improve the feature extraction ability of the whole model. The dataset collected water hyacinth images from ponds and lakes in Guangxi, Yunnan, and the China Plant Image Library. The test results show that efficient YOLOV5 reached 87.6% mAP, which was 7.1% higher than that of YOLOV5s, and the average detection time was 62 FPS. The ablation experiment verifies the effectiveness of each module of efficient YOLOV5, and its detection accuracy and model parameters meet the real-time detection requirements of the Eichhornia crassipes unmanned cleaning boat.
引用
收藏
页数:17
相关论文
共 50 条
[21]   Improved YOLOv5 for real-time traffic signs recognition in bad weather conditions [J].
Thi Phuc Dang ;
Ngoc Trinh Tran ;
Van Hau To ;
Minh Khoa Tran Thi .
The Journal of Supercomputing, 2023, 79 :10706-10724
[22]   An Efficient and Intelligent Detection Method for Fabric Defects based on Improved YOLOv5 [J].
Lin, Guijuan ;
Liu, Keyu ;
Xia, Xuke ;
Yan, Ruopeng .
SENSORS, 2023, 23 (01)
[23]   Real-Time Waste Detection Based on YOLOv8 [J].
Mehadjbia, Abdelhak ;
Slaoui-Hasnaoui, Fouad .
4TH INTERDISCIPLINARY CONFERENCE ON ELECTRICS AND COMPUTER, INTCEC 2024, 2024,
[24]   YOLOv5s-BC: an improved YOLOv5s-based method for real-time apple detection [J].
Liu, Jingfan ;
Liu, Zhaobing .
JOURNAL OF REAL-TIME IMAGE PROCESSING, 2024, 21 (03)
[25]   Tea Bud Detection Model in a Real Picking Environment Based on an Improved YOLOv5 [J].
Li, Hongfei ;
Kong, Min ;
Shi, Yun .
BIOMIMETICS, 2024, 9 (11)
[26]   Road Defect Detection Based on Yolov5 Algorithm [J].
Lei, Yankun ;
Wang, Baoping ;
Zhang, Nan ;
Sun, Qin .
PROCEEDINGS OF THE 13TH INTERNATIONAL CONFERENCE ON COMPUTER ENGINEERING AND NETWORKS, VOL II, CENET 2023, 2024, 1126 :488-493
[27]   A Fatigue Driving Detection Algorithm Based On YOLOv5 [J].
Li Zhanli ;
Jia Ni ;
Jin Hongmei .
FOURTEENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING, ICGIP 2022, 2022, 12705
[28]   Lightweight safflower cluster detection based on YOLOv5 [J].
Guo, Hui ;
Wu, Tianlun ;
Gao, Guomin ;
Qiu, Zhaoxin ;
Chen, Haiyang .
SCIENTIFIC REPORTS, 2024, 14 (01)
[29]   Road Traffic Waterlogging Detection Based on YOLOv5 [J].
Liu, Jianqiang ;
Shang, Yujie ;
Li, Xingyao ;
Hao, Huizhen ;
Geng, Peng .
DATA SCIENCE AND INFORMATION SECURITY, PT 2, IAIC 2023, 2024, 2059 :45-58
[30]   Driver Attention Detection Based on Improved YOLOv5 [J].
Wang, Zhongzhou ;
Yao, Keming ;
Guo, Fuao .
APPLIED SCIENCES-BASEL, 2023, 13 (11)