Research on Insect Pest Identification in Rice Canopy Based on GA-Mask R-CNN

被引:5
|
作者
Liu, Sitao [1 ]
Fu, Shenghui [1 ,2 ]
Hu, Anrui [1 ,3 ]
Ma, Pan [4 ]
Hu, Xianliang [5 ]
Tian, Xinyu [1 ]
Zhang, Hongjian [1 ,3 ]
Liu, Shuangxi [1 ,2 ]
机构
[1] Shandong Agr Univ, Coll Mech & Elect Engn, Tai An 271018, Peoples R China
[2] Shandong Prov Agr Equipment Intellectualizat Engn, Tai An 271018, Peoples R China
[3] Shandong Prov Key Lab Hort Machinery & Equipment, Tai An 271018, Peoples R China
[4] Jinan Acad Agr Sci, Jinan 250300, Peoples R China
[5] Shandong Xiangchen Technol Grp Co Ltd, Jinan 251400, Peoples R China
来源
AGRONOMY-BASEL | 2023年 / 13卷 / 08期
关键词
rice stem borer; rice leaf roller; generate adversarial network; multistage residuals; ECA attention module;
D O I
10.3390/agronomy13082155
中图分类号
S3 [农学(农艺学)];
学科分类号
0901 ;
摘要
Aiming at difficult image acquisition and low recognition accuracy of two rice canopy pests, rice stem borer and rice leaf roller, we constructed a GA-Mask R-CNN (Generative Adversarial Based Mask Region Convolutional Neural Network) intelligent recognition model for rice stem borer and rice leaf roller, and we combined it with field monitoring equipment for them. Firstly, based on the biological habits of rice canopy pests, a variety of rice pest collection methods were used to obtain the images of rice stem borer and rice leaf roller pests. Based on different segmentation algorithms, the rice pest images were segmented to extract single pest samples. Secondly, the bug generator based on a generative adversarial network strategy improves the sensitivity of the classification network to the bug information, generates the pest information images in the real environment, and obtains the sample dataset for deep learning through multi-way augmentation. Then, through adding channel attention ECA module in Mask R-CNN and improving the connection of residual blocks in the backbone network ResNet101, the recognition accuracy of the model is improved. Finally, the GA-Mask R-CNN model was tested on a multi-source dataset with an average precision (AP) of 92.71%, recall (R) of 89.28% and a balanced score F1 of 90.96%. The average precision, recall, and balanced score F1 are improved by 7.07, 7.65, and 8.83%, respectively, compared to the original Mask R-CNN. The results show that the GA-Mask R-CNN model performance indexes are all better than the Mask R-CNN, the Faster R-CNN, the SSD, the YOLOv5, and other network models, which can provide technical support for remote intelligent monitoring of rice pests.
引用
收藏
页数:18
相关论文
共 50 条
  • [21] Human Detection Based on Improved Mask R-CNN
    Wang, Yuejuan
    Wu, Ji
    Li, Heting
    5TH ANNUAL INTERNATIONAL CONFERENCE ON INFORMATION SYSTEM AND ARTIFICIAL INTELLIGENCE (ISAI2020), 2020, 1575
  • [22] Research on Image Identification Method of Rock Thin Slices in Tight Oil Reservoirs Based on Mask R-CNN
    Liu, Tao
    Li, Chunsheng
    Liu, Zongbao
    Zhang, Kejia
    Liu, Fang
    Li, Dongsheng
    Zhang, Yan
    Liu, Zhigang
    Liu, Liyuan
    Huang, Jiacheng
    ENERGIES, 2022, 15 (16)
  • [23] A Mask R-CNN based particle identification for quantitative shape evaluation of granular materials
    Yang, Dangfu
    Wang, Xiang
    Zhang, Haoran
    Yin, Zhen-yu
    Su, Dong
    Xu, Jun
    POWDER TECHNOLOGY, 2021, 392 : 296 - 305
  • [24] Identification and Reconstruction of Citrus Branches under Complex Background Based on Mask R-CNN
    Yang C.
    Wang Z.
    Xiong L.
    Liu Y.
    Kang X.
    Zhao W.
    Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery, 2019, 50 (08): : 22 - 30and69
  • [25] Research on infrared small target segmentation algorithm based on improved mask R-CNN
    Ren, Kan
    Chen, Zhuo
    Gu, Guohua
    Chen, Qian
    OPTIK, 2023, 272
  • [26] Research on garment flat multi-component recognition based on Mask R-CNN
    LI, Tao
    Lyu, Ye-Xin
    Ma, Ling
    Xie, Yong
    Zou, Feng-Yuan
    INDUSTRIA TEXTILA, 2023, 74 (01): : 49 - 56
  • [27] Research on Key Algorithm for Sichuan Pepper Pruning Based on Improved Mask R-CNN
    Zhang, Chen
    Zhang, Yan
    Liang, Sicheng
    Liu, Pingzeng
    SUSTAINABILITY, 2024, 16 (08)
  • [28] Research on Warehouse Image Instance Segmentation Method Based on Enhanced Mask R-CNN
    Wang, Zhibo
    Yang, Deguo
    PROCEEDINGS OF INTERNATIONAL CONFERENCE ON ALGORITHMS, SOFTWARE ENGINEERING, AND NETWORK SECURITY, ASENS 2024, 2024, : 318 - 322
  • [29] Application of the Mask R-CNN model to cold front identification in Eurasia
    Qin, Yujing
    He, Shuya
    Lu, Chuhan
    Ding, Liuguan
    INTERNATIONAL JOURNAL OF CLIMATOLOGY, 2024, 44 (11) : 3766 - 3777
  • [30] Pedestrian Detection and Segmentation Method Based on Mask R-CNN
    Chen, Jia-jun
    Qing, Xiao-qu
    Yu, Hua-peng
    Chang, Yong-xin
    2018 INTERNATIONAL CONFERENCE ON ELECTRICAL, CONTROL, AUTOMATION AND ROBOTICS (ECAR 2018), 2018, 307 : 459 - 463