IDEAS home Printed from https://ideas.repec.org/a/gam/jsusta/v15y2023i12p9583-d1171148.html
   My bibliography  Save this article

Maize Seedling Leave Counting Based on Semi-Supervised Learning and UAV RGB Images

Author

Listed:
  • Xingmei Xu

    (College of Information and Technology, Jilin Agricultural University, Changchun 130118, China)

  • Lu Wang

    (College of Information and Technology, Jilin Agricultural University, Changchun 130118, China)

  • Xuewen Liang

    (College of Information and Technology, Jilin Agricultural University, Changchun 130118, China)

  • Lei Zhou

    (College of Information and Technology, Jilin Agricultural University, Changchun 130118, China)

  • Youjia Chen

    (College of Land Science and Technology, China Agricultural University, Beijing 100193, China)

  • Puyu Feng

    (College of Land Science and Technology, China Agricultural University, Beijing 100193, China)

  • Helong Yu

    (College of Information and Technology, Jilin Agricultural University, Changchun 130118, China)

  • Yuntao Ma

    (College of Information and Technology, Jilin Agricultural University, Changchun 130118, China
    College of Land Science and Technology, China Agricultural University, Beijing 100193, China)

Abstract

The number of leaves in maize seedlings is an essential indicator of their growth rate and status. However, manual counting of seedlings is inefficient and limits the scope of the investigation. Deep learning has shown potential for quickly identifying seedlings, but it requires larger, labeled datasets. To address these challenges, we proposed a method for counting maize leaves from seedlings in fields using a combination of semi-supervised learning, deep learning, and UAV digital imagery. Our approach leveraged semi-supervised learning and novel methods for detecting and counting maize seedling leaves accurately and efficiently. Specifically, we used a small amount of labeled data to train the SOLOv2 model based on the semi-supervised learning framework Noisy Student. This model can segment complete maize seedlings from UAV digital imagery and generate foreground images of maize seedlings with background removal. We then trained the YOLOv5x model based on Noisy Student with a small amount of labeled data to detect and count maize leaves. We divided our dataset of 1005 images into 904 training images and 101 testing images, and randomly divided the 904 training images into four sets of labeled and unlabeled data with proportions of 4:6, 3:7, 2:8, and 1:9, respectively. The results indicated that the SOLOv2 Resnet101 outperformed the SOLOv2 Resnet50 in terms of segmentation performance. Moreover, when the labeled proportion was 30%, the student model SOLOv2 achieved a similar segmentation performance to the fully supervised model with a mean average precision (mAP) of 93.6%. When the labeled proportion was 40%, the student model YOLOv5x demonstrated comparable leaf counting performance to the fully supervised model. The model achieved an average precision of 89.6% and 57.4% for fully unfolded leaves and newly appearing leaves, respectively, with counting accuracy rates of 69.4% and 72.9%. These results demonstrated that our proposed method based on semi-supervised learning and UAV imagery can advance research on crop leaf counting in fields and reduce the workload of data annotation.

Suggested Citation

  • Xingmei Xu & Lu Wang & Xuewen Liang & Lei Zhou & Youjia Chen & Puyu Feng & Helong Yu & Yuntao Ma, 2023. "Maize Seedling Leave Counting Based on Semi-Supervised Learning and UAV RGB Images," Sustainability, MDPI, vol. 15(12), pages 1-17, June.
  • Handle: RePEc:gam:jsusta:v:15:y:2023:i:12:p:9583-:d:1171148
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2071-1050/15/12/9583/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2071-1050/15/12/9583/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Han, Congying & Zhang, Baozhong & Chen, He & Wei, Zheng & Liu, Yu, 2019. "Spatially distributed crop model based on remote sensing," Agricultural Water Management, Elsevier, vol. 218(C), pages 165-173.
    2. Shenglian Lu & Zhen Song & Wenkang Chen & Tingting Qian & Yingyu Zhang & Ming Chen & Guo Li, 2021. "Counting Dense Leaves under Natural Environments via an Improved Deep-Learning-Based Object Detection Algorithm," Agriculture, MDPI, vol. 11(10), pages 1-16, October.
    3. Chuandong Zhang & Huali Ding & Qinfeng Shi & Yunfei Wang, 2022. "Grape Cluster Real-Time Detection in Complex Natural Scenes Based on YOLOv5s Deep Learning Network," Agriculture, MDPI, vol. 12(8), pages 1-12, August.
    4. Liang, Zhengyuan & van der Werf, Wopke & Xu, Zhan & Cheng, Jiali & Wang, Chong & Cong, Wen-Feng & Zhang, Chaochun & Zhang, Fusuo & Groot, Jeroen C.J., 2022. "Identifying exemplary sustainable cropping systems using a positive deviance approach: Wheat-maize double cropping in the North China Plain," Agricultural Systems, Elsevier, vol. 201(C).
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Rui Zhang & Mingwei Yao & Zijie Qiu & Lizhuo Zhang & Wei Li & Yue Shen, 2024. "Wheat Teacher: A One-Stage Anchor-Based Semi-Supervised Wheat Head Detector Utilizing Pseudo-Labeling and Consistency Regularization Methods," Agriculture, MDPI, vol. 14(2), pages 1-21, February.
    2. Zishang Yang & Jiawei Liu & Lele Wang & Yunhui Shi & Gongpei Cui & Li Ding & He Li, 2024. "Fast and Precise Detection of Dense Soybean Seedlings Images Based on Airborne Edge Device," Agriculture, MDPI, vol. 14(2), pages 1-21, January.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Zejin Sun & Hui Yang & Zhifu Zhang & Junxiao Liu & Xirui Zhang, 2022. "An Improved YOLOv5-Based Tapping Trajectory Detection Method for Natural Rubber Trees," Agriculture, MDPI, vol. 12(9), pages 1-19, August.
    2. Fen Yang & Hossein Moayedi & Amir Mosavi, 2021. "Predicting the Degree of Dissolved Oxygen Using Three Types of Multi-Layer Perceptron-Based Artificial Neural Networks," Sustainability, MDPI, vol. 13(17), pages 1-20, September.
    3. Anwen Liu & Yang Xiang & Yajun Li & Zhengfang Hu & Xiufeng Dai & Xiangming Lei & Zhenhui Tang, 2022. "3D Positioning Method for Pineapple Eyes Based on Multiangle Image Stereo-Matching," Agriculture, MDPI, vol. 12(12), pages 1-17, November.
    4. Karunanayake, N. & Aimmanee, P. & Lohitvisate, W. & Makhanov, S.S., 2020. "Particle method for segmentation of breast tumors in ultrasound images," Mathematics and Computers in Simulation (MATCOM), Elsevier, vol. 170(C), pages 257-284.
    5. Fan, Xiangyu & Schütze, Niels, 2024. "Assessing crop yield and water balance in crop rotation irrigation systems: Exploring sensitivity to soil hydraulic characteristics and initial moisture conditions in the North China Plain," Agricultural Water Management, Elsevier, vol. 300(C).
    6. Yujin Hwang & Seunghyeon Lee & Taejoo Kim & Kyeonghoon Baik & Yukyung Choi, 2022. "Crop Growth Monitoring System in Vertical Farms Based on Region-of-Interest Prediction," Agriculture, MDPI, vol. 12(5), pages 1-14, April.
    7. Zhigui Guan & Yuanjun Zhao & Guojing Geng, 2022. "The Risk Early-Warning Model of Financial Operation in Family Farms Based on Back Propagation Neural Network Methods," Computational Economics, Springer;Society for Computational Economics, vol. 60(4), pages 1221-1244, December.
    8. Ali Arefinia & Omid Bozorg-Haddad & Khaled Ahmadaali & Javad Bazrafshan & Babak Zolghadr-Asli & Xuefeng Chu, 2022. "Estimation of geographical variations in virtual water content and crop yield under climate change: comparison of three data mining approaches," Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development, Springer, vol. 24(6), pages 8378-8396, June.
    9. Alireza Arabameri & Aman Arora & Subodh Chandra Pal & Satarupa Mitra & Asish Saha & Omid Asadi Nalivan & Somayeh Panahi & Hossein Moayedi, 2021. "K-Fold and State-of-the-Art Metaheuristic Machine Learning Approaches for Groundwater Potential Modelling," Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), Springer;European Water Resources Association (EWRA), vol. 35(6), pages 1837-1869, April.
    10. Dhouib, M. & Zitouna-Chebbi, R. & Prévot, L. & Molénat, J. & Mekki, I. & Jacob, F., 2022. "Multicriteria evaluation of the AquaCrop crop model in a hilly rainfed Mediterranean agrosystem," Agricultural Water Management, Elsevier, vol. 273(C).
    11. Tenreiro, Tomás R. & García-Vila, Margarita & Gómez, José A. & Jimenez-Berni, José A. & Fereres, Elías, 2020. "Water modelling approaches and opportunities to simulate spatial water variations at crop field level," Agricultural Water Management, Elsevier, vol. 240(C).
    12. Zhang, Wang & Tian, Yong & Sun, Zan & Zheng, Chunmiao, 2021. "How does plastic film mulching affect crop water productivity in an arid river basin?," Agricultural Water Management, Elsevier, vol. 258(C).
    13. Moreira, Tatiana & Groot Koerkamp, Peter & Janssen, Arni & Stomph, Tjeerd-Jan & van der Werf, Wopke, 2023. "Breaking the mould: Developing innovative crop protection strategies with Reflexive Interactive Design," Agricultural Systems, Elsevier, vol. 210(C).
    14. Anlan Ding & Baoliang Peng & Ke Yang & Yanhua Zhang & Xiaoxuan Yang & Xiuguo Zou & Zhangqing Zhu, 2022. "Design of a Machine Vision-Based Automatic Digging Depth Control System for Garlic Combine Harvester," Agriculture, MDPI, vol. 12(12), pages 1-19, December.
    15. Guo, Daxin & Olesen, Jørgen Eivind & Manevski, Kiril & Ma, Xiaoyi, 2021. "Optimizing irrigation schedule in a large agricultural region under different hydrologic scenarios," Agricultural Water Management, Elsevier, vol. 245(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jsusta:v:15:y:2023:i:12:p:9583-:d:1171148. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.