Deep learning techniques for enhancement of weeds growth classification

Dmitrii Vypirailenko, Elizaveta Kiseleva, Dmitrii Shadrin, Mariia Pukalchik

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    2 Citations (Scopus)

    Abstract

    Automatic weed control is becoming a popular tool for agriculture with its potential for boosting crop productivity. Most of the research in this area has focused on developing deep learning systems for weeds recognition, ignoring the possible different stages of their growth. In the meantime, in order to effectively control weeds, it is useful to know their exact species and growth stage. This study presents another effective method for solving this problem. We use the transfer learning approach applied for Dense Convolutional Neural Network to recognize weed and identify their growth stages. In our work, transfer learning helps to pre-train the deep neural network model for learning useful features such as leaf characteristics directly from the input data representation. We explore various convolutional neural networks (ResNet, MobileNet, Wide ResNet, DenseNet) architectures and deep learning approaches for addressing this problem. We used the publicly available dataset with labeled data for 18 different weed species. The results show that the proposed method has good performance and better results in solving the classification task (71.81% top1 accuracy and 93.45% top3 accuracy) than previous methods in terms of memory and precision. We provide access to our code [1] that includes the whole pipeline and can help with tasks of classification, using the transfer learning datasets.

    Original languageEnglish
    Title of host publicationI2MTC 2021 - IEEE International Instrumentation and Measurement Technology Conference, Proceedings
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    ISBN (Electronic)9781728195391
    DOIs
    Publication statusPublished - 17 May 2021
    Event2021 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2021 - Virtual, Glasgow, United Kingdom
    Duration: 17 May 202120 May 2021

    Publication series

    NameConference Record - IEEE Instrumentation and Measurement Technology Conference
    Volume2021-May
    ISSN (Print)1091-5281

    Conference

    Conference2021 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2021
    Country/TerritoryUnited Kingdom
    CityVirtual, Glasgow
    Period17/05/2120/05/21

    Keywords

    • Convolutional Neural Networks
    • DenseNet
    • leaves
    • Transfer learning
    • weeds

    Fingerprint

    Dive into the research topics of 'Deep learning techniques for enhancement of weeds growth classification'. Together they form a unique fingerprint.

    Cite this