Skip to main content

ORIGINAL RESEARCH article

Front. Plant Sci.
Sec. Sustainable and Intelligent Phytoprotection
Volume 15 - 2024 | doi: 10.3389/fpls.2024.1484587
This article is part of the Research Topic Precision Information Identification and Integrated Control: Pest Identification, Crop Health Monitoring, and Field Management View all articles

Persistent Monitoring of Insect-Pests on Sticky Traps through Hierarchical Transfer Learning and Slicing-Aided Hyper Inference

Provisionally accepted
  • 1 Department of Mechanical Engineering, College of Engineering, Iowa State University, Ames, Iowa, United States
  • 2 Department of Computer Science, College of Liberal Arts & Sciences, Iowa State University, Ames, Iowa, United States
  • 3 Iowa Soybean Association, Ankeny, Iowa, United States
  • 4 Department of Computer Science, College of Engineering and Computing, Missouri University of Science and Technology, Rolla, Missouri, United States
  • 5 Data Science Institute, University of Arizona, Tucson, Arizona, United States
  • 6 Department of Plant Pathology and Microbiology, College of Agriculture and Life Sciences, Iowa State University, Ames, Iowa, United States
  • 7 Department of Agronomy, College of Agriculture and Life Sciences, Iowa State University, Ames, Iowa, United States
  • 8 Department of Mechanical Engineering, Iowa State University, Ames, United States

The final, formatted version of the article will be published soon.

    Effective monitoring of insect-pests is vital for safeguarding agricultural yields and ensuring food security. Recent advances in computer vision and machine learning have opened up significant possibilities of automated persistent monitoring of insect-pests through reliable detection and counting of insects in setups such as yellow sticky traps. However, this task is fraught with complexities, encompassing challenges such as, laborious dataset annotation, recognizing small insect-pests in low-resolution or distant images, and the intricate variations across insect-pests life stages and species classes. To tackle these obstacles, this work investigates combining two solutions, Hierarchical Transfer Learning (HTL) and Slicing-Aided Hyper Inference (SAHI), along with applying a detection model. HTL pioneers a multi-step knowledge transfer paradigm, harnessing intermediary in-domain datasets to facilitate model adaptation. Moreover, slicingaided hyper inference subdivides images into overlapping patches, conducting independent object detection on each patch before merging outcomes for precise, comprehensive results. The outcomes underscore the substantial improvement achievable in detection results by integrating a diverse and expansive in-domain dataset within the HTL method, complemented by the utilization of SAHI. We also present a hardware and software infrastructure for deploying such models for real-life applications. Our results can assist researchers and practitioners looking for solutions for insect-pest detection and quantification on yellow sticky traps.

    Keywords: Insect-pest monitoring, Yellow sticky traps, deep learning, Transfer Learning, Edge-IoT cyberinfrastructure

    Received: 22 Aug 2024; Accepted: 28 Oct 2024.

    Copyright: © 2024 Fotouhi, Menke, Prestholt, Gupta, Carroll, Yang, Skidmore, O'Neal, Merchant, Das, Kyveryga, Ganapathysubramanian, Singh, Singh and Sarkar. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Arti Singh, Department of Agronomy, College of Agriculture and Life Sciences, Iowa State University, Ames, 50011-1051, Iowa, United States
    Soumik Sarkar, Department of Mechanical Engineering, Iowa State University, Ames, United States

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.