Smart Agriculture: Real-time Pest Detection in Rice Crops with YOLOv8 and ESP-32 Camera Technology

Abstract

Rice is a vital crop globally, serving as a primary food source for a significant portion of the world's population. The cultivation of rice, particularly during the vegetative phase, plays a pivotal role in determining overall crop quality, pest resistance, nutrient uptake, and sustainable agricultural practices. In regions like Sri Lanka, where paddy cultivation holds historical significance, safeguarding paddy fields from various pests becomes paramount to ensuring optimal yields and sustaining the livelihoods of local farmers. This research project aims to address the pressing need for effective pest management in the vegetative phase of paddy growth by leveraging emerging technologies. By utilizing state-of-the-art methodologies, the project seeks to enhance the early identification and control of pests that pose significant threats to paddy fields. By focusing on this critical growth stage, the research aims to minimize potential crop damage and optimize agricultural practices, ultimately improving overall productivity and mitigating economic losses for farmers.

Through the utilization of advanced pest identification techniques and innovative control measures, this project aspires to provide farmers with timely and accurate information about the pests affecting their paddy fields. By promptly identifying these pests, farmers can take appropriate measures to protect their crops, optimize resource utilization, and minimize the use of harmful chemicals. This research endeavors to contribute to the sustainable management of paddy fields, foster resilient agricultural practices, and ensure the availability of high-quality rice production. By empowering farmers with efficient pest identification and control strategies during the vegetative phase, this project aims to safeguard paddy fields, enhance yields, and promote sustainable agriculture in the face of evolving pest challenges.

Country : Sri Lanka

1 Herath K.H.M.2 H.M. Samadhi Chathuranga Rathnayaka

  1. Undergraduate, Department of Data Science, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka
  2. Lecturer, Department of Data Science, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka

IRJIET, Volume 7, Issue 11, November 2023 pp. 705-709

doi.org/10.47001/IRJIET/2023.711092

References

  1. I.B.M.P.N.R.A.B.Helina Farhood, “sceince direct,” [Online]. Available: https://www.sciencedirect.com/science/article/abs/pii/B9780323905084000071 (Accessed: 19 03 2023).
  2. Agronomy, “MDPI,” 28 02 2023. [Online]. Available at: Image_Agriculture (Accessed: 23 04 2023).
  3. Y. Qing, “An Insect Imaging System to Automate Rice Light-Trap Pest Identification,” integrative Agriculture, p. 8, 2012.
  4. S. Li, “An intelligent monitoring system of diseases and pests on rice canopy,” An intelligent monitoring system of diseases and pests on rice canopy, 2022.
  5. R. Courtney, “iapps2010”, Plant Protection, 23 10 2021. [Online]. Available: https://iapps2010.me/2021/10/23/camera-traps-are-an- important-tool-for-the-future-in-the-management-of- many-pests/. [Accessed: 21 05 2023].
  6. Nitin Rai a et al. (2023) Applications of deep learning in Precision Weed Management: A Review, Computers and Electronics in Agriculture. Elsevier. Available at: https://www.sciencedirect.com/science/article/pii/S0168 16992300086 8 [Accessed: 18 03 2023].
  7. Q. Yao, “Development of an automatic monitoring system for rice-trap pests based on machine vision,” 2020.
  8. Liu, J. and Wang, X. (2021) Plant diseases and pests detection based on Deep Learning: A Review - Plant Methods, BioMed Central. BioMed Central. Available at: https://plantmethods.biomedcentral.com/articles/10.118 6/s13007-02100722-9 [Accessed: 22 05 2023].