Autonomous IoT-Integrated Tomato Plant Disease Detection: Harnessing YOLOv8 Algorithm and Micro-Navigation for Precision Agriculture

Abstract

The nation of India, with abundant biodiversity, must contend with the effects of climate change on ecosystems and habitats. The tomato, or Solanum lycopersicum, is a critically important fruit utilized extensively in Indian and Western cuisines. However, the tomato is a fruit that may contract illness because of pest infestations, bacterial activity, microbes, and changes in the climate. Given the necessity for mass production, which renders “hand-picking” unfeasible, automation of a tomato field would be crucial. This would necessitate innovative solutions for disease diagnosis and classification in a large-scale production. This study examines various approaches related to tomato iden-tification, emphasizing performance analysis. To detect pests and illnesses in crops, the suggested method includes an autonomous mobile robot fitted with sensors, such as RGB cameras and Ultrasonic Sensors enhanced with Wi-Fi-enabled data transfer for IoT technology. The RGB camera takes crop visuals in real time and uses image processing, deep learning techniques, and the YOLOv8 algorithm to identify disease symptoms. To make the suggested mobile robot, an effective and long-lasting instrument for disease management in agriculture Micro-ROS is used. Its ability to identify illnesses quickly reduces the environmental impact and guarantees food safety, which is a big step toward a sustainable agricultural future.