ROS-based Robotic System for Tomato Disease and Ripeness Classification using Convolutional Neural Networks

Robotic systems can play a crucial role in the agricultural field as the increasing demands for crops lead to continuous pressure for more crop quality and quantity. Agricultural work is very tedious under poor weather circumstances. The agricultural robots represent a replacement for labor in carrying out the tiresome tasks and efficiently avoiding exposing humans to health risks. The proposed work implements a ground robot to navigate the farm and monitor the plants using the Robot Operating System. The monitoring includes the classification of nine types of tomato leaf diseases and three tomato ripeness levels using Convolutional Neural Networks and computer vision using a raspberry pi camera. The model is trained on Colab, and raspberry pi3 is used to run Keras pre-trained model on TurtleBot3. Three CNN architectures are used and compared for the disease and ripeness classification of tomatoes.