Automated Wheat Disease Detection Using A ROS-Based Autonomous Guided UAV

Abstract

With the increase in world population, food resources have to be modified to be more productive, resistive, and reliable. Wheat is one of the most important food resources in the world, mainly because of the variety of wheat-based products. Wheat crops are threatened by three main types of diseases which cause large amounts of annual damage in crop yield. These diseases can be eliminated by using pesticides at the right time. While the task of manually spraying pesticides is burdensome and expensive, agricultural robotics can aid farmers by increasing the speed and decreasing the amount of chemicals. In this work, a smart autonomous system has been implemented on an unmanned aerial vehicle to automate the task of monitoring wheat fields. First, an image-based deep learning approach is used to detect and classify disease-infected wheat plants. To find the most optimal method, different approaches have been studied. Because of the lack of a public wheat-disease dataset, a custom dataset has been created and labeled. Second, an efficient mapping and navigation system is presented using a simulation in the robot operating system and Gazebo environments. A 2D simultaneous localization and mapping algorithm is used for mapping the workspace autonomously with the help of a frontier-based exploration method.

A deep learning based approach for automated plant disease classification using vision transformer

“…So the sooner the accuracy converges, the higher value this unit gets. Model 3, model 4, and model 8 with the input resolution of 200 by 200 have achieved the same average F1-score, recall, and precision with the EfficientNet model presented by 1 . However, these models have much lower computational costs based on GFlops in comparison with the EfficientNet.…”

“…Most of these datasets contains images that are captured in the acceptable circumstances since in the agriculture purposes the images are usually recorded in a good conditions. For example, for diagnosing wheat rust, aerial and non-aerial images of wheat farms were collected in 1 . The images were labeled for object detection.…”

“…Wheat rust classification dataset. The first dataset used in this paper is collected by Safari et al 1 , which is called "Wheat Rust Classification Dataset (WRCD)". The Wheat Rust Classification dataset includes three classes: healthy wheat, yellow rust and brown rust.…”

Adaptive Learning Model for Detecting Wheat Diseases

“…In study [26], for their UAV to be able to recognize three different forms of wheat leaf diseases, the authors developed a two-stage classifier. They first found individual plant leaves using an object detection model, such as the YOLOV4 or EfficientDet models, and then cropped the image using bounding box coordinates.…”

“…• The dataset contains images of yellow-rust(stripe rust), brown-rust (leaf rust) wheat leaf diseases, and healthy wheat leaf [36].…”