A Survey on Automatic Crops Damage Assessment Using Remote Sensing

This article consideration a combination of unmanned aerial vehicles (UAVs), machine learning and remote sensing technology as promising technologies to tackle this challenge. The deployment of UAVs as sensor platforms is a rapidly evolving research area for precision biosecurity and agricultural applications. In this experiment, data collection activities were carried out on crops that were severely affected by various factors, such as natural disasters. In this study, we describe the deployment of a drone platform for collecting high-resolution RGB images for orthophoto imaging. An unsupervised machine learning formula was developed to construct a significant divide of the image at each level of the damaged culture. The implementation algorithm is based on a K-means clustering algorithm. The results show that the algorithm provides the accurate data and the field can be consistently divided into subcategories one for crop damaged area etc. The methods present in this document is a place for further research on automatic damage crop assessment. The motivation of the work is to find the accurate damage area of the field using UAV’s. So that we will get 100% accurate damage area.