Multi-Spectral Image Segmentation Based on the K-means Clustering

Abstract

Agriculture is one of the oldest economic aspects of human civilisation, and it is still undergoing a dynamic makeover in the course of the application of IT innovative mechanisms in farming methodology. Remote sensing has vied a significant role in crop classification, crop health and yield assessment. Multispectral remote sensing plays a vital role in providing enhancement of more detailed analysis of crop segmentation. In this article, pixel-based clustering of 12 channels is carried out using the satellite image from Sentinel 2 remote sensing satellite via k-means clustering. K-means clustering algorithm is usually a better method of classifying high-resolution satellite imagery. The extracted regions are classified using a minimum distance decision rule.