NDVI image extraction of an agricultural land using an autonomous quadcopter with a filter-modified camera

Abstract

The Normalized Difference Vegetation Index (NDVI) has been used in applications related to monitoring crops in agricultural areas. This metric was used with automation to survey agricultural fields, and to provide an estimation of the conditions of crops in contrast to actual observations and care done by local farmers. Having several agricultural areas in the country, this can be beneficial. A quadcopter was used as the platform, equipped with a flight controller and a Raspberry Pi Zero that communicated with a Robot Operating System (ROS) for commands and data acquisition. Through ROS, the quadcopter was further equipped with a filter-modified digital camera, and a GPS module. Images taken by the camera were transferred to a computer for offline processing of the stitching and NDVI extraction of the images. Stitching was done with Speeded Up Robust Features (SURF) and Scale Invariant Feature Transform (SIFT). NDVI was acquired using the blue band of the images containing near infrared (NIR) light data, and the red band containing visible light data. The results showed that SIFT is more suitable for the study where image features had varying lighting and rotation; the values acquired from the final NDVI image showed consistency with the actual state of the corn crops observed in the study.