Design of NDVI Plant Health Monitoring for Pepper Vines

Abstract

The advancement in the Internet of Things (IoTs) enables image processing on a small and low-cost scale in the agriculture sector. Low productivity due to the pest and disease has been identified as one of the major pepper production constraints. The classification of images for pepper vines in the early stages will help pepper farmers to identify the health status of the pepper plants, thus help farmers to maximise the pepper production. This project is to propose the use of No InfraRed (NoIR) camera and Global Positioning System (GPS) module with Raspberry Pi to analyse the health of black pepper plants and track the coordinate location of the plants. The NoIR Camera has No InfraRed (NoIR) filter on the lens which makes it capable of doing Infrared photography and taking pictures in low light (twilight) environments. Internet of Things (IoTs) is designed to transfer data over a network without requiring human-to-human or human-to-computer interaction. The utilisation of Normalized Difference Vegetation Index (NDVI) included in the prototype to determine the health of pepper plants. OpenCV is used for NDVI image processing because it is open-source software and portable as it can run on any devices that run C++ or Python. Python language is also used to handle image capturing and image transfer operations. The images and reports of the pepper plant can be viewed via an android application. This application will help the farmers to monitor plant growth efficiently for better production.