Development of a Stereo NDVI Imaging System Using Raspberry Pi

Abstract

Multispectral imagery for sensing applications are very pricey and sometimes not available. This paper shows the development of an imaging system that captures near infrared light and visible light to produce a Normalized Difference Vegetation Index (NDVI) image. It utilizes the Raspberry Pi microcomputer which was capable of performing different image processing techniques to process images captured by the multi-spectral band digital cameras. The system applied image rectification, and stereo correspondence prior to calculation of the NDVI. Images produced were validated and are 70 percent comparable to an existing system.

Keywords

• multispectral image
• stereo
• vegetation index
• microcomputer
• image processing