Strategy for the Development of a Smart NDVI Camera System for Outdoor Plant Detection and Agricultural Embedded Systems

Volker Dworak,Ali Zarezadeh,Matthias Hoffmann,Christophe Bobda,Joern Selbeck,Karl-Heinz Dammer

doi:10.3390/s130201523

Abstract

The application of (smart) cameras for process control, mapping, and advanced imaging in agriculture has become an element of precision farming that facilitates the conservation of fertilizer, pesticides, and machine time. This technique additionally reduces the amount of energy required in terms of fuel. Although research activities have increased in this field, high camera prices reflect low adaptation to applications in all fields of agriculture. Smart, low-cost cameras adapted for agricultural applications can overcome this drawback. The normalized difference vegetation index (NDVI) for each image pixel is an applicable algorithm to discriminate plant information from the soil background enabled by a large difference in the reflectance between the near infrared (NIR) and the red channel optical frequency band. Two aligned charge coupled device (CCD) chips for the red and NIR channel are typically used, but they are expensive because of the precise optical alignment required. Therefore, much attention has been given to the development of alternative camera designs. In this study, the advantage of a smart one-chip camera design with NDVI image performance is demonstrated in terms of low cost and simplified design. The required assembly and pixel modifications are described, and new algorithms for establishing an enhanced NDVI image quality for data processing are discussed.

Highlights

Agriculture research activities focus on reducing carbon dioxide, environmental impact and cost.precision farming, which combines various information or databases to increase the agricultural input-to-output ratio, is often used [1,2,3]
These results demonstrate the need for an adapted normalized difference vegetation index (NDVI) algorithm to establish a useful plant camera
Both NDVI images need some enhancement in the algorithms to overcome these drawbacks

Summary

Introduction

Agriculture research activities focus on reducing carbon dioxide, environmental impact and cost.precision farming, which combines various information or databases to increase the agricultural input-to-output ratio, is often used [1,2,3]. Coverage levels or the amount of biomass [4] is typically determined using sensors, for e.g., control of an online field sprayer. The coverage level or plant counts are typical values used to control a field sprayer. The coverage level can be calculated from the NDVI image of the local field conditions [2], and the plant number in a local scene can be estimated using an additional algorithm. The NIR reflection is high for vital plants and low for soil; plants absorb more light with red wavelengths, from 620 nm to 660 nm, than soil [6,7]. Nutrient supply of the plants influences absorption through chlorophyll activity in the transition band from red to NIR (660 nm to 740 nm) and thereby corresponds to the stress of the plant [8].

Methods

Results

Conclusion