Evaluation of a Low-cost Camera for Agricultural Applications
Abdon Francisco Aureliano Netto *
Department of Electrical Engineering, Federal University of São João Del Rei, Brazil.
Rodrigo Nogueira Martins
Department of Agricultural Engineering, Federal University of Viçosa, Brazil.
Guilherme Silverio Aquino de Souza
Department of Forestry, Federal University of Viçosa, Brazil.
Fernando Ferreira Lima dos Santos
Department of Agricultural Engineering, Federal University of Viçosa, Brazil.
Jorge Tadeu Fim Rosas
Department of Agricultural Engineering, Federal University of Viçosa, Brazil.
*Author to whom correspondence should be addressed.
Abstract
This study aimed to modify a webcam by replacing its near-infrared (NIR) blocking filter to a low-cost red, green and blue (RGB) filter for obtaining NIR images and to evaluate its performance in two agricultural applications. First, the sensitivity of the webcam to differentiate normalized difference vegetation index (NDVI) levels through five nitrogen (N) doses applied to the Batatais grass (Paspalum notatum Flugge) was verified. Second, images from maize crops were processed using different vegetation indices, and thresholding methods with the aim of determining the best method for segmenting crop canopy from the soil. Results showed that the webcam sensor was capable of detecting the effect of N doses through different NDVI values at 7 and 21 days after N application. In the second application, the use of thresholding methods, such as Otsu, Manual, and Bayes when previously processed by vegetation indices showed satisfactory accuracy (up to 73.3%) in separating the crop canopy from the soil.
Keywords: NDVI, Paspalum notatum, fluegge, Otsu, segmentation