Autoria: NEVES, M. C.; NEVES JÚNIOR, O. R.; LUIZ, A. J. B.; SANCHES, I. D.

Resumo: The low altitude aerial images are becoming more common every day due to low cost and ease of use of platforms such as remotely piloted aircraft. The potential application of this type of data is very high. One example is the precision agriculture, a farming management concept based on observing, measuring and responding to inter and intra-field variability in crops, an activity than can greatly benefit from this technology. The low altitude of image acquisition allows very high level of scene details but aggravates problems such as lighting variation and image deformation. In addition, often common cameras are used in different situations altitude, inclination, lighting and camera setup. These specific characteristics in relation to the orbital data require development of new methods and approaches to exploit the potential of data and to mitigate problems and limitations. In this work, we present a proposal for a method that provides a green coverage index. It reflects the green pixels density in an area. The proposed index has similar applicability to vegetation indices but does not require near-infrared data, not available in common cameras. We show problems especially related to agriculture applications, present initial test results discuss the possibilities and limitations of the method.

Ano de publicação: 2017

Tipo de publicação: Artigo em anais e proceedings

Unidade: Embrapa Meio Ambiente

Palavras-chave: Agricultura, Agriculture, Computer vision, Image analysis, Image processing, Imagem de satélite, Leaf area index, Processamento de imagem, Remote sensing, Sensoriamento remoto, Visão computacional, Índice de área foliar