Sugarcane crop line angle estimation based on pixel accumulation and Savitzky-Golay filtering

  • Raphael P. Ferreira UFSCar
  • André C. Hernandes UFSCar

Resumo


This paper describes an automatic method that measures the orientation angle of sugarcane planting lines in relation to the vertical axis of an image using digital image processing techniques. The methodology has three main steps: First, RGB images are converted to the Excess Green vegetation index. The image is then binarized based on the Otsu Method threshold and morphological operation. Then, different vertical projection vectors of the cut lines are generated with different orientation angles of the image. The orientation angle is detected where the maximum variation between black (ground) and white (cut lines) occurs, measured after applying the Savitzky-Golay filter. A full factorial experimental design was performed over 40 images taken from a drone and previously annotated. Results showed that the proposed methodology was able to detect the crop lines with a median absolute error of 0.9° and interquartile range of just 1.5◦, without any outlier, even in the presence of images with almost no indication of orientation, and even faulty lines.
Palavras-chave: Filtering, Crops, Vegetation mapping, Imaging, Graphics processing units, Parallel processing, Indexes
Publicado
11/10/2021
FERREIRA, Raphael P.; HERNANDES, André C.. Sugarcane crop line angle estimation based on pixel accumulation and Savitzky-Golay filtering. In: SIMPÓSIO BRASILEIRO DE ROBÓTICA E SIMPÓSIO LATINO AMERICANO DE ROBÓTICA (SBR/LARS), 13. , 2021, Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 . p. 102-107.