Segmentación automática de imágenes digitales para estimar el vigor en viñas

Abstract

The geographic information required to implement precision viticulture applications in real fields has led to the extensive use of remote sensing and airborne imagery. While advantageous because they cover large areas and provide diverse radiometric data, they are unreachable to most of medium-size Spanish growers who cannot afford such image sourcing. This research develops a new methodology to generate globally-referenced vigor maps in vineyards from ground images taken with a camera mounted on a conventional tractor. This monocular camera was able to sense in the visible, NIR, and UV spectra, selectively isolated with bandpass filters. The versatility of the system was further enhanced by implementing two sampling levels: intensive coverage of 1 m 2 and super-intensive for 0.1 m 2 . The core of the procedure resides in the algorithm for automatically segmenting the filtered images in such a way that relative differences in canopy vigor were objectively quantified. The calculation of the dynamic threshold involved the mathematical concepts of gradient and curvature. Field results showed that relative differences in vine vigor can be detected from NIR-filtered images and intensive sampling. Furthermore, individual images were successfully merged into a global vigor map that can be directly employed by end-users. Super-intensive sampling and UV perception were not appropriate for building vigor maps, but could be of interest for other agronomical purposes as the early detection of diseases. Field tests proved the feasibility of building global vigor maps from ground-based imagery, and showed the potential of this technique as a predictive instrument for modest-size producers.Additional key words: dynamic threshold; GPS; NIR; precision viticulture; UV; vigor map. Resumen Segmentación automática de imágenes digitales para estimar el vigor en viñasLa información requerida para implementar aplicaciones de viticultura de precisión en parcelas reales ha desembocado en el uso extensivo de la teledetección y la detección aérea. Si bien estos métodos son ventajosos por cubrir vastas áreas y proveer diversa información radiométrica, suelen ser inalcanzables para el productor español medio debido a los gastos ocasionados. Esta investigación desarrolla una nueva metodología para generar mapas de vigor con referencias globales basados en imágenes digitales tomadas con una cámara montada sobre un tractor convencional y con capacidad para percibir en el espectro visible, infrarrojo cercano (NIR) y ultravioleta (UV). Para hacer el sistema más versátil se analizaron dos niveles de muestreo: intensivo (1 m 2 de cobertura vegetal) y super-intensivo (0,1 m 2 de cobertura). El núcleo de la metodología propuesta se basa en el algoritmo de segmentación de imágenes para cuantificar automáticamente diferencias en vigor vegetativo. El cálculo del umbral dinámico se fundamenta en los conceptos matemáticos de gradiente y curvatura. Los resultados obtenidos mostraron que es posible cuantificar diferencias en vigor vegetativo de viña...

Crop Biometric Maps: The Key to Prediction

“…Two assessments of vegetation were conducted according to the field of view of the camera: wide view with 8 mm focal length ( Figure 3b ); and narrow view with 12 mm focal length ( Figure 3c ). NIR-filtered images enhance vegetation from the background, and a customized dynamic segmentation algorithm [ 18 ] was developed to quantize the variation of the amount of leaves along the rows. The camera was mounted on a side bar attached to the tractor's cabin, and the vehicle's GPS provided its instantaneous position associated to each image automatically taken, following the architectural principles set in [ 21 ].…”

“…The construction of regular grids with global references given in the LTP coordinate system is described in [ 16 ]. The implementation of conditioning filters to enhance the robustness of GPS data can be checked in [ 17 ], and finally, the estimation of spatial variation of vine vegetation with machine vision has been reported in [ 18 ]. Section 6 applies this methodology to the particular case of vineyards, presenting more insights and practical solutions on the proposed philosophy.…”

Structure from Linear Motion (SfLM): An On-the-Go Canopy Profiling System Based on Off-the-Shelf RGB Cameras for Effective Sprayers Control

“…In [17], a monocular monochrome camera with two different optical band-pass filters was used. The system acquires both UV and NIR bands; the segmentation is obtained by looking for the optimal threshold of the histogram of gray values of the images: vegetation is highlighted by working in the near-infrared band.…”

Extracción de Características en Viñedos Mediante Algoritmos de Clasificación Difusa y Técnicas de Inteligencia Artificial

“…Por este motivo diversos autores (Rabatel et al, 2007, Berenstein et al, 2010, Braun et al, 2010, Nuske et al 2011a, Sáiz-Rubio & Rovira-Más, 2012, Wang et al, 2012, Liu et al, 2013, Nuske et al 2014, Skrabanek & Majerík, 2016 han desarrollado metodologías automatizadas, basadas en procesamiento de imágenes, que permitan con el menor grado de intervención humana caracterizar la parte aérea del viñedo, sin embargo no es un problema resuelto.…”