Automated segmentation of vineyard rows for data extraction using UAVs



Good news for Winemakers! Digital Falcon jointly with The University of Melbourne has developed a new method to automatically segment crops with distinct row and canopy configurations (e.g. vineyard, fruit orchards and vegetable crops) in aerial imagery. The algorithm uses skeletonisation techniques, developed for fingerprint analysis, to detect the crop’s unique signature and seperate canopy pixels from non-canopy pixels. When evaluated on a commercial vineyard, the algorithm achieved a vine row detection accuracy of 97.1%. By simplifying the skill set required to collect and analyse remotely sensed data, we can start to realise the potential unmanned aerial systems (UAS) has in precision agriculture and environmental monitoring.

Description: Several studies have demonstrated that high-resolution visual/near-infrared (VNIR) vineyard maps acquired from unmanned aerial systems (UAS) can be used to monitor crop spatial variability and plant biophysical parameters in vineyards and orchards. The false colour orthomosaic (67 ha), shown in Figure 1, contains 14 ha of vine plots, although less than 10% of the orthomosaic’s pixels are actual vines. Manually separating vine pixels from non-vine pixels is time consuming, costly and often inaccurate.

MODSIM: Andrew from Digital Falcon will be presenting this algorithm in a scientific paper entitled ‘Automated detection and segmentation of vine rows using high resolution UAS imagery in a commercial vineyard’ at the 21st International Congress on Modelling and Simulation (MODSIM2015) to be held on the Gold Coast, Queensland from Sunday 29 November to Friday 4 December 2015.

More details: CLICK HERE

New Tool to Help Manage Grapevines: VitiCanopy App

From The University of Adelaide news:


A new, free phone app developed by University of Adelaide researchers will help grapegrowers and viticulturists manage their vines by giving a quick measure of vine canopy size and density.

The iPad and iPhone app uses the devices’ camera and GPS capability to calculate the size and density of the vine canopy and its location in the vineyard. The aim is to help users monitor their vines and manage the required balance between vegetative growth and fruit production.

The development of the app – called VitiCanopy – has been supported by Wine Australia as part of a wider project investigating the relationships between vine balance and wine quality.

“Overcropped vines or vines with excessive canopy are referred to as ‘out-of-balance’ – generally being associated with lower quality fruit and hence lower returns,” says project leader Dr Cassandra Collins, Senior Lecturer in Viticulture with the School of Agriculture, Food and Wine. “To achieve vine balance, grapevines require enough leaf area to ripen the fruit and produce a desired fruit quality, but not too much that it’s detrimental to fruit development through shading or a higher incidence of disease.”

Vine balance can be measured as a ratio of leaf area to fruit yield. Traditional ways, however, of measuring leaf area are tedious, laborious and time-consuming and can damage the vines – or alternatively it can require expensive and complex instruments.

“Our app offers a very simple way to measure leaf area index (LAI),” says chief investigator Dr Roberta De Bei. “This measurement can then be related to fruit yield for an assessment of vine balance as well as capture canopy variation across a vineyard. The GPS capability of the app means that information gathered can also be mapped.”

The research and development team also included Professor Steve Tyerman and Associate Professor Matthew Gilliham, University of Adelaide, and Dr Sigfredo Fuentes, University of Melbourne, and Treasury Wine Estates.

Wine Australia’s Research Development and Extension Portfolio Manager, Dr Liz Waters, says this new app will help viticulturists optimise vine balance for best grape quality.

“Wine Australia is committed to helping viticulturists manage their vines to maximise quality, profit and sustainability and to improve competitiveness across the grape and wine community. We encourage growers to explore this new tool to help them get the most from their vineyards,” says Dr Waters.

The app is available from Apple’s app store. To use the app a grower takes a standardised image of the vine canopy. The app then analyses the image and calculates LAI, taking into account the canopy shape and density, and recording the time and location of the image. An android version of the app is being developed.

The University’s commercialisation company, Adelaide Research & Innovation (ARI), has supported the release of the app. The project was supported by Wine Australia, the University of Adelaide Wine Future initiative (formerly the Wine2030 Research Network) and The Vineyard of the Future.

VitiCanopy App: Available from Apple Store for FREE

Link to the App” CLICK HERE


VitiCanopy App is already available from the Apple Store.

Soon to come: Android version.

A smartphone and tablet app has been developed by a team from The University of Adelaide na The University of Melbourne enabling growers to characterise the canopy architecture and leaf area index of their grapevines. The capabilities of the app could see it become an important tool for growers, irrigation practitioners and scientists to assess spatial and temporal growth and canopy architecture dynamics that can be associated with final yield and quality of grapes.

In theory, the same App can be used for other horticultural trees, such as olive trees, apple trees, citrus, etc. The parameter that needs to be characterised per specie and training system is the light extinction coefficient (k). Previous reserch has shown that for the cover photography method, a k = 0.5 is suitable for Eucalyptus trees (Fuentes et al. 2008); k = 0.65 for apple trees (Poblete-Echeverria et al. 2014) and k = 0.7 for grapevines (Fuentes et al. 2014).

New Paper: Assessment by image analysis of foamability and effervescence of sparkling wines during the prise de mousse and ageing process

rbve n7 2015 - revista completa (dragged)

Link to full article: CLICK HERE

Worldwide wine trade has experienced an increase of sparkling wine commercialisation and consumption. Specifically, emerging countries, such as Brazil, have doubled their consumption of sparkling wine during the last ten years, which is produced mainly from local growers. Nevertheless, in order to maintain its domestic competitiveness and increase international trade, Brazilian sparkling wine needs to position quality sparkling wine quicker in the market. However, sparkling wine production is costly compared to still wines, which is related to (among many factors) the storage time required for the second fermentation. The objective of this study was to assess sparkling wines during the prise de mousse by using a rapid, non-expensive and robust method based on a robotic wine pourer and automated image acquisition and analysis by using the Fizz-eyeRobot. This method was used to analyse sparkling wines during different stages in the prise de mousse process. Results showed that the use of new image analysis techniques to assess objectively visual characteristics of foamability and effervescence might assist winemakers in the decision-making process regarding the optimum autolysis time. The use of objective analysis might result in decreasing the cost associated with storage time and assist in the production of high quality sparkling wines.

Key words: quality, frizz, foam, vinification, hough transformation, Fizz-eyeRobot.

Drones, they’ll change the way we live

Link to Full article: CLICK HERE

cover orchard


Higher incidences of climate anomalies (such as frosts and heat waves) and increasing water demands, are having an impact on the majority of grape-growing regions globally, leading to early harvests and berry shrivel.

Dr Sigfredo Fuentes is a University of Melbourne senior researcher and international co-ordinator of the Vineyard of the Future Initiative. He is using a ‘multicopter’, nicknamed the ‘viticopter’, developed by mechanical engineering students, and powered by an app, to gather vital information for growers.

“The app will help wine growers determine which vines are starting to become stressed before there are damages that could impact yield and quality of berries,” Dr Fuentes explains.