Conference Paper

Towards grape-vine management based on mapping of airborne hyperspectral images

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

ResearchGate has not been able to resolve any citations for this publication.
Article
Full-text available
The evaluation of phenotypic characters of grapevines is required directly in vineyards and is strongly limited by time, costs and the subjectivity of person in charge. Sensor-based techniques are prerequisite in order to allow non-invasive phenotyping of individual plant traits, to increase the quantity of object records and to reduce error variation. Thus, a Prototype-Image- Acquisition-System (PIAS) was developed for semi-automated capture of geo-referenced images in an experimental vineyard. Different strategies were tested for image interpretation using MATLAB®. The interpretation of images from the vineyard with real background is more practice-oriented but requires the calculation of depth maps. Different image analysis tools were verified in order to enable contactless and non-invasive detection of bud burst and quantification of shoots at an early developmental stage (BBCH 10) and enable fast and accurate determination of the grapevine berry size at BBCH 89. Depending on the time of image acquisition at BBCH 10 up to 94 % of green shoots were visible in images. The mean berry size (BBCH 89) was recorded non-invasively with a precision of 1 mm.
Article
Full-text available
Prototype based classi cation oers intuitive and sparse models with excellent generalization ability. However, these models usually crucially depend on the underlying Euclidian metric; moreover, online variants likely suer from the problem of local optima. We here propose a generalization of learning vector quantization with three additional features: (I) it directly integrates neighborhood cooperation, hence is less aected by local optima; (II) the method can be combined with any dierentiable similarity measure whereby metric parameters such as relevance factors of the input dimensions can automatically be adapted according to the given data; (III) it obeys a gradient dynamics hence shows very robust behavior, and the chosen objective is related to margin optimization.
Conference Paper
Training and application of prototype based learning approaches such as Learning Vector Quantization, Radial Basis Function networks, and Supervised Neural Gas require the use of distance metrics to measure the similarities between feature vectors as well as class prototypes. While the Euclidean distance is used in many cases, the highly correlated features within the hyperspectral representation and the high dimensionality itself favor the use of more sophisticated distance metrics. In this paper we first investigate the role of different metrics for successful classification of hyperspectral data sets from real-world classification tasks. Second, it is shown that considerable performance gains can be achieved by a classification system that combines a number of prototype based models trained on differently parametrized divergence measures. Data sets are tested using a number of different combination strategies.
Chapter
This article has no abstract.
Article
We perform correlation analysis between air temperature and surface brightness temperature over the Adelaide Central Business District and the surrounding parklands. The results indicate that three effective surface areas associated with three different mechanisms exist. They are the effective surface area with upward sensible heat transfer to heat up and maintain the air temperature, the effective surface area with downward sensible heat transfer to cool down the air, and the effective surface area related to very localized conditions (e.g., sky-view factors). The three mechanisms occur at different times of the day and result in different air temperature and surface temperature correlations. The first effective surface area exists in the daytime after the surface is heated up by solar radiation and can persist into the night, particularly in urban environments. The second effective area occurs in night-time when the surface has been cooled down sufficiently. The third effective area coexists with the second one and has a weaker correlation between the surface and air temperatures. It was also found that in an urban area, exclusion of roof pixels in the calculation of surface brightness temperature can increase the correlation between the surface and air temperatures in the middle of the night. © 2015 Society of Photo-Optical Instrumentation Engineers.
Article
The aim of this study was to demonstrate the capability of hyperspectral imaging in predicting anthocyanin content changes in wine grapes during ripening. One hundred twenty groups of Cabernet Sauvignon grapes were collected periodically after veraison. The hyperspectral images were recorded by a hyperspectral imaging system with a spectral range from 900 to 1700nm. The anthocyanin content was measured by the pH differential method. A quantitative model was developed using partial least squares regression (PLSR) or support vector regression (SVR) for calculating the anthocyanin content. The best model was obtained using SVR, yielding a coefficient of validation (P-R(2)) of 0.9414 and a root mean square error of prediction (RMSEP) of 0.0046, higher than the PLSR model, which had a P-R(2) of 0.8407 and a RMSEP of 0.0129. Therefore, hyperspectral imaging can be a fast and non-destructive method for predicting the anthocyanin content of wine grapes during ripening. Copyright © 2014 Elsevier Ltd. All rights reserved.
Conference Paper
Parametric geocoding is a standard procedure for orthorectification of hyperspectral airborne scanner data. Boresight parameters are estimated by using the image coordinates of precisely known ground reference points. To fully automate the processing of the recorded hyperspectral data ground reference points should be selected and matched by an algorithm without user interaction. In this article a two-step procedure is presented. First, direct geocoding of the data is done without ground reference points. This step is solely based on the data of the inertial measurement unit with differential GPS. Next, the hyperspectral data is normalized and pixels are clustered with an unsupervised method. Image blocks of an edge image of the resulting regions are matched with a high resolution edge image of a digital orthophoto of the calibration site. The found correspondences are used as ground control points in the second geocoding step.
Article
The emergence of precision agriculture technologies and an increasing demand for higher quality grape products has led to a growing interest in the practice of precision viticulture; monitoring and managing spatial variations in productivity-related variables within single vineyards. Potentially, one of the most powerful tools in precision viticulture is the use of remote sensing through its ability to rapidly provide a synoptic view of grapevine shape, size and vigour over entire vineyards. Its potential for improving viticultural practice is evident by the relationships that are known to exist between these canopy descriptors and grape quality and yield. This paper introduces the reader to remote sensing and reviews its recent, and potential, applications in viticulture.
Article
Remote-Sensing (RS) is the most widely used technique for crop monitoring in precision viticulture systems. This paper considers the possibility of substituting RS information obtained by various proximal sensing technologies employed directly in vineyards in order to enable a simultaneous evaluation of canopy health and vigour status. To this aim, a mobile lab has been developed. It consists of (a) two GreenSeeker RT100 sensors, a commercial optical device calculating NDVI, and Red/NIR indices in real time; (b) three pairs of ultrasonic sensors to estimate canopy thickness; and (c) a DGPS receiver to geo-reference data collected while travelling in a vineyard. During the 2007–2008 campaign, tests were carried out in a commercial vineyard in order to evaluate the monitoring system performance regarding disease appearance, diffusion, and vegetative development variations due to the normal growing process of vines. Surveys with the mobile lab were conducted in two groups of rows, treated and untreated with agrochemicals, and compared to manual morphological and physiological observations that characterised the phytosanitary status of the canopy. Measurement repeatability was verified; both NDVI values and ultrasonic data showed high repeatability (with r=0.88 and r=0.85, respectively). Optical data were processed in order to obtain NDVI maps, which clearly showed differences in canopy vigour evolution in the two examined groups, with low vegetative vigour in areas infected by Plasmopara viticola, as confirmed by manual assessment. Maps of the percentage infection index (I%I) were produced according to pathological manual survey results. The comparison between I%I and NDVI maps qualitatively confirmed the real vine phytosanitary status. Ultrasonically measured canopy thickness (UCT) was calculated and compared to manually measured canopy thickness (MCT) (r=0.78). UCT and NDVI values were compared in order to identify areas affected by disease among zones presenting critical vegetation conditions. KeywordsGround sensing-NDVI-Canopy thickness-Vegetative vigour
Airborne/spaceborne remote sensing for the grape and wine industry
  • D Lamb
  • A Hall
  • J Louis
Lamb, D., Hall, A. and Louis, J. (2001) Airborne/spaceborne remote sensing for the grape and wine industry. Proc. of the 1st National Conference on Geospatial Information & Agriculture. Sydney. p. 600-608.