Abstract—Spectral information alone is often not sufficient to distinguish certain terrain classes such as permanent crops like orchards, vineyards, and olive groves from other types of vegetation. However, instances of these classes possess distinctive spatial structures that can be observable in detail in very high spatial resolution images. This paper proposes a novel unsupervised algorithm for the detection and segmentation of orchards. The detection step uses a texture model that is based on the idea that textures are made up of primitives (trees) appearing in a near-regular repetitive arrangement (planting patterns). The algorithm starts with the enhancement of potential tree locations by using multi-granularity isotropic filters. Then, the regularity of the planting patterns is quantified using projection profiles of the filter responses at multiple orientations. The result is a regularity score at each pixel for each granularity and orientation. Finally, the segmentation step iteratively merges neighboring pixels and regions belonging to similar planting patterns according to the similarities of their regularity scores, and obtains the boundaries of individual orchards along with estimates of their granularities and orientations. Extensive experiments using Ikonos and QuickBird imagery as well as images taken from Google Earth show that the proposed algorithm provides good localization of the target objects even when no sharp boundaries exist in the image data. Index Terms—Texture analysis, periodic signal analysis, regularity detection, orientation estimation, texture segmentation I.

A forecast model for estimating the annual variation in regional wine yield based on remote sensing was developed for the main wine regions of Portugal. Normalized Difference Vegetation Index (NDVI) time-series obtained by the VEGETATION sensor, on board the most recent Satellite Pour l’Observation de la Terre (SPOT) satellite, over the period 1998–2008 were used for four test sites located in the main wine regions of Portugal: Douro (two sites), Vinhos Verdes and Alentejo. The CORINE (Coordination of Information on the Environment) Land Cover maps from 2000 were initially used to select the suitable regional test sites. The NDVI values of the second decade of April of the previous season to harvest were significantly correlated to the wine yield for all studied regions. The relation between the NDVI and grapevine induction and differentiation of the inflorescence primordial or bud fruitful-ness during the previous season is discussed. This NDVI measurement can be made about 17 months before harvest and allows us to obtain very early forecasts of potential regional wine yield. Appropriate statistical tests indicated that the wine yield forecast model explains 77–88 % of the inter-annual variability in wine yield. The comparison of

Commission VII

Vine-plot mapping and monitoring are crucial issues in land management, particularly for areas where vineyards are dominant, like in some French regions. In this context, the availability of an automatic tool for vineyard detection and characterization would be very useful. Due to the periodic patterns induced by this culture, frequency analysis appears to be a very suited tool for vineyard detection in aerial images. A recursive process using Fast Fourier Transform algorithm has been developed to meet this need. This results in vine plot segmentation, with contours in polygonal form and characterization with accurate estimation of interrow width and row orientation. To foster large-scale applications, tests and validation have been carried out on standard very high spatial resolution remote-sensing data. More than 71 % of adults, mechanically trained vines have been well detected with 44 % having a good contour extraction and 27 % beeing grouped by two or three. 1

Abstract: The objective of the study is to map and count the individual cabbages at the early growth stage in Sg. Palas, Cameron Highland grown under a mix cropping system and estimate its production. With ground verification, an IKONOS 4 m multispectral imagery acquired on 25 February 2001 was digitally processed at an orthorectified level. A Digital Terrain Model (DTM) was developed and a scanned topographical map was overlaid with IKONOS data to precisely locate the attribute data and map the individual young growing cabbages. Using a supervised and unsupervised classification, less than and above 1.5 month-old cabbages were mapped and quantified. The algorithm and processing technique developed in this study can easily estimate a production of 25,000 cabbages/ha in Sg Palas area. Integrating the data with a Geographic Information System (GIS) may help Cameron Highland farmers to better market their cabbages in the future. The potential use of airborne hyperspectral imaging data such as UPM-TropAIR’s AISA TropAIRMAPTM to map and predict the supply of cabbages should be the next step in precision farming revolution using remote sensing.

www.soil-journal.net/1/287/2015/