Classification of crop-shelter coverage by RGB aerial images: a compendium of experiences and findings.

Image processing is a powerful tool apt to perform selective data extraction from high-content images. In agricultural studies, image processing has been applied to different scopes, among them the classification of crop shelters has been recently considered especially in areas where there is a lack of public control in the building activity. The application of image processing to crop-shelter feature recognition make it possible to automatically produce thematic maps that constitute a basic knowledge for local authorities to cope with environmental problems and for technicians to be used in their planning activity. This paper reviews the authors’ experience in the definition of methodologies, based on the main image processing methods, for crop-shelter feature extraction from aerial digital images. Some experiences of pixel-based and object-oriented methods are described and discussed. The results show that the methodology based on object-oriented methods improves crop-shelter classification and reduces computational time, compared to pixel-based methodologies.

[1]  Claudia Arcidiacono,et al.  IMAGE PROCESSING FOR THE CLASSIFICATION OF CROP SHELTERS , 2008 .

[2]  N. K. Sönmez,et al.  Use of remote sensing and geographic information system technologies for developing greenhouse databases , 2006 .

[3]  Philippe De Maeyer,et al.  An automated satellite image classification design using object-oriented segmentation algorithms: A move towards standardization , 2007, Expert Syst. Appl..

[4]  Simona Consoli,et al.  Remote sensing to estimate ET-fluxes and the performance of an irrigation district in southern Italy , 2006 .

[5]  F. Agüera,et al.  Automatic greenhouse delineation from QuickBird and Ikonos satellite images , 2009 .

[6]  Yun Zhang,et al.  Region based segmentation of QuickBird multispectral imagery through band ratios and fuzzy comparison , 2009 .

[7]  Kazunobu Ishii,et al.  Remote-sensing Technology for Vegetation Monitoring using an Unmanned Helicopter , 2005 .

[8]  Xuexia Chen,et al.  A simple and effective radiometric correction method to improve landscape change detection across sensors and across time , 2005 .

[9]  Patrick E. Clark,et al.  Intermountain plant community classification using Landsat TM and SPOT HRV data. , 2001 .

[10]  M. A. Aguilar,et al.  Using texture analysis to improve per-pixel classification of very high resolution images for mapping plastic greenhouses , 2008 .

[11]  F. M. Danson,et al.  Satellite remote sensing of forest resources: three decades of research development , 2005 .

[12]  Stephen J. Walsh,et al.  Remote sensing of forested wetlands: application of multitemporal and multispectral satellite imagery to determine plant community composition and structure in southeastern USA , 2001, Plant Ecology.

[13]  Chih-Hung Tan,et al.  Use of spectral information for wetland evapotranspiration assessment , 2002 .

[14]  J. P. Marques de Sá,et al.  Pattern Recognition: Concepts, Methods and Applications , 2001 .

[15]  F. Agüera,et al.  Detecting greenhouse changes from QuickBird imagery on the Mediterranean coast , 2006 .

[16]  Stuart R. Phinn,et al.  Natural and anthropogenic changes to mangrove distributions in the Pioneer River Estuary (QLD, Australia) , 2007, Wetlands Ecology and Management.

[17]  J. Clevers,et al.  Combined use of optical and microwave remote sensing data for crop growth monitoring , 1996 .

[18]  Frank Nevens,et al.  Reducing the visual impact of 'greenhouse parks' in rural landscapes , 2008 .

[19]  F. Carvajal,et al.  GREENHOUSES DETECTION USING AN ARTIFICIAL NEURAL NETWORK WITH A VERY HIGH RESOLUTION SATELLITE IMAGE , 2006 .

[20]  Timothy A. Warner,et al.  Utilizing Landsat TM Imagery to Map Greenhouses in Qingzhou, Shandong Province, China , 2004 .

[21]  J. Tenhunen,et al.  On the relationship of NDVI with leaf area index in a deciduous forest site , 2005 .

[22]  David M. Johnson,et al.  Impacts of vegetation dynamics on the identification of land-cover change in a biologically complex community in North Carolina, USA , 2002 .

[23]  Robert H. Fraser,et al.  Automatic Detection of Fire Smoke Using Artificial Neural Networks and Threshold Approaches Applied to AVHRR Imagery , 2001 .

[24]  S. Leblanc,et al.  Derivation and validation of Canada-wide coarse-resolution leaf area index maps using high-resolution satellite imagery and ground measurements , 2002 .

[25]  B. Markham,et al.  Revised Landsat-5 TM radiometric calibration procedures and postcalibration dynamic ranges , 2003, IEEE Trans. Geosci. Remote. Sens..

[26]  Heather M. Cheshire,et al.  A comparison of single date and multitemporal satellite image classifications in a semi-arid grassland , 2001 .

[27]  U. Beisl.  Absolute spectroradiometric calibration of the ADS40 sensor , 2006 .