Original Articles
30 September 2010

CLASSIFICATION OF CROP-SHELTER COVERAGE BY RGB AERIAL IMAGES: A COMPENDIUM OF EXPERIENCES AND FINDINGS

Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.
1923
Views
868
Downloads

Authors

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.

Altmetrics

Downloads

Download data is not yet available.

Citations

How to Cite



“CLASSIFICATION OF CROP-SHELTER COVERAGE BY RGB AERIAL IMAGES: A COMPENDIUM OF EXPERIENCES AND FINDINGS” (2010) Journal of Agricultural Engineering, 41(3), pp. 1–11. doi:10.4081/jae.2010.3.1.