The e-ROSA project seeks to build a shared vision of a future sustainable e-infrastructure for research and education in agriculture in order to promote Open Science in this field and as such contribute to addressing related societal challenges. In order to achieve this goal, e-ROSA’s first objective is to bring together the relevant scientific communities and stakeholders and engage them in the process of coelaboration of an ambitious, practical roadmap that provides the basis for the design and implementation of such an e-infrastructure in the years to come.
This website highlights the results of a bibliometric analysis conducted at a global scale in order to identify key scientists and associated research performing organisations (e.g. public research institutes, universities, Research & Development departments of private companies) that work in the field of agricultural data sources and services. If you have any comment or feedback on the bibliometric study, please use the online form.
You can access and play with the graphs:
- Evolution of the number of publications between 2005 and 2015
- Map of most publishing countries between 2005 and 2015
- Network of country collaborations
- Network of institutional collaborations (+10 publications)
- Network of keywords relating to data - Link
MAPPING LAND COVER TYPES FROM VERY HIGH SPATIAL RESOLUTION IMAGERY: AUTOMATIC APPLICATION OF AN OBJECT BASED CLASSIFICATION SCHEME
Although geographic object based image analysis (GEOBIA) has been successfully applied to derive local maps (1-10s km(2)) from very high spatial resolution (VHR) image data (pixels < 1.0 x 1.0 m), its potential for automatically mapping large areas remains unknown. The aim of this study was to create and apply a GEOBIA method to automatically map land cover classes in subsets with different environmental and land cover characteristics from VHR image data. Airborne Vexcel Ultracam-D image data with four multi-spectral bands and 0.25 m pixels were captured for the study area, located 50 km from Melbourne, Victoria, Australia. Five subsets showing different environments and characteristics were selected for the study. Four of them were used to create a GEOBIA classification method for mapping land cover types. A step-wise approach was adopted, where individual steps of segmentation and classification were used to establish a contextual knowledge base. Thus, context features became useful for classifying land cover types. The following land cover types were mapped from the five subsets: woody vegetation, non-woody vegetation; water bodies, bare ground, urban features and agricultural areas. The overall accuracy of the four land cover maps used to develop the GEOBIA classification scheme was 77.5%. The classification accuracy was calculated using 100 validation sites per land cover class, visually identified from the Ultracam-D data. Finally, the effectiveness of replicating the GEOBIA classification scheme was tested against the independent fifth subset. This classification produced very similar results, with an overall accuracy of 74.8%, which indicates that the developed GEOBIA classification scheme may be automatically applied to other independent areas, and potentially for larger spatial extent mapping.
Inappropriate format for Document type, expected simple value but got array, please use list format