Image Retrieval based on Wavelet Computation and Neural Network Classification
WIAMIS '07 Proceedings of the Eight International Workshop on Image Analysis for Multimedia Interactive Services
Classification and annotation of digital photos using optical context data
CIVR '08 Proceedings of the 2008 international conference on Content-based image and video retrieval
Classification of Multispectral High-Resolution Satellite Imagery Using LIDAR Elevation Data
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II
Environmental Modelling & Software
International Journal of Geographical Information Science
The role of Virtual Globes in geoscience
Computers & Geosciences
An optimized framework for seamlessly integrating OGC Web Services to support geospatial sciences
International Journal of Geographical Information Science
Hi-index | 0.00 |
Orthoimages are essential in many Web applications to facilitate the background context that helps to understand other georeferenced information. Catalogues and service registries of Spatial Data Infrastructures do not necessarily register all the services providing access to imagery data on the Web, and it is not easy to automatically identify whether the data offered by a Web service are directly imagery data or not. This work presents a method for an automatic detection of the orthoimage layers offered by Web Map Services. The method combines two types of heuristics. The first one consists in analysing the text in the capabilities document. The second type is content-based heuristics, which analyse the content offered by the Web Map Service layers. These heuristics gather and analyse the colour features of a sample collection of image fragments that represent the offered content. An experiment has been performed over a set of Web Map Service layers, which have been fetched from a repository of capabilities documents gathered from the Web. This has proven the efficiency of the method (precision of 87% and recall of 60%). This functionality has been offered as a Web Processing Service, and it has been integrated within the Virtual Spain project to provide a catalogue of orthoimages and build realistic 3D views.