Remote Sensing Image Analysis Without Expert Knowledge - A Web-Based Classification Tool On Top of Taverna Workflow Management System
Open Access
- 18 October 2016
- conference paper
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 44 (4) , 042020
Abstract
Providing software solutions via internet has been known for quite some time and is now an increasing trend marketed as "software as a service". A lot of business units accept the new methods and streamlined IT strategies by offering web-based infrastructures for external software usage - but geospatial applications featuring very specialized services or functionalities on demand are still rare. Originally applied in desktop environments, the ILMSimage tool for remote sensing image analysis and classification was modified in its communicating structures and enabled for running on a high-power server and benefiting from Tavema software. On top, a GIS-like and web-based user interface guides the user through the different steps in ILMSimage. ILMSimage combines object oriented image segmentation with pattern recognition features. Basic image elements form a construction set to model for large image objects with diverse and complex appearance. There is no need for the user to set up detailed object definitions. Training is done by delineating one or more typical examples (templates) of the desired object using a simple vector polygon. The template can be large and does not need to be homogeneous. The template is completely independent from the segmentation. The object definition is done completely by the software.Keywords
This publication has 6 references indexed in Scilit:
- Geographic Object-Based Image Analysis – Towards a new paradigmISPRS Journal of Photogrammetry and Remote Sensing, 2014
- Object model and two-stage classification for automated object-based analysis of remote sensing imagery2009
- A survey of image classification methods and techniques for improving classification performanceInternational Journal of Remote Sensing, 2007
- Classification of Mediterranean crops with multisensor data: per-pixel versus per-object statistics and image segmentationInternational Journal of Remote Sensing, 1996
- A review on image segmentation techniquesPattern Recognition, 1993
- A survey on image segmentationPattern Recognition, 1981