23 January 2002 Advanced knowledge-based methodology for the training phase within the classification process of remote sensing imagery
Author Affiliations +
Abstract
The emphasis of this paper will be on an advanced knowledge-based methodology for the training phase within the change detection process. Firstly, we will demonstrate an improved and flexible methodology for defining and describing training areas in the course of a change detection process using knowledge-based image analysis techniques (Erdas Imagine Expert Classifier). Using the GIS-database which comprises several data sources at point of time t0 the outlines of the desired object classes will be determined and rated according to their accuracy. Combining these information with the image data of the first phase (t1), we are entering the first training stage. Here, not only a single standard object signature (reflectance) but a large amount of parameters is checked. For each parameter the inference mechanism automatically checks the separability for different object classes and thus evaluates the suitability of each signature. As an output of the classification stage - again applying knowledge-based rules - we obtain probability vectors which decide in favor of a confirmation, modification or an elimination of the given outlines for the specific class. The new outlines and up-dated ancillary data are put into the next training phase. Due to possibly changed image properties it is meaningful to test all signatures for the given outlines again, and proceed as described above. In conclusion it can be stated that the proposed knowledge-based method and its implementation has been proved to be a very valuable and reliable method for environmental change detection purposes.
© (2002) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ulrich Michel, Ulrich Michel, } "Advanced knowledge-based methodology for the training phase within the classification process of remote sensing imagery", Proc. SPIE 4545, Remote Sensing for Environmental Monitoring, GIS Applications, and Geology, (23 January 2002); doi: 10.1117/12.453660; https://doi.org/10.1117/12.453660
PROCEEDINGS
8 PAGES


SHARE
Back to Top