Size-Constrained Region Merging: A New Tool to Derive Basic Landcover Units from Remote Sensing Imagery

Details Size-Constrained Region Merging: A New Tool to Derive Basic Landcover Units from Remote Sensing Imagery Size-Constrained Region Merging: A New Tool to Derive Basic Landcover Units from Remote Sensing Imagery

Sep 2004

adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2004esasp.553e...8c&link_type=abstract

Proceedings of ESA-EUSC 2004 - Theory and Applications of Knowledge-Driven Image Information Mining with Focus on Earth Observa

Statistics

Applications

Image Segmentation, Object-Oriented Image Analysis, Landcover Mapping

Scientific paper

Landcover maps typically represent the territory as a mosaic of contiguous units "polygons- that are assumed to correspond to geographic entities" like e.g. lakes, forests or villages-. They may also be viewed as representing a particular level of a landscape hierarchy where each polygon is a holon - an object made of subobjects and part of a superobject. The focal level portrayed in the map is distinguished from other levels by the average size of objects compounding it. Moreover, the focal level is bounded by the minimum size that objects of this level are supposed to have. Based on this framework, we have developed a segmentation method that defines a partition on a multiband image such that i) the mean size of segments is close to the one specified; ii) each segment exceeds the required minimum size; and iii) the internal homogeneity of segments is maximal given the size constraints. This paper briefly describes the method, focusing on its region merging stage. The most distinctive feature of the latter is that while the merging sequence is ordered by increasing dissimilarity as in conventional methods, there is no need to define a threshold on the dissimilarity measure between adjacent segments.

Affiliated with

Also associated with

No associations

Rating

Size-Constrained Region Merging: A New Tool to Derive Basic Landcover Units from Remote Sensing Imagery does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Size-Constrained Region Merging: A New Tool to Derive Basic Landcover Units from Remote Sensing Imagery, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Size-Constrained Region Merging: A New Tool to Derive Basic Landcover Units from Remote Sensing Imagery will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-1064371