eCognition Multi-resolution segmentation and object export
The multiresolution segmentation algorithm consecutively merges pixels. Thus it is a bottom-up segmentation algorithm based on a pairwise region merging technique. Multiresolution segmentation is an optimization procedure which, for a given number of image objects, minimizes the average heterogeneity and maximizes their respective homogeneity. This homogeneity criterion is defined as a combination of spectral homogeneity and shape homogeneity.
The Multiresolution Segmentation algorithm locally minimizes the average heterogeneity of image objects for a given resolution of image objects. This processing block, segments images with provided scale (homogeneity threshold) and exports segmented polygons as .shp file.
Use Cases: This block can be used as an initial step in landcover, vegetation, water, urban area analysis, and change detection workflows
- Any projected aerial or satellite image
- Projected image (non-geographic coordinate system)
- Format : GeoTiff
- Image band : 3-5 bands (RGB+)
- VAR_SP - Scale parameter (default: 42): The Scale Parameter is an abstract term that determines the maximum allowed heterogeneity for the resulting image objects. For heterogeneous data, the resulting objects for a given scale parameter will be smaller than in more homogeneous data. By modifying the value in the Scale Parameter value you can vary the size of image objects.
- VAR_Shape (default: 0.1, range: 0…1): The value of the Shape field modifies the relationship between shape and color criteria.
- VAR_Compactness (default: 0.5, range: 0…1): The compactness criterion is used to optimize image objects with regard to compactness.
- VAR_SIMP (default: 1, possible values: 0 or 1): Flag to control how segmented image objects are exported. 0 - means polygon will follow pixel outline of the image object, 1 - means simplified/smoothed shape.
- The output will be a Shapefile (.shp) with 2D polygons
Terms & Conditions
View the End User License Agreement conditions.