Stddev Split Segmentation
The algorithm ‘stddev split segmentation’ is a C++ implementation of the customized algorithm ‘split objects based on StdDev’ generated by Christian Weise in 2012. Both algorithms use the ‘contrast split segmentation’ to split a given image object domain by contrast and stop the splitting as soon as a defined standard deviation is reached.
This segmentation approach is helpful on surface data to find surface edges etc. The example project contains two use cases of the algorithm and offers the user an environment to test the algorithm. The rule set also contains the customized algorithm ‘split objects based on StdDev’ for re-engineering the 'stddev split segmentation'.
- 'Step Size' parameter = Measure of accuracy. Smaller values will result to “better” object outlines. It represents the (gray) value which the algorithm increased systematically (starting from min value of selected input layer) to split the object domain
- 'Maximum output' parameter = Measure of Size. Defines the maximum allowed standard deviation for created objects. Smaller values will result to smaller objects.
Was this article helpful?
Articles in this section
- 3D Powerline Vegetation Risk Analysis
- Python Hexagon Segmentation
- eCognition Oil Palm Application (1.3) Architect Solution
- Architect Solution - Power Line Risk Area Extraction
- Pixel-Based Object Resizing Surface Tension Artificial
- Pixel-Based Object Resizing Object Generalization Complex Landcover
- Building Generalization
- Customized Image Object Fusion
- Hexagon Segmentation
- Clearance Mapping around Powerlines