Customized Image Object Fusion
The ‘image object fusion’ algorithm in eCognition offers user a way to generate customized object fusion approaches or in other words to execute a customized segmentation. The concept of ‘image object fusion’ algorithm is complex. Christian Weise generated a customized algorithm (CA) ‘customized image object fusion’ to makes the life easier to use the ‘image object fusion’ algorithm. Please note, the initial name of the customized algorithm (in 2011) was ‘multiple object difference conditions-based fusion’ … quote from Christian: the worst algorithm name ever ;-)
The unique feature of this algorithm is to combine several conditions (strictly speaking several feature differences) with surface tension (common border). As a result, the algorithm will generate large homogeneous objects without losing small contrast objects (see image above). On the bottom line, users can define their own segmentation strategy with it.
To use the ‘customized image object fusion’ please download the customized algorithm and load it into your project, after it you will find the ‘customized image object fusion’ in the algorithm list. The 'Example Project - Customized Image Object Fusion' provides use case examples and some parameter hints.
Interesting related content:
- eCognition Deconstructed video: Image Object Fusion
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