This title appears in the Scientific Report :
2011
Please use the identifier:
http://dx.doi.org/10.1127/1432-8364/2011/0085 in citations.
Object-based Change Detection
Object-based Change Detection
The iteratively reweighted multivariate alteration detection (IR-MAD) has shown to be a very useful tool for detecting changes in imagery acquired over the same area but at different times. However, applying the paradigm of object-based image analysis (OBIA) leads to the problem how to connect corre...
Saved in:
Personal Name(s): | Listner, C. |
---|---|
Niemeyer, I. | |
Contributing Institute: |
Nukleare Entsorgung; IEK-6 |
Published in: | Photogrammetrie, Fernerkundung, Geoinformation, 2011 (2011) S. 233 - 245 |
Imprint: |
Stuttgart
Schweizerbart
2011
|
Physical Description: |
233 - 245 |
DOI: |
10.1127/1432-8364/2011/0085 |
Document Type: |
Journal Article |
Research Program: |
Nukleare Sicherheitsforschung |
Series Title: |
Photogrammetrie, Fernerkundung, Geoinformation
4 |
Subject (ZB): | |
Publikationsportal JuSER |
The iteratively reweighted multivariate alteration detection (IR-MAD) has shown to be a very useful tool for detecting changes in imagery acquired over the same area but at different times. However, applying the paradigm of object-based image analysis (OBIA) leads to the problem how to connect corresponding objects extracted from images recorded at two different times. Moreover, the huge number of object features available in OBIA results in numerical instabilities within the MAD method due to near-singular covariance matrices. The paper introduces recent developments for object-based change detection. First, a new approach to segmentation for object-based change detection will be presented: The algorithm segments the first image using the multiresolution segmentation. Assigned to the second image, all segmentation merges are checked for consistency and removed if the check fails. Second, the paper shows how to address the numerical problems in the MAD algorithm by regularisation as well as by dimensionality reduction using Principal Component Analysis (PCA). It will be demonstrated how to integrate the adapted segmentation and IR-MAD into the object-based change detection workflow. |