Back to Search
Start Over
Integration of Contextual Knowledge in Unsupervised Subpixel Classification: Semivariogram and Pixel-Affinity Based Approaches
- Source :
- IndraStra Global.
- Publication Year :
- 2018
- Publisher :
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 2018.
-
Abstract
- This letter investigates the use of coarse-image features for predicting class labels at a given finer spatial scale. In this regard, two unsupervised subpixel mapping approaches, a semivariogram method, and a pixel-affinity based method are proposed. Furthermore, segmentation-based spectral unmixing is explored so as to address the spectral variability and nonconvexity of classes. In addition, the gradient information is employed to resolve uncertainties in the unmixing process. The proposed modifications based on pixel-affinity and semivariogram have produced an accuracy improvement of 5% or more over the state-of-the-art approaches.
- Subjects :
- semivariogram
Pixel
INFORMATION
business.industry
Computer science
subpixel mapping
0211 other engineering and technologies
Hyperspectral imaging
Pattern recognition
02 engineering and technology
IMAGERY
Geotechnical Engineering and Engineering Geology
Subpixel rendering
Class (biology)
Computer Science::Computer Vision and Pattern Recognition
Contextual information
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Artificial intelligence
Electrical and Electronic Engineering
business
Variogram
Image resolution
021101 geological & geomatics engineering
Subjects
Details
- Language :
- English
- ISSN :
- 23813652
- Database :
- OpenAIRE
- Journal :
- IndraStra Global
- Accession number :
- edsair.doi.dedup.....4d5703c70c6d40c2d9b9fad351e30254
- Full Text :
- https://doi.org/10.1002/2014GL061241