Back to Search
Start Over
Combining transductive and active learning to improve object-based classification of remote sensing images
Combining transductive and active learning to improve object-based classification of remote sensing images
- Source :
- Remote Sensing Letters, Remote Sensing Letters, Taylor and Francis, 2016, 7 (4), pp.358-367. ⟨10.1080/2150704X.2016.1142678⟩
- Publication Year :
- 2016
- Publisher :
- HAL CCSD, 2016.
-
Abstract
- International audience; In this letter, we propose a new active transductive learning (ATL) framework for object-based classification of satellite images. The framework couples graph-based label propagation with active learning (AL) to exploit positive aspects of the two learning settings. The transductive approach considers both labelled and unlabelled image objects to perform its classification as they are all available at training time while the AL strategy smartly guides the construction of the training set employed by the learner. The proposed framework was tested in the context of a land cover classification task using RapidEye optical imagery. A reference land cover map was elaborated over the whole study area in order to get reliable information about the performance of the ATL framework. The experimental evaluation under- lines that, with a reasonable amount of training data, our framework outperforms state of the art classification methods usually employed in the field of remote sensing.
- Subjects :
- 010504 meteorology & atmospheric sciences
Exploit
Computer science
Training time
0211 other engineering and technologies
02 engineering and technology
Land cover
Machine learning
computer.software_genre
01 natural sciences
RAPIDEYE
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]
Earth and Planetary Sciences (miscellaneous)
Electrical and Electronic Engineering
021101 geological & geomatics engineering
0105 earth and related environmental sciences
Remote sensing
Training set
[INFO.INFO-DB]Computer Science [cs]/Databases [cs.DB]
business.industry
Object based
15. Life on land
[INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR]
Graph (abstract data type)
Classification methods
Artificial intelligence
business
computer
Label propagation
Subjects
Details
- Language :
- English
- ISSN :
- 2150704X and 21507058
- Database :
- OpenAIRE
- Journal :
- Remote Sensing Letters, Remote Sensing Letters, Taylor and Francis, 2016, 7 (4), pp.358-367. ⟨10.1080/2150704X.2016.1142678⟩
- Accession number :
- edsair.doi.dedup.....d6bde7d096e869c252499f369866a230
- Full Text :
- https://doi.org/10.1080/2150704X.2016.1142678⟩