Object-oriented ensemble classification for polarimetric SAR Imagery using restricted Boltzmann machines
| Autor: | Fachao Qin, Weidong Sun, Jiming Guo |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Object-oriented programming
Boosting (machine learning) 010504 meteorology & atmospheric sciences Pixel business.industry Computer science Deep learning Big data 0211 other engineering and technologies Stacking Boltzmann machine Pattern recognition 02 engineering and technology 01 natural sciences Earth and Planetary Sciences (miscellaneous) Computer vision Artificial intelligence AdaBoost Electrical and Electronic Engineering business 021101 geological & geomatics engineering 0105 earth and related environmental sciences |
| Zdroj: | Remote Sensing Letters. 8:204-213 |
| ISSN: | 2150-7058 2150-704X |
| DOI: | 10.1080/2150704x.2016.1258128 |
| Popis: | A series of deep learning algorithms have recently shown excellent performances in many different fields. Deep models are usually generated by stacking similar modules, e.g., restricted Boltzmann machines (RBMs), and they are especially suitable for discriminating complex objects through the use of ‘big data’. However, object-oriented classification (OOC) for polarimetric synthetic aperture radar (PolSAR) imagery is based on homogeneous regions instead of pixels, which results in a degraded performance for the deep models, as the data volume is inadequate. To solve this problem, we adopt an RBM as the module, and use it to construct an adaptive boosting (AdaBoost) model instead of a stacked deep model, to carry out OOC for PolSAR imagery. The experimental results demonstrate that the proposed model is superior to the stacked RBM model and the other common methods for OOC. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|