Copertina

Feature-Level Fusion of Polarized SAR and Optical Images Based on Random Forest and Conditional Random Fields

Salvato in:
Pubblicato in:Remote Sensing vol. 13, no. 7 (2021), p. 1323
Autore principale: Kong, Yingying
Altri autori: Biyuan Yan, Liu, Yanjuan, Leung, Henry, Peng, Xiangyang
Pubblicazione:
MDPI AG
Soggetti:
Feature extraction
Machine learning
Vegetation
Accuracy
Experiments
Classification
Synthetic aperture radar
Support vector machines
Color
Decomposition
Image classification
Decision trees
Object recognition
Land cover
Datasets
Conditional random fields
Remote sensing
Accesso online:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
Abstract:In terms of land cover classification, optical images have been proven to have good classification performance. Synthetic Aperture Radar (SAR) has the characteristics of working all-time and all-weather. It has more significant advantages over optical images for the recognition of some scenes, such as water bodies. One of the current challenges is how to fuse the benefits of both to obtain more powerful classification capabilities. This study proposes a classification model based on random forest with the conditional random fields (CRF) for feature-level fusion classification using features extracted from polarized SAR and optical images. In this paper, feature importance is introduced as a weight in the pairwise potential function of the CRF to improve the correction rate of misclassified points. The results show that the dataset combining the two provides significant improvements in feature identification when compared to the dataset using optical or polarized SAR image features alone. Among the four classification models used, the random forest-importance_ conditional random fields (RF-Im_CRF) model developed in this paper obtained the best overall accuracy (OA) and Kappa coefficient, validating the effectiveness of the method.
ISSN:2072-4292
DOI:10.3390/rs13071323
Fonte:Advanced Technologies & Aerospace Database