A New Method to Improve the Results of Classification Obtained from Compact Polarimetry Data
|
Amir Aghabalaei * , Hamid Ebadi , Yasser Maghsoudi |
K.N.Toosi University of Technology |
|
Abstract: (4156 Views) |
Recently, a new mode is proposed in Dual Polarimetry (DP) imaging systems that is called Compact Polarimetry (CP) which has several important advantages in comparison with Full Polarimetry (FP) such as reduction ability in complexity, cost, mass, and data rate of a Synthetic Aperture RADAR (SAR) system. Despite these advantages, the CP mode, compared to the FP mode, still achieves less information to be extracted from targets. Therefore, accuracies of classification obtained from CP data are lower than those obtained from FP data. In this paper, a new method is proposed to improve the results of classification obtaind by using CP data. For this propose, two ways are considered. First, the CP modes simulated by RADARSAT-2 FP mode, and second, Pseudo Quad Polarimetry (PQ) modes reconstructed by exploited CP modes are combine in the extracted polarimetric feature level. Results of this study show that this combination can be increase the classification accuracies. |
|
Keywords: Compact Polarimetry, Combination in Feature Level, Classification. |
|
Full-Text [PDF 1696 kb]
(1520 Downloads)
|
Type of Study: Research |
Subject:
Aerial Photogrammetry Received: 2016/03/3 | Accepted: 2016/07/3 | Published: 2018/01/10
|
|
|
|
|
Send email to the article author |
|