Tampere University of Technology

TUTCRIS Research Portal

Performance Comparison of Learned vs. Engineered Features for Polarimetric SAR Terrain Classification

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


Original languageEnglish
Title of host publication2019 41st Photonics & Electromagnetics Research Symposium (PIERS)
Publication statusAccepted/In press - 2019
Publication typeA4 Article in a conference publication
EventPhotonics & Electromagnetics Research Symposium - Rome, Italy
Duration: 17 Jun 201920 Oct 2019


ConferencePhotonics & Electromagnetics Research Symposium
Abbreviated titlePIERS 2019
Internet address


In this work, we propose to use learned features for terrain classification of Polarimetric Synthetic Aperture Radar (PolSAR) images. In the proposed classification framework, the learned features are extracted from sliding window regions using Convolutional Neural Networks (CNNs), and then they are used for the classification with the linear Support Vector Machine (SVM) classifier. The classification performance of the proposed approach is compared with numerous target decomposition theorems (TDs) as the engineered features tested with two classifiers: Collective Network of Binary Classifiers (CNBCs) and SVMs. The experimental evaluations over two commonly used benchmark AIRSAR PolSAR images, San Francisco Bay and Flevoland at L-Band, reveal that the classification performance of the learned features with CNNs outperforms the performance of the engineered features as TDs even the dimension of learned features is the quarter of the engineered features.