Semantic segmentation of PolSAR image data using advanced deep learning model

Rajat Garg,Shashi Kumar,Nikunj Bansal,Manish Prateek,Anil Kumar

doi:10.1038/s41598-021-94422-y

Abstract

Urban area mapping is an important application of remote sensing which aims at both estimation and change in land cover under the urban area. A major challenge being faced while analyzing Synthetic Aperture Radar (SAR) based remote sensing data is that there is a lot of similarity between highly vegetated urban areas and oriented urban targets with that of actual vegetation. This similarity between some urban areas and vegetation leads to misclassification of the urban area into forest cover. The present work is a precursor study for the dual-frequency L and S-band NASA-ISRO Synthetic Aperture Radar (NISAR) mission and aims at minimizing the misclassification of such highly vegetated and oriented urban targets into vegetation class with the help of deep learning. In this study, three machine learning algorithms Random Forest (RF), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM) have been implemented along with a deep learning model DeepLabv3+ for semantic segmentation of Polarimetric SAR (PolSAR) data. It is a general perception that a large dataset is required for the successful implementation of any deep learning model but in the field of SAR based remote sensing, a major issue is the unavailability of a large benchmark labeled dataset for the implementation of deep learning algorithms from scratch. In current work, it has been shown that a pre-trained deep learning model DeepLabv3+ outperforms the machine learning algorithms for land use and land cover (LULC) classification task even with a small dataset using transfer learning. The highest pixel accuracy of 87.78% and overall pixel accuracy of 85.65% have been achieved with DeepLabv3+ and Random Forest performs best among the machine learning algorithms with overall pixel accuracy of 77.91% while SVM and KNN trail with an overall accuracy of 77.01% and 76.47% respectively. The highest precision of 0.9228 is recorded for the urban class for semantic segmentation task with DeepLabv3+ while machine learning algorithms SVM and RF gave comparable results with a precision of 0.8977 and 0.8958 respectively.

Highlights

Synthetic Aperture Radar (SAR) is a type of active sensor that generates its energy which is transmitted in the form of electromagnetic waves and receives a part of this energy after interaction with the earth’s s urface[1]
Area C contains a small forest as clear from the decomposed SAR image, but it has been very sparsely captured by Random Forest (RF) and K-Nearest Neighbour (KNN) algorithms while it is almost missed by the Support Vector Machine (SVM) algorithm as depicted in (Fig. 1c–e)
This affects the prediction of traditional machine learning algorithms as well and KNN is worst affected resulting in maximum misclassification of the oriented urban targets as vegetation

Summary

Introduction

Synthetic Aperture Radar (SAR) is a type of active sensor that generates its energy which is transmitted in the form of electromagnetic waves and receives a part of this energy after interaction with the earth’s s urface[1]. While the decomposition methods are used to generate a false-color composite image based on the backscatter values, they often misclassify some urban areas as vegetation due to the diffused scattering type from oriented urban targets. This misclassification can be corrected with the help of semantic segmentation tasks using advanced machine learning algorithms. We have used the Gabor filter, Median filter, Gaussian filter, and Canny edge detector to extract the SAR image features These features combined with the RGB bands of the false-color composite image are used to train the machine learning models for the task of semantic segmentation. Several polarimetric decomposition models have been developed to provide at least three scattering elements within a resolution c ell[23,24,25]

Objectives

Methods

Results

Discussion

Conclusion