Polarimetric calibration of spaceborne and airborne multifrequency SAR data for scattering-based characterization of manmade and natural features

Kumar, Shashi; Babu, Arun; Agrawal, Shefali; Asopa, Udit; Shukla, Shashwat; Maiti, A.

doi:10.1016/j.asr.2021.02.023

Cited by 16 publications

(3 citation statements)

References 94 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The radiometric normalisation and Orthorectification process successfully minimize the radiometric and geometric distortions from the SAR data 54 . To retrieve all the scattering information contributed by different objects in a small area, fully polarimetric quad-pol data are used because retrieval of all the scattering elements within a resolution cell is mathematically and practically rigorous with single or dual polarised SAR data 62 , 63 . The remote sensing community has widely used the fully polarimetric quad-pol SAR data to implement model-based decomposition approaches in the retrieval of scattering parameters 64 – 66 .…”

Section: Resultsmentioning

confidence: 99%

Semantic segmentation of PolSAR image data using advanced deep learning model

Garg

Kumar

Bansal

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

Semantic segmentation of PolSAR image data using advanced deep learning model

Garg

Kumar

Bansal

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Due to crosstalk among polarization channels, phase bias and channel imbalance, there are polarimetric distortions in a PolSAR system. The researchers in 4 tried to estimate and minimize the mentioned distortions through polarimetric calibration of PolSAR images. There is rich scattering information in a PolSAR image.…”

Section: Introductionmentioning

confidence: 99%

Two-step discriminant analysis based multi-view polarimetric SAR image classification with high confidence

Imani

2022

Sci Rep

View full text Add to dashboard Cite

Polarimetric synthetic aperture radar (PolSAR) image classification is a hot topic in remote sensing field. Although recently many deep learning methods such as convolutional based networks have provided great success in PolSAR image classification, but they need a high volume of labeled samples, which are not usually available in practice, or they cause a high computational burden for implementation. In this work, instead of spending cost for network training, the inherent nature of PolSAR image is used for generation of convolutional kernels for extraction of deep and robust features. Moreover, extraction of diverse scattering characteristics contained in the coherency matrix of PolSAR and fusion of their output classification results with a high confidence have high impact in providing a reliable classification map. The introduced method called discriminative features based high confidence classification (DFC) utilizes several approaches to deal with difficulties of PolSAR image classification. It uses a multi-view analysis to generate diverse classification maps with different information. It extracts deep polarimetric-spatial features, consistent and robust with respect to the original PolSAR data, by applying several pre-determined convolutional filters selected from the important regions of image. Convolutional kernels are fixed without requirement to be learned. The important regions are determined with selecting the key points of image. In addition, a two-step discriminant analysis method is proposed to reduce dimensionality and result in a feature space with minimum overlapping and maximum class separability. Eventually, a high confidence decision fusion is implemented to find the final classification map. Impact of multi-view analysis, selection of important regions as fixed convolutional kernels, two-step discriminant analysis and high confidence decision fusion are individually assessed on three real PolSAR images in different sizes of training sets. For example, the proposed method achieves 96.40% and 98.72% overall classification accuracy by using 10 and 100 training samples per class, respectively in L-band Flevoland image acquired by AIRSAR. Generally, the experiments show high efficiency of DFC compared to several state-of-the-art methods especially for small sample size situations.

show abstract

“…

The fully polarimetric SAR (PolSAR) data can be used to analyze the scattering mechanisms from different natural and manmade targets using the amplitude and phase information obtained from the co-polarimetric and cross-polarimetric channels. Different polarimetric decomposition and classification techniques are widely used to extact information from the PolSAR data sets (Kumar et al, 2020;Ullmann et al, 2016), but the polarimetric distortions present in the PolSAR data sets leads to wrong results from the polarimetric decomposition and classification models (Kumar et al, 2021), which in turn result in the ground target misinterpretation (Jung & Park, 2018;Maiti et al, 2021). The most important of the polarimetric distortions is the channel imbalance, crosstalk, and Faraday rotation errors (Babu et al, 2019a).

…”

mentioning

confidence: 99%

Polarimetric Calibration and Spatio‐Temporal Polarimetric Distortion Analysis of UAVSAR PolSAR Data

Babu

Kumar

Agrawal

2022

Earth and Space Science

Self Cite

View full text Add to dashboard Cite

The polarimetric distortions present in the PolSAR datasets leads to unexpected results from the polarimetric decomposition and classification models which in turn results in the ground target misinterpretation. The most important polarimetric distortions in airborne PolSAR datasets are the channel imbalance and crosstalk. The minimization of these polarimetric distortions using polarimetric calibration techniques is very important to carry out the quantitative analysis using PolSAR data, time series analysis and to compare results between different sensors. In the current state of the art, the spatial variability of the polarimetric distortions at different slant-range positions in the dataset were not completely analysed and also the temporal variability of the polarimetric distortions using multiple datasets needs to be more investigated. Therefore, the main objectives of this study were to develop an operational processor to perform the external polarimetric calibration of the L-band UAVSAR system and to analyze the spatio-temporal behavior of the polarimetric distortions. The Polarimetric Distortion Matrix (PDM) was formulated after considering the crosstalk and channel imbalance polarimetric distortions to derive the scattering matrix free from all kinds of polarimetric distortions from the observed scattering matrix. The Quegan, improved Quegan and Ainsworth methods for polarimetric calibration were implemented to solve the PDM. The residual channel imbalance and crosstalk after polarimetric calibration were estimated to compare the calibration efficiency of these methods. After that, a spatio-temporal analysis was carried out with several datasets to assess the spatio-temporal behavior of these polarimetric distortions. The polarimetric signatures and the coherency Matrix behaviour of the trihedral corner reflectors were used to analyse the ground target characterization improvement after polarimetric calibration. The results obtained from this study revealed that the crosstalk is the major cause for the polarimetric distortions, the channel imbalance and phase bias present in the datasets were not high. From the spatio-temporal analysis, it was found that the variability of these polarimetric distortions both in spatial and temporal domains were minimum and can be discarded without causing any considerable error in the polarimetric calibration process.

show abstract

Polarimetric calibration of spaceborne and airborne multifrequency SAR data for scattering-based characterization of manmade and natural features

Cited by 16 publications

References 94 publications

Semantic segmentation of PolSAR image data using advanced deep learning model

Semantic segmentation of PolSAR image data using advanced deep learning model

Two-step discriminant analysis based multi-view polarimetric SAR image classification with high confidence

Polarimetric Calibration and Spatio‐Temporal Polarimetric Distortion Analysis of UAVSAR PolSAR Data

Contact Info

Product

Resources

About