scholarly journals Novel Clustering Schemes for Full and Compact Polarimetric SAR Data: An Application for Rice Phenology Characterization

2020 ◽  
Author(s):  
Subhadip Dey ◽  
Avik Bhattacharya ◽  
Debanshu Ratha ◽  
Dipankar Mandal ◽  
Heather McNairn ◽  
...  
Keyword(s):  
Temporal Analysis ◽  
Test Site ◽  
Unsupervised Clustering ◽  
Degree Of Polarization ◽  
Phenological Stages ◽  
Sar Images ◽  
Growing Period ◽  
Entropy Parameter ◽  
Sar Data ◽  
Type Parameter

<div>Information on rice phenological stages from Synthetic Aperture Radar (SAR) images is of prime interest for in-season monitoring. Often, prior in-situ measurements of phenology are not available. In such situations, unsupervised clustering of SAR images might help in discriminating phenological stages of a crop throughout its growing period. Among the existing unsupervised clustering techniques using full-polarimetric (FP) SAR images, the eigenvalue-eigenvector based roll-invariant scattering-type parameter, and the scattering entropy parameter are widely used in the literature. In this study, we utilize a unique target scattering-type parameter, which jointly uses the Barakat degree of polarization and the elements of the polarimetric coherency matrix. Likewise, we also utilize an equivalent parameter proposed for compact-polarimetric (CP) SAR data. These scattering-type parameters are analogous to the Cloude-Pottier's parameter for FP SAR data and the ellipticity parameter for CP SAR data. Besides this, we also introduce new clustering schemes for both FP and CP SAR data for segmenting diverse scattering mechanisms across the phenological stages of rice. In this study, we use the RADARSAT-2 FP and simulated CP SAR data acquired over the Indian test site of Vijayawada under the Joint Experiment for Crop Assessment and Monitoring (JECAM) initiative. The temporal analysis of the scattering-type parameters and the new clustering schemes help us to investigate detailed scattering characteristics from rice across its phenological</div><div>stages.</div>

scholarly journals Novel Clustering Schemes for Full and Compact Polarimetric SAR Data: An Application for Rice Phenology Characterization

2020 ◽  
Author(s):  
Subhadip Dey ◽  
Avik Bhattacharya ◽  
Debanshu Ratha ◽  
Dipankar Mandal ◽  
Heather McNairn ◽  
...  
Keyword(s):  
Temporal Analysis ◽  
Test Site ◽  
Unsupervised Clustering ◽  
Degree Of Polarization ◽  
Phenological Stages ◽  
Sar Images ◽  
Growing Period ◽  
Entropy Parameter ◽  
Sar Data ◽  
Type Parameter

<div>Information on rice phenological stages from Synthetic Aperture Radar (SAR) images is of prime interest for in-season monitoring. Often, prior in-situ measurements of phenology are not available. In such situations, unsupervised clustering of SAR images might help in discriminating phenological stages of a crop throughout its growing period. Among the existing unsupervised clustering techniques using full-polarimetric (FP) SAR images, the eigenvalue-eigenvector based roll-invariant scattering-type parameter, and the scattering entropy parameter are widely used in the literature. In this study, we utilize a unique target scattering-type parameter, which jointly uses the Barakat degree of polarization and the elements of the polarimetric coherency matrix. Likewise, we also utilize an equivalent parameter proposed for compact-polarimetric (CP) SAR data. These scattering-type parameters are analogous to the Cloude-Pottier's parameter for FP SAR data and the ellipticity parameter for CP SAR data. Besides this, we also introduce new clustering schemes for both FP and CP SAR data for segmenting diverse scattering mechanisms across the phenological stages of rice. In this study, we use the RADARSAT-2 FP and simulated CP SAR data acquired over the Indian test site of Vijayawada under the Joint Experiment for Crop Assessment and Monitoring (JECAM) initiative. The temporal analysis of the scattering-type parameters and the new clustering schemes help us to investigate detailed scattering characteristics from rice across its phenological</div><div>stages.</div>

Novel Clustering Schemes for Full and Compact Polarimetric SAR Data: A Case Study for Rice Phenology Characterization

2020 ◽  
Author(s):  
Subhadip Dey ◽  
Avik Bhattacharya ◽  
Debanshu Ratha ◽  
Dipankar Mandal ◽  
Heather McNairn ◽  
...  
Keyword(s):  
Morphological Characteristics ◽  
Temporal Analysis ◽  
Crop Growth ◽  
Unsupervised Clustering ◽  
Degree Of Polarization ◽  
Growth Stages ◽  
Phenological Stages ◽  
Sar Images ◽  
Sar Data ◽  
Type Parameter

Information on rice phenological stages from Synthetic Aperture Radar (SAR)images is of prime interest for in-season monitoring. Often, prior in-situ measurements of phenology are not available. In such situations, unsupervised clustering of SAR images might help in discriminating phenological stages of a crop throughout its growing period. Among the existing unsupervised clustering techniques using full-polarimetric (FP) SAR images, the eigenvalue-eigenvector based roll-invariant scattering-type parameter, and the scattering entropy parameter are widely used in the literature. In this study, we utilize a unique target scattering-type parameter, which jointly uses the Barakat degree of polarization and the elements of the polarimetric coherency matrix. In particular, the degree of polarization attributes to scattering randomness from a target. The scattering randomness in crops increases with advancements in its growth stages due to the development of branches and foliage. Hence, the degree of polarization varies with changes in the crop growth stages. Besides, the elements of the coherency matrices are directly related to the crop geometry as well as soil and crop water content. There-fore, this complementarity information captures the scattering randomness at each crop growth stage while taking into account diverse crop morphological characteristics. Likewise, we also utilize an equivalent parameter proposed for compact-polarimetric (CP) SAR data. These scattering-type parameters are analogous to the Cloude-Pottier’s parameter for FP SAR data and the ellipticity parameter for CP SAR data. Besides this, we also introduce new clustering schemes for both FP and CP SAR data for segmenting diverse scattering mechanisms across the phenological stages of rice. In this study, we use the RADARSAT-2 FP and simulated CP SAR data acquired over the Indian test site of Vijayawada under the Joint Experiment for Crop Assessment and Monitoring (JECAM) initiative. The temporal analysis of the scattering-type parameters and the new clustering schemes help us to investigate detailed scattering characteristics from rice across its phenological stages.<div>(Submitted to ISPRS journal)</div>

scholarly journals Differentially Deep Subspace Representation for Unsupervised Change Detection of SAR Images

2019 ◽  
Vol 11 (23) ◽  
pp. 2740 ◽  
Author(s):  
Bin Luo ◽  
Chudi Hu ◽  
Xin Su ◽  
Yajun Wang
Keyword(s):  
Principal Component Analysis ◽  
Change Detection ◽  
Principal Component ◽  
Temporal Analysis ◽  
Component Analysis ◽  
Sar Images ◽  
Linear Change ◽  
Non Linear ◽  
Multi Temporal ◽  
Sar Data

Temporal analysis of synthetic aperture radar (SAR) time series is a basic and significant issue in the remote sensing field. Change detection as well as other interpretation tasks of SAR images always involves non-linear/non-convex problems. Complex (non-linear) change criteria or models have thus been proposed for SAR images, instead of direct difference (e.g., change vector analysis) with/without linear transform (e.g., Principal Component Analysis, Slow Feature Analysis) used in optical image change detection. In this paper, inspired by the powerful deep learning techniques, we present a deep autoencoder (AE) based non-linear subspace representation for unsupervised change detection with multi-temporal SAR images. The proposed architecture is built upon an autoencoder-like (AE-like) network, which non-linearly maps the input SAR data into a latent space. Unlike normal AE networks, a self-expressive layer performing like principal component analysis (PCA) is added between the encoder and the decoder, which further transforms the mapped SAR data to mutually orthogonal subspaces. To make the proposed architecture more efficient at change detection tasks, the parameters are trained to minimize the representation difference of unchanged pixels in the deep subspace. Thus, the proposed architecture is namely the Differentially Deep Subspace Representation (DDSR) network for multi-temporal SAR images change detection. Experimental results on real datasets validate the effectiveness and superiority of the proposed architecture.

scholarly journals Joint Use of Scattered and Received Wave Polarization Information for Target Characterization and Scattering Power Decomposition

2020 ◽  
Author(s):  
Alejandro C. Frery ◽  
Debanshu Ratha ◽  
Avik Bhattacharya ◽  
Dipankar Mandal ◽  
Subhadip Dey
Keyword(s):  
Covariance Matrix ◽  
Scattered Wave ◽  
Degree Of Polarization ◽  
Total Power ◽  
Geometrical Factor ◽  
Wave Polarization ◽  
Decomposition Techniques ◽  
Target Characterization ◽  
Sar Data ◽  
Type Parameter

This manuscript was submitted on 31 December 2019 to IEEE Transactions on Geoscience and Remote Sensing.<br><br>Abstract: Incoherent target decomposition techniques provide unique scattering information from polarimetric SAR data either by fitting appropriate scattering models or by optimizing the ``received" wave intensity through the diagonalization of the coherency (or covariance) matrix. Hence, the information provided by the ``scattered" wave might be neglected. This scattered wave information can be well utilized to gain complete polarimetric information for numerous applications. In this study, a new roll-invariant scattering-type parameter is introduced, which jointly uses the degree of polarization as the ``scattered" wave information and the elements of the covariance matrix as the ``received" wave information from both full-polarimetric (FP) and compact-polarimetric (CP) SAR data. This scattering-type parameter, which is comparable to that of the Cloude $\alpha$ for FP SAR data and the ellipticity parameter $\chi$ for CP SAR data, can be well utilized to characterize various targets. Furthermore, this new scattering-type parameter is adequately utilized to obtain a non-model based three-component scattering power decomposition technique. The double-bounce and the odd-bounce scattering powers are obtained by modulating the total polarized power by a proper geometrical factor easily derived using the new scattering-type parameter for both FP and CP SAR data. Moreover, due to its natural and direct formulation, the decomposition scattering powers are non-negative and roll-invariant while the total power is conserved. The proposed method is qualitatively and quantitatively assessed utilizing the L-band ALOS-2 and C-band Radarsat-2 FP and the associated simulated CP SAR data.

scholarly journals Mid-season Crop Classification Using Dual-, Compact-, and Full-polarization in Preparation for the Radarsat Constellation Mission (RCM)

2019 ◽  
Vol 11 (13) ◽  
pp. 1582 ◽  
Author(s):  
Mahdianpari ◽  
Mohammadimanesh ◽  
McNairn ◽  
Davidson ◽  
Rezaee ◽  
...  
Keyword(s):  
Variable Importance ◽  
Sar Images ◽  
Object Based ◽  
Multi Temporal ◽  
Importance Analysis ◽  
Crop Mapping ◽  
Crop Classification ◽  
Sar Data ◽  
Highly Correlated ◽  
Marginal Improvement

Despite recent research on the potential of dual- (DP) and full-polarimetry (FP) Synthetic Aperture Radar (SAR) data for crop mapping, the capability of compact polarimetry (CP) SAR data has not yet been thoroughly investigated. This is of particular concern, given the availability of such data from RADARSAT Constellation Mission (RCM) shortly. Previous studies have illustrated potential for accurate crop mapping using DP and FP SAR features, yet what contribution each feature makes to the model accuracy is not well investigated. Accordingly, this study examined the potential of the early- to mid-season (i.e., May to July) RADARSAT-2 SAR images for crop mapping in an agricultural region in Manitoba, Canada. Various classification scenarios were defined based on the extracted features from FP SAR data, as well as simulated DP and CP SAR data at two different noise floors. Both overall and individual class accuracies were compared for multi-temporal, multi-polarization SAR data using the pixel- and object-based random forest (RF) classification schemes. The late July C-band SAR observation was the most useful data for crop mapping, but the accuracy of single-date image classification was insufficient. Polarimetric decomposition features extracted from CP and FP SAR data produced relatively equal or slightly better classification accuracies compared to the SAR backscattering intensity features. The RF variable importance analysis revealed features that were sensitive to depolarization due to the volume scattering are the most important FP and CP SAR data. Synergistic use of all features resulted in a marginal improvement in overall classification accuracies, given that several extracted features were highly correlated. A reduction of highly correlated features based on integrating the Spearman correlation coefficient and the RF variable importance analyses boosted the accuracy of crop classification. In particular, overall accuracies of 88.23%, 82.12%, and 77.35% were achieved using the optimized features of FP, CP, and DP SAR data, respectively, using the object-based RF algorithm.

scholarly journals Brief Communication: Rapid mapping of landslide events: the 3 December 2013 Montescaglioso landslide, Italy

2014 ◽  
Vol 14 (7) ◽  
pp. 1835-1841 ◽  
Author(s):  
A. Manconi ◽  
F. Casu ◽  
F. Ardizzone ◽  
M. Bonano ◽  
M. Cardinali ◽  
...  
Keyword(s):  
High Resolution ◽  
Synthetic Aperture Radar ◽  
Southern Italy ◽  
Surface Deformation ◽  
Synthetic Aperture ◽  
Sar Images ◽  
Main Road ◽  
Rapid Mapping ◽  
X Band ◽  
Sar Data

Abstract. We present an approach to measure 3-D surface deformations caused by large, rapid-moving landslides using the amplitude information of high-resolution, X-band synthetic aperture radar (SAR) images. We exploit SAR data captured by the COSMO-SkyMed satellites to measure the deformation produced by the 3 December 2013 Montescaglioso landslide, southern Italy. The deformation produced by the deep-seated landslide exceeded 10 m and caused the disruption of a main road, a few homes and commercial buildings. The results open up the possibility of obtaining 3-D surface deformation maps shortly after the occurrence of large, rapid-moving landslides using high-resolution SAR data.

Monitoring Three Gorge Area Landslide currently movement by Mutilplatform SAR Interferometry

2020 ◽  
Author(s):  
Tao Li ◽  
Yangmao Wen ◽  
Lulu Chen ◽  
Jinge Wang
Keyword(s):  
High Resolution ◽  
Surface Deformation ◽  
Test Site ◽  
Deformation Monitoring ◽  
Sar Interferometry ◽  
Sar Image ◽  
Landslide Area ◽  
Sar Images ◽  
The Past ◽  
Huangtupo Landslide

&lt;p&gt;Three Gorge area landslide hazards developed very fast after the Dam started to impound the water since 2007. There were lots of research literatures concentrated on the Badong Huangtupo Landslide area for the whole city center had to change its position in 2009. Several literatures used Envisat SAR images time series to monitoring the surface deformation from 2008~2010. The results showed good consistent with the water level changes and precipitation. &amp;#160;The high resolution TerraSAR Spotlight images had been used to monitoring the Shuping landslide and Fanjiaping landslide area in Zigui country from 2009~2012,the InSAR results showed good details of the landslide boundary and deformation rate with DInSAR technology.&lt;/p&gt;&lt;p&gt;This paper studies several landslide area in the Three Gorge by InSAR technology in the past few years, such as Huangtupo, Huanglashi , Daping and &amp;#160;Baiheping landslide area , etc. al . The high resolution SAR images covered Badong and Wushan area have been collected, including the Sentinel-1, TerraSAR, RadarSAT-2, ALOS-2 SAR images. The high resolution topography in those landslide area have been collected both by UAV lidar and high resolution topography map.&lt;/p&gt;&lt;p&gt;The Huangtupo landslide area changed a lot in the past 3 years with the buildings ruins cleared and red soil covered by the local government. The time series results by Sentinel data in this area shows the big changes but could not derive reasonable deformation results.&lt;/p&gt;&lt;p&gt;Three Gorges Research Center for Geo-hazards (TGRC) of China University of Geosciences(CUG) built the Badong field test site in Huangtupo landslide area. This test site is composed with a tunnel group and a series of monitoring system including the inside sensors, surface deformation monitoring sensors and so on. In this paper, we mounted several new designed dihedral corner reflectors on the Huangtupo landslide area for high precision deformation monitoring by InSAR. Both the &amp;#160;ascending and the &amp;#160;descending orbit data of RadarSAT-2 high resolution SAR image &amp;#160;and TerraSAR Spotlight images have been collected in this field.&lt;/p&gt;&lt;p&gt;The preliminary results from those new acquiring SAR data series show that the traditional landslide area such as Huanglashi , Daping, Baiheping are all moving slowly with good coherence in SAR image series. &amp;#160;The poor vegetation coverage in those landslide area helped to get the credible &amp;#160;InSAR results. The high resolution DEM is the critical elements for the DInSAR techniques in those landslide area. The steep&amp;#160; topography in those landslide area distorted the SAR images correspondingly.&lt;/p&gt;&lt;p&gt;Our results shows that it is possible to use ascending and descending high resolution SAR images to monitor the landslide area with mm level precision, while the vegetation is not so dense. High resolution SAR interferometry helped a lot for the landslide boundary detection and detailed analysis. The lower resolution SAR images such as Sentinel-1 still could provide some deformation results in landslide area, but it need more auxiliary data to interpret the results.&lt;/p&gt;

Sign in / Sign up

Export Citation Format

Share Document