Visualization of and software for omnibus test based change detected in a time series of polarimetric SAR data |
Allan Aasbjerg Nielsen, Knut Conradsen, Henning Skriver, Morton John Canty
|
Abstract | Based on an omnibus likelihood ratio test statistic for the equality of several variance-covariance matrices following the complex Wishart distribution and a factorization of this test statistic with associated p-values, change analysis in a time series of multilook polarimetric SAR data in the covariance matrix representation is carried out. The omnibus test statistic and its factorization detect if and when change occurs. Using airborne EMISAR and spaceborne RADARSAT 2 data this paper focuses on change detection based on the p-values, on visualization of change at pixel as well as segment level, and on computer software. |
Keywords | Complex covariance matrix test statistic, complex Wishart distribution, multitemporal SAR data, quad polarization, full polarization, dual polarization, remote sensing change detection, visualization. |
Type | Journal paper [With referee] |
Journal | Canadian Journal of Remote Sensing |
Year | 2017 Vol. 43 No. 6 pp. 582-592 |
Note | SAR input images to wcRjl and wishart_change_Q etc are images of the (row-wise) upper-right elements of the covariance or coherency matrix, e.g. for full polarimetry: a vector with nine real (i.e., non-complex) elements, namely [ShhShh* Re(ShhShv*) Im(ShhShv*) Re(ShhSvv*) Im(ShhSvv*) ShvShv* Re(ShvSvv*) Im(ShvSvv*) SvvSvv*]. - Matlab code in zip-file (NEW VERSION of wishart_change_Q /10 April 2018), Python code at http://mortcanty.github.io/SARDocker/, Python code for Google Earth Engine at https://github.com/mortcanty/earthengine, JavaScript code to run directly in GEE Code Editor at http://fwenvi-idl.blogspot.de/2017/10/polsar-change-detection-in-google-earth.html. |
Electronic version(s) | [pdf] [zip] |
Publication link | http://doi.org/10.1080/07038992.2017.1394182 |
BibTeX data | [bibtex] |
IMM Group(s) | Image Analysis & Computer Graphics |