Satellite SAR Sea Ice Classification

IRGS (Iterative Region Growing With Semantics) is a computer vision algorithm designed for region-based scene segmentation and classification. MAGIC (MAp-Guided Ice Classification) is the software system where IRGS and other algorithms are implemented.

SAR Image Downscaled

MAGIC was originally created to read and classify SAR (synthetic aperture radar) images provided by the Canadian Ice Service (CIS) along with associated ice maps. IRGS provides a pixel-level classification of each polygon (i.e. subregion) knowing only the number of ice types in that polygon. For each polygon, the CIS analyst assigns the ice type concentrations, classes, and floe sizes and stores this information in an "Egg Code". So, although a polygon may be assigned 40% multi-year ice, the map does not pinpoint the location of the multi-year ice in the polygon. For the image on the right, the polygon of interest is outlined in red; its associated egg code shows that it contains four different classes of ice. IRGS takes this information to generate a pixel-level classification where each pixel can be assigned a particular ice type.

MAGIC uses one of many provided classification algorithms (e.g., IRGS) and overlays the results on the image. A sample classification is shown below - note that this image is a portion of a much larger original image and had to be shrunk by a factor of 4 for display purposes. IRGS is a Markov Random Field (MRF) based approach which has been shown to perform significantly better classifications of SAR sea ice imagery compared to other algorithms. Multiple classification results from different algorithms can be saved for comparison.

How does IRGS work? IRGS begins by performing an oversegmentation of the polygon or image using a watershed algorithm.  Using a Markov model based on Gaussian statistics and inter-region edge strength, the resulting regions are then iteratively (a) classified knowing the number of ice types in the scene and then (b) merged in a greedy fashion based on energy minimization.  A more detailed description of IRGS and how it has been extended to multi-band and polarimetric data can be found in the journal papers listed at the bottom of the page.  An animation showing regions being merged by IRGS is found below.

The image on the right below shows the results of classifying the polygon above using IRGS. Within MAGIC the overlay can be turned on and off and the transparency adjusted to compare the classification result with the underlying image.

MAGIC v2.0 and the associated classification algorithms are still under active development.
The images have been significantly down-scaled for use in this article. Do not use them for research purposes without permission.

Animation showing regions merged by IRGS

Results of classifying polygon using IRGS

 
RADARSAT–2 Data and Products © MacDONALD, DETTWILER AND ASSOCIATES LTD. (2004–2008) - All Rights Reserved “RADARSAT” is an official mark of the Canadian Space Agency.SAR Images in this article are provided by the Canadian Ice Service. The following copyright notice applies:

Related people

Directors

David A. Clausi

Students

Kirsten Robinson, Peter Kruzlics, Nazanin Asadi

Alumni

Kai (Alex) Qin, Namrata Bandekar, Peter Yu, Philippe Maillard, Qiyao Yu, Shuhrat Ochilov, Steven Leigh, Xuezhi (Bruce) Yang, Zhijie Wang

Related research areas

Multiresolution Techniques
Remote Sensing


Related publications

Journal articles 

Leigh, S.Z. Wang, and D. A. Clausi, "Automated ice-water classification using dual polarization SAR satellite imagerypdf", IEEE Transactions on Geoscience and Remote Sensing, November, Accepted. Details

 

Yu, P.D. A. Clausi, and K. Qin, "Unsupervised polarimetric SAR image segmentation and classification using region growing with edge penaltypdf", IEEE Transactions on Geoscience and Remote Sensing, vol. 50, issue 4, pp. 1302 - 1317, 2012. Details

Clausi, D. A.K. Qin, M. S. Chowdhury, P. Yu, and P. Maillard, "MAGIC: MAp-Guided Ice Classification system for operational analysispdf", Canadian Journal of Remote Sensing, vol. 36, no. 1, pp. S13-S25, 2010. Details

 

Qin, K., and D. A. Clausi, "Multivariate image segmentation using semantic region growing with adaptive edge penaltypdf",IEEE Transactions on Image Processing, vol. 19, no. 8, pp. 2157 - 2170, 2010. Details

Yu, Q., and D. A. Clausi, "IRGS: Image segmentation using edge penalties and region growingpdf", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, no. 12, pp. 2126 - 2139, 2008. Details

 

Maillard, P., T. Alencar-Silva, and D. A. Clausi, "An evaluation of RADARSAT-1 and ASTER data for mapping veredas (palm swamps)pdf", Sensors, pp. 6055-6076, 2008. Details

Yu, Q., and D. A. Clausi, "SAR sea-ice image analysis based on iterative region growing using semanticspdf", IEEE Transactions on Geoscience and Remote Sensing, vol. 45, no. 12, pp. 3919 - 3931, 2007. Details

Maillard, P.D. A. Clausi, and H. Deng, "Operational map-guided classification of SAR sea ice imagerypdf", IEEE Transactions on Geoscience and Remote Sensing, vol. 43, no. 12, pp. 2940 - 2951, 2005.  Details

 

Deng, H., and D. A. Clausi, "Unsupervised segmentation of synthetic aperture radar sea ice imagery using a novel Markov random field modelpdf", IEEE Transactions on Geoscience and Remote Sensing, vol. 43, issue 12, pp. 528 - 538, 2005. Details

Deng, H., and D. A. Clausi, "Unsupervised image segmentation using a simple MRF model with a new implementation schemepdf", Pattern Recognition, vol. 37, no. 12: Elsevier, pp. 2323–2335, 2004. Details

 

Conference papers

Li, F.D. A. ClausiL. Wang, and L. Xu, "A Semi-supervised Approach for Ice-water Classification Using Dual-Polarization SAR Satellite Imagerypdf", CVPR 2015 Earthvision Workshop, Accepted. Details

 

Amelard, R.A. WongD. A. Clausi, and F. Li, "Unsupervised Classification of Sea-Ice and Water Using Synthetic Aperture Radar via an Adaptive Texture Sparsifying Transformpdf", IEEE International Geoscience and Remote Sensing Symposium, March, 2013. Details

Clausi, D. A.K. Qin, M. S. Chowdhury, P. Yu, and P. Maillard, "MAGIC: MAp-Guided Ice Classification system for operational analysispdf", Canadian Journal of Remote Sensing, vol. 36, no. 1, pp. S13-S25, 2010. Details

Yu, Q., and D. A. Clausi, "Filament preserving segmentation for SAR sea ice imagery using a new statistical modelpdf",18th International Conference on Pattern Recognition (ICPR), vol. 4, Hong Kong, pp. 849 - 852, Aug. 21 - 24, 2006. Details

Yu, Q., and D. A. Clausi, "Joint image segmentation and interpretation using iterative semantic region growing on SAR sea ice imagerypdf", 18th International Conference on Pattern Recognition (ICPR), vol. 2, Hong Kong, pp. 223 - 226, Aug. 21 - 24, 2006. Details

Deng, H., and D. A. Clausi, "Unsupervised segmentation of synthetic aperture radar sea ice imagery using a novel Markov random field modelpdf", Pattern Recognition in Remote Sensing, vol. 43, no. 3, Kingston on Thames, Kingston University, UK, pp. 528 - 538, Aug. 27, 2005. Details

Deng, H., and D. A. Clausi, "Unsupervised segmentation of synthetic aperture radar sea ice imagery using MRF modelspdf", 1st Canadian Conference on Computer and Robot Vision, London, Ontario, Canada, pp. 43 - 50, January, 2004. Details

Clausi, D. A., and H. Deng, "Fusion of Gabor filter and co-occurrence probability features for texture recognitionpdf", 16th International Conference on Vision Interface (VI ’03), Halifax, NS, Canada, pp. 237 - 242, June 11 - 13, 2003. Details

Theses

Leigh, S., "Automated Ice-Water Classification using Dual Polarization SAR Imagery", Department of Systems Design Engineering, Waterloo, ON, Canada, University of Waterloo, pp. 110, 2013. Details

 

Bandekar, N.., "Illumination and Noise-Based Scene Classification - Application to SAR Sea Ice Imagerypdf", Department of Systems Engineering, Waterloo, ON, Canada, University of Waterloo, pp. 77, 2012. Details

Clausi, D. A., "Texture Segmentation of SAR Sea Ice Imagery", Department of Systems Design Engineering, Waterloo, Ontario, Canada, University of Waterloo, pp. 176, 1996. Details