Change search
ReferencesLink to record
Permanent link

Direct link
Multitemporal Spaceborne Polarimetric SAR Data for Urban Land Cover Mapping
KTH, School of Architecture and the Built Environment (ABE), Urban Planning and Environment, Geodesy and Geoinformatics.
2011 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Urban represents one of the most dynamic areas in the global change context. To support rational policies for sustainable urban development, remote sensing technologies such as Synthetic Aperture Radar (SAR) enjoy increasing popularity for collecting up-to-date and reliable information such as urban land cover/land-use. With the launch of advanced spaceborne SAR sensors such as RADARSAT-2, multitemporal fully polarimetric SAR data in high-resolution become increasingly available. Therefore, development of new methodologies to analyze such data for detailed and accurate urban mapping is in demand.

 

This research investigated multitemporal fine resolution spaceborne polarimetric SAR (PolSAR) data for detailed urban land cover mapping. To this end, the north and northwest parts of the Greater Toronto Area (GTA), Ontario, Canada were selected as the study area. Six-date C-band RADARSAT-2 fine-beam full polarimetric SAR data were acquired during June to September in 2008. Detailed urban land covers and various natural classes were focused in this study.

 

Both object-based and pixel-based classification schemes were investigated for detailed urban land cover mapping. For the object-based approaches, Support Vector Machine (SVM) and rule-based classification method were combined to evaluate the classification capacities of various polarimetric features. Classification efficiencies of various multitemporal data combination forms were assessed. For the pixel-based approach, a temporal-spatial Stochastic Expectation-Maximization (SEM) algorithm was proposed. With an adaptive Markov Random Field (MRF) analysis and multitemporal mixture models, contextual information was explored in the classification process. Moreover, the fitness of alternative data distribution assumptions of multi-look PolSAR data were compared for detailed urban mapping by this algorithm.

 

Both the object-based and pixel-based classifications could produce the finer urban structures with high accuracy. The superiority of SVM was demonstrated by comparison with the Nearest Neighbor (NN) classifier in object-based cases. Efficient polarimetric parameters such as Pauli parameters and processing approaches such as logarithmically scaling of the data were found to be useful to improve the classification results. Combination of both the ascending and descending data with appropriate temporal span are suitable for urban land cover mapping. The SEM algorithm could preserve the detailed urban features with high classification accuracy while simultaneously overcoming the speckles. Additionally the fitness of the G0p and Kp distribution assumptions were demonstrated better than the Wishart one.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology , 2011. , viii, 54 p.
Series
Trita-SOM , ISSN 1653-6126 ; 2011-05
Keyword [en]
RADARSAT-2, spaceborne, polarimetric SAR, urban land cover, classification
National Category
Computer and Information Science
Identifiers
URN: urn:nbn:se:kth:diva-31176ISBN: 978-91-7415-909-7OAI: oai:DiVA.org:kth-31176DiVA: diva2:403014
Presentation
2011-03-16, Seminarierum 4055, KTH, Drottning Kristinas väg 30, Stockholm, 14:17 (English)
Opponent
Supervisors
Note

QC 20110315

Available from: 2011-03-15 Created: 2011-03-10 Last updated: 2013-12-04Bibliographically approved
List of papers
1. Multitemporal radarsat-2 polarimetric SAR data for urban land-cover mapping
Open this publication in new window or tab >>Multitemporal radarsat-2 polarimetric SAR data for urban land-cover mapping
2010 (English)In: 100 Years ISPRS Advancing Remote Sensing Science, PT 1, 2010, Vol. 38, 175-180 p.Conference paper (Refereed)
Abstract [en]

The objective of this research is to evaluate multi-temporal RADARSAT-2 polarimetric SAR data for urban land-cover classification using a novel classification scheme. Six-date RADARSAT-2 Polarimetric SAR data in both ascending and descending orbits were acquired during June to September 2008 in the rural-urban fringe of the Greater Toronto Area. The major land-cover types are builtup areas, roads, golf courses, forest, water and several types of agricultural crops. In this research, the different urban land-cover types and their corresponding polarimetric behaviors were studied. The polarimetric signatures of the various urban land-cover types were extracted from the RADARSAT-2 SAR images and analyzed using a new hierarchical multitemporal classification method. The results showed that the new classification method yielded high classification accuracy, with overall accuracy of 82.1% and Kappa coefficient 0.80 for the major 11 land-cover classes. The classification scheme can effectively extract the urban structures by mapping urban related classes such as streets and major roads with the higher user's accuracy, which is difficult to achieve using a single-date data.

 

Series
, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives, ISSN 2194-9034
Keyword
Land cover, classification, SAR, hierarchical, multitemporal
National Category
Remote Sensing
Identifiers
urn:nbn:se:kth:diva-31424 (URN)000339410100030 ()2-s2.0-79957643144 (ScopusID)
Conference
ISPRS Technical Commission VII Symposium on Advancing Remote Sensing Science; Vienna; Austria; 5 July 2010 through 7 July 2010
Note

QC 20110315

Available from: 2011-03-15 Created: 2011-03-15 Last updated: 2015-06-11Bibliographically approved
2. Multitemporal RADARSAT-2 polarimetric SAR data for urban cover classification using support vector machine
Open this publication in new window or tab >>Multitemporal RADARSAT-2 polarimetric SAR data for urban cover classification using support vector machine
2010 (English)In: 30th EARSeL Symposium, Paris, France, June, 2010, 2010, 581-588 p.Conference paper (Refereed)
Abstract [en]

This research investigates the various RADARSAT-2 polarimetric SAR features for urban land cover classification using object-based method combining with support vector machine (SVM) and ruled-based approach. Six-dates of RADARSAT-2 fine-beam polarimetric SAR data were acquired in the rural-urban fringe of Greater Toronto Area during June to September, 2008. The major landuse/land-cover classes were high-density built-up areas, low-density built-up areas, roads, forests, parks, golf courses, water and several types of agricultural crops. The polarimetric SAR features examined are the parameters from Pauli, Freeman and Cloude-Pottier decompositions as well as the elements from coherence matrix and the intensities and their logarithm form of each channel. For urban land cover classification, SVM is combined with rule-based method for the object-based classification. The image objects containing the multitemporal polarimetric features were classified using the SVM classifier first. The SVM classification results were further refined using a rule-based approach. Rules were built to recognize specific classes defined by the shape features and the spatial relationships within the context. In terms of the effectiveness of different SAR ploarimtric parameters, the results indicated that the processed Pauli feature set could produce best classification result while the use of all the polarimetric features did not produce the best classification result. The raw Pauli parameters could generate similar result as all T elements. The logarithm parameters such as log intensity and processed Pauli parameters perform better than the intensity and raw Pauli respectively. The proposed object-based classification using SVM and rule-based approach yielded higher classification accuracies than the object-based classification using nearest neighbor classifier. 

 

 

 

Keyword
Polarimetric SAR, multitemporal, landuse/land-cover, SVM, object-based analysis
National Category
Remote Sensing
Identifiers
urn:nbn:se:kth:diva-31426 (URN)978-3-00-033435-1 (ISBN)
Conference
30th EARSeL Symposium, Paris, France, June, 2010
Note
QC 20110315Available from: 2011-03-15 Created: 2011-03-15 Last updated: 2012-03-07Bibliographically approved
3. Multi-temporal RADARSAT-2 polarimetric SAR data for urban land-cover classification using an object-based support vector machine and a rule-based approach
Open this publication in new window or tab >>Multi-temporal RADARSAT-2 polarimetric SAR data for urban land-cover classification using an object-based support vector machine and a rule-based approach
2013 (English)In: International Journal of Remote Sensing, ISSN 0143-1161, E-ISSN 1366-5901, Vol. 34, no 1, 1-26 p.Article in journal (Refereed) Published
Abstract [en]

We have investigated multi-temporal polarimetric synthetic aperture radar (SAR) data for urban land-cover classification using an object-based support vector machine (SVM) in combinations of rules. Six-date RADARSAT-2 high-resolution polarimetric SAR data in both ascending and descending passes were acquired in the rural-urban fringe of the Greater Toronto Area during the summer of 2008. The major land-use/land-cover classes include high-density residential areas, low-density residential areas, industrial and commercial areas, construction sites, parks, golf courses, forests, pasture, water, and two types of agricultural crops. Various polarimetric SAR parameters were evaluated for urban land-cover mapping and they include the parameters from Pauli, Freeman and Cloude-Pottier decompositions, the coherency matrix, intensities of each polarization, and their logarithm forms. The multi-temporal SAR polarimetric features were classified first using an SVM classifier. Then specific rules were developed to improve the SVM classification results by extracting major roads and streets using shape features and contextual information. For the comparison of the polarimetric SAR parameters, the best classification performance was achieved using the compressed logarithmic filtered Pauli parameters. For the evaluation of the multi-temporal SAR data set, the best classification result was achieved using all six-date data (kappa = 0.91), while very good classification results (kappa = 0.86) were achieved using only three-date polarimetric SAR data. The results indicate that the combination of both the ascending and the descending polarimetric SAR data with an appropriate temporal span is suitable for urban land-cover mapping.

National Category
Remote Sensing
Identifiers
urn:nbn:se:kth:diva-103959 (URN)10.1080/01431161.2012.700133 (DOI)000308994100001 ()2-s2.0-84868092003 (ScopusID)
Note

QC 20121029

Available from: 2012-10-29 Created: 2012-10-25 Last updated: 2013-12-04Bibliographically approved
4. RADARSAT-2 polarimetric SAR data for urban land cover mapping using spatial- temporal SEM algorithm and mixture models
Open this publication in new window or tab >>RADARSAT-2 polarimetric SAR data for urban land cover mapping using spatial- temporal SEM algorithm and mixture models
2011 (English)In: 6th Joint Urban Remote Sensing Event (JURSE 2011), Munich, Germany, April 2011, 2011, 241-244 p.Conference paper (Refereed)
National Category
Remote Sensing
Identifiers
urn:nbn:se:kth:diva-31428 (URN)10.1109/JURSE.2011.5764749 (DOI)2-s2.0-79957667699 (ScopusID)978-1-4244-8658-8 (ISBN)
Conference
JURSE Urban Remote Sensing
Note
QC 20110315Available from: 2011-03-15 Created: 2011-03-15 Last updated: 2012-03-07Bibliographically approved

Open Access in DiVA

fulltext(2046 kB)1984 downloads
File information
File name FULLTEXT03.pdfFile size 2046 kBChecksum SHA-512
e58a6bbe51ba7d273446d9c6659f65072586b964e85124a0b3b393f2aa6d5a97683ce79eb0a8a618e77576ca6e7c2a47b99314cdb4801d059c07baf5db1d2c77
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Niu, Xin
By organisation
Geodesy and Geoinformatics
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 1985 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 325 hits
ReferencesLink to record
Permanent link

Direct link