Fusion of Multitemporal Multi-Angle ENVISAT ASAR and HJ-1 Data for Object-based Urban Land Cover Classification
2012 (English)In: FUSION OF MULTITEMPORAL ENVISAT ASAR AND HJ-1 DATA FOR OBJECT-BASED LAND COVER MAPPING, 2012, 52-57 p.Conference paper (Other academic)
The key goal of this work is to analyze the synergistic effects of multitemporal data fusion for urban land cover mapping. In particular this analysis is carried out using multitemporal ENVISAT ASAR images and one Chinese HJ-1 optical image acquired over Beijing in 2009. The major land cover classes are high-density built-up areas, low-density built-up areas, roads, airports, forests, parks, golf courses, grass/pasture, crops, bare fields and water. The methodology used in this research including orthorectification, SAR speckle filtering, and object-based classification. The segmentation is based on the newly developed algorithm KTH-SEG that utilizes an edge-aware region growing and merging approach. Fusion of the various combinations of multitemporal multi-angle SAR data and HJ-1 data were compared with SAR and optical data alone. The preliminary results show that the fusion of ENVISAT ASAR and HJ-1 data performed much better than optical data alone or SAR data alone. The fusion of 4-date SAR data and optical data can achieve similar classification accuracy as the fusion of 8-date SAR data and optical data if multi-angle, dual look direction SAR data with suitable temporal compositions are selected. Compared to eCognition, the KTH-SEG performed better in extracting linear features such as roads and rivers.
Place, publisher, year, edition, pages
2012. 52-57 p.
data fusion, image segmentation, land cover mapping, urban
Other Computer and Information Science
Research subject Geodesy and Geoinformatics; Geodesy and Geoinformatics
IdentifiersURN: urn:nbn:se:kth:diva-147163OAI: oai:DiVA.org:kth-147163DiVA: diva2:727774
1st Workshop on Temporal Analysis of Image Data, Mykonos, Greece, 23-25 May 2012
QC 201406262014-06-232014-06-232014-06-26Bibliographically approved