An optimized object-based analysis for vegetation mapping using integration of Quickbird and Sentinel-1 data
- PDF / 8,032,755 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 79 Downloads / 203 Views
GCEC 2017
An optimized object-based analysis for vegetation mapping using integration of Quickbird and Sentinel-1 data Ahmed Abdulkareem Ahmed 1 & Biswajeet Pradhan 1 & Maher Ibrahim Sameen 1 & Ali Muayad Makky 1 Received: 25 January 2018 / Accepted: 29 May 2018 # Saudi Society for Geosciences 2018
Abstract This study proposed a workflow for an optimized object-based analysis for vegetation mapping using integration of Quickbird and Sentinel-1 data. The method is validated on a set of data captured over a part of Selangor located in the Peninsular Malaysia. The method comprised four components including image segmentation, Taguchi optimization, attribute selection using random forest, and rule-based feature extraction. Results indicated the robustness of the proposed approach as the area under curve of forest; grassland, old oil palm, rubber, urban tree, and young oil palm were calculated as 0.90, 0.89, 0.87, 0.87, 0.80, and 0.77, respectively. In addition, results showed that SAR data is very useful for extracting rubber and young oil palm trees (given by random forest importance values). Finally, further research is suggested to improve segmentation results and extract more features from the scene. Keywords Vegetation mapping . Taguchi optimization . Random forest . OBIA . Remote sensing . GIS
Introduction Land use and land cover mapping is an essential task in remote sensing as it serves many applications (Knorn et al. 2009). In particular, vegetation mapping in urban areas is important for urban planning (Niemelä 1999) and many environmental studies. There are several techniques available for vegetation mapping in literature including pixel-based and objectbased analysis (Yan et al. 2006). A literature review revealed that, object-based methods were found more suitable (Blaschke 2010) because; of its ability to integrate data from different sources, spatial and texture, information could be incorporated into the feature extraction process, etc. Due to similar spectral responses of vegetation features, object-based
This article is part of the Topical Collection on Global Sustainability through Geosciences and Civil Engineering * Biswajeet Pradhan [email protected]; [email protected] 1
School of Systems, Management and Leadership, Faculty of Engineering and Information Technology, University of Technology Sydney, PO Box 123, Building 11, Level 06, 81 Broadway, Ultimo, NSW 2007, Australia
methods and SAR data are suitable to design a classification framework. In addition, the output of object-based analysis is a GIS readymade product, which can be easily integrated with other types of geodatabases. There are several studies investigated vegetation mapping using SAR and optical satellite images. Widhalm et al. (2015) demonstrated the use of C-band Sentinel 1 data in order to derive a circumpolar wetness classification map. The study showed that difference backscatter of summer to winter values depended solely on soil moisture content, showed expected higher values for wet regions. Fontanelli et
Data Loading...
