Developing an Extraction Method of Urban Built-Up Area Based on Remote Sensing Imagery Transformation Index

Studying urban areas using remote sensing imagery has become a challenge, both visually and digitally. Supervised classification, one of the digital classification approaches to differentiate between built-up and non-built-up area, used to be leading in digital studies of urban area. Then the next generation uses index transformation for automatic urban data extraction. The extraction of urban built-up land can be automatically done with NDBI although it has one limitation on separating built-up land and bare land. The previous studies provide opportunities for further research to increase the accuracy of the extraction, particularly using index transformation. This study aims to obtain the maximum accuracy of the extraction by merging several indices including NDBI, NDVI, MNDWI, NDWI, and SAVI. The merging of the indices is using four stages: merging of two indices, three indices, four indexes and five indices. Several operations were experimented to merge the indices, either by addition, subtraction, or multiplication. The results show that merging NDBI and MNDWI produce the highest accuracy of 90.30% either by multiplication (overlay) or reduction. Application of SAVI, NDBI, and NDWI also gives a good effect for extracting urban built-up areas and has 85.72% mapping accuracy.

[1]  Changshan Wu,et al.  The use of single-date MODIS imagery for estimating large-scale urban impervious surface fraction with spectral mixture analysis and machine learning techniques , 2013 .

[2]  J. Campbell.  Introduction to remote sensing , 1987 .

[3]  Rasmus Fensholt,et al.  Using Landsat Vegetation Indices to Estimate Impervious Surface Fractions for European Cities , 2015, Remote. Sens..

[4]  X. H,et al.  A new index for delineating built-up land features in satellite imagery , 2008 .

[5]  Jay Gao,et al.  Use of normalized difference built-up index in automatically mapping urban areas from TM imagery , 2003 .

[6]  N. M. Sari,et al.  The Relationship between the Mixed Pixel Spectral Value of Landsat 8 OLI Data and LAPAN Surveillance Aircraft (LSA) Aerial-Photo Data , 2017 .

[7]  COMPARISON OF METHODOLOGIES TO DERIVE A NORMALIZED DIFFERENCE THERMAL INDEX (NDTI) FROM ATLAS IMAGERY , 2007 .

[8]  S. G. Nelson,et al.  Relationship Between Remotely-sensed Vegetation Indices, Canopy Attributes and Plant Physiological Processes: What Vegetation Indices Can and Cannot Tell Us About the Landscape , 2008, Sensors.

[9]  Todd R. Lookingbill,et al.  Exurban development derived from Landsat from 1986 to 2009 surrounding the District of Columbia, USA , 2012 .

[10]  Gabriele Moser,et al.  Article in Press G Model International Journal of Applied Earth Observation and Geoinformation Mapping Natural and Urban Environments Using Airborne Multi-sensor Ads40–mivis–lidar Synergies , 2022 .

[11]  Stéphane Couturier,et al.  Morpho-spatial extraction of urban nuclei in diffusely urbanized metropolitan areas , 2011 .

[12]  Iswari Nur Hidayati,et al.  Pemetaan Lahan Terbangun Perkotaan Menggunakan Pendekatan NDBI dan Segmentasi Semi-Automatik , 2017 .

[13]  Y. Yamagata,et al.  Landsat analysis of urban growth: How Tokyo became the world's largest megacity during the last 40 years , 2012 .

[14]  Yanghua Gao,et al.  An Improved Optimal Segmentation Threshold Algorithm and Its Application in the Built-up Quick Mapping , 2017, Journal of the Indian Society of Remote Sensing.

[15]  P. Shi,et al.  Improving the normalized difference built-up index to map urban built-up areas using a semiautomatic segmentation approach , 2009 .

[16]  Y. Yamaguchi,et al.  Characterizing the Urban Growth from 1975 to 2003 of Hanoi City Using Remote Sensing and a Spatial Metric , 2016 .

[17]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[18]  Avnish Varshney,et al.  A Comparative Study of Built-up Index Approaches for Automated Extraction of Built-up Regions From Remote Sensing Data , 2014, Journal of the Indian Society of Remote Sensing.

[19]  Hanqiu Xu.  Extraction of Urban Built-up Land Features from Landsat Imagery Using a Thematicoriented Index Combination Technique , 2007 .

[20]  Yunhao Chen,et al.  A Genetic Algorithm-Based Urban Cluster Automatic Threshold Method by Combining VIIRS DNB, NDVI, and NDBI to Monitor Urbanization , 2018, Remote. Sens..

[21]  B. Gao.  NDWI—A normalized difference water index for remote sensing of vegetation liquid water from space , 1996 .

[22]  Dengsheng Lu,et al.  Examining Urban Impervious Surface Distribution and Its Dynamic Change in Hangzhou Metropolis , 2016, Remote. Sens..