A SVM-based method to extract urban areas from DMSP-OLS and SPOT VGT data

Monitoring Urban Dynamics in the Southeast U.S.A. Using Time-Series DMSP/OLS Nightlight Imagery

“…The non-built-up areas were mislabeled as built-up areas in urban cores due to the saturation of NTL data as the incorporation of vegetation variables cannot completely eliminate the saturation effect of NTL data in urban cores. Comparing with previous studies [15,35], the results are satisfactory at the regional level. …”

A new method for extracting built-up urban areas using DMSP-OLS nighttime stable lights: a case study in the Pearl River Delta, southern China

“…Because of the fine spatial resolution of Landsat TM/ETM+ data (30 × 30 m 2 ), built-up urban areas extracted from the Landsat TM/ETM+ images are feasible and acceptable for evaluating the mapping results of NSL data (Cao et al 2009;He et al 2006;Henderson et al 2003;Small, Pozzi, and Elvidge 2005;Sutton, Cova, and Elvidge 2006). In this article, a decision-tree method was developed to extract the built-up urban areas from Landsat TM/ETM+ images based on the commonly used spectral-analysis algorithms.…”

“…Large amounts of natural lands in cities are being replaced by artificial surfaces, which cause numerous environmental and ecological problems (Milesi et al 2003;Imhoff et al 2004;Su et al 2010;Chen et al 2012). Therefore, accurately monitoring the regional expansion of built-up areas in China is essential (He et al 2006;Liu et al 2012 (Cao et al 2009;Liu et al 2012;Bhatti and Tripathia 2014), are commonly used. However, because of the limited geographic coverage of medium-and high-resolution images, these methods require a large number of scenes to cover the regional and national scales (Liu et al 2003(Liu et al , 2005(Liu et al , 2010Zhang, He, and Liu 2014).…”

“…Subsequent studies demonstrated the superiority of DMSP-OLS NSL in extracting the built-up urban areas at global (Elvidge et al 1997(Elvidge et al , 1999(Elvidge et al , 2007 (Imhoff et al 1997a(Imhoff et al , 1997bSmall, Pozzi, and Elvidge 2005;Lu et al 2008;Cao et al 2009;Shi et al 2014;Wei et al 2014). However, most NSL-based studies presently use empirical threshold-based approaches (e.g., Imhoff et al 1997aImhoff et al , 1997bHenderson et al 2003;Milesi et al 2003).…”

“…In comparison, they set empirical thresholds to extract built-up urban areas of different sizes and NSL intensities. Therefore, the threshold methods not only overestimate the built-up area in urban regions because of 'blooming' NSL but also miss small patches of built-up lands in developing towns, where the NSL is much lower (e.g., Imhoff et al 1997a;Owen 1998;Sutton et al 2001;Lawrence et al 2002;Henderson et al 2003;Small, Pozzi, and Elvidge 2005;Cao et al 2009). …”