Abstract: Nighttime remote sensing images have been widely used in the extraction of city information,as nighttime light data are closely related to human activities. As a new generation of noctilucent remote sensing data source, LJ1-01 has higher spatial and spectral resolutions, and can express the scope and internal structure of urban built-up areas more clearly. In this study, LJ1-01 nighttime light remote sensing images were used to extract the urban built-up area of Changchun City based on human settlement index (HSI),vegetation and build adjusted nighttime light urban index(VBANUI), and support vector machine(SVM) supervised classification. The results were compared with those obtained by suomi national polar orbiting partnership/visible infrared imaging radiometer suite (NPP/VIIRS) using the same method. It showed that the extraction accuracy of the traditional vegetation adjusted nighttime light urban index(VANUI) is improved by VBANUI proposed in this paper. Among them, the urban built-up area extracted by VBANUI using LJ1-01 has the best result, with the Kappa coefficient of 0.80 and the overall classification accuracy of 90.74%; The optimal Kappa coefficients of urban built-up areas extracted by HSI using LJ1-01 and NPP/VIIRS are 0.75 and 0.72, respectively, and the overall classification accuracy is 88.27% and 86.54%, respectively; The kappa coefficients of Landsat-NDBI composite data, Landsat-NDBI-VIIRS composite data, Landsat-NDBI-LJ composite data, and Landsat-NDBI-LJlog composite data in SVM supervised classification are 0.602, 0.627, 0.643, and 0.681, respectively, and their overall classification accuracy is 81.11%, 81.52%, 82.25%, and 84.48% respectively. The results show that the LJ1-01 nighttime image is the best among the three extraction methods. This study proves that the LJ1-01 night light remote sensing image is more suitable for urban level built-up area extraction than NPP/VIIRS night light remote sensing image.

Key words: LJ1-01 nighttime light remote sensing image, NPP/VIIRS nighttime light remote sensing image, urban built-up area, VBANUI, human settlement index, support vector machine