With rapid development, synthetic aperture radar (SAR), such as ERS (C-band), PALSAR (L-band), Cosmo-SkyMed (X-band) and TerraSAR (X-band), has offered abundant data source for urban environment research. The gray level co-occurrence matrix (GLCM) is used in this paper to extract urban areas texture features, and the performance of images with different band frequencies (C-band, L-band and X-band), different polarization modes (HH, HV, VH and VV) and different spatial resolutions (1m, 5m and 12m) are analyzed and compared. The results indicate that for different band frequencies, images in X-band perform better than C- and L-band. While for images with the same band frequency, polarization and spatial resolution play significant roles in urban areas extraction. Furthermore, we consider the sensitivity of GLCM method with respect to texture window size and to image resolution, and the conclusion can be drawn that high resolution images need large window sizes.