Urban area extraction using polarimetric synthetic aperture radar (PolSAR) data is an important application for urban planning and disaster assessment. Due to the variability in urban structures, the problem of mistaking built-up areas for vegetation remains challenging. Then, a new urban extraction method is proposed using eigenvalues and optimal roll-invariant features. First, similar to the entropy/anisotropy plane, a 2-D RVI/PA plane is adopted to construct the extractor of surface scattering areas. Then, the optimal ratio of the correlation coefficient is proposed as an extractor to depict the scattering characteristics of buildings with various orientation angles, while restraining the scattering characteristics of other land covers. In addition, reliable hidden features are selected to refine the extraction results. Finally, the spatial information extraction and classification methods are introduced to automatically determine the thresholds of the parameters above, based on which the urban area extraction map can be obtained. C-band Gaofen-3 SAR data collected in Runan, Henan Province, China, and San Francisco, USA, and L-band E-SAR data collected in Oberpfaffenhofen, Germany, are used to validate the performance of the proposed method. Experimental results demonstrate that the method can distinguish between urban and natural areas with high accuracy and has good visual effects in extracting building areas.