Tibetan Plateau is a typical study area of global environmental change, and lake is an important ecological factor to reveal eco-environmental evolution. Using remote sensing technology to monitor the succession law of lakes on the plateau is of great significance to global environment change research. Based on water index computed by spectral feature fitting (SFF) method, this paper uses “whole-local ” spatial scale transformation mechanism, along with iterative algorithm, to obtain high-precise extraction of modern lakes on the Tibetan Plateau. Moreover, uses integrated data of LANDSAT ETM+ images and SRTM data to further detect and recover paleo shorelines. By comparing paleo and modern lakes, it shows that lakes on the Tibetan Plateau have shrunk significantly since the great lake period, which provides fundamental information support to researches on global paleo-climatology and paleo-hydrology change.