Solving the problem of a lack of matching points to complete the terrain reconstruction for the landing area during the Lunar Lander landing process. An SFS(shape from shading) algorithm for 3D terrain recovery based on gradient constraints of the feature edges. The irradiance equation is established on the Lommel-Seeliger model to simulate the Lunar surface reflection. Based on the extract results of the terrain feature edge

gradient ratio of the rest part can be solved after least square fitting and surface smoothness constraint. The SFS problem becomes regularized after the quantitative constraints of irradiance equation. The average relative recovery accuracy can reach -0.199 for synthetic images

and also can reach 0.051 and 0.022 for real image after testing. The proposed algorithm can work effectively for 3D terrain reconstruction

and the recovery accuracy is superior to the existing SFS algorithm.