This paper addresses the issue of direction-of-arrival (DOA) estimation under the coexistence of mutual coupling and nonuniform noise. We first construct a selection matrix based on the structural characteristics of the mutual coupling matrix (MCM) to form a new manifold matrix which is not affected by the mutual coupling effect. Then, we employ the covariance fitting criteria to form a semidefinite programming for DOA estimation. Compared to most of existing sparse methods, our method does not require discretization of the angle space, hence is able to achieve super-resolution. Simulations are carried out to verify the effectiveness of the propose method.