A class of subspace-based methods for direction-of-arrival (DOA) estimation and tracking in the case of uniform linear arrays (ULAs) with mutual coupling is proposed. By treating the angularly-independent mutual coupling as angularly-dependent complex array gains, the middle subarray is found to have the same complex array gains. Using this property, a new way for parameterizing the steering vector is proposed and the corresponding method for joint estimation of DOAs and mutual coupling matrix (MCM) using the whole array data is derived based on subspace principle. Simulation results show that the proposed algorithm has a better performance than the conventional subarray-based method especially for weak signals. Furthermore, to achieve low computational complexity for online and time-varying DOA estimation, three subspace tracking algorithms with different arithmetic complexities and tracking abilities are developed. More precisely, by introducing a better estimate of the subspace to the conventional tracking algorithms, two modified methods, namely modified projection approximate subspace tracking (PAST) (MPAST) and modified orthonormal PAST (MOPAST), are developed for slowly changing subspace, whereas a Kalman filter with a variable number of measurements (KFVM) method for rapidly changing subspace is introduced. Simulation results demonstrate that these algorithms offer high flexibility and effectiveness for tracking DOAs in the presence of mutual coupling.