This paper uses two navigation schemes to prove the potential of a novel autonomous orbit determination with stellar horizon atmospheric refraction measurements. Scheme one needs a single processor and uses an extended Kalman filter. The second scheme needs two parallel processors. One processor uses a batched leastsquare initial state estimator and a high-precision dynamic state propagator. The other processor uses a real-time orbit predictor. Simulations have been executed respectively for three types (low/medial/high) of satellite orbits on which various numbers of stars. Are observed. The results show both schemes can autonomously determine the orbits with a considerable performance. The second Scheme in general performs a little better than the first scheme.