Summary: An adaptive output feedback dynamic surface control scheme is proposed for a class of output feedback nonlinear systems with unmodeled dynamics and output constraint. The radial basis function neural networks are utilized to approximate unknown nonlinear continuous functions. The \(K\)-filters and dynamic signal are designed to estimate the unmeasured states and deal with the dynamic uncertainties, respectively. By introducing a Barrier Lyapunov Function (BLF) and designing the adaptive controller, the boundedness of the BLF and the output constraint can be guaranteed. By theoretical analysis, the closed-loop control system is shown to be semi-globally uniformly ultimately bounded, and satisfy the output constraint. Simulation results show the effectiveness of the proposed approach.