Abstract: Target maneuvering is always accompanied with rapid attitude variations, which are helpful to achieve high cross-range resolution for coherent pulse radar. Thus it provides the feasibility to detect target maneuver based on one-dimensional high resolution Doppler profile (1D-HRDP). In this paper, the formulation of the HRDP is first introduced, and the profiling requirements are derived subsequently, including rotation angle, coherent processing time (CPI), and digital sampling rate. The profiling procedure is thus shown. The principle of maneuver detection based on the HRDP is then fully exploited. The difference of target attitude rates between nonmaneuvering and maneuvering motion modes is analyzed, which is the basis for maneuver detection. Due to the nonstationarity of the HRDP, the maneuver detection problem is reformulated as a pattern classification problem, where nonmaneuvering and maneuvering motion modes are distinguished. A novel detector is then developed based on the back propagation (BP) neural network. Two novel indices for performance evaluation are proposed. They reflect the dynamic performance of the maneuver detector more reasonably than the classical index, which is the average detection delay. Finally, the simulation results show that the proposed detector performs better than the other three up-to-date feature-based detectors as a whole.