A synchronous motion-based control strategy for unmanned aerial vehicle (UAV) landing on an unmanned surface vehicle (USV) is proposed to address the problem of low accuracy or even failure of UAV landing on the surface of a USV under wave action. Firstly, the landing marks are identified and localized based on computer vision; secondly, the USV attitude angle is predicted based on a bidirectional long-short term memory (Bi-LSTM) neural network to ensure that the UAV can respond to USV attitude changes in real-time; furthermore, the UAV attitude controller is designed based on a PID algorithm to realize UAV–USV synchronous motion. The experimental results demonstrate that the proposed UAV–USV synchronous motion landing scheme with high landing accuracy is more suitable for the UAV to achieve autonomous landing on a USV in a complex marine environment.