Sea surface target recognition and tracking system for unmanned surface vehicle with heterogeneous sensors

  Objectives  In order to meet the needs of long-distance sea target recognition and tracking through the navigation radar and integrated optoelectronic equipment of an unmanned ship operating in a marine environment, a novel unmanned ship autonomous sensing system is developed with heterogeneous sensor association, target track prediction and photoelectric camera attitude compensation.

  Methods  By using the target track prediction algorithm based on a Kalman filter for the target position information output by the navigation radar, target positioning accuracy can be improved and real-time target information can be provided to the photoelectric camera. The posture compensation algorithm based on the ship's posture in the photoelectric camera is used to complete the tasks of target image collection, recognition and tracking. An unmanned surface vehicle equipped with our proposed sensing system has completed dynamic target recognition and tracking tasks under Sea State 3 conditions.

  Results  The target tracking error is reduced by 6% and the target recognition success rate is increased to 96.25%, which verifies the environmental adaptability of this sensing system.

  Conclusions  Through testing experiments, the proposed recognition and tracking system can effectively solve the problems of difficult image acquisition and poor recognition effects of sea surface targets, effectively improving the success rate of target recognition.