Tracking Algorithm with Adaptive Bandwidth of Kernel Function for UAV Autonomous Aerial Refueling

Abstract

Abstract. The use of machine vision to track the receiver aircraft's receptacle is one of the key steps in automated aerial refueling. Traditional Meanshift tracking algorithm's kernel bandwidth is fixed, when the target size changes, it will produce with the bias even with the loss of the situation. Aiming at this problem, this paper proposes a kernel bandwidth adaptive algorithm based on corner matching. First, use backward tracking method to amend the core window center. Then according to the Harris algorithm to detect the corner, use small-scale approach for the two points between frames to match and regression analysis, namely determine the update parameters of nuclear window width. Experiments show that the algorithm can track the target accurately when the size of tracking target change, and the kernel window width can be better suited to the target size.

Review of Sensor Technology to Support Automated Air-to-Air Refueling of a Probe Configured Uncrewed Aircraft

“…Once the UA and the tanker are in closer proximity, as defined by the astern position (10 to 15 ft. aft of the drogue), it is necessary to transition to CV to provide guidance information to the GNC for the placement of the probe tip into the drogue coupler. Given the limitations associated with DGPS, demonstrations to date [ 37 , 38 , 89 ], and academic research on the A3R portion of a mission, a pivot to a CV solution is most appropriate for the final engagement [ 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 ]. As the aircraft moves to an astern position ( Figure 4 ) using an INS/GNSS/DGPS-derived position solution, the camera system installed on the UA can begin to detect objects within the domain.…”

“…While no UA currently exists in the Department of Defense (DoD) that has been authorized to conduct the A3R portion of a mission, the task has been accomplished on both crewed aircraft and UA as a demonstration. Extensive research has been conducted on the algorithms required to complete the task from as a receiver, specifically the computer vision (CV) portion of A3R [ 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 ]. As ranges increase for UAs to travel to complete the mission, the demand for a UA capable of A3R will continue to increase as well.…”