自主空中加油视觉导航系统中的锥套检测算法

在软管式自主空中加油视觉相对导航系统中实现锥套的准确检测至关重要，由于加油机尾流及气流的影响，做随机运动的锥套区域的准确检测是具有一项挑战性的任务。将加油机锥套检测考虑为运动目标检测问题，提出了一种多尺度低秩和稀疏分解锥套检测算法。首先，对锥套图像序列进行平稳小波分解，得到多尺度低频图像序列；再将较粗尺度低频图像序列获得的目标作为下一较细尺度低频图像序列的目标可信图，再进行该尺度的低秩和稀疏分解获得稀疏项，即目标锥套区域。通过在真实加油机锥套图像数据上的实验结果表明，所提算法在进行锥套检测时是有效的。

Drogue detection algorithm in visual navigation system for autonomous aerial refueling

Drogue detection is important for relative navigation system for probe-and-drogue autonomous aerial refueling. It is a challenging task to detect the drogue with random motion due to disturbances caused by both the tanker wake vortex and atmospheric turbulence. In this paper, the problem of drogue detection was considered as moving object detection. A method based on multi-scale low rank and sparse decomposition was proposed for drogue detection. Firstly, the image sequences were decomposed by stationary wavelet transform respectively. Then the object in the low frequency sub-band image sequences of coarse scale was used as object confidence map to feedback the low sub-band image sequences of next fine scale for low rank and sparse decomposition. The experimental results show that the proposed algorithm is effective for drogue detection in real autonomous aerial refueling data.