ANTI-ROTATION AND ANTI-SCALE IMAGE MATCHING ALGORITHM FOR NAVIGATION SYSTEM

抗旋转和尺度变化的导航系统图像匹配算法(英文)

Based on the inertial navigation system, the influences of the excursion of the inertial navigation system and the measurement error of the wireless pressure altimeter on the rotation and scale of the real image are quantitatively analyzed in scene matching. The log-polar transform （LPT） is utilized and an anti-rotation and anti- scale image matching algorithm is proposed based on the image edge feature point extraction. In the algorithm, the center point is combined with its four-neighbor points, and the corresponding computing process is put forward. Simulation results show that in the image rotation and scale variation range resulted from the navigation system error and the measurement error of the wireless pressure altimeter, the proposed image matching algo- rithm can satisfy the accuracy demands of the scene aided navigation system and provide the location error-correcting information of the system.

在惯性导航系统中,定量分析了景象匹配过程中惯性导航系统漂移和无线电气压高度表测量误差对实测图的旋转和尺度所造成的影响,引入了对数极坐标变换。基于图像边缘特征提取,提出了一种结合中心点的4-邻域点共同参与计算的抗旋转和小尺度变化的图像匹配算法,并给出了相应的算法流程。仿真分析表明,在导航系统误差漂移所引起的图像旋转和气压高度表所引起的尺度变化范围内,该算法能满足匹配准确性的要求,并能有效给出系统的定位误差修正信息。