基于Newton迭代的摄像机位姿估计算法

Estimation of Camera Pose Based on Newton Iteration Algorithm

在军事上,利用移动机器人实时准确的跟踪前方的引导员,在野外复杂环境中完成后勤运输与救援任务有重要的意义.针对跟踪系统实时性的要求,利用收敛速度较快的Newton迭代法计算摄像机的位姿.通过对实验结果的分析,Newton迭代法计算摄像机的位姿能够很好的满足跟踪系统的精度要求;完成摄像机位姿的计算耗时不到1ms,该算法可以满足跟踪系统对跟踪实时性的要求.

It is important that transportation robot real-time accurately tracking its front guider transports logistics materials to the destination in the wild complex terrain circumstances in the military.According to real-time requirements of tracking system,the faster convergence Newton iterative algorithm is used to calculate camera pose.The experimental result indicates that,Camera pose calculated by Newton algorithm meets the requirements of the system tracking precision.Completing estimation of camera pose takes less than 1ms,which meets the requirements of the system tracking real-time.