运动物体参数估计与跟踪的线对应新算法

A new algorithm for motion estimation and tracking based on line correspondence

在分析刚体平面运动前后对应直线参数关系的基础上,提出了用直线对应原理估计物体运动参数的新算法.线对应法可以同时估计物体的平移和旋转参数,这一点是传统的点对应和其他方法难以实现的.推导出对运动物体自动跟踪的迭代公式,在跟踪过程中用齐次坐标实现了坐标系转换和运动合成的一体化.仿真实验证明,在大噪声环境下这一算法仍然可以获得相当精确的运动参数.

The relationships of line parameters between the states before and after planar motion of a rigid body are first deduced. A new algorithm based on the line correspondence for estimating motion parameter is proposed, which can be used to estimate the objects revolving parameters in addition to the objects translating parameters. For the conventional point correspondence algorithm, it is hard to work out all of them at the same time. Furthermore the iterative formula for automatic moving object tracking is presented as well. The homogeneous coordinate is adopted to facilitate the complex coordinate system transfer plus motion synthesis along the tracking process. The simulating experiments show that the quite accurate results under the high noisy environment can be acquired by this algorithm.