关键词: 基础矩阵, 运动序列, 逐层迭代, 数据内点

Abstract: Concerning the estimation of fundamental matrix in motion sequences under the unknown environment, a layer-by-layer iterative approach was proposed. This approach was based on optimal robust estimation method, and added the constrained condition of motion continuity and multi-scale correspondence to reduce false correspondence. Then data inliers of model from high level were added into the data set of low level in order to update the data set and estimate the homographic model simultaneously. Finally, global optimization was done on bottom level to rectify the model. The experiments show that geometric transform error is no more than 2.891821pixel and variance of error fluctuated range is no more than 0.295172pixel, both the mean and the fluctuated variance of error are reduced in some degree when the scene surface has relatively plentiful depth levels and good continuity from motion sequences.

Key words: fundamental matrix, motion sequence, layer-by-layer iteration, data inlier