Improved optical flow motion estimation for digital image stabilization
Proceedings of SPIE(2015)
摘要
Optical flow is the instantaneous motion vector at each pixel in the image frame at a time instant. The gradient-based approach for optical flow computation can't work well when the video motion is too large. To alleviate such problem, we incorporate this algorithm into a pyramid multi-resolution coarse-to-fine search strategy. Using pyramid strategy to obtain multi-resolution images; Using iterative relationship from the highest level to the lowest level to obtain inter-frames' affine parameters; Subsequence frames compensate back to the first frame to obtain stabilized sequence. The experiment results demonstrate that the promoted method has good performance in global motion estimation
更多查看译文
关键词
optical flow,pyramid,global motion estimation,affine transformation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络