计算机视觉
放大倍数
计算机科学
像素
人工智能
欧拉路径
噪音(视频)
帧(网络)
运动(物理)
计算机图形学(图像)
数学
图像(数学)
电信
数学物理
拉格朗日
作者
Le Liu,Le Lü,Jingjing Luo,Jun Zhang,Xiuhong Chen
出处
期刊:
日期:2014-10-01
卷期号:: 50-54
被引量:31
标识
DOI:10.1109/cisp.2014.7003748
摘要
A post-processing technique is introduced to improve the Eulerian video magnification method, which is a state-of-the-art motion magnification method to manipulate small movements in videos based on spatio-temporal filtering. The proposed method use the Eulerian video magnification as a video spatio-temporal motion analyzer to get the pixel-level motion mapping. Then the input video pixels are warped based-on this mapping to amplify the motion. This processing does not involve pixel value modifying, which makes it supports larger amplification and is significantly less influenced by the frame noise.
科研通智能强力驱动
Strongly Powered by AbleSci AI