光流
计算机科学
稳健性(进化)
像素
阈值
计算机视觉
不连续性分类
正规化(语言学)
人工智能
全变差去噪
忠诚
算法
降噪
图像(数学)
数学
电信
数学分析
基因
化学
生物化学
作者
Christopher Zach,Thomas Pock,Horst Bischof
出处
期刊:Springer eBooks
[Springer Nature]
日期:2007-09-21
卷期号:: 214-223
被引量:1275
标识
DOI:10.1007/978-3-540-74936-3_22
摘要
Variational methods are among the most successful approaches to calculate the optical flow between two image frames. A particularly appealing formulation is based on total variation (TV) regularization and the robust L1 norm in the data fidelity term. This formulation can preserve discontinuities in the flow field and offers an increased robustness against illumination changes, occlusions and noise. In this work we present a novel approach to solve the TV-L1 formulation. Our method results in a very efficient numerical scheme, which is based on a dual formulation of the TV energy and employs an efficient point-wise thresholding step. Additionally, our approach can be accelerated by modern graphics processing units. We demonstrate the real-time performance (30 fps) of our approach for video inputs at a resolution of 320 × 240 pixels.
科研通智能强力驱动
Strongly Powered by AbleSci AI