CVApr 13, 2017

Video Acceleration Magnification

arXiv:1704.04186v299 citations
Originality Incremental advance
AI Analysis

This addresses video analysis challenges in fields like medical imaging and sports, offering an incremental improvement over prior methods by handling large motions more effectively.

The paper tackles the problem of magnifying subtle changes in videos with large motion, which distorts existing linear magnification methods, by proposing a method to magnify acceleration instead, ignoring linear motion. The result is a pure Eulerian approach that works without optical flow or alignment, demonstrated with quantitative and qualitative evidence against state-of-the-art methods.

The ability to amplify or reduce subtle image changes over time is useful in contexts such as video editing, medical video analysis, product quality control and sports. In these contexts there is often large motion present which severely distorts current video amplification methods that magnify change linearly. In this work we propose a method to cope with large motions while still magnifying small changes. We make the following two observations: i) large motions are linear on the temporal scale of the small changes; ii) small changes deviate from this linearity. We ignore linear motion and propose to magnify acceleration. Our method is pure Eulerian and does not require any optical flow, temporal alignment or region annotations. We link temporal second-order derivative filtering to spatial acceleration magnification. We apply our method to moving objects where we show motion magnification and color magnification. We provide quantitative as well as qualitative evidence for our method while comparing to the state-of-the-art.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes