Video Acceleration Magnification

Video Acceleration Magnification

Zhang, Yichao (External organisation)
Pintea, S. (TU Delft Pattern Recognition and Bioinformatics)
van Gemert, J.C. (TU Delft Pattern Recognition and Bioinformatics)

O'Conner, L. (editor)

2017

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.

Acceleration
Cameras
Tracking
Feature extraction
Laplace equations
Linearity
Taylor series

http://resolver.tudelft.nl/uuid:86869ecb-84f1-457b-bf87-202dd5f06274

https://doi.org/10.1109/CVPR.2017.61

IEEE, Piscataway

978-1-5386-0458-8

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

30th IEEE Conference on Computer Vision and Pattern Recognition, 2017-07-21 → 2017-07-26, Honolulu, United States

Institutional Repository

conference paper

© 2017 Yichao Zhang, S. Pintea, J.C. van Gemert