Separating Transparent Layers of Repetitive Dynamic Behaviors

Authors:
Bernard Sarel;Michal Irani
Affiliations:
Weizmann Institute of Science;Weizmann Institute of Science
Venue:
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Year:
2005

Citing 0
Cited 5

Jointmotion estimation and layer segmentation in transparent image sequenc: application to noise reduction in X-ray image sequences

EURASIP Journal on Advances in Signal Processing
Median Photometric Stereo as Applied to the Segonko Tumulus and Museum Objects

International Journal of Computer Vision
Robust spatial regularization and velocity layer separation for optical flow computation on transparent sequences

MICAI'10 Proceedings of the 9th Mexican international conference on Advances in artificial intelligence: Part I
Variational Multi-Valued Velocity Field Estimation for Transparent Sequences

Journal of Mathematical Imaging and Vision
Smoke Detection in Video: An Image Separation Approach

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we present an approach for separating two transparent layers of complex non-rigid scene dynamics. The dynamics in one of the layers is assumed to be repetitive, while the other can have any arbitrary dynamics. Such repetitive dynamics includes, among other, human actions in video (e.g., a walking person), or a repetitive musical tune in audio signals. We use a global-to-local space-time alignment approach to detect and align the repetitive behavior. Once aligned, a median operator applied to space-time derivatives is used to recover the intrinsic repeating behavior, and separate it from the other transparent layer. We show results on synthetic and real video sequences. In addition, we show the applicability of our approach to separating mixed audio signals (from a single source).