EgoSampling: Fast-Forward and Stereo for Egocentric Videos

TL;DR

EgoSampling introduces an adaptive frame sampling method for egocentric videos that produces stable fast-forwarded videos and enables stereo video creation by leveraging natural head movements.

Contribution

It presents a novel energy minimization framework for adaptive frame sampling that improves video stability and creates stereo pairs from egocentric videos.

Findings

Produces more stable fast-forwarded videos

Enables stereo video creation from head movement data

Operates in polynomial time for optimal solutions

Abstract

While egocentric cameras like GoPro are gaining popularity, the videos they capture are long, boring, and difficult to watch from start to end. Fast forwarding (i.e. frame sampling) is a natural choice for faster video browsing. However, this accentuates the shake caused by natural head motion, making the fast forwarded video useless. We propose EgoSampling, an adaptive frame sampling that gives more stable fast forwarded videos. Adaptive frame sampling is formulated as energy minimization, whose optimal solution can be found in polynomial time. In addition, egocentric video taken while walking suffers from the left-right movement of the head as the body weight shifts from one leg to another. We turn this drawback into a feature: Stereo video can be created by sampling the frames from the left most and right most head positions of each step, forming approximate stereo-pairs.