EgoSampling: Wide View Hyperlapse from Egocentric Videos
This addresses the issue of boring and shaky wearable camera videos for users wanting to share or browse their experiences quickly, representing an incremental improvement in video processing techniques.
The paper tackled the problem of creating stable, fast-forwarded hyperlapse videos from shaky, long egocentric videos by proposing EgoSampling, an adaptive frame sampling method formulated as an energy minimization problem, which also increases the field-of-view by mosaicking frames and allows combining multiple videos.
The possibility of sharing one's point of view makes use of wearable cameras compelling. These videos are often long, boring and coupled with extreme shake, as the camera is worn on a moving person. Fast forwarding (i.e. frame sampling) is a natural choice for quick video browsing. However, this accentuates the shake caused by natural head motion in an egocentric video, making the fast forwarded video useless. We propose EgoSampling, an adaptive frame sampling that gives stable, fast forwarded, hyperlapse videos. Adaptive frame sampling is formulated as an energy minimization problem, whose optimal solution can be found in polynomial time. We further turn the camera shake from a drawback into a feature, enabling the increase in field-of-view of the output video. This is obtained when each output frame is mosaiced from several input frames. The proposed technique also enables the generation of a single hyperlapse video from multiple egocentric videos, allowing even faster video consumption.