Towards Semantic Fast-Forward and Stabilized Egocentric Videos
This work addresses the tediousness of watching long first-person videos, which is a problem for users of wearable cameras and video-sharing platforms, but it appears incremental as it builds on existing fast-forward methods.
The authors tackled the problem of summarizing and stabilizing long, unedited egocentric videos by developing a method that extracts semantic information from frames to balance smoothness and relevance during fast-forwarding, and introduced a new dataset and smoothness evaluation metric for testing.
The emergence of low-cost personal mobiles devices and wearable cameras and the increasing storage capacity of video-sharing websites have pushed forward a growing interest towards first-person videos. Since most of the recorded videos compose long-running streams with unedited content, they are tedious and unpleasant to watch. The fast-forward state-of-the-art methods are facing challenges of balancing the smoothness of the video and the emphasis in the relevant frames given a speed-up rate. In this work, we present a methodology capable of summarizing and stabilizing egocentric videos by extracting the semantic information from the frames. This paper also describes a dataset collection with several semantically labeled videos and introduces a new smoothness evaluation metric for egocentric videos that is used to test our method.