Special Issue on Egocentric Vision and Lifelogging Tools of the Journal of Visual Communication and Image Representation (JVCI)
The emergence of low-cost, high-quality personal wearable cameras combined with the increasing storage capacity of video-sharing websites have evoked a growing interest in ﬁrst-person videos. Since most videos are composed of long-running unedited streams which are usually tedious and unpleasant to watch. State-of-the-art fast-forward methods currently face the challenge of providing an adequate balance between smoothness in visual ﬂow and the emphasis on the relevant parts. In this work, we present the Multi-Importance Fast-Forward (MIFF), a fully automatic methodology to fast-forward egocentric videos facing these challenges. The dilemma of deﬁning what is the semantic information of a video is addressed by a learning process based on the preferences of the user. Results show that the proposed method keeps over 3 times more semantic content than the state-of-the-art fast-forward. Finally, we discuss the need of a particular video stabilization techniques for fast-forward egocentric videos.
Source code (NEW!)
Methodology and Results
We compare the proposed methodology against the following methods:
- EgoSampling – Poleg et al., Egosampling: Fast-forward and stereo for egocentric videos, CVPR 2015.
- Microsoft Hyperlapse – Joshi et al., Real-time hyperlapse creation via optimal frame selection, ACM. Trans. Graph. 2015.
- Stabilized Semantic Fast-Forward (SSFF) – Silva et al., Towards semantic fast-forward and stabilized egocentric videos, EPIC@ECCV 2016.
We conducted the experimental evaluation using the following datasets:
- EgoSequences – Poleg et al., Egosampling: Fast-forward and stereo for egocentric videos, CVPR 2015.
- Semantic Dataset – Silva et al., Towards Semantic Fast-Forward and Stabilized Egocentric Videos, EPIC@ECCV 2016.
Felipe Cadar ChamoneUndergraduate Student
João Pedro Klock FerreiraUndergraduate Student