Unsupervised understanding of location and illumination changes in egocentric videos
Alejandro Betancourta b✉, Natalia Díaz-Rodríguezc, Emilia Ivanova Barakovab, Lucio Marcenaroa, Matthias Rauterberg Ab, Carlo S. Regazzonia
- aDepartment of Engineering (DITEN), University of Genova, Genova, Italy
- bDepartment of Industrial Design, Eindhoven University of Technology, Eindhoven, Netherlands
- cComputer Science Department, University of California Santa Cruz, CA, USA
- ✉Corresponding author
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
Wearable cameras stand out as one of the most promising devices for the upcoming years, and as a consequence, the demand of computer algorithms to automatically understand the videos recorded with them is increasing quickly. An automatic understanding of these videos is not an easy task, and its mobile nature implies important challenges to be faced, such as the changing light conditions and the unrestricted locations recorded. This paper proposes an unsupervised strategy based on global features and manifold learning to endow wearable cameras with contextual information regarding the light conditions and the location captured. Results show that non-linear manifold methods can capture contextual patterns from global features without compromising large computational resources. The proposed strategy is used, as an application case, as a switching mechanism to improve the hand-detection problem in egocentric videos.
TL;DRResults show that non-linear manifold methods can capture contextual patterns from global features without compromising large computational resources. (Semantic Scholar)