Organizing egocentric videos of daily living activities. (December 2017)

• Record Type: Journal Article
• Authors: Ortis, Alessandro; Farinella, Giovanni M.; D'Amico, Valeria; Addesso, Luca; Torrisi, Giovanni; Battiato, Sebastiano
• Is Part Of: Pattern recognition. Volume 72(2017:Dec.)
• Page Start: 207
• Page End: 218
• Publication Date: 2017-12
• Subjects: First person vision -- Video summarization -- Video indexing; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.07.010
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A method for automatic organization of egocentric videos. An effective and fast content-based video segmentation. A framework for clustering of video clips. The method overcomes other state of the art in terms of both accuracy and computational time. The overall system is robust both on wearable and mobile domains. Abstract: Egocentric videos are becoming popular since the possibility to observe the scene flow from the user's point of view (First Person Vision). Among the different applications of egocentric vision is the daily living monitoring of a user wearing the camera. We propose a system able to automatically organize egocentric videos acquired by the user over different days. Through an unsupervised temporal segmentation, each egocentric video is divided in chapters by considering the visual content. The obtained video segments related to the different days are hence connected according to the scene context in which the user acts. Experiments on a challenging egocentric video dataset demonstrate the effectiveness of the proposed approach that outperforms with a good margin the state of the art in accuracy and computational time.