Behavioural Pattern Discovery from Collections of Egocentric Photo-Streams
Abstract
The automatic discovery of behaviour is of high importance when aiming to assess and improve the quality of life of people. Egocentric images offer a rich and objective description of the daily life of the camera wearer. This work proposes a new method to identify a person's patterns of behaviour from collected egocentric photo-streams. Our model characterises time-frames based on the context (place, activities and environment objects) that define the composition of the image. Based on the similarity among the time-frames that describe the collected days for a user, we propose a new unsupervised greedy method to discover the behavioural pattern set based on a novel semantic clustering approach. Moreover, we present a new score metric to evaluate the performance of the proposed algorithm. We validate our method on 104 days and more than 100k images extracted from 7 users. Results show that behavioural patterns can be discovered to characterise the routine of individuals and consequently their lifestyle.
Cite
Text
Menchón et al. "Behavioural Pattern Discovery from Collections of Egocentric Photo-Streams." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-66823-5_28Markdown
[Menchón et al. "Behavioural Pattern Discovery from Collections of Egocentric Photo-Streams." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/menchon2020eccvw-behavioural/) doi:10.1007/978-3-030-66823-5_28BibTeX
@inproceedings{menchon2020eccvw-behavioural,
title = {{Behavioural Pattern Discovery from Collections of Egocentric Photo-Streams}},
author = {Menchón, Martín and Talavera, Estefanía and Massa, Jose M. and Radeva, Petia},
booktitle = {European Conference on Computer Vision Workshops},
year = {2020},
pages = {469-484},
doi = {10.1007/978-3-030-66823-5_28},
url = {https://mlanthology.org/eccvw/2020/menchon2020eccvw-behavioural/}
}