Analyzing First-Person Stories Based on Socializing, Eating and Sedentary Patterns

TL;DR

This paper introduces a new egocentric image dataset and compares machine learning and deep learning methods for classifying images into socializing, eating, and sedentary activity categories, aiding lifestyle analysis.

Contribution

It provides a novel egocentric dataset with manual labels and evaluates classification approaches using traditional and deep learning techniques for lifestyle pattern recognition.

Findings

Deep learning methods outperform traditional classifiers.

The dataset effectively captures lifestyle patterns.

Classification accuracy demonstrates feasibility for lifestyle monitoring.

Abstract

First-person stories can be analyzed by means of egocentric pictures acquired throughout the whole active day with wearable cameras. This manuscript presents an egocentric dataset with more than 45,000 pictures from four people in different environments such as working or studying. All the images were manually labeled to identify three patterns of interest regarding people's lifestyle: socializing, eating and sedentary. Additionally, two different approaches are proposed to classify egocentric images into one of the 12 target categories defined to characterize these three patterns. The approaches are based on machine learning and deep learning techniques, including traditional classifiers and state-of-art convolutional neural networks. The experimental results obtained when applying these methods to the egocentric dataset demonstrated their adequacy for the problem at hand.