Analyzing First-Person Stories Based on Socializing, Eating and Sedentary Patterns
This work addresses lifestyle pattern analysis for researchers or health professionals using wearable camera data, but it is incremental as it applies existing methods to a new dataset.
The researchers tackled the problem of analyzing first-person stories by creating an egocentric dataset of over 45,000 manually labeled images from four people to identify socializing, eating, and sedentary patterns, and proposed machine learning and deep learning approaches that demonstrated adequacy for classifying images into 12 target categories.
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.