Predicting Daily Activities From Egocentric Images Using Deep Learning

TL;DR

This paper introduces a deep learning approach using CNNs and late fusion ensemble to predict daily activities from egocentric images, achieving over 83% accuracy on a large dataset.

Contribution

It presents a novel deep learning method with a late fusion ensemble that incorporates contextual information for activity prediction from egocentric images.

Findings

Achieved 83.07% overall accuracy in activity classification.

Demonstrated the effectiveness of fine-tuning for new users.

Collected a large dataset of 40,103 images over 6 months.

Abstract

We present a method to analyze images taken from a passive egocentric wearable camera along with the contextual information, such as time and day of week, to learn and predict everyday activities of an individual. We collected a dataset of 40,103 egocentric images over a 6 month period with 19 activity classes and demonstrate the benefit of state-of-the-art deep learning techniques for learning and predicting daily activities. Classification is conducted using a Convolutional Neural Network (CNN) with a classification method we introduce called a late fusion ensemble. This late fusion ensemble incorporates relevant contextual information and increases our classification accuracy. Our technique achieves an overall accuracy of 83.07% in predicting a person's activity across the 19 activity classes. We also demonstrate some promising results from two additional users by fine-tuning the classifier with one day of training data.