Predicting the Future from First Person (Egocentric) Vision: A Survey

TL;DR

This survey reviews recent advances in egocentric vision focusing on predicting future human activities, trajectories, and interactions, emphasizing applications, datasets, models, and the need for standardization in real-world scenarios.

Contribution

It provides a comprehensive overview of the evolution, challenges, and future directions in egocentric vision for future prediction tasks, highlighting gaps and opportunities.

Findings

Methods can significantly impact human-robot interaction and assistive technologies.

Current datasets and models are evolving but lack standardization for real-world applications.

Further research should focus on task standardization and dataset development for industrial scenarios.

Abstract

Egocentric videos can bring a lot of information about how humans perceive the world and interact with the environment, which can be beneficial for the analysis of human behaviour. The research in egocentric video analysis is developing rapidly thanks to the increasing availability of wearable devices and the opportunities offered by new large-scale egocentric datasets. As computer vision techniques continue to develop at an increasing pace, the tasks related to the prediction of future are starting to evolve from the need of understanding the present. Predicting future human activities, trajectories and interactions with objects is crucial in applications such as human-robot interaction, assistive wearable technologies for both industrial and daily living scenarios, entertainment and virtual or augmented reality. This survey summarises the evolution of studies in the context of future prediction from egocentric vision making an overview of applications, devices, existing problems, commonly used datasets, models and input modalities. Our analysis highlights that methods for future prediction from egocentric vision can have a significant impact in a range of applications and that further research efforts should be devoted to the standardisation of tasks and the proposal of datasets considering real-world scenarios such as the ones with an industrial vocation.