Egocentric Field-of-View Localization Using First-Person Point-of-View Devices

TL;DR

This paper introduces a method for localizing a person's field-of-view in an environment using first-person images, videos, and sensor data, enabling applications in AR, social interaction analysis, and event understanding.

Contribution

It presents a novel approach that combines image/video matching with sensor data to accurately determine egocentric FOV in various environments.

Findings

Effective in indoor and outdoor settings

Supports single and multi-user localization

Enhances applications in AR and social analysis

Abstract

We present a technique that uses images, videos and sensor data taken from first-person point-of-view devices to perform egocentric field-of-view (FOV) localization. We define egocentric FOV localization as capturing the visual information from a person's field-of-view in a given environment and transferring this information onto a reference corpus of images and videos of the same space, hence determining what a person is attending to. Our method matches images and video taken from the first-person perspective with the reference corpus and refines the results using the first-person's head orientation information obtained using the device sensors. We demonstrate single and multi-user egocentric FOV localization in different indoor and outdoor environments with applications in augmented reality, event understanding and studying social interactions.