Fusing Video and Inertial Sensor Data for Walking Person Identification

TL;DR

This paper presents a practical system combining video and inertial sensors to identify walking persons, demonstrating robustness and achieving up to 76% accuracy within 2 seconds.

Contribution

It introduces a novel walking person identification method that fuses video and inertial sensor data for improved accuracy and practicality.

Findings

Achieves up to 76% correct identification rate in 2 seconds

Effectively associates smartphone sensors with human objects in videos

Demonstrates robustness in identifying persons during walking activities

Abstract

An autonomous computer system (such as a robot) typically needs to identify, locate, and track persons appearing in its sight. However, most solutions have their limitations regarding efficiency, practicability, or environmental constraints. In this paper, we propose an effective and practical system which combines video and inertial sensors for person identification (PID). Persons who do different activities are easy to identify. To show the robustness and potential of our system, we propose a walking person identification (WPID) method to identify persons walking at the same time. By comparing features derived from both video and inertial sensor data, we can associate sensors in smartphones with human objects in videos. Results show that the correctly identified rate of our WPID method can up to 76% in 2 seconds.