Home // MMEDIA 2016, The Eighth International Conferences on Advances in Multimedia // View article

A Crowd-sourced Method for Real-time Detection and Localization of Unexpected Events

Authors:
Taishi Yamamoto
Kenta Oku
Kyoji Kawagoe

Keywords: event detection, smart phones, crowd-sourced system, global positioning system, sensor data

Abstract:
In this paper, a Real-Time Smart and Quick Unexpected-Event Detect (RT-SQUED) method is proposed to detect and localize unexpected events, such as traffic accidents, in real-time, assuming crowd sourcing with smartphone devices. The authors previously proposed the SQUED, a crowd-sourced system for detection and localization of unexpected events from smartphone-sensor data. When SQUED users find an event, they point their smartphones toward a direction of the event. SQUED can detect the location and the time of the event using the smartphone-sensor data. However, the SQUED method is difficult to scale because of its computational cost problem. Therefore, it becomes difficult to detect events in real-time. Our new method, called RT-SQUED, solves this problem using concurrent two-phase processing. RT-SQUED is composed of rough and concrete processing phases. In this paper, effectiveness of RT-SQUED is also discussed.

Pages: 19 to 22

Copyright: Copyright (c) IARIA, 2016

Publication date: February 21, 2016

Published in: conference

ISSN: 2308-4448

ISBN: 978-1-61208-452-7

Location: Lisbon, Portugal

Dates: from February 21, 2016 to February 25, 2016