Abstract
Every year millions of people gather at Makkah, Saudi Arabia during the Hajj, an annual Islamic pilgrimage. The area at Makkah is small, and the number of attendees increases each year, which has created an ongoing and ever increasing problem of crowd management. In this paper, we present our integrated solution to the localization challenge of tracking specific users in a highly crowded area where GPS signal may be weak or even unavailable. Smartphone based Human Activity Recognition (HAR) uses various sensors that are built into the smartphone to sense a person's activity in real time. Applications that incorporate HAR can be used to track a person's movements and are very useful in areas such as health care. We also propose a group-tracking mechanism that can be applied when a group member appears to get lost. Other members of the group will be immediately notified and receive an estimation of the lost member's location. Using wireless signals (RSSI) and inertial sensor data, we have developed a mathematical model and a system for both outdoor and indoor localization. The experimental results show that the proposed system is able to detect locations of users with high accuracy, with an error of less than 2.5 meters. The system will be used by millions of users in Makkah, where there have been thousands of reported cases of pilgrims getting lost during the Hajj, however, it is scalable to accommodate any other crowded population.