It is often frustrating for drivers to find parking spaces, and parking itself is costly in almost every major city in the world. Here we propose a crowdsourcing solution by exploiting sensors in smart-phones to collect real-time parking availability information. We design a phone-based system to track a driver's trajectory to detect when they are about to leave their parking spot. We focus on the efficiency and accuracy of using a phone to monitor the driver's walking trajectory, applying a waist-mounted PDR method that can measure the driver's moving distance with a high accuracy. In addition, we design a map matching algorithm to calibrate the direction errors when the driver is in an indoor environment, using widely-available building floor plans. The results of our experiment show that we can achieve about 98% accuracy in estimating the user's walking distance, with an overall location error of about 0.48 m.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Artificial Intelligence