DeepVIP: Deep Learning-Based Vehicle Indoor Positioning Using Smartphones
Baoding Zhou, Zhining Gu, Fuqiang Gu, Peng Wu, Chengjing Yang, Xu Liu, Linchao Li, Yan Li, Qingquan Li
Abstract
The advent of sensor-rich smart devices (e.g., smartphones) has enabled a lot of applications and services. One of these applications and services is smartphone-based vehicle indoor positioning, which is a key technology for smart car parking and driverless cars. So far, most vehicle indoor positioning solutions either use infrastructures (e.g., WiFi access points) or inertial sensors, which suffer from low positioning accuracy, limited coverage, or high cost to deploy new equipment. To tackle these challenges, in this work we propose a novel Deep Learning-based Vehicle Indoor Positioning (DeepVIP) approach using smartphone built-in sensors, including accelerometer, gyroscope, magnetometer, and gravity sensor. Experiments are conducted in indoor parking areas. Experimental results show that the proposed method outperforms the state-of-the-art methods.