The OBD-II is a standard diagnostic port which has been widely used in the vehicle diagnostic and maintenance. In this thesis, we design and implement an edge-computing based anomaly detection platform (ECADP) for car driving, which collects the value of OBD parameters from the engine ECU of vehicle through OBD-II and detect anomalies with a pre-trained driving behavior model. The platform can be installed on a small single-board computer called Raspberry Pi. The anomaly detection service runs with low latency.