Internet of Things (IoT) is playing an increasingly important role in Intelligent Transportation Systems (ITS) for real-time sensing and communication. In ITS, the velocity of vehicles provides important information for traffic management. However, the present methods for monitoring vehicle speed have many shortcomings. In this paper, we propose MagSpeed, a novel vehicle speed estimation method based on a small magnetic sensor. The developed magnetic sensor system is wireless, cost-effective, and environmental-friendly. Through modelling of local magnetic field perturbations caused by a moving vehicle, we extract the characteristics of magnetic waveforms for speed estimation. In addition, we compare the performance of the models with other speed estimation algorithms, which shows the superior accuracy of the proposed technique in speed estimation.