In order to minimize the occurrence of ?re accidents caused by electric bicycles entering buildings, this paper develops an intelligent elevator blocking system based on the mobile Internet of Things. This system uses Qualcomm MSM8953 as the main chip and designs a development board based on this main chip as an embedded platform. At the same time, the platform is equipped with the Shu?eNetV2 object detection algorithm, which realizes the detection, recognition, and voice prompt functions for electric bicycles entering elevators. Compared to other similar systems, this system has the advantages of small size and strong scalability, and reduces application costs while improving ?exibility. The test results show that the recognition accuracy of the system can reach over 98.3%. The system has the value of achieving commercialization and industrialization.