Abstract:In order to realize the human-computer interaction of handwriting in the air and bring a new human-computer interaction experience to users, an air handwriting track recognition system based on inertial sensor is designed. The system mainly includes four parts: data acquisition and filtering module, quaternion coordinate system conversion module, integration acquisition and measurement track module and neural network identification module. In this paper, the Kalman filter algorithm is used in the two links of original data acquisition and integration acquisition. In order to verify the accuracy of the system, taking the writing of the number 8 in the air as an example, the trajectory in the space after Kalman filtering is complete and clear, which is also verified by the capture of the number 0-9 trajectory. The AlexNet neural network migration learning module is designed for trajectory recognition. The experimental results show that the recognition accuracy is 87.3%, and the trajectory recognition degree is high, which achieves the expected effect.