Pedestrian inertial navigation based on CNN-SVM gait recognition algorithm

Pedestrian inertial navigation technology based on inertial measurement unit (IMU) has been widely used in indoor and outdoor applications in recent years. But the IMU has a relatively low measurement accuracy that leads to error accumulation. Zero speed update algorithms (ZUPT) are often used to suppress the accumulation of errors. The key to the zero-speed update algorithm is to accurately find the stance phase in the pedestrian gait cycle. In this paper, an adaptive zero-speed detection algorithm based on CNN-SVM gait recognition is proposed for pedestrian positioning. First, the CNN-SVM algorithm is used to distinguish six gaits and find the optimal detection threshold according to different gaits. At the same time, it is proposed to use the zero-angle velocity update algorithm (ZARU) to correct the angle error, and to improve the accuracy of positioning by combining the information of zero-speed update and zero-angle velocity update through Kalman filter. Finally, the validity of the proposed algorithm is verified by experiments.