Research on Indoor Location Technology in Metro Station

In order to assist blind people to travel independently and solve the problems of jumping of location points and poor real-time location caused by traditional indoor location method, a method based on region classification and electronic map fusion is proposed. In this method, the idea of position fingerprint matching is adopted. In the off-line stage, the best Gauss filtering template is searched for RSSI sequence generated by Bluetooth sensor by iteration optimization. The filtered sequence mean is used to construct position fingerprint database, and the support vector machine model is used to classify the position fingerprint database at the first level. In the online stage, the idea of sliding window is used to classify the location area in two levels. In the window range, KNN algorithm based on Euclidean distance is used to calculate the position coordinates, and the path layer information of electronic map is used to correct the position coordinates, so as to further control the error range and improve the location efficiency. Experiments in the subway station hall show that the filtering method improves the positioning accuracy by nearly 4%, and the positioning accuracy can reach 1.59 m by using this positioning algorithm.