Positioning method based on multi-mark fingerprint positioning

Abstract

The invention discloses a positioning method based on multi-mark fingerprint positioning. The method comprises the steps of drawing a wifi deployment map, and marking the position of a wireless AP (Access Point) on the map; then coordinating the map during offline sampling, marking each coordinate point as a training tuple, dividing the training tuples by using signal strength RSSI (Received Signal Strength Indicator) information of the wireless AP acquired by a mobile terminal at each coordinate point in a WiFi network, and establishing an offline database after filtering, wherein the offline database comprises the training tuples as well as marks and coordinates corresponding to the training tuples; and finally, calculating Manhattan distances between the raining tuples and tested tuples by traversing a training tuple set in the offline database during online positioning, updating a priority queue according to the Manhattan distances, and collecting statistics on the frequency of occurrence of each training tuple in the priority queue, wherein the coordinate point corresponding to the training tuple occurring most frequently is the coordinate point of the mobile terminal to be positioned.

Description

technical field [0001] The invention belongs to the technical field of positioning and tracking, and in particular relates to a positioning method based on multi-identification fingerprint positioning. Background technique [0002] At present, positioning service has become an indispensable service in daily life. With the massive construction of public facilities such as shopping malls and stations, people's demand for indoor positioning continues to increase, and indoor positioning is gradually becoming a research hotspot. However, indoor multipath conditions are complex, the traditional Bluetooth positioning method has large errors, and it is difficult to distinguish users. At the same time, special equipment is required to measure user coordinates, which increases the complexity of the system. The positioning method based on wireless local area network RSSI signal measurement is gradually becoming a hotspot for indoor positioning due to its low cost, large coverage and si...

AI Technical Summary

Problems solved by technology

The classic algorithms in the deterministic method include the nearest neighbor method (Nearest Neighbor, NN), the K nearest neighbor method (K Nearest Neighbor, KNN) and the weighted K nearest neighbor method (Weighted K Nearest Neighbor, WKNN). The mean value of the signal characteristics is calculated, and the utilization rate of the original data is low, so the positioning error is relatively large. Compared with the deterministic algorithm, the probabilistic algorithm is based on the idea of ​​mathematical statistics, which can better solve the impact caused by the environment. However, the utilization rate of the original data is also low

[0004] The existing algorithm does not handle the pre-measured data very well. Whether it is calculating the average value or weighting the average value, there will be a certain amount of data loss in the middle, which indirectly increases the algorithm error.

Images