Indoor positioning method based on WiFi (Wireless Fidelity) fingerprints

The invention discloses an indoor positioning method based on WiFi (Wireless Fidelity) fingerprints. The method comprises the steps of continuously acquiring RSSI (Received Signal Strength Indication) values of WiFi signals within a certain period of time for each known position point in a place to be positioned, preprocessing the acquired data, counting times num that each AP (Access Point) occurs in the signal sequence of a certain position point, deleting AP signal data with num which is smaller than half of the total length of the sequence, calculating the average value mu and the standard deviation delta of the preprocessed data, and storing the average value mu and the standard deviation delta in a database; and acquiring the RSSI values of the WiFi signals at a point to be positioned, uploading the RSSI values to a sever, matching the acquired data of the point to be positioned with values in the database by adopting a multilevel probability algorithm to obtain W position estimation values with the maximum probability and performing time averaging to obtain the position estimation of the point to be measured. Compared with the prior art, the method has the advantages that the positioning accuracy is guaranteed, the operability and the practicability of the system are improved, and the goal of accurate positioning at distance of 3m can be achieved.