Method for improving WiFi positioning result jumping based on cell phone sensor information

Abstract

The invention discloses a method for improving WiFi positioning result jumping based on cell phone sensor information. The method specifically includes the following steps of obtaining sensor data, processing and analyzing the data, judging the movement state, and obtaining the positioning result. By means of the method, the unstable factors such as the signal strength are taken into full consideration to improve WiFi positioning result jumping; no additional devices are needed, the method is convenient and rapid to implement, low in deploy cost and simple and effective in judgment algorithm.

Description

Technical field: [0001] The invention relates to a method for improving the jitter of WiFi positioning results based on mobile phone sensor information. Background technique: [0002] With the advent of the mobile Internet era, various smart phones are rapidly occupying the mobile phone market. Since every smartphone has a WiFi function, it has pushed WiFi into a boom. Therefore, it is the best choice technology to use the widely existing WiFi network to locate the targets in dense buildings or indoors. Positioning through the WiFi network can make up for the limitations of satellite positioning in dense buildings and indoor applications, expand the application industry and scope of positioning services, improve positioning accuracy, reduce deployment costs, and improve equipment utilization. [0003] Now the most commonly used method based on WiFi positioning is the fingerprint identification method. WiFi positioning based on fingerprint identification is divided into tw...

AI Technical Summary

Problems solved by technology

[0008] The first method of state detection based on body position markers is a relatively mature human body movement state detection method, but this method requires a high-speed camera to capture human body movement, and if the camera capture speed is not timely, the detection results will have a large deviation

In addition, this method requires the deployment of a large number of cameras, and if low-quality cameras are used, the detection results may be greatly affected by the surrounding light and other environments

In general, this method is expensive, and it can only be applied to a small range of indoor environments, and cannot be promoted and used on a large scale

[0009] The second method based on multi-device state detection needs to fix multiple devices on the human body, which adds extra trouble to the user

The whole set of sensor equipment worn by it is expensive and not suitable for general personal use

In addition, since the sensor itself has no computing power, the data needs to be transmitted to the computer through the network for processing, and it cannot be portable and can be detected anytime, anywhere.

[0010] The third SVM-based state detection method requires sample training in advance, and the division of motion states is too fine to achieve simple and fast results.

[0011] The above three methods are too fine-grained for the division of motion states, and the algorithm is very complicated to implement

Images