A Behavior-Based Method for Indoor Localization and Landmark Semantic Identification

Abstract

The invention discloses an indoor location and landmark semantic identification method based on behaviors. The method comprises steps as follows: on the basis of action modes of an indoor person, data of the designed action modes is collected by a built-in inertial sensor arranged in a smart phone, the data is subjected to preprocessing and characteristic extraction, and action sequences are identified by a support vector machine and are recognized as behavior patterns with a fuzzy pattern recognition algorithm; an initial locating point is determined according to WIFI signals, and an approximate walking track is determined with a dead reckoning method; the behavior patterns and locations are analyzed respectively; more accurate indoor location is realized by continuously updating landmarks, and the landmarks are subjected to semantic identification according to attributes of the landmarks. When the indoor pedestrian is located, drift errors produced through dead reckoning are corrected according to the behavior patterns and a landmark set. According to the method, the location errors can be corrected by the landmarks, disturbance of environmental factors and noise of the sensor are effectively treated, and precision of indoor location is remarkably improved.

Description

technical field [0001] The invention relates to the field of indoor pedestrian positioning and landmark semantic identification based on inertial sensors, and proposes a behavior-based indoor positioning and landmark semantic identification method. Background technique [0002] Indoor positioning based on inertial sensors is to first collect RF signals in an indoor environment, and cluster the collected RF signals and corresponding fingerprint databases to obtain the initial position of pedestrians through clustering algorithms; then collect and process acceleration sensors, gyroscopes and The data of the geomagnetic sensor is used to calculate the displacement and heading angle of the pedestrian when walking, combined with the principle of dead reckoning, on the basis of the known previous position, the current position of the pedestrian is calculated according to the displacement and heading angle during the walking time period. [0003] In the heading reckoning algorithm,...

AI Technical Summary

Problems solved by technology

For indoor positioning methods, some only filter and process the sensor data, although the drift error is reduced to a certain extent, but the positioning accuracy is not fundamentally improved; some methods correct the positioning error through radio frequency signals such as Bluetooth, Although the positioning accuracy is slightly improved, radio frequency signal positioning requires cumbersome calibration work; some methods combine sensor data and WIFI signals to identify specific landmarks, and use landmarks to correct the cumulative error of sensor drift. Although the positioning accuracy is greatly improved, However, it is only suitable for large places equipped with services such as elevators and escalators, and is not suitable for small and medium-sized apartment indoor environments

Images