| With the boom of pervasive applications,indoor localization becomes more and more important.Recently,the indoor localization method based on Wi-Fi has become the mainstream benefited from the quick development of wireless network and the popularity of wireless access technology and the rapid popularization of WIFI network equipment and mobile intelligent terminal.But the traditional fingerprint based positioning method requires the site survey which requires collecting fingerprint data of location scene to establish location fingerprint database.Due to the requirement of site survey,the time required and the workload is huge which needs to collect and record data of every location points.And when the indoor environment has changed,such as the alteration of indoor APs,the indoor layout adjustment and even the opening and closing of doors and windows,the established location fingerprint database cannot reflect the indoor situation.So in order to guarantee the authenticity and timeliness of the fingerprint database,the real-time updating is needed to adapt to the changes in the room.All these factors greatly limit its scope of application.About this problem,there has attracted many domestic and foreign researchers.In order to ensure the timeliness and accuracy of fingerprint database at the same time,but also can reduce the labor cost and time cost which making it become a kind of universal indoor positioning technology,it has become a new research direction in the field of indoor positioning,as well as a challenge for many researchers who always want to solve it.Therefore the form of crowdsourcing is utilized to collect indoor information and to record a large number of path information.The consistency of the low dimensional embedded manifold in the path is used for geographical position matching in order to establish the database of location fingerprints.Gauss particle filter denoising sensor data is used to further solve the problem of pedestrian step difference.According to the continuity of the user's location and the path information,the reasonable nearest neighbor points are selected,and the accurate positioning is realized.The e xperiments can achieve comparable accuracy to the traditional method.The proposed method can adapt to the environmental changes in real time,and the positioning accuracy is better than the traditional positioning method after 2 weeks and even after 1 month.This paper mainly addresses the following four aspects:ˇIn the case that the positioning error is not large,the time consumed by the location fingerprint database is greatly reduced by the form of crowdsourcing;ˇSolve the problem that the traditional database cannot adapt to the change of the room,and can update the fingerprint database according to the newly collected data;ˇThe Gauss particle filter is used to denoise the sensor data,and then the walking distance is calculated with the known number of steps,and further to solve the problem of pedestrian step difference;ˇThe location of the nearest neighbor is selected by using the continuity of the location and the detailed path information,which can effectively eliminate the false nearest neighbor points,thus reducing the positioning error. |
PDF Full Text Request