Research And Implementation Of Indoor Map Automatic Construction Method Based On Crowdsourcing

Location-based services and applications,such as location-based social networks,games and advertising,have grown rapidly over the past decade.This is due to the widespread use of smart mobile devices and the development of positioning technology.These location-based services and applications typically use maps to display user locations.Outdoor location service providers offer almost all areas of the outdoor street map,but the development of indoor floor plans is still very limited,greatly affecting the indoor positioning based on the rapid development and deployment of services and applications.At present,most of the indoor applications are dependent on the manual creation of the indoor floor plan.Manually adding,editing and maintaining a large number of building floor plans requires significant cost and effort.In order to solve the above problems,this thesis proposes an automatic method of indoor map based on smart phone and crowdsourcing.The method is used to collect the data of human action in the room through the mobile sensor,and the number of steps,steps and directions of the person are calculated by the pedestrian dead reckoning algorithm to determine the position information of the person at each step,and the human walking trajectory.The In order to construct the map accurately and efficiently,this thesis adopts the method of crowdsourcing to obtain the trajectory information of a large number of pedestrians.Through the analysis of a large number of trajectories,the indoor map information is constructed.In order to detect the indoor mark points,this thesis presents an effective up and down position detection algorithm and the room door position detection algorithm.The up and down detection is based on the slope of the barometric data and the acceleration level.The room door position detection is carried out in conjunction with the gyroscope and WiFi,and the location of the door is further determined by the density-based clustering algorithm.According to the location of the door,this thesis carries on the segmentation and the cluster processing to the massive pedestrian track data.For the type of room trajectory,this thesis uses the?-shape algorithm to construct the room shape and size.In this thesis,the principal component analysis algorithm is used to construct the length and width of the corridor.According to the location of the coordinates of the track,will be built out of the room and corridor spliced ??into a complete indoor map,so as to complete the indoor mapautomatically built.In this thesis,the method is implemented and experimented in the actual environment.The experimental results show that the average error of the room position is 1.96 m and the average error of the length of the corridor is 1.85 m in the automatic building experiment with multi-room.The map constructed by this method basically reflects the relative positional relationship between the rooms and corridors in the real map,and the order of the positions of the rooms in the corridor.This thesis puts forward the automatic construction method of indoor map based on crowdsourcing,which realizes the automatic construction of indoor map.