Researches On Target Locating And Route Planning Of Indoor Multi-floor

The development of modern society and population increase,large construction floor height increasing,increasingly complex internal structure,people for LBS(Location based service)demand increase,with the rapid development of Internet technology and the widespread popularity of intelligent terminal,accurate indoor positioning and emergency evacuation Services in daily life and the indoor increasingly highlight the importance of emergency rescue.In daily life scenarios,the infrastructure in WLAN is complete,and the location technology based on RSSI(Received Signal Strength Indication)fingerprint has been widely studied and applied due to its advantages such as low cost,simple deployment,strong penetration and convenient access,etc.,which requires no additional hardware facilities.In indoor emergency rescue scenarios,escape evacuation path planning and guiding trapped people to escape actively play an important role in fire rescue of large buildings based on the Internet of Things.At present,most of the existing indoor positioning and evacuation studies are based on two-dimensional space,that is,a single floor,which cannot meet the requirements of positioning and evacuation for large high-rise buildings.The traditional RSSI based fingerprint location technology needs to build the RSSI fingerprint database in the offline stage,but the time-consuming and labors of the fingerprint database construction process hinder the development of fingerprint location technology.The existing two-dimensional emergency evacuation model can be used to guide and rescue the trapped people.However,due to the limited environmental information,the real-time data of the fire site and the behavior characteristics of the trapped people were not considered,resulting in low safety.In view of the difficulty in fingerprint database construction and emergency evacuation,this paper proposes a multi-storey fingerprint database construction method based on crowdsourcing and HMM(Hidden Markov Model),and proposes a real-time fire perception multi-floor escape path dynamic planning method.The specific work contents are as follows:In this paper,we propose a low-cost and high-efficiency multi-floor fingerprint database construction method based on crowdsourcing aiming at the difficulty of fingerprint construction.Firstly,the indoor floor plan is transformed into indoor semantic map.Secondly,the data of IMU(inertial measurement unit)in the smartphone of crowdsourcing users are collected,and the sensor data are classified into corresponding floors by KF(Kalman filter)fusion algorithm.A segmented trajectory acquisition method is proposed,according to the sensor data,the relative trajectory and RSSI value sequence of the user are acquired.Finally,HMM(hidden Markov model)and TM-Viterbi(track matching Viterbi algorithm)is used to match the trajectory with the main path of indoor semantic map,thus providing the floor label and physical location label for RSSI value sequence.The HMM map matching algorithm of MCSLoc does not need the user’s initial location,so as to build a multi floor fingerprint database.We propose a dynamic escape route planning method for indoor multi-floor buildings based on real-time fire awareness aiming at the difficulty of emergency evacuation(DERP).DERP is enabled by two novel designs.First,a three-dimensional(3D)fire information model is constructed by cellular automata considering the overall situation of indoor 3D topological structure,fire situation and crowd distribution.Second,a multiple constraints 3D indoor emergency escape route planning algorithm is designed based on a 3D path safety function.In the smart building,the disaster point can be effectively avoided,and the safe route can be planned in real time by obtaining the threat situation of fire,and the dynamic escape path planning of multi-floor and multi-exit can be realized in the fire scene.The experimental results show that MCSLoc can quickly obtain the absolute initial position of the trajectory,effectively construct the multi floor fingerprint database,improve the multi floor positioning efficiency,and achieve the positioning accuracy of 1.87 meters.The experimental results show that derp achieves 100% disaster avoidance rate.Compared with the classic A* and Dijkstra algorithm,the average escape time is shorter,and the escape route can be planned and adjusted dynamically in time and the escape probability of the trapped personnel can be improved.