104results about How to "Improve indoor positioning accuracy" patented technology

The invention provides an ultrasonic wave based indoor three-dimensional positioning system and method, which belong to the technical field of positioning and navigation. The system is a wireless sensor network system, and through combining with the radio frequency technology and the ultrasonic technology, the system can implement accurate positioning by using a TDOA (time difference of arrival) algorithm and a trilateral location algorithm. By using the system provided by the invention, the centimeter-level positioning accuracy can be achieved, and the real-time positioning of a plurality of target nodes in a passive positioning mode can be realized, so that the application of the system in positioning or navigating a plurality of targets becomes possible. The system also has the advantages of good confidentiality, low cost and low power consumption.

The invention discloses an indoor positioning method based on MEMS insert device and android smart mobile phone fusion, and belongs to the field of data processing and mobile terminal application. The method is characterized in that a Kalman filtering-based zero speed correction accumulative error elimination algorithm is adopted based on the motion characteristics of indoor positioning pedestrians and the drift error of an MEMS inert device on the premise of MEMS insert device and android smart mobile phone fusion; and different data sampling modes are designed based on the advantages and disadvantages of a gyroscope and an electron compass and the motion characteristics of the pedestrians in the pedestrian motion course angle determination process, and are fused with a particle filtering course angle determination algorithm in order to further increase the pedestrian course precision. The method can reduce the accumulative error in the inertial navigation resolving process, and allows accurate pedestrian displacement information and course angle information to be obtained.

The invention discloses an RSSI and TOA distance measurement based WIFI indoor positioning method. The RSSI and TOA distance measurement based WIFI indoor positioning method comprises the steps of acquiring an RSSI signal and establishing a database, adopting a positioning matching algorithm to perform data processing, adopting arrival time or colored noise elimination to perform distance measurement, establishing and rotating a planar rotating frame and performing searching, positioning and judgment. The RSSI and TOA distance measurement based WIFI indoor positioning method adopts united RSSI and TOA distance measurement to perform positioning, overcomes the defects existing when an RSSI and TOA are independently positioned and improves positioning precision and accuracy. Especially, a measurement error adapts to change of distance measurement data by establishing a target state equation and a colored noise measurement equation, and large-deviation data filtering-out effect is good. In addition, the planar rotating frame diagram established by means of the method enables the positioning process to be accurate and enables a positioning result to be high in accuracy and approximate to an actual result, and the RSSI and TOA distance measurement based WIFI indoor positioning method can be widely applied to WIFI based indoor positioning.

The invention provides a Wi-Fi fingerprint-assisted indoor mobile terminal inertial navigation method which comprises the following steps: calculating a weighting coefficient by using the value of Euclidean distance, obtained by virtue of a Wi-Fi fingerprint positioning technology, and the value of an inertial navigation distance of a mobile terminal; periodically weighing the pedestrian position obtained by Wi-Fi fingerprint positioning and the position obtained by inertial navigation of the mobile terminal; and calculating the final position of the mobile terminal. Compared with existing pure indoor navigation methods based on an inertial sensor of the mobile terminal, the method provided by the invention can be used for eliminating accumulative errors in the navigation of the inertial sensor, so that the indoor navigation precision is effectively improved.

The invention discloses an indoor positioning method based on manifold learning and an improved support vector machine. The method comprises a step of determining a positioning area, dividing the positioning area according to an indoor structural characteristic and a layout characteristic, and obtaining a classification result, a step of obtaining offline training data, and collecting hotspot RSS signal values which can be received by the reference points in different classification area as a training data set, a step of using an isometric mapping algorithm to carry out training data characteristic extraction, a step of using the training data to carry out support vector machine classified training, using a taboo search algorithm to carry out support vector machine classification hyper parameter searching, and establishing the support vector regression model of each category at the same time, a step of carrying out online positioning, collecting the RSS signal value of each hotspot of a target, using a support vector machine classification model to carry out classification, and obtaining the rough positioning area of the target, and a step of carrying out the accurate positioning of the target by using the support vector regression model according to the classification result. According to the method, the time-varying characteristic of the wireless signal intensity is effectively suppressed, and the precision is obviously improved.

The invention discloses an indoor positioning method based on multi-layer fingerprint matching. The indoor positioning method based on multi-layer fingerprint matching includes a first step of building four layers of fingerprint maps according to indoor environment; a second step of matching a signal intensity vector actually received by a user in a rule fingerprint map and a random fingerprint map to obtain positioning results of the two times of matching by using a k-nearest neighbor method; a third step of transforming the signal intensity vector actually received by the user into a distance vector, and matching the distance vector in a rule fingerprint distance map and the random fingerprint distance map to obtain positioning results of the two times of matching by using the k-nearest neighbor method; a fourth step of averaging user estimated position coordinates obtained according to the four-layer fingerprint matching to obtain final user estimated position coordinates. The indoor positioning method based on multi-layer fingerprint matching provided by the invention builds a fingerprint database according to received signal intensity and actual positions of rule reference points and random reference points and distances based on a path-loss model, thereby reducing effects of indoor multipath environment by using a multi-layer fingerprint strategy and improving indoor positioning accuracy.

The invention provides a method for probability type fingerprint matching in WiFi (Wireless Fidelity) indoor positioning. The method is a method for probability type indoor positioning based on perception probability and kernel density estimation, and comprises five steps. Particularly, the method is a method for introducing the technologies of perception probability and non-parameter kernel density estimation into maximum likelihood probability. The method for probability type fingerprint matching in WiFi (Wireless Fidelity) indoor positioning can characterize distribution features of complex radio frequency signals more accurately through the kernel density estimation method, thus reducing a positioning error and obtaining better positioning accuracy.

The invention discloses an IMU-based indoor positioning method, and its technical characteristics are: step S1, according to the collected human body motion acceleration data, use a finite state machine to segment the effective gait and complete step counting and step length estimation; step S2 , according to the angular velocity (gyroscope), acceleration (acceleration sensor) and magnetic field strength (magnetic field sensor) data of effective gait, use the complementary filtering model to calculate the motion direction of current gait; Step S3, according to step length, motion direction estimation result and The map information is subjected to particle filtering, and the parameters of the step size model and the complementary filtering model are adjusted according to the properties of effective surviving particles. The invention uses a finite state machine to effectively remove invalid gait information and reduce the amount of data calculation; uses a complementary filter model to effectively fuse various sensor information to provide more accurate direction measurement results; uses a particle filter method to dynamically adjust the gait model and Complementary filtering model parameters, thereby reducing the step size estimation error and direction measurement error; comprehensively, the present invention can effectively suppress the error accumulation phenomenon in the dead reckoning process, and improve the accuracy of indoor positioning.

The invention discloses an internet-of-things intelligent mobile phone indoor locating method and system based on a wireless sensor network. The method comprises the steps that an intelligent mobile phone sends position sensing messages of an area where the intelligent mobile phone is located to wireless base stations through a wifi transmission module on the intelligent mobile phone, wherein signals of at least three wireless base stations cover the area where the intelligent mobile phone is located, and the intelligent mobile phone generates a position sensing message for each wireless base station; the wireless base stations send the position sensing messages to a data collection center, and the data collection center sends the position sensing messages to a locating server, wherein the locating server comprises a locating coverage and a locating coordinate system; the locating server calculates a coordinate of the intelligent mobile phone in the locating coordinate system according to the position sensing messages, and then the coordinate is converted into a coordinate in an intelligent mobile phone map and is sent to the intelligent mobile phone. The method and system makes up the blank of a GPS in the indoor localization, achieves all-dimensional and real-time location of the mobile phone, and greatly improves the precision of the mobile phone indoor location.

The invention discloses an indoor mobile phone positioning solving method comprising the following steps: S1, distributing a plurality of particles around a positioned target to form a particle set, and determining posture and normalization weight of each particle in the particle set by using a particle filter algorithm and an indoor geomagnetic field map according to the received direction of a monitoring sensor of a smart mobile phone and magnetic-field components; S2, performing Kring interpolation on the geomagnetic field map according to the corresponding magnetic-field component tested by the sensor of the smart mobile phone; S3, when a system tests that the target positioning is failure, performing a self-adaption re-sampling strategy, and when the system tests that the positioned target is correct, recovering the former re-sampling process; and S4, determining an estimated position of the positioned target in the indoor geomagnetic field map according to the posture and normalization weight of each particle in a re-sampling particle set. The indoor mobile phone positioning solving method can be used for achieving high indoor positioning accuracy with average of 1-2 m; and in addition, compared with a WiFi indoor positioning technology, the indoor mobile phone positioning solving method is low in energy consumption, high in reliability, and low in cost.

The invention discloses a UWB assisted inertial positioning method based on a fault-tolerant decision-making tree. For the non-line-of-sight problem of errors of an inertial navigation system with time accumulation and UWB positioning and the gross error problem due to a multipath effect and human body influence. A gyroscope high-precision segmented fitting error compensation model is proposed andadopted, and inertial navigation error drift is inhibited; meanwhile, based on UWB assisted personnel indoor inertial positioning, a fault-tolerant decision-making tree judgment model having the combined action of inertial navigation and UWB single-point positioning data is constructed, gross error factors of UWB positioning are eliminated, thus extended Kalman filter is applied to inertial navigation and UWB parameter differences, UWB assisted enhanced inertial navigation positioning is achieved, long-time continuous and reliable positioning can be achieved, and the method has a very strongengineering application value.

The invention relates to an indoor and outdoor parking positioning system and method. An outdoor satellite positioning module is navigated by means of a Beidou satellite; an indoor Zigbee positioning module adopts ranging-based RSSI positioning algorithm for performing indoor positioning, Kalman filtering is utilized for performing optimizing processing on positioning data, and finally a geometric three-edge positioning algorithm is adopted for obtaining the indoor position of the indoor positioning module; an indoor and outdoor fusion switching module fuses, switches and integrates indoor and outdoor positioning modes based on a particle filter according to the intensity of indoor and outdoor positioning communication signals so as to achieve smooth transition of an indoor and outdoor positioning result; the positioning result adopts an outdoor two-dimensional electronic map and an indoor plane graph as the basis, a positioning result is displayed. The indoor and outdoor parking positioning system and method can be used indoors and outdoors, indoor application places can be large underground parking garages mainly, the system is low in complexity, the positioning precision can meet the requirement for automobile running navigation and parking positioning.

The invention discloses an indoor positioning and navigation method by use of multi-information fusion and relates to an indoor navigation and positioning method. The method comprises the following steps of firstly, acquiring an indoor space distributed information planar graph including GPS (Global Positioning System) position information, geomagnetic data information and path data; then, enabling a mobile terminal to calculate a current position through built-in inertial sensor information; then, acquiring the geomagnetic data of the current position, and implementing indoor geomagnetic positioning through a geomagnetic matching algorithm; furthermore, correcting the current position according to a bluetooth base station of an indoor correction point; and finally, obtaining position information of a user by use of multi-information fusion, and implementing indoor navigation in combination with the path data of the planar graph. In combination with multiple positioning methods, the indoor positioning precision is effectively improved and the GPS information of an indoor position is acquired, the indoor path navigation is completed, and the method has wide application values.

The invention discloses an indoor positioning method for a high-speed unmanned rotor craft. The indoor positioning method comprises the following steps: multiple wireless routers are mounted in an area providing a positioning service; the area is divided into grids, and WiFi signal intensity in every grid is measured; the WiFi signal intensity is continuously measured by the craft in fixed time intervals; the craft asks for positioning to a server and uploads measured data; the server calculates the position of the craft according to a measuring result, and sends the result to the craft; the craft receives the positioning result. The method can effectively improve the indoor positioning precision of the unmanned rotor craft moving at the high speed.

The invention discloses an indoor mixed positioning method. The indoor mixed positioning method comprises the following steps: displaying the current map to obtain the relevant road network information in a first preset period; obtaining the PDR related hardware parameters and calculating a PDR trajectory in the first preset period; positioning the starting point by means of the WiFi location algorithm and the PDR trajectory, facing and entering the next positioning period; performing indoor location by means of the PDR location algorithm mainly, and carrying out similarity matching with the current PDR data and the road network data; and combining the similarity matching results with the current WiFi positioning results to detect and correct the current PDR positioning results. Accordingto the invention, the indoor positioning accuracy is further improved, and the indoor positioning accuracy can reach 1 meter to 3 meters.

The invention is suitable for the technical field of WiFi data positioning. The invention discloses a WiFi data-based position fingerprint database establishment and fitting method, comprising a position fingerprint database establishing step and a fingerprint database fitting step, wherein the position fingerprint database establishing step comprises the steps of dividing a grid fingerprint database, dividing a grid region at the latitude of a to-be-divided fingerprint database region, and taking two points as diagonal lines of a rectangular region for setting to obtain a blank grid fingerprint; and the fingerprint database filling step includes: filling grids at corresponding positions with the WiFi signal intensity data accumulatively uploaded by the user and the measured WiFi signal intensity data according to signal intensity data positions. Due to the fact that the plane grid fingerprint database is adopted, the problem that the positioning accuracy is reduced due to uneven fingerprint information distribution can be effectively solved. Meanwhile, Gaussian filtering is carried out on original collected data, errors caused by data collection are reduced, and a solid foundationis laid for subsequent further improvement of indoor positioning precision.

The invention discloses a road network correction-based hybrid indoor positioning method and belongs to the indoor positioning field. The method of the invention includes the following steps of: map production and positioning base station laying; wireless signal acquisition and processing; and hybrid indoor positioning algorithm operation. The method of the present invention supports various wireless sensor signals including Bluetooth, Wi-Fi, UWB, RFID and the like; a wireless signal filtering and area determination method is adopted, and therefore, irrelevant signals can be further eliminated, and the influence of environmental factors on positioning results can be reduced; an indoor map data-based positioning correction method is adopted, so that indoor positioning accuracy can be further improved; and a positioning calculation structure based on a positioning base station and a spatial database is adopted, so that the efficiency of positioning calculation can be further improved.

The invention provides an indoor double-layered positioning method for a walker. The indoor double-layered positioning method for the walker includes the following steps of lower-layer filtering: judging whether a detected object is in a static state or not in the present moment according to a preset static detecting mode, calculating mobile position coordinate information of the present moment, performing error state biased estimation and acquiring calibrated mobile position coordinate information of the present moment if the detected object is in the static state, and continuing judging if the detected object is not in the static state; upper-layer filtering: finding out finished moment of a zero velocity stage in the present moment, performing preset correction on the calibrated mobile position coordinate information of the present moment in the finished moment, acquiring a first difference, comparing the first difference with a second difference between the calibrated mobile position coordinate information of the present moment and calibrated mobile position coordinate information of a previous moment, detecting that the walker walks anticlockwise or clockwise in the present moment, and performing anticlockwise or clockwise correction if the walker walks anticlockwise or clockwise in the present moment. By the indoor double-layered positioning method for the walker, indoor positioning precision based on an inertial sensor is higher.

The invention provides an indoor positioning method, a device and a system, wherein the method comprises the following steps: detecting a wireless network received by a user terminal and correspondingsignal intensity; converting signal intensity in to a corresponding coding image; inputting the coding image into a prebuilt indoor positioning model, and determining positioning information of the user terminal according to an output result. According to the method provided by the invention, the signal intensity is converted into the coding image, and indoor positioning is executed through a model obtained by training of a deep convolutional neural network, thus, indoor positioning precision is improved.

The invention discloses an indoor online positioning method based on combination of a PDR and a hidden Markov model. The indoor online positioning method comprises the following steps: S1, acquiring aPDR step length deviation maximum value and a gyroscope angle deviation maximum value at each moment; S2, dividing the area to be positioned into a plurality of small grids; S3, determining a PDR initial position; S4, drawing an original walking track of the user; S5, determining an area with the maximum PDR positioning probability on the grid map; S6, obtaining a plurality of positions with themaximum WiFi positioning probability and a final positioning area; S7, constructing a hidden Markov model and determining parameters of the hidden Markov model; S8, determining a final positioning position; S9, redrawing a final positioning track of the PDR and determining the current positioning position; According to the invention, the problem of low positioning precision caused by accumulated errors of sensors or unstable WiFi signals in PDR and WiFi positioning technologies based on smart phones in the prior art is solved.

Disclosed are an apparatus for transmitting positioning signals, a method for indoor positioning based on the positioning signals, and an apparatus for performing the same. The method comprises receiving a plurality of acoustic or ultrasonic waves; measuring strengths of the received plurality of acoustic or ultrasonic waves; identifying frequencies of the received plurality of acoustic waves or ultrasonic waves; and performing positioning based on the measured strengths and the identified frequencies of the received plurality of acoustic waves or ultrasonic waves. Accordingly, positioning can be easily performed without additional separate hardware configurations, and positioning accuracy suitable for indoor positioning services can be achieved.

The embodiment of the invention provides an indoor location method and system. The method comprises: obtaining the current signal intensity value of a terminal to be detected monitored by each monitoring terminal; matching the fingerprints in a pre-built fingerprint database based on the current signal intensity value and the identity identification of the monitoring terminal corresponding to the current signal intensity value, and obtaining the probability density function and coordinates corresponding to the current signal intensity value at each monitoring points covered by each monitoring terminal; substituting the current signal intensity value into the corresponding probability density function, and calculating the corresponding probability density; and calculating the position where the terminal to be detected is located based on the probability density and the coordinates corresponding to the current signal intensity value at each monitoring point covered by each monitoring terminal through adoption of a pre-built weight position solution formula. According to the embodiment of the invention, the training time and the location cost are reduced while the indoor location precision is improved.

The invention provides an indoor positioning tracking method based on channel classification and a system thereof. The method comprises the following steps of 1, solving the position of a one-order imaginary anchor node according to an architectural plan and the position of an anchor node, wherein the anchor node has a known position, and the one-order imaginary anchor node is a mirror symmetry node, which corresponds with the wall surface, of the anchor node; 2, according to a step 4 of a previous process, recording information of three reflecting paths with strongest energies, and if no step 4 of the previous process exists, performing no recording; 3, performing channel classification according to channel pulse response, and determining whether a line-of-sight path exists between the anchor node and a to-be-positioned node; and 4, selecting a plurality of reflecting paths according to the number of line-of-sight paths, and performing positioning according to the lien-of-sight paths.

The invention discloses an indoor positioning method based on the reverse positioning principle. The method comprises the following steps: a one-way transmission signal mode is adopted, a positioningtag periodically transmits a positioning packet containing a timestamp to calibrate a relative arrival time of a received signal of a positioning base station; the positioning tag periodically transmits a synchronization packet to accurately calibrate a clock difference of the positioning base station; the positioning base station packages the received synchronization packet and the positioning packet into a datagram based on a user datagram protocol, and forwards the datagram to a positioning engine through a switch; the positioning engine completes the data analysis of the positioning packetand the synchronization packet, and forms an arrival time difference of the positioning tag to each positioning base station; after an observation value is weighted by using a known position of the positioning base station, a hyperbolic equation is solved by using a weighted least squares method to obtain a spatial location of the positioning tag. By adoption of the indoor positioning method disclosed by the invention, the clock difference of the positioning base station can be accurately measured, the indoor positioning accuracy is improved, the software and hardware costs of the positioningtag can also be reduced, and the scheme is simple and is easy to implement.

The invention discloses a GPS indoor positioning system and an indoor positioning method based on the GPS indoor positioning system. The system comprises an outdoor GPS receiver (1), a GPS signal modulation and demodulation device (2), wireless communication devices (5), multiple antenna devices (3) and a mobile terminal (5), wherein the outdoor GPS receiver (1) receives an outdoor GPS signal, and measures the outdoor pseudo-range observed quantity d and satellite position data S; the GPS signal modulation and demodulation device (2) modulates and demodulates the GPS signal to obtain GPS radio frequency signals; the antenna devices (3) receives and forwards the corresponding GPS radio frequency signals respectively; and the mobile terminal (5) receives the GPS radio frequency signals to measure the indoor pseudo-range observed quantity D, receives the outdoor pseudo-range observed quantity d, the satellite position data S and position data K of the antenna devices (3), and calculates positioning data by combining the indoor pseudo-range observed quantity D to realize indoor positioning.

The invention discloses an indoor positioning method and system and a computer readable medium. The method comprises that an initial position of a target object is determined by means of wireless positioning and visual feature and map matching positioning; and according to the initial position of the target object, the target object is located in real time by means of short time interframe featurematching positioning and visual feature and map feature matching positioning. Via the indoor positioning method, the computational complexity of the visual feature and map matching positioning manneris reduced.

The present invention belongs to the indoor navigation positioning technology field, and relates to an improved time delay estimation method based on mutual correlation, especially to a wireless sensor network indoor timing time delay estimation method. The technical scheme of solving the problem is the improved time delay estimation method based on mutual correlation, comprising the following steps: the step 1, sending signals to a receiving terminal at four base stations in a wireless transmission network; the step 2, performing mutual correlation operation of the signals, wherein the peak point of the function is the time difference of two base station signals reaching the receiving terminal; the step 3, using a parabola interpolation method to obtain the maximum value; and the step 4, obtaining the time delay of the signal receiving terminal and the distance difference between the base stations and the receiving terminal according to the distance different algorithm. The improved time delay estimation method based on the mutual correlation can estimate the non-integer time delay in the non-correlation background noise so as to solve the platform problem that the error cannot be overcome when the time delay true value is not the integral multiple of the sample interval, improve the noise robustness and improve the indoor location precision.

The invention discloses a WLAN positioning and networking method based on signal statistical distribution. The correlation between access points (Access point, AP) is firstly considered, and the probability density function of a signal at a reference point is calculated; then, the probability density function is used to calculate the appearing probabilities of different signal vectors at the reference point, and in combination of the position prior probability of the reference point, the weighting probability of the reference point is calculated; then, the average positioning precision of thereference point is calculated to obtain the average positioning precision of a target area; and finally, a simulated annealing algorithm is used to optimize the AP position in the target area. According to the WLAN positioning and networking method based on signal statistical distribution disclosed in the invention, the AP position can be selected reasonably, and the blindness of AP layout is avoided.

The invention discloses a zero-speed correcting and locating method based on difference statistics. The zero-speed correcting and locating method comprises the following steps: performing base line shift elimination and smoothing and noise reduction treatment on original acceleration measurement signals to obtain treated acceleration measurement signals; respectively performing difference calculation on static-state acceleration magnitudes and motion-state acceleration magnitudes in the treated acceleration measurement signals and performing statistic analysis on a difference result to obtaina difference threshold value capable of distinguishing a dynamic state and a static state; comparing the acceleration measurement difference result with the difference threshold valve and utilizing anacceleration sampling point as a zero-speed correcting point to perform zero-speed correction if the difference result is smaller than the difference threshold value; performing trapezoid quadratic integral on the zero-speed corrected acceleration to obtain a final locating result. The zero-speed correcting and locating method disclosed by the invention can find the zero-speed correcting point more accurately, so that inertial errors are effectively controlled; thus, the zero-speed correcting and locating method can be widely applied to varieties of service based on positions.

The invention discloses a seamless indoor and outdoor positioning system and positioning method based on combination a chirp spread spectrum (CSS) with a GPS. The positioning system is composed of an outdoor GPS satellite module, an indoor CSS positioning module, an indoor and outdoor positioning fusion switching module and a positioning result display module. The outdoor satellite positioning module utilizes a GPS satellite for navigation. The indoor CSS positioning module carries out an indoor distance measurement process by using a symmetrical double-sided two-way ranging (SDS-TWR) method, carries out optimization processing on positioning ranging data by using Kalman filtering, and then obtains an indoor position of the indoor positioning module by using a geometric trilateral positioning algorithm. The indoor and outdoor positioning fusion switching module carries out fusion, switching and integration on indoor and outdoor positioning methods based on indoor and outdoor positioning communication signal strength, thereby realizing smooth indoor and outdoor positioning result transition; and the positioning result display module displays a positioning result based on an outdoor two-dimensional electronic map and an indoor planar graph. Compared with the existing positioning system, the provided positioning system enables seamless connection of precise indoor and outdoor positioning to be realized based on combination a CSS technology with a GPS satellite navigation technology.