CN104977003A - Indoor people search method, cloud server, and system based on shared track - Google Patents

Abstract

The invention discloses an indoor tracing method based on a shared track, which includes: acquiring motion data of a target terminal in real time; determining the indoor walking track of the target terminal according to the real-time acquired motion data of the target terminal; sharing the track with other terminals or designated terminals The indoor walking track of the target terminal is used to navigate to the current position of the target terminal; the invention also discloses an indoor person tracing cloud server and system based on the shared track. The indoor person-finding method, cloud server and system based on the shared track proposed by the present invention can accurately and quickly complete indoor person-finding.

Description

Indoor person-finding method, cloud server and system based on shared trajectory

technical field

The invention relates to the technical field of indoor positioning, in particular to an indoor tracing method based on a shared trajectory, a cloud server and a system.

Background technique

Indoor public environments such as shopping malls, office buildings, airports, and railway stations are unavoidable activity areas for people. Studies have shown that people spend 80% of their time indoors every day, and indoor location-based services are particularly important. Indoor positioning uses various technologies such as wireless communication, base station positioning, and inertial navigation positioning to realize the positioning of people and objects in indoor space. The early indoor positioning technology was mainly realized by deploying special hardware equipment, such as infrared equipment, sound wave equipment, visual equipment, wireless radio frequency transmitters and detection devices, etc. This type of method uses a positioning signal source with a known position, and the positioned terminal receives the signal from each positioning signal source and uses a specific ranging method to measure the distance between each other, and finally determines the location of the object through a trilateral or even multilateral positioning method. Spatial location. Although these methods have achieved good indoor positioning results, due to their dependence on expensive specific hardware devices, the cost of positioning is greatly increased, and the deployment is too difficult, thus lacking in practical feasibility.

In daily life, there are always situations of looking for someone. For example, when you meet a friend in a strange city, the two physically go around in the same building, but you can’t find each other’s exact location; when you need to go to the new customer’s Talking in the office, facing a completely unfamiliar building, may delay meeting with customers and cause unnecessary losses.

For the above problems, there is no effective solution at present.

Contents of the invention

In view of this, the object of the present invention is to propose a method, cloud server and system for indoor person tracing based on shared trajectories, which can accurately and quickly complete indoor person tracing.

Based on the above-mentioned purpose, the indoor tracing method based on shared trajectory provided by the present invention includes:

Obtain the motion data of the target terminal in real time;

According to the motion data of the target terminal obtained in real time, the indoor walking trajectory of the target terminal is determined;

Share the indoor walking track of the target terminal with other terminals or designated terminals for them to navigate to the current location of the target terminal.

In some implementations, the motion data acquired in real time from the target terminal includes the acceleration data of the built-in accelerometer of the target terminal and the direction data of the built-in gyroscope and compass of the target terminal;

The step of determining the indoor walking trajectory of the target terminal according to the real-time acquisition of the motion data of the target terminal further includes:

Calculate the step size and step frequency of the target terminal according to the acceleration data of the accelerometer;

Calculate the direction of movement of the target terminal based on the direction data of the gyroscope and compass;

According to the initial position and initial direction of the target terminal, combined with the step length, step frequency, and motion direction, the indoor walking trajectory is obtained.

In some implementations, the step of obtaining the indoor walking trajectory according to the initial position and initial direction of the target terminal in combination with the step size, step frequency, and motion direction further includes:

According to the initial position and initial direction of the target terminal, combined with the step length, step frequency, and motion direction, the position information of each step of the target terminal is obtained;

Match the location information of each step of the target terminal with the points of interest on the indoor map;

The matching position information of each step obtained from the matching of the target terminal is displayed on the indoor map in real time to form an indoor walking track with the matching position information of each step.

In some embodiments, the method also includes:

Obtain the current location information of the specified terminal and the topological map of points of interest in the indoor map;

Calculate the shortest path from the current location of the specified terminal to the current location of the target terminal through the path planning algorithm;

Return the shortest path to the specified terminal for navigation.

Another aspect of the present invention also provides a cloud server for indoor person tracing based on shared tracks, including:

The data acquisition module is used to acquire the motion data of the target terminal in real time;

A track module, configured to determine the indoor walking track of the target terminal according to the target terminal motion data acquired in real time;

The sharing module is used to share the indoor walking track of the target terminal with other terminals or designated terminals, so that they can navigate to the current position of the target terminal;

The archiving module is used to store the motion data of the terminal acquired in real time and its indoor walking track.

In some embodiments, the motion data acquired by the data acquisition module in real time from the target terminal includes the acceleration data of the built-in accelerometer of the target terminal and the direction data of the built-in gyroscope and compass of the target terminal;

The track module is also used to calculate the step length and step frequency of the target terminal according to the acceleration data of the accelerometer; calculate the direction of motion of the target terminal according to the direction data of the gyroscope and compass; and, according to the initial position and The initial direction, combined with the step length and step frequency, and the direction of motion, can obtain the indoor walking trajectory.

In some embodiments, the trajectory module is further used to obtain the position information of each step of the target terminal according to the initial position and initial direction of the target terminal, in combination with the step length, step frequency, and direction of motion; the position information of each step of the target terminal Matching with points of interest on the indoor map; and displaying the matching location information of each step obtained through the matching of the target terminal on the indoor map in real time to form an indoor walking track with the matching location information of each step.

In some implementations, the data acquisition module is also used to acquire the current location information of the designated terminal and the topological map of points of interest of the indoor map;

The trajectory module is also used to calculate the shortest path from the current location of the specified terminal to the current location of the target terminal through a path planning algorithm; the sharing module is also used to return the shortest path to the specified terminal for navigation.

Another aspect of the present invention also provides an indoor person-finding system based on a shared trajectory, including at least one target terminal, at least one designated terminal, and the above-mentioned cloud server;

The target terminal is used to collect its own motion data and upload it to the cloud server;

The specified terminal is used to receive the indoor walking track of the target terminal from the cloud server and navigate to the target terminal according to the indoor walking track.

In some embodiments, the target terminal includes an accelerometer and a gyroscope.

It can be seen from the above that the indoor tracing method, cloud server and system provided by the present invention based on the shared trajectory obtain the motion data collected in real time from the target terminal, given the initial position and initial direction, and use inertial navigation technology Obtain the walking trajectory of user A holding the target terminal in the public indoor space and use the pixel value to match the indoor map; then share the real-time indoor walking trajectory of user A with user B holding the specified terminal or more other users; It is also possible to obtain the shared key set and uploaded by the target terminal at the same time, so that user B holding the specified terminal can use the shared key to download the walking track of user A, and navigate from the current position to the target point based on the indoor point-of-interest topology map. Under the premise of ensuring user privacy, the efficiency of indoor tracing is greatly improved.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required in the embodiments. Obviously, the accompanying drawings in the following description are only some of the present invention. Embodiments, for those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

Fig. 1 is the flow chart of the embodiment of the method for finding people indoors based on shared track provided by the present invention;

FIG. 2 is a flowchart of an inertial navigation method according to an embodiment of an indoor person-finding method based on shared trajectories provided by the present invention;

Fig. 3 is the cloud service flow chart of the embodiment of the indoor people-finding method based on the shared trajectory provided by the present invention;

FIG. 4a is an example diagram of an indoor map with points of interest in an embodiment of the indoor people-finding method based on shared trajectories provided by the present invention;

Fig. 4b is an example diagram of path planning based on topological maps of an embodiment of the indoor people-finding method based on shared trajectories provided by the present invention;

Fig. 5 is a structural example diagram of an embodiment of an indoor person-finding cloud server based on a shared trajectory provided by the present invention;

Fig. 6 is a structural example diagram of an embodiment of an indoor person-finding system based on a shared trajectory provided by the present invention.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be further clearly, completely and detailedly described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described The embodiments are only some of the embodiments of the present invention, not all of them. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments of the present invention belong to the protection scope of the present invention.

It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are to distinguish two entities with the same name but different parameters or parameters that are not the same, see "first" and "second" It is only for the convenience of expression, and should not be construed as a limitation on the embodiments of the present invention, which will not be described one by one in the subsequent embodiments.

As shown in FIG. 1 , it is a flow chart of an embodiment of the method for finding people indoors based on shared trajectories provided by the present invention.

The indoor method for finding people based on the shared trajectory mainly includes the following steps:

Step 101: Obtain the motion data of the target terminal in real time;

Step 102: Determine the indoor walking track of the target terminal according to the motion data of the target terminal acquired in real time;

Step 103: Share the indoor walking track of the target terminal with other terminals or designated terminals for them to navigate to the current location of the target terminal.

Further, the acquired motion data of the target terminal is used to calculate the indoor walking trajectory of the athlete holding the target terminal using the inertial navigation method. During the movement of the athlete holding the target terminal, the target terminal held by the athlete passes through the motion sensor. The motion path information is sampled according to a fixed sampling frequency f, wherein: the motion data acquired in real time from the motion sensor of the target terminal includes the acceleration data of the built-in accelerometer of the target terminal, and the direction data of the built-in gyroscope and compass of the target terminal.

As shown in Figure 2, the step 102 of determining the indoor walking track of the target terminal according to the real-time acquisition of the motion data of the target terminal may further include:

Step 201: Calculate the step length and step frequency of the target terminal according to the acceleration data of the accelerometer;

Determine the number of user steps based on the acceleration data measured by the accelerometer, remove high-frequency noise in the measurement data through a low-pass filter, and perform numerical denoising by running the Kalman filter algorithm; identify the acceleration within the measurement time range through the peak and valley detection method The maximum and minimum values of the target terminal, and according to the adjacent maximum and minimum values, use the adaptive threshold method to judge whether the athlete holding the target terminal takes a step. Whenever it is determined that the athlete holding the target terminal takes a step, Add 1 to the pedometer, and the total number of steps taken by the athlete holding the target terminal within the measurement time is recorded as N; the adaptive threshold method can effectively modify the acceleration range determined as a stride according to the athlete's walking posture and habits , can obtain the most suitable stride judgment method for a specific athlete through a limited distance in a short time;

The step length A of the user is determined by using the linear relationship between the step length and the step frequency, that is, A _i =a·f(i)+b. Among them, i is the number of steps, a and b are the step parameters of the athlete, which can be determined by linear regression of sampled data.

Step 202: Calculate the movement direction of the target terminal according to the direction data of the gyroscope and the compass;

The role of the compass is mainly to provide the initial direction for the inertial navigation method. In the positioning process of the inertial navigation method, the gyroscope is used to estimate the walking direction. Therefore, the determination of the initial direction:

In the initial stage of positioning, the athlete holding the target terminal obtains the absolute direction of the user's current indoor environment (that is, the orientation of the person in the world coordinate system obtained by the compass) by obtaining the compass data, and provides an initial positioning based on the inertial navigation method. direction. During the movement of the athlete holding the target terminal, the target terminal (which can be any portable smart device) can determine the angle change of the athlete during the travel process by obtaining the return value measured by the gyroscope, and compare the angle change with the The obtained initial direction of the movement of the athlete holding the target terminal is superimposed to obtain the absolute movement direction of the target terminal; when the target terminal does not obtain the initial direction of the target terminal provided by the landmark, it can only calculate the relative angle; In the process of taking a step, that is, the angle change α _i in the process of the i-th step of the user is calculated by a time integration within the time period t ₀ ~ t _n , Calculate the position of the user's k+1th step (x _k+1 , y _k+1 ),

in, $\left\{\begin{array}{c}{x}_{k+1}=x_k+A_{k+1}\·co\mathrm{the\; s}{\mathrm{\α}}_{k+1}\\ {\mathrm{the\; y}}_{k+1}={\mathrm{the\; y}}_k+A_{k+1}\&Center\; Dot;{\mathrm{sin\α}}_{k+1}\end{array}\right..$

Step 203: According to the initial position and initial direction of the target terminal, combined with the step length, step frequency, and motion direction, the indoor walking trajectory is obtained;

The integral of the angle change of each step measured by the gyroscope can determine the direction of travel of the athlete currently holding the target terminal; the direction information, step length will be combined with the position information of the current athlete's current step (x _k , y _k ) , the next step position information (x _k+1 , y _k+1 ) of the athlete can be located. In this way, the user's indoor walking trajectory can be obtained; in addition, the indoor walking trajectory is represented by the pixel value of the picture, that is, (x, y) is the pixel value of the indoor picture.

Among them, the key difficulty in using the inertial navigation method to calculate the indoor walking trajectory lies in the determination of the initial position and initial direction; the initial position and initial direction of the current inertial navigation method are determined by using the position where the GPS signal disappears at the entrance of the building and the compass. However, the accuracy of the initial position and initial direction is not high, which directly affects the subsequent positioning accuracy. In order to solve this problem, indoor points of interest (stairs, elevators, doorways, etc.) can be selected as the initial position. Such points of interest are directly calibrated on the indoor map, and the positioning accuracy is relatively high. In addition, when people get out of elevators, stairs, and doorways, the direction of travel is mostly in and out, so that the error generated by the compass is calibrated to improve the accuracy of the initial direction.

Furthermore, the step 203 of obtaining the indoor walking track according to the initial position and initial direction of the target terminal, combined with the step size, step frequency, and motion direction may further include:

Step 301: Obtain the position information of each step of the target terminal according to the initial position and initial direction of the target terminal, combined with step length, step frequency, and motion direction;

Step 302: Match the location information of each step of the target terminal with the points of interest on the indoor map;

Step 303: Display the matching position information of each step obtained through the matching of the target terminal on the indoor map in real time to form an indoor walking track with the matching position information of each step.

Using image pixel values to uniquely determine the absolute coordinates of indoor points of interest on indoor maps is a manual calibration method. Using the widely existing points of interest indoors, the walking trajectory of the athlete holding the target terminal is matched with the indoor map, and the current location of the target terminal is displayed on the indoor map in real time. During the matching process, there will be a matching error, which is defined as error; define the coordinates of the indoor interest point (i) as Using the inertial navigation method to locate the coordinates of the user at the point of interest i is Then use the Euclidean distance to measure the matching error error, that is The goal of matching optimization is to minimize the error to obtain the accurate indoor walking trajectory of the user. The calculation formula of error is as follows:

The matching error for the ith interest point is error _i , and the optimization objective is:

$\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; no</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}{\mathrm{<span\; class="notranslate">\; error</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

Wherein, i=1, 2, . . . , n, n is the number of interest points of the indoor map.

The error optimization method adopts genetic algorithm to solve, and specifically the following steps can be adopted:

(1) Chromosomal coding

In this scheme, the matching error of each interest point is represented by m genes, that is, assuming that in a specific indoor space, the maximum matching error of two interest points is 2 ^m . The determination of m is determined according to the size of the indoor space and the maximum distance between two interest points. In this way, there are 2 ^m kinds of chromosomes.

(2) Genetic Algorithm Parameter Determination

· p _c = 0.7 (with this probability, some genes of 2 selected chromosomes are exchanged, resulting in 2 offspring)

p _m = 0.001 (randomly change the gene values of 2 offspring with this probability)

(3) Fitness function determination

The fitness function is the optimization objective:

$\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}{\mathrm{<span\; class="notranslate">\; error</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

Preferably, the indoor person-finding method based on shared trajectories also includes:

Obtain the current location information of the specified terminal and the topological map of points of interest in the indoor map;

Calculate the shortest path from the current position of the specified terminal to the current position of the target terminal through the path planning algorithm;

Return the shortest path to the specified terminal for navigation.

Since the indoor walking trajectory of the shared target terminal has been matched with the indoor map, the shortest path from the current location of user B (designated terminal) to the current location of user A (target terminal) can be calculated through a path planning algorithm based on the topological map of points of interest.

The method for constructing the topological map of POIs is as follows: first, mark the POIs of the indoor map on the indoor map, and assign pixel coordinate values, (x, y); the distance between each pair of POIs is measured by inertial navigation; The point topological relationship is shown in Figures 4a and 4b.

Based on the current location of user B and the current location of user A, run the Dijkstra algorithm to calculate the shortest path, and navigate user B to user A's location.

It can be seen from the above-mentioned embodiments that the indoor person-finding method based on the shared trajectory provided by the present invention obtains the motion data collected in real time from the target terminal, gives the initial position and initial direction, and uses inertial navigation technology to obtain the target terminal. The walking trajectory of user A in the public indoor space is matched with the indoor map using the pixel value; then the real-time indoor walking trajectory of user A is shared with user B holding a designated terminal or more other users; The shared key is set and uploaded by the terminal at the same time, so that user B holding the specified terminal can use the shared key to download the walking track of user A, and navigate from the current position to the target point based on the topological map of indoor points of interest. On the premise of ensuring user privacy This greatly improves the efficiency of indoor tracing.

It should be pointed out that the indoor walking track described in the embodiment of the present invention refers to the walking track on a two-dimensional plane, and the coordinate position information of the point of interest is also limited to the position information and range information on the two-dimensional plane. For example, in an indoor public space with a multi-storey building, multiple planes should be established at different height levels, and the method described in the present invention can be used in each plane to trace people, and the traces and users in different planes can be traced. mutual interference should be avoided.

Another aspect of the present invention provides a cloud server for indoor person tracing based on shared tracks. Referring to accompanying drawing 5, it is a structural example diagram of an embodiment of an indoor people tracing cloud server based on a shared trajectory provided by the present invention.

As shown in Figure 5, the indoor person-finding cloud server 400 based on the shared trajectory includes:

The data acquisition module 401 is used to acquire the motion data of the target terminal in real time;

The trajectory module 402 is configured to determine the indoor walking trajectory of the target terminal according to the target terminal motion data acquired in real time;

The sharing module 403 is used to share the indoor walking track of the target terminal with other terminals or designated terminals, so that they can navigate to the current position of the target terminal;

The archiving module 404 is configured to store the motion data of the terminal acquired in real time and its indoor walking track.

Further, the acquired motion data of the target terminal is used to calculate the indoor walking trajectory of the athlete holding the target terminal by using the inertial navigation method. During the movement of the athlete holding the target terminal, the target terminal held by the athlete passes through the motion sensor. The motion path information is sampled according to a fixed sampling frequency f, wherein: the motion data acquired in real time from the motion sensor of the target terminal includes the acceleration data of the built-in accelerometer of the target terminal, and the direction data of the built-in gyroscope and compass of the target terminal;

The trajectory module 402 is also used to calculate the step length and step frequency of the target terminal according to the acceleration data of the accelerometer; determine the user's steps according to the acceleration data measured by the accelerometer, and remove high and low points in the measurement data through a low-pass filter. frequency noise, the Kalman filter algorithm is used for numerical denoising; the peak and valley detection method is used to identify the maximum and minimum values of the acceleration within the measurement time range, and according to the adjacent maximum and minimum values, an adaptive threshold is used method to judge whether the athlete holding the target terminal is taking a step. Whenever it is determined that the athlete holding the target terminal takes a step, the pedometer is incremented by 1, and the total number of steps taken by the athlete holding the target terminal within the measurement time is recorded as N; The adaptive threshold method can effectively modify the acceleration range determined as a stride according to the athlete's walking posture and habits, and can obtain the most suitable stride determination method for a specific athlete through a limited distance in a short time;

The step length A of the user is determined by using the linear relationship between the step length and the step frequency, that is, A _i =a·f(i)+b. Among them, i is the number of steps, a and b are the step parameters of the athlete, which can be determined by linear regression of sampled data.

The trajectory module 402 is also used to calculate the movement direction of the target terminal according to the direction data of the gyroscope; the function of the compass is mainly to provide an initial direction for the inertial navigation method, and the gyroscope is used to determine the walking direction in the positioning process of the inertial navigation method afterwards. Therefore, the determination of the initial direction: the athlete holding the target terminal obtains the absolute direction of the user's current indoor environment by obtaining compass data at the beginning of positioning (that is, the person in the world coordinate system obtained by the compass Heading), which provides an initial orientation based on the inertial navigation method. During the movement of the athlete holding the target terminal, the target terminal (which can be any portable smart device) can determine the angle change of the athlete during the travel process by obtaining the return value measured by the gyroscope, and compare the angle change with the The obtained initial direction of the movement of the athlete holding the target terminal is superimposed to obtain the absolute movement direction of the target terminal; when the target terminal does not obtain the initial direction of the target terminal provided by the landmark, it can only calculate the relative angle; In the process of taking a step, that is, the angle change α _i in the process of the i-th step of the user is calculated by a time integration within the time period t ₀ ~ t _n , The position (x _k+1 , y _k+1 ) of the user's k+1th step can be obtained by calculation, where,

$\left\{\begin{array}{c}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&Center\; Dot;</span>\mathrm{<span\; class="notranslate">\; c</span>}\mathrm{<span\; class="notranslate">\; o</span>}\mathrm{<span\; class="notranslate">\; the\; s</span>}{\mathrm{<span\; class="notranslate">\; \&alpha;</span>}}_{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\\ {\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; A</span>}}_{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; \&CenterDot;</span>{\mathrm{<span\; class="notranslate">\; sin\&alpha;</span>}}_{\mathrm{<span\; class="notranslate">\; k</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}\end{array}\right.<span\; class="notranslate">\; .</span>$

And, the track module 402 is also used to obtain the indoor walking track according to the initial position and initial direction of the target terminal in combination with the step length, step frequency, and motion direction; the integral of the angle change of each step measured by the gyroscope can be determined The direction of travel of the athlete currently holding the target terminal; the direction information and step length will be combined with the position information (x _k , y _k ) of the current athlete’s current step to locate the next position information of the athlete (x _k+1 , y _k+1 ). In this way, the user's indoor walking trajectory can be obtained; in addition, the indoor walking trajectory is represented by the pixel value of the picture, that is, (x, y) is the pixel value of the indoor picture.

Among them, the key difficulty in using the inertial navigation method to calculate the indoor walking trajectory lies in the determination of the initial position and initial direction; the initial position and initial direction of the current inertial navigation method are determined by using the position where the GPS signal disappears at the entrance of the building and the compass. However, the accuracy of the initial position and initial direction is not high, which directly affects the subsequent positioning accuracy. In order to solve this problem, indoor points of interest (stairs, elevators, doorways, etc.) can be selected as the initial position. Such points of interest are directly calibrated on the indoor map, and the positioning accuracy is relatively high. In addition, when people get out of elevators, stairs, and doorways, the direction of travel is mostly in and out, so that the error generated by the compass is calibrated to improve the accuracy of the initial direction.

Furthermore, the trajectory module 402 is also used to obtain the position information of each step of the target terminal according to the initial position and initial direction of the target terminal in combination with the step length, step frequency, and motion direction; and combine the position information of each step of the target terminal with Indoor map interest points are matched; and, the matching position information of each step obtained by the matching of the target terminal is displayed on the indoor map in real time, forming an indoor walking track with the matching position information of each step.

Using image pixel values to uniquely determine the absolute coordinates of indoor points of interest on indoor maps is a manual calibration method. Using the widely existing points of interest indoors, the walking trajectory of the athlete holding the target terminal is matched with the indoor map, and the current position of the target terminal is displayed on the indoor map in real time. During the matching process, there will be a matching error, which is defined as error; define the coordinates of the indoor interest point (i) as Using the inertial navigation method to locate the coordinates of the user at the point of interest i is Then use the Euclidean distance to measure the matching error error, that is The goal of matching optimization is to minimize the error to obtain the accurate indoor walking trajectory of the user. The calculation formula of error is as follows:

The matching error for the ith interest point is error _i , and the optimization objective is:

$\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; i</span>}\mathrm{<span\; class="notranslate">\; no</span>}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}{\mathrm{<span\; class="notranslate">\; error</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

Wherein, i=1, 2, . . . , n, n is the number of interest points of the indoor map.

The error optimization method adopts genetic algorithm to solve, and specifically the following steps can be adopted:

(1) Chromosomal coding

In this scheme, the matching error of each interest point is represented by m genes, that is, assuming that in a specific indoor space, the maximum matching error of two interest points is 2 ^m . The determination of m is determined according to the size of the indoor space and the maximum distance between two interest points. In this way, there are 2 ^m kinds of chromosomes.

(2) Genetic Algorithm Parameter Determination

· p _c = 0.7 (with this probability, some genes of 2 selected chromosomes are exchanged, resulting in 2 offspring)

p _m = 0.001 (randomly change the gene values of 2 offspring with this probability)

(3) Fitness function determination

The fitness function is the optimization objective:

$\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; no</span>}}{<span\; class="notranslate">\; \&Sigma;</span>}}{\mathrm{<span\; class="notranslate">\; error</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$

Preferably, the data acquisition module 401 is also used to acquire the current location information of the specified terminal and the point-of-interest topological map of the indoor map;

The trajectory module 402 is also used to calculate the shortest path from the current location of the specified terminal to the current location of the target terminal through a path planning algorithm; the sharing module 403 is also used to return the shortest path to the specified terminal for navigation.

Since the indoor walking trajectory of the shared target terminal has been matched with the indoor map, the shortest path from the current location of user B (designated terminal) to the current location of user A (target terminal) can be calculated through a path planning algorithm based on the topological map of points of interest.

The method for constructing the topological map of POIs is as follows: first, mark the POIs of the indoor map on the indoor map, and assign pixel coordinate values, (x, y); the distance between each pair of POIs is measured by inertial navigation; The point topological relationship is shown in Figures 4a and 4b.

Based on the current location of user B and the current location of user A, run the Dijkstra algorithm to calculate the shortest path, and navigate user B to user A's location.

It can be seen from the above embodiments that the indoor person tracing cloud server based on shared trajectory provided by the present invention obtains the motion data collected in real time from the target terminal, gives the initial position and initial direction, and uses inertial navigation technology to obtain The walking trajectory of user A of the terminal in the public indoor space is matched with the indoor map using the pixel value; then the real-time indoor walking trajectory of user A is shared with user B holding the specified terminal or more other users; The shared key is set and uploaded by the target terminal at the same time, so that user B holding the specified terminal can use the shared key to download the walking track of user A, and navigate from the current location to the target point based on the indoor point-of-interest topological map, while ensuring user privacy Under the premise, the efficiency of indoor tracing is greatly improved.

The cloud server 400 may be a Baidu cloud server. Baidu cloud server is a relatively stable cloud server; by using Baidu cloud, users can realize data synchronization function conveniently and quickly, and better realize the interaction between users. In order to meet the needs of more users, users can upload and share their own paths through the cloud, or download other people's paths to find the person you are looking for.

This embodiment of the method can use the data storage function in Frontia. Frontia is an MBaaS (Backend as a Service) service provided by Baidu Open Cloud for developers. The Baidu cloud service process based on this application includes: applying for application permissions, creating a project as test, obtaining the API Key of this project, creating a Bucket, uploading data, storing data, and downloading data.

It should be pointed out that the indoor walking track described in the present invention refers to the walking track on a two-dimensional plane, and the coordinate position information of the point of interest is also limited to the position information and range information on the two-dimensional plane. For example, in an indoor public space with a multi-storey building, multiple planes should be established at different height levels, and the method described in the present invention can be used in each plane to trace people, and the traces and users in different planes can be traced. mutual interference should be avoided.

Referring to FIG. 6 , it is a structural example diagram of an embodiment of an indoor person-finding system based on a shared track provided by the present invention.

The indoor people tracing system based on the shared trajectory includes at least one target terminal, at least one designated terminal, and a cloud server as described in the above-mentioned embodiments;

The target terminal is used to collect its own motion data and upload it to the cloud server;

The specified terminal is used to receive the indoor walking track of the target terminal from the cloud server and navigate to the target terminal according to the indoor walking track.

The embodiment of the indoor people tracing system based on shared trajectory provided by the present invention relates to indoor positioning technology, and the system includes at least two smart terminals as the target terminal and designated terminal respectively, a cloud server, and an indoor map stored in the cloud server. The function of the system is to use the track shared between users to realize the user to find the person who shares the track with him in the indoor public scene. The method includes: a) user A walks indoors with a target terminal, and the target terminal collects the motion data of the user and uploads it to the cloud server; b) after the cloud server receives the motion data, it runs an indoor positioning method based on inertial navigation to obtain user A's indoor positioning method. Walking trajectory; c) User A’s indoor walking trajectory is stored in the cloud server, and shared with the specified terminal carried by the specified user B by using the cloud server sharing function; d) User B (optionally after entering the verification password) can download user A’s Indoor walking trajectory, navigating from user B's current location to user A's location. The system of the invention can be applied to location-based services such as friend discovery and location sharing.

Further, the target terminal includes an accelerometer, a gyroscope, and a magnetometer, which are respectively used to collect readings from their built-in motion sensors.

It can be seen from the above-mentioned embodiments that the indoor people tracing system based on the shared trajectory provided by the present invention obtains the motion data of the user A, calculates the walking trajectory of the user A by using the inertial navigation method, and uploads it to the cloud and the system based on the point of interest. After the topological indoor map is matched, it is shared with other users; the user B whose trajectory is shared downloads the trajectory data of user A, and uses the path planning method to navigate from user B's current location to user A's location to realize the indoor people-finding function.

In combination with the indoor person-finding system based on shared tracks, an indoor person-finding method based on shared tracks is introduced below.

The purpose of the indoor person-finding system based on shared tracks is to use shared tracks between users to enable users to find people with whom they share tracks in indoor public scenes. In order to achieve the above-mentioned purpose, the steps of the technical solution of the indoor person-finding method of the indoor person-finding system based on the shared trajectory include:

Step a): User A walks indoors with the target terminal, and the target terminal collects the user's motion data and uploads it to the cloud server;

Step b): After the cloud server receives the motion data of the target terminal, it runs the indoor positioning method based on inertial navigation (specifically, the method provided by the above-mentioned another indoor person-finding method can be used), and obtains the indoor walking track of user A;

c) The indoor walking trajectory of user A is stored in the cloud server, and shared with the specified terminal carried by the specified user B by using the sharing function of the cloud server;

d) User B can download user A's indoor walking trajectory after verifying the password, and navigate from user B's current location to user A's location using the topological trajectory based on points of interest.

The indoor person-finding method of the indoor person-finding system based on shared trajectories is applicable to any large-scale public indoor scenes, such as shopping centers, railway stations, airports, libraries, and the like. At present, wireless access points (Access Point, AP) with wireless Internet access are installed in major public indoor spaces, and are free for users to use, providing conditions for target terminals, designated terminals and cloud servers to communicate.

Preferably, the target terminal in step a) can use a built-in inertial measurement unit (IMU), which includes an accelerometer, a gyroscope, a magnetometer, and a wireless communication module, such as a Wi-Fi module.

The motion data collected by the target terminal in step a) includes acceleration readings, angular velocity readings and magnetic force data.

In step a), in order to ensure the positioning accuracy of the inertial navigation, the user can hold the mobile terminal as much as possible, so as to improve the accuracy of sensor data.

The indoor walking track obtained in step b) is saved in the cloud through the pixel value of the indoor map picture.

In step c), using the sharing function of the cloud server, the indoor walking track of user A can be shared with other designated users or more users except user B holding a designated terminal.

In step c), the shared password can be set so that only authenticated users can download the shared track, which enhances privacy and security.

The interest points in step d) are indoor feature points, such as doorways, turning points, escalators, elevators, stairs, and the like.

In step d), the indoor point of interest is associated based on the pixel value of the indoor map picture, and an indoor topological map is established.

In step d), the shortest path is calculated by using the Dijkstra algorithm based on the indoor topological map.

The indoor person-finding method is simple and feasible, and can be applied to location-based services such as friend discovery and location sharing.

The target terminal and designated terminal can be one or more of smart phones, tablet computers, notebook computers, and smart wearable devices; the above-mentioned cloud server can be Baidu Cloud, Google Cloud, Alibaba Cloud, etc.

Those of ordinary skill in the art should understand that: the above descriptions are only specific embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present invention etc., should be included within the protection scope of the present invention.

Claims (10)

1. A kind of indoor people-finding method based on shared track, it is characterized in that, comprising: Obtain the motion data of the target terminal in real time; According to the motion data of the target terminal obtained in real time, the indoor walking trajectory of the target terminal is determined; Share the indoor walking track of the target terminal with other terminals or designated terminals for them to navigate to the current location of the target terminal. 2. The method according to claim 1, wherein the motion data obtained in real time from the target terminal includes the acceleration data of the built-in accelerometer of the target terminal and the direction data of the built-in gyroscope and compass of the target terminal; The step of determining the indoor walking trajectory of the target terminal according to the real-time acquisition of the motion data of the target terminal further includes: Calculate the step size and step frequency of the target terminal according to the acceleration data of the accelerometer; Calculate the direction of movement of the target terminal based on the direction data of the gyroscope and compass; According to the initial position and initial direction of the target terminal, combined with the step length, step frequency, and motion direction, the indoor walking trajectory is obtained. 3. The method according to claim 2, wherein the step of obtaining the indoor walking trajectory according to the initial position and initial direction of the target terminal in combination with the step length, step frequency, and motion direction further comprises: According to the initial position and initial direction of the target terminal, combined with the step length, step frequency, and motion direction, the position information of each step of the target terminal is obtained; Match the location information of each step of the target terminal with the points of interest on the indoor map; The matching position information of each step obtained from the matching of the target terminal is displayed on the indoor map in real time to form an indoor walking track with the matching position information of each step. 4. The method according to claim 3, further comprising: Obtain the current location information of the specified terminal and the topological map of points of interest in the indoor map; Calculate the shortest path from the current location of the specified terminal to the current location of the target terminal through the path planning algorithm; Return the shortest path to the specified terminal for navigation. 5. A cloud server for indoor people tracing based on shared tracks, characterized in that it comprises: The data acquisition module is used to acquire the motion data of the target terminal in real time; A track module, configured to determine the indoor walking track of the target terminal according to the target terminal motion data acquired in real time; The sharing module is used to share the indoor walking track of the target terminal with other terminals or designated terminals, so that they can navigate to the current position of the target terminal; The archiving module is used to store the motion data of the terminal acquired in real time and its indoor walking trajectory. 6. The cloud server according to claim 5, wherein the motion data obtained by the data acquisition module in real time from the target terminal includes the acceleration data of the built-in accelerometer of the target terminal and the direction of the built-in gyroscope and compass of the target terminal data; The track module is also used to calculate the step length and step frequency of the target terminal according to the acceleration data of the accelerometer; calculate the direction of motion of the target terminal according to the direction data of the gyroscope and compass; and, according to the initial position and The initial direction, combined with the step length and step frequency, and the direction of motion, can obtain the indoor walking trajectory. 7. The cloud server according to claim 6, wherein the track module is also used to obtain the position of each step of the target terminal according to the initial position and initial direction of the target terminal, in combination with step length, step frequency, and motion direction Information; match the location information of each step of the target terminal with the points of interest on the indoor map; and display the matching location information of each step obtained by the matching of the target terminal on the indoor map in real time to form matching location information with each step indoor walking track. 8. The cloud server according to claim 7, wherein the data acquisition module is also used to acquire the current location information of the designated terminal and the point-of-interest topological map of the indoor map; The trajectory module is also used to calculate the shortest path from the current location of the specified terminal to the current location of the target terminal through a path planning algorithm; the sharing module is also used to return the shortest path to the specified terminal for navigation. 9. An indoor people tracing system based on shared tracks, characterized in that it includes at least one target terminal, at least one designated terminal, and the cloud server according to any one of claims 1-6; The target terminal is used to collect its own motion data and upload it to the cloud server; The specified terminal is used to receive the indoor walking track of the target terminal from the cloud server and navigate to the target terminal according to the indoor walking track. 10. The system according to claim 9, wherein the target terminal comprises an accelerometer and a gyroscope.