CN117560629B - Safe and robust indoor pedestrian track tracking method and system - Google Patents
Safe and robust indoor pedestrian track tracking method and system Download PDFInfo
- Publication number
- CN117560629B CN117560629B CN202410038094.5A CN202410038094A CN117560629B CN 117560629 B CN117560629 B CN 117560629B CN 202410038094 A CN202410038094 A CN 202410038094A CN 117560629 B CN117560629 B CN 117560629B
- Authority
- CN
- China
- Prior art keywords
- fingerprint positioning
- base station
- wifi fingerprint
- wifi
- track
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000012216 screening Methods 0.000 claims description 22
- 238000005457 optimization Methods 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 230000001133 acceleration Effects 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000001276 Kolmogorov–Smirnov test Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 3
- 230000005021 gait Effects 0.000 claims description 3
- 238000003064 k means clustering Methods 0.000 claims description 3
- 230000004807 localization Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/12—Detection or prevention of fraud
- H04W12/121—Wireless intrusion detection systems [WIDS]; Wireless intrusion prevention systems [WIPS]
- H04W12/122—Counter-measures against attacks; Protection against rogue devices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/60—Context-dependent security
- H04W12/63—Location-dependent; Proximity-dependent
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
- H04W4/027—Services making use of location information using location based information parameters using movement velocity, acceleration information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention relates to a safe and robust indoor pedestrian track tracking method and system, belongs to the technical field of indoor pedestrian track tracking, and solves the problems that a WiFi base station is easy to attack, the positioning accuracy is low, and the production and the safety of a factory are easily influenced in the prior art. According to the safe and robust indoor pedestrian track tracking method and system, the attacked base station is identified and filtered, so that the risk that the fingerprint positioning accuracy is influenced by the attack of the base station is reduced, the fingerprint positioning accuracy is improved, and the performance of position service in an industrial Internet environment is guaranteed; by fusing the WiFi fingerprint and the PDR positioning result, the robustness of the track tracking result is improved, and therefore the problems of weak safety and poor robustness of the current track tracking method are solved.
Description
Technical Field
The invention relates to the technical field of indoor pedestrian track tracking, in particular to a safe and robust indoor pedestrian track tracking method and system.
Background
In the industrial internet environment, a location-based service is indispensable, and is therefore essential for estimating a location and tracking a trajectory.
The WiFi fingerprint positioning can directly collect signal strength by using the existing WiFi equipment without installing additional hardware equipment, so that the technology is widely valued and researched under the condition of not increasing cost. Fingerprint positioning technology is mainly due to the fact that radio signals have different signal strength sequences at different position points, so that each position point can construct unique signal characteristics according to received signal strength. But the WiFi base station is easy to be invaded by a mode including DDOS (distributed denial of service ), the signal strength is easy to be polluted, and the propagation characteristic is easy to be affected by environment, so that the WiFi base station is easy to be attacked, the positioning accuracy is further damaged, and the production and the safety of an intelligent factory are affected. Although a PDR (pedestrian dead reckoning ) algorithm based on inertial navigation data can provide step length constraint for a WiFi fingerprint positioning technology, a large error problem in fingerprint positioning directly influences the track tracking effect of fusion of the two.
In summary, the WiFi base station in the prior art is vulnerable, the positioning accuracy is low, and the production and security of the factory are easily affected.
Disclosure of Invention
In view of the above problems, the invention provides a safe and robust indoor pedestrian track tracking method and system, which solve the problems that a WiFi base station is easy to attack, the positioning accuracy is low, and the production and the safety of a factory are easily influenced in the prior art.
The invention provides a safe and robust indoor pedestrian track tracking system, which comprises an acquisition module 21, a fingerprint positioning module 22, a safe base station screening module 23, a PDR track tracking module 24, a reliable fingerprint positioning module 25 and a track optimizing module 26; wherein,
the acquisition module 21 is used for acquiring WiFi signal intensity, acceleration data and gyroscope data;
the fingerprint positioning module 22 is configured to perform fingerprint positioning according to the strength of the WiFi signal received by each to-be-positioned point on the track based on the selected base station, and estimate a WiFi fingerprint positioning result by using a fingerprint positioning algorithm;
the security base station screening module 23 is configured to calculate whether each base station is attacked according to the WiFi fingerprint positioning result sent by the fingerprint positioning module 22, identify and filter the attacked base station through the K-S test and clustering algorithm, reserve the normal base station and inform the fingerprint positioning module 22 to use the normal base station for fingerprint positioning, and obtain a WiFi fingerprint positioning result based on the normal base stationThe method comprises the steps of carrying out a first treatment on the surface of the Wherein, the base station refers to a WiFi base station;
a PDR track tracking module 24 for calculating and obtaining relative track by utilizing PDR algorithm based on inertial navigation data according to the acceleration data and gyroscope data obtained by the acquisition module 21;
The reliable fingerprint positioning module 25 is used for screening abnormal large errors in fingerprint positioning results and eliminating WiFi fingerprint positioning results based on normal base stationsAn abnormally large error locating point;
the track optimization module 26 is configured to obtain a WiFi fingerprint global track according to the WiFi fingerprint positioning result processed by the reliable fingerprint positioning module 25 and based on the normal base stationThe method comprises the steps of carrying out a first treatment on the surface of the Relative trajectory to be obtained using inertial navigation data-based PDR algorithmTo fit WiFi fingerprint global track->Obtaining the best fit track +.>。
Further, the acquisition module 21 is specifically configured to acquire fingerprint information of a reference point offline, including a MAC address of the base station and a signal strength of the base station received at the reference point; the method is also used for acquiring fingerprint information, acceleration data and gyroscope data of the test points on the track on line; where the reference point refers to a landmark point and the test point is a point on the track for which the real position is known.
The invention also provides a safe and robust indoor pedestrian track tracking method, which comprises the following steps:
s101, randomly screening different base station subsets for multiple times to obtain WiFi fingerprint positioning results under the different base station subsets, and then calculating to obtain difference values of the WiFi fingerprint positioning results among the different base station subsets by using K-S test; wherein, the base station refers to a WiFi base station;
s102, taking the difference value obtained in the S101 as a clustering feature, selecting a WiFi fingerprint positioning result with highest density, counting the occurrence frequency of different base stations, identifying and eliminating the attacked base station, and obtaining a WiFi fingerprint positioning result based on a normal base station;
S103, estimating the step length of the pedestrian by using a PDR algorithm based on inertial navigation data, comparing the difference between the pedestrian step length and the WiFi fingerprint positioning result of the fingerprint positioning algorithm at adjacent time by using the pedestrian step length as a reference, screening out abnormal large errors, and removing the WiFi fingerprint positioning result based on a normal base stationWiFi fingerprint positioning results of the positioning points with abnormal large errors;
s104, obtaining a WiFi fingerprint global track according to the WiFi fingerprint positioning result processed by S103 and based on the normal base stationThe method comprises the steps of carrying out a first treatment on the surface of the Based on minimum residual optimization, by optimizing the relative trajectory obtained with the PDR algorithm based on inertial navigation data>Rotation translation is carried out to fit WiFi fingerprint global track +.>Obtaining the best fit track +.>And takes this as the final tracking result.
Further, S101 specifically includes:
s101.1, randomly screening different base station subsets for multiple timesThe method comprises the steps of carrying out a first treatment on the surface of the Wherein the number of base stations in each subset of base stations is the same; respectively calculating and obtaining the trajectories of different base station subsets by using a fingerprint positioning algorithmThe WiFi fingerprint positioning results of the respective to-be-positioned points are expressed as:
;
in the method, in the process of the invention,is->Sub-set of individual base stations>WiFi fingerprint positioning result sets of the to-be-positioned points; />Is->The third sub-set of base stations>WiFi fingerprint localization results for each pending site.
Further, S101.1, the fingerprint positioning algorithm includes a KNN algorithm.
Further, S101 specifically further includes:
s101.2, calculating to obtain difference values of WiFi fingerprint positioning results among different base station subsets by using K-S test; wherein, for the firstSubset of individual base stations and->The difference value of WiFi fingerprint positioning results among the base station subsets is obtained by calculation in the following mode:
separately calculateAnd->And preset value->The difference between them is->And (3) with,/>Is->The third sub-set of base stations>WiFi fingerprint positioning results of the to-be-positioned sites and preset value +.>Difference between->Is->The third sub-set of base stations>WiFi fingerprint positioning results of the to-be-positioned sites and preset value +.>Difference between->For j base station subset pair +.>WiFi fingerprint positioning result sets of the to-be-positioned points;
calculation ofAnd->The difference between them gives +.>Subset of individual base stations and->Difference value of WiFi fingerprint positioning result among subsets of base stations +.>:
;
In the method, in the process of the invention,the respective representation is based on->And->Is>Probability density at; />Representation->Absolute value of (2); />Indicating that the maximum value is taken; />Representation->And->Any value between the minimum value and the maximum value is gathered in the union of (1).
Further, S102 specifically includes:
s102.1, taking difference values of WiFi fingerprint positioning results among different base station subsets as clustering features, and inputting the clustering number to be partitioned by using a K-means clustering algorithmThen +.>And clustering the sub-clusters, selecting the sub-cluster with the most elements, and obtaining a WiFi fingerprint positioning result corresponding to the sub-cluster.
Further, S102 specifically further includes:
s102.2, using the WiFi fingerprint positioning result obtained in the S102.1 to count the occurrence frequency of different base stations, wherein the occurrence frequency is smaller than the first super-parameterThe base station of the (2) is judged to be an attacked base station, other base stations are judged to be normal base stations, the attacked base stations are identified and removed, and a WiFi fingerprint positioning result based on the normal base stations is obtained; wherein the first superparameter->Setting according to the positioning environment.
Further, S103 specifically includes:
s103.1, estimating the step length of the pedestrian by using a PDR algorithm based on inertial navigation data, and comparing the step length with the difference of WiFi fingerprint positioning results of a fingerprint positioning algorithm at adjacent moments by taking the step length as a reference to obtain the difference value of each to-be-positioned point;
S103.2by combining the difference at each site to be localized with a second superparameterComparing, and screening abnormal large errors;
if the difference at the to-be-positioned point is larger than the second super-parameterJudging whether the WiFi fingerprint positioning result is +.>The to-be-positioned point is an abnormally large error positioning point, and the WiFi fingerprint positioning result is removed;
if the difference value at the to-be-positioned point is not greater than the second super-parameterJudging whether the WiFi fingerprint positioning result is +.>The to-be-positioned point is not an abnormally large error positioning point, and the WiFi fingerprint positioning result is reserved.
Further, S104 specifically includes:
obtaining a WiFi fingerprint global track according to the WiFi fingerprint positioning result processed by S103 and based on the normal base station;
Gait detection and course angle calculation are carried out based on acceleration data and gyroscope data, and pedestrian step length estimation is combinedObtaining the relative track->;
By minimum residual optimization ofProceeding withRotation translation is carried out to fit WiFi fingerprint global track +.>The objective function is:
,/>;
in the method, in the process of the invention,is the relative track->Go up to->Position estimation results of the to-be-positioned points; />Is WiFi fingerprint global track->Go up to->WiFi fingerprint positioning results of the to-be-positioned points; />Representing the result of positioning from a WiFi fingerprint based on a normal base station>After the abnormal large error locating points are removed, the number of the normal WiFi fingerprint locating results is increased; />Expressed as:
;
in the method, in the process of the invention,、/>and->Respectively representing rotation parameters, a horizontal axis offset and a vertical axis offset under a two-dimensional plane; the rotation parameter corresponding to the minimum objective function, the horizontal axis offset and the vertical axis offset under the two-dimensional plane can be obtained through an optimization algorithm, so as to obtain the best fitting track +.>。
Compared with the prior art, the invention has at least the following beneficial effects:
(1) According to the safe and robust indoor pedestrian track tracking method and system, the attacked base station is identified and filtered, so that the risk that fingerprint positioning accuracy is influenced by the attack of the base station is reduced, fingerprint positioning accuracy is improved, and the performance of position service in an industrial Internet environment is guaranteed.
(2) According to the safe and robust indoor pedestrian track tracking method and system, the robustness of the track tracking result is improved through fusion of the WiFi fingerprint and the PDR positioning result, so that the problems of weak safety and poor robustness of the conventional track tracking method are solved.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention.
FIG. 1 is a schematic diagram of a safe and robust indoor pedestrian trajectory tracking system disclosed herein;
FIG. 2 is a schematic diagram of an internal architecture of a trajectory optimization module disclosed in the present invention;
fig. 3 is a flowchart of a safe and robust indoor pedestrian track tracking method disclosed by the invention.
Reference numerals:
21-an acquisition module; 22-a fingerprint positioning module; 23-a secure base station screening module; a 24-PDR track tracking module; 25-a reliable fingerprint positioning module; 26-track optimization module.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present invention and features in the embodiments may be combined with each other. In addition, the invention may be practiced otherwise than as specifically described and thus the scope of the invention is not limited by the specific embodiments disclosed herein.
The invention discloses a safe and robust indoor pedestrian track tracking system, which is shown in fig. 1 and comprises an acquisition module 21, a fingerprint positioning module 22, a safe base station screening module 23, a PDR track tracking module 24, a reliable fingerprint positioning module 25 and a track optimizing module 26.
The acquisition module 21 is used for acquiring WiFi signal intensity, acceleration data and gyroscope data.
Specifically, the acquisition module 21 is configured to acquire fingerprint information of a reference point offline, including a MAC address of a base station and a signal strength of the base station received at the reference point; the method is also used for acquiring fingerprint information, acceleration data and gyroscope data of the test points on the track on line; where the reference point refers to a landmark point and the test point is a point on the track for which the real position is known.
The fingerprint positioning module 22 is configured to perform fingerprint positioning according to the strength of the WiFi signal received by each to-be-positioned point on the track based on the selected base station, and estimate a WiFi fingerprint positioning result by using a fingerprint positioning algorithm.
The security base station screening module 23 is configured to calculate whether each base station is attacked according to the WiFi fingerprint positioning result sent by the fingerprint positioning module 22, identify and filter the attacked base station through the K-S test and clustering algorithm, reserve the normal base station and inform the fingerprint positioning module 22 to use the normal base station for fingerprint positioning, and obtain the WiFi fingerprint positioning based on the normal base stationResultsThe method comprises the steps of carrying out a first treatment on the surface of the Wherein, the base station refers to a WiFi base station.
A PDR track tracking module 24 for calculating based on the acceleration data and gyroscope data obtained by the acquisition module 21 by using a PDR algorithm based on inertial navigation dataRelative track for starting point->。
The reliable fingerprint positioning module 25 is used for screening abnormal large errors in fingerprint positioning results and eliminating WiFi fingerprint positioning results based on normal base stationsAn abnormally large error locating point;
the track optimization module 26 is configured to obtain a WiFi fingerprint global track according to the WiFi fingerprint positioning result processed by the reliable fingerprint positioning module 25 and based on the normal base stationThe method comprises the steps of carrying out a first treatment on the surface of the Relative trajectory to be obtained using inertial navigation data-based PDR algorithmTo fit WiFi fingerprint global track->Obtaining the best fit track +.>。
Fig. 3 shows the flow of internal trajectory optimization by the trajectory optimization module 26, wherein two trajectories are obtained from the PDR relative trajectory output module and the WiFi global trajectory output module, the PDR trajectory tracking module 24 and the reliable fingerprint positioning module 25, respectivelyAnd->Then, the track fitting is carried out for a plurality of times through an iteration module, and finally, the optimal fit track is output by an optimal track output module>。
The invention also provides a safe and robust indoor pedestrian track tracking method, as shown in fig. 3, which is realized based on the safe and robust indoor pedestrian track tracking system and comprises the following steps:
s101, randomly screening different base station subsets for multiple times to obtain WiFi fingerprint positioning results under the different base station subsets, and then calculating to obtain difference values of the WiFi fingerprint positioning results among the different base station subsets by using K-S test; wherein, the base station refers to a WiFi base station.
S101 specifically includes:
s101.1, acquiring fingerprint information of a reference point offline, wherein the fingerprint information comprises an MAC address of a base station and signal intensity of a base station received at the reference point; and collecting signal intensity, acceleration data and gyroscope data of pedestrians during movement on line.
Randomly screening different base station subsets for a plurality of times; wherein the number of base stations in each subset of base stations is the same.
Sum upThe subset of different base stations satisfies:
,(1);
in the method, in the process of the invention,representing the selected->The number of elements in the subset of base stations; />Representing the number of base stations contained in each subset of base stations; />Indicating the total number of base stations.
The fingerprint positioning algorithm, optionally KNN (K Nearest Neighbor) algorithm, is used to calculate and obtain the positions of different base stationsThe WiFi fingerprint positioning results of the respective to-be-positioned points are expressed as:
,(2);
in the method, in the process of the invention,is->Sub-set of individual base stations>WiFi fingerprint positioning result sets of the to-be-positioned points; />Is->The third sub-set of base stations>WiFi fingerprint localization results for each pending site.
S101.2, calculating to obtain difference values of WiFi fingerprint positioning results among different base station subsets by using K-S test; wherein, for the firstSubset of individual base stations and->The difference value of WiFi fingerprint positioning results among the base station subsets is obtained by calculation in the following mode:
separately calculateAnd->And preset value->The difference between them is->And->The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>And->Respectively specifically expressed as->And->,/>Is->The third sub-set of base stations>WiFi fingerprint positioning results of the to-be-positioned sites and preset value +.>Difference between->Is->The third sub-set of base stations>WiFi fingerprint positioning results of the to-be-positioned sites and preset value +.>Difference between->For j base station subset pair +.>And a WiFi fingerprint positioning result set of the to-be-positioned sites.
Calculation ofAnd->The difference between them gives +.>Subset of individual base stations and->Difference value of WiFi fingerprint positioning result among subsets of base stations +.>:
,(3);
In the method, in the process of the invention,the respective representation is based on->And->Is>Probability density at; />Representation->Absolute value of (2); />Indicating that the maximum value is taken; />Representation->And->Any value between the minimum value and the maximum value is gathered in the union of (1).
S102, taking the difference value obtained in the S101 as a clustering feature, selecting a WiFi fingerprint positioning result with highest density, counting the occurrence frequency of different base stations, identifying and eliminating the attacked base station, and obtaining a WiFi fingerprint positioning result based on a normal base station。
S102 specifically comprises the following steps:
s102.1, taking difference values of WiFi fingerprint positioning results among different base station subsets as clustering features, and inputting the clustering number to be partitioned by using a K-means clustering algorithmThen +.>Clustering the sub-clusters, selecting one type of sub-cluster with the largest elements, and obtaining WiFi fingerprint positioning corresponding to the sub-clusterAs a result.
S102.2, using the WiFi fingerprint positioning result obtained in the S102.1 to count the occurrence frequency of different base stations; wherein, for the firstPersonal base station->The frequency of occurrence of which is thus counted is expressed as +.>The specific calculation mode is as follows:
,(4);
,(5);
in the method, in the process of the invention,representing WiFi fingerprint positioning results->A corresponding subset of base stations.
Will occur less frequently than the first super-parameterThe base station of (2) is judged to be an attacked base station, the rest base stations are judged to be normal base stations, the attacked base stations are identified and removed, and a WiFi fingerprint positioning result based on the normal base stations is obtained>The method comprises the steps of carrying out a first treatment on the surface of the Wherein the first superparameter->Setting according to the positioning environment.
S103, estimating the step length of the pedestrian by using a PDR algorithm based on inertial navigation data, and taking the step length as a referenceComparing differences between the WiFi fingerprint positioning result and the WiFi fingerprint positioning result of the fingerprint positioning algorithm at adjacent moments, screening out abnormal large errors, and removing the WiFi fingerprint positioning result based on the normal base stationThe WiFi fingerprint positioning result of the positioning point with the abnormal large error.
S103.1. pedestrian step estimation using inertial navigation data based PDR algorithmThe calculation mode is as follows:
,(6);
in the method, in the process of the invention,and->Maximum and minimum acceleration values in a one-step cycle, respectively, < >>Is constant.
To be used forComparing differences of WiFi fingerprint positioning results of the fingerprint positioning algorithm at adjacent moments with the differences of the WiFi fingerprint positioning results at adjacent moments to obtain differences of all to-be-positioned points; wherein, for the->WiFi fingerprint positioning result based on normal base station of each to-be-positioned site +.>,/>And->Respectively->First, calculating the first coordinate information and the second coordinate information of the (b) and the restDifferences in WiFi fingerprint positioning results based on normal base stations at the individual pending sites. Specifically, for the remainder->The +.>The site of undetermined->,/>And->Respectively->First coordinate information and second coordinate information, of->And->Difference value of +.>The method comprises the following steps:
,(7)。
correspondingly, the first is based on the PDR algorithm based on inertial navigation dataPending site and->The distance between the various pending sites should be:
,(8);
in the method, in the process of the invention,represents the first->Pending site and->The time interval for signal acquisition between the various pending sites can be derived from the acquisition time stamp.
Since the PDR algorithm based on inertial navigation data can provide high-precision relative track tracking result in a short time, the method is used forFor reference, compare->And->Difference between:
,(9)。
s103.2. By combining the difference at each of the pending sites with a second superparameterAnd comparing, and screening the abnormal large errors.
If the difference at the to-be-positioned point is larger than the second super-parameterJudging whether the WiFi fingerprint positioning result is +.>The to-be-positioned point is an abnormally large error positioning point, and the WiFi fingerprint positioning result is removed; wherein the second superparameter->Typically take 5 empirically.
If the difference value at the to-be-positioned point is not greater than the second super-parameterJudging whether the WiFi fingerprint positioning result is +.>The to-be-positioned point is not an abnormally large error positioning point, and the WiFi fingerprint positioning result is reserved.
S104, obtaining a WiFi fingerprint global track according to the WiFi fingerprint positioning result processed by S103 and based on the normal base stationThe method comprises the steps of carrying out a first treatment on the surface of the Based on minimum residual optimization, by optimizing the relative trajectory obtained with the PDR algorithm based on inertial navigation data>Rotation translation is carried out to fit WiFi fingerprint global track +.>Obtaining the best fit track +.>And takes this as the final tracking result.
S104 specifically comprises:
obtaining a WiFi fingerprint global track according to the WiFi fingerprint positioning result processed by S103 and based on the normal base station。
Gait detection and course angle calculation are carried out based on acceleration data and gyroscope data, and pedestrian step length estimation is combinedObtaining the relative track->The method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Initial position +.>。
By minimum residual optimization ofPerforming rotation and translation to fit WiFi fingerprint global track +.>The objective function is:
,/>,(10);
in the method, in the process of the invention,is the relative track->Go up to->Position estimation results of the to-be-positioned points; />Is WiFi fingerprint global track->Go up to->WiFi fingerprint positioning results of the to-be-positioned points; />Representing the result of positioning from a WiFi fingerprint based on a normal base station>After the abnormal large error locating points are removed, the number of the normal WiFi fingerprint locating results is increased; />Expressed as:
,(11);
in the method, in the process of the invention,、/>and->Respectively representing rotation parameters, a horizontal axis offset and a vertical axis offset under a two-dimensional plane; the rotation parameter corresponding to the minimum objective function, the horizontal axis offset and the vertical axis offset under the two-dimensional plane can be obtained through an optimization algorithm, so as to obtain the best fitting track +.>。
Compared with the prior art, the safe and robust indoor pedestrian track tracking method and system provided by the invention have the advantages that through identifying and filtering the attacked base station, the risk that the fingerprint positioning accuracy is influenced by the attack of the base station is reduced, the fingerprint positioning accuracy is improved, and the performance of the position service in the industrial Internet environment is ensured; by fusing the WiFi fingerprint and the PDR positioning result, the robustness of the track tracking result is improved, and therefore the problems of weak safety and poor robustness of the current track tracking method are solved.
The present invention is not limited to the above-mentioned embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. The safe and robust indoor pedestrian track tracking system is characterized by comprising an acquisition module (21), a fingerprint positioning module (22), a safe base station screening module (23), a PDR track tracking module (24), a reliable fingerprint positioning module (25) and a track optimizing module (26); wherein,
the acquisition module (21) is used for acquiring WiFi signal intensity, acceleration data and gyroscope data;
the fingerprint positioning module (22) is used for performing fingerprint positioning according to the intensity of the WiFi signal received by each to-be-positioned point on the track based on the selected base station, and estimating and obtaining a WiFi fingerprint positioning result by utilizing a fingerprint positioning algorithm;
the security base station screening module (23) is used for calculating whether each base station is attacked according to the WiFi fingerprint positioning result sent by the fingerprint positioning module (22), identifying and filtering the attacked base station through the K-S test and clustering algorithm, reserving the normal base station and informing the fingerprint positioning module (22) of using the normal base station for fingerprint positioning to obtain the WiFi fingerprint positioning result based on the normal base station;
A PDR track tracking module (24) for calculating and obtaining relative track by utilizing a PDR algorithm based on inertial navigation data according to the acceleration data and the gyroscope data obtained by the acquisition module (21);
A reliable fingerprint positioning module (25) for screening abnormal large errors in the fingerprint positioning result and eliminatingWiFi fingerprint positioning result based on normal base stationAn abnormally large error locating point;
the track optimization module (26) is used for obtaining the WiFi fingerprint global track according to the WiFi fingerprint positioning result processed by the reliable fingerprint positioning module (25) and based on the normal base stationThe method comprises the steps of carrying out a first treatment on the surface of the Relative trajectory +.>Fitting WiFi fingerprint global track +.>Obtaining the best fit track +.>。
2. The safe and robust indoor pedestrian trajectory tracking system of claim 1, characterized by an acquisition module (21), in particular for off-line acquisition of fingerprint information of a reference point, comprising a MAC address of a base station and a signal strength of a base station received at the reference point; the method is also used for acquiring fingerprint information, acceleration data and gyroscope data of the test points on the track on line; where the reference point refers to a landmark point and the test point is a point on the track for which the real position is known.
3. A safe and robust indoor pedestrian track tracking method based on the safe and robust indoor pedestrian track tracking system of claim 1 or 2, comprising the following steps:
s101, randomly screening different base station subsets for multiple times to obtain WiFi fingerprint positioning results under the different base station subsets, and then calculating to obtain difference values of the WiFi fingerprint positioning results among the different base station subsets by using K-S test;
s102, taking the difference value obtained in the S101 as a clustering feature, selecting a WiFi fingerprint positioning result with highest density, counting the occurrence frequency of different base stations, identifying and eliminating the attacked base station, and obtaining a WiFi fingerprint positioning result based on a normal base station;
S103, estimating the step length of the pedestrian by utilizing a PDR algorithm based on inertial navigation data, comparing the difference between the pedestrian step length and the WiFi fingerprint positioning result of the fingerprint positioning algorithm at adjacent moments by taking the pedestrian step length as a reference, screening out abnormal large errors, and removing the WiFi fingerprint positioning result based on a normal base stationWiFi fingerprint positioning results of the positioning points with abnormal large errors;
s104, obtaining a WiFi fingerprint global track according to the WiFi fingerprint positioning result processed by S103 and based on the normal base stationThe method comprises the steps of carrying out a first treatment on the surface of the Based on minimum residual optimization, relative track obtained by PDR algorithm based on inertial navigation data ∈>Rotation translation, fitting WiFi fingerprint global track +.>Obtaining the best fit track +.>And takes this as the final tracking result.
4. The safe and robust indoor pedestrian trajectory tracking method according to claim 3, wherein S101 specifically comprises:
s101.1, randomly screening different base station subsets for a plurality of times; wherein the number of base stations in each subset of base stations is the same; benefit (benefit)Respectively calculating by using fingerprint positioning algorithm to obtain the positions of different base stations on the tracksThe WiFi fingerprint positioning results of the respective to-be-positioned points are expressed as:
;
in the method, in the process of the invention,is->Sub-set of individual base stations>WiFi fingerprint positioning result sets of the to-be-positioned points; />Is->The third sub-set of base stations>WiFi fingerprint localization results for each pending site.
5. The safe and robust indoor pedestrian trajectory tracking method of claim 4, wherein S101.1 the fingerprint positioning algorithm comprises a KNN algorithm.
6. The safe and robust indoor pedestrian trajectory tracking method of claim 5, wherein S101 further specifically comprises:
s101.2, calculating to obtain difference values of WiFi fingerprint positioning results among different base station subsets by using K-S test; wherein, for the firstSubset of individual base stations and->The difference value of WiFi fingerprint positioning results among the base station subsets is obtained by calculation in the following mode:
separately calculateAnd->And preset value->The difference between them is->And (3) with,/>Is->The third sub-set of base stations>WiFi fingerprint positioning results of the to-be-positioned sites and preset value +.>Difference between->Is->The third sub-set of base stations>WiFi fingerprint positioning results of the to-be-positioned sites and preset value +.>Difference between->For j base station subset pair +.>WiFi fingerprint positioning result sets of the to-be-positioned points;
calculation ofAnd->The difference between them gives +.>Subset of individual base stations and->Difference value of WiFi fingerprint positioning result among subsets of base stations +.>:
;
In the method, in the process of the invention,the respective representation is based on->And->Is>Probability density at;representation->Absolute value of (2); />Indicating that the maximum value is taken; />Representation->And->Any value between the minimum value and the maximum value is gathered in the union of (1).
7. The safe and robust indoor pedestrian trajectory tracking method of claim 6, wherein S102 specifically comprises:
s102.1, taking difference values of WiFi fingerprint positioning results among different base station subsets as clustering features, and inputting the clustering number to be partitioned by using a K-means clustering algorithmThen get +.>And clustering the sub-clusters, selecting the sub-cluster with the most elements, and obtaining a WiFi fingerprint positioning result corresponding to the sub-cluster.
8. The safe and robust indoor pedestrian trajectory tracking method of claim 7, wherein S102 further specifically comprises:
s102.2, using the WiFi fingerprint positioning result obtained in the S102.1 to count the occurrence frequency of different base stations, wherein the occurrence frequency is smaller than the first super-parameterThe base station of the (2) is judged to be an attacked base station, other base stations are judged to be normal base stations, the attacked base stations are identified and removed, and a WiFi fingerprint positioning result based on the normal base stations is obtained; wherein the first superparameter->Setting according to the positioning environment.
9. The safe and robust indoor pedestrian trajectory tracking method of claim 8, wherein S103 specifically comprises:
s103.1, estimating the step length of the pedestrian by utilizing a PDR algorithm based on inertial navigation data, and comparing the step length with the difference of WiFi fingerprint positioning results of a fingerprint positioning algorithm at adjacent moments by taking the step length as a reference to obtain the difference value of each to-be-positioned point;
s103.2. By combining the difference at each of the pending sites with a second superparameterComparing, and screening abnormal large errors;
if the difference at the to-be-positioned point is larger than the second super-parameterJudging whether the WiFi fingerprint positioning result is +.>The to-be-positioned point is an abnormally large error positioning point, and the WiFi fingerprint positioning result is removed;
if the difference value at the to-be-positioned point is not greater than the second super-parameterJudging the WiFi fingerprint positioning result based on the normal base stationThe to-be-positioned point is not an abnormally large error positioning point, and the WiFi fingerprint positioning result is reserved.
10. The safe and robust indoor pedestrian trajectory tracking method of claim 9, wherein S104 specifically comprises:
obtaining a WiFi fingerprint global track according to the WiFi fingerprint positioning result processed by S103 and based on the normal base station;
Gait detection and course angle calculation are carried out based on acceleration data and gyroscope data, and pedestrian step length estimation is combinedObtaining the relative track->;
By minimum residual optimization ofPerforming rotation translation, and fitting WiFi fingerprint global track +.>The objective function is:
,/>;
in the method, in the process of the invention,is the relative track->Go up to->Position estimation results of the to-be-positioned points; />Is WiFi fingerprint global trackGo up to->WiFi fingerprint positioning results of the to-be-positioned points; />Representing positioning results from WiFi fingerprints based on normal base stationsAfter the abnormal large error locating points are removed, the number of the normal WiFi fingerprint locating results is increased; />Expressed as:
;
in the method, in the process of the invention,、/>and->Respectively representing rotation parameters, a horizontal axis offset and a vertical axis offset under a two-dimensional plane; obtaining a rotation parameter corresponding to the minimum objective function, a horizontal axis offset and a vertical axis offset under a two-dimensional plane through an optimization algorithm, thereby obtaining a best fit track +.>。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410038094.5A CN117560629B (en) | 2024-01-11 | 2024-01-11 | Safe and robust indoor pedestrian track tracking method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410038094.5A CN117560629B (en) | 2024-01-11 | 2024-01-11 | Safe and robust indoor pedestrian track tracking method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117560629A CN117560629A (en) | 2024-02-13 |
CN117560629B true CN117560629B (en) | 2024-04-02 |
Family
ID=89813127
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410038094.5A Active CN117560629B (en) | 2024-01-11 | 2024-01-11 | Safe and robust indoor pedestrian track tracking method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117560629B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113271537A (en) * | 2021-05-20 | 2021-08-17 | 北京智慧图科技有限责任公司 | Indoor positioning system of mixing chamber |
CN114440895A (en) * | 2022-03-04 | 2022-05-06 | 杭州电子科技大学 | Atmospheric pressure assisted Wi-Fi/PDR indoor positioning method based on factor graph |
CN115413026A (en) * | 2022-09-02 | 2022-11-29 | 中国电信股份有限公司 | Base station selection method, system, equipment and storage medium based on clustering algorithm |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2503832B1 (en) * | 2005-02-22 | 2019-08-21 | Skyhook Wireless, Inc. | Method for calculating the position of WiFi-enabled devices |
KR102034527B1 (en) * | 2014-02-11 | 2019-10-21 | 한국전자통신연구원 | System for filtering location of Mobile terminal by fusing wi-fi location and sensing information |
US12069536B2 (en) * | 2019-03-19 | 2024-08-20 | Invensense, Inc. | Revising an unstable location fingerprint database for an area |
-
2024
- 2024-01-11 CN CN202410038094.5A patent/CN117560629B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113271537A (en) * | 2021-05-20 | 2021-08-17 | 北京智慧图科技有限责任公司 | Indoor positioning system of mixing chamber |
CN114440895A (en) * | 2022-03-04 | 2022-05-06 | 杭州电子科技大学 | Atmospheric pressure assisted Wi-Fi/PDR indoor positioning method based on factor graph |
CN115413026A (en) * | 2022-09-02 | 2022-11-29 | 中国电信股份有限公司 | Base station selection method, system, equipment and storage medium based on clustering algorithm |
Non-Patent Citations (2)
Title |
---|
WiFi辅助的IMU室内定位方法的研究;袁国良;谢奎;;信息技术与网络安全;20180510(第05期);全文 * |
人机共享环境下基于Wi-Fi指纹的室内定位方法;赵林生;王鸿鹏;刘景泰;;机器人;20190107(第03期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117560629A (en) | 2024-02-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109215347B (en) | Traffic data quality control method based on crowdsourcing trajectory data | |
EP3534114B1 (en) | Lane determination method, device and storage medium | |
CN111862659B (en) | GPS track data matching and complementing method | |
CN107563419B (en) | Train positioning method combining image matching and two-dimensional code | |
CN108377252B (en) | Vehicle-road cooperation information pushing method and device | |
US20180083914A1 (en) | Communication apparatus, server apparatus, communication system, computer program product, and communication method | |
CN111105437B (en) | Vehicle track abnormality judging method and device | |
CN109005173A (en) | A kind of car networking abnormal intrusion detection method based on traffic flow density variation | |
CN112183367B (en) | Vehicle data error detection method, device, server and storage medium | |
US11180154B2 (en) | Fingerprinting drivers based on vehicle turns | |
CN103916860B (en) | Outlier data detection method based on space time correlation in wireless senser cluster l network | |
CN116611620B (en) | Smart city safety collaborative management information system | |
GB2490773A (en) | Means for classifying vehicular mobility data | |
CN106922176A (en) | Lane detection | |
CN112313536A (en) | Object state acquisition method, movable platform and storage medium | |
CN117560629B (en) | Safe and robust indoor pedestrian track tracking method and system | |
CN103454653B (en) | A kind of outlier replacement method based on gps system and device | |
CN113959452A (en) | Map matching method, system and terminal based on urban road network | |
Tang et al. | A novel method for road intersection construction from vehicle trajectory data | |
CN114449533B (en) | Base station deployment method, environment awareness method, device, computer equipment and storage medium | |
CN112770252A (en) | Single-point similarity-based man-vehicle association method, device, equipment and storage medium | |
CN112612044A (en) | Method and system for drift point filtering | |
CN109344776B (en) | Data processing method | |
CN116935065A (en) | Lane line instance detection method and system based on fusing and fusion | |
CN111372309B (en) | Positioning method and device based on LTE signal and readable storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |