CN104180805A - Smart phone-based indoor pedestrian positioning and tracking method - Google Patents
Smart phone-based indoor pedestrian positioning and tracking method Download PDFInfo
- Publication number
- CN104180805A CN104180805A CN201410438351.0A CN201410438351A CN104180805A CN 104180805 A CN104180805 A CN 104180805A CN 201410438351 A CN201410438351 A CN 201410438351A CN 104180805 A CN104180805 A CN 104180805A
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- rss
- particle
- room
- wifi
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a smart phone-based indoor pedestrian positioning and tracking method, comprising the following steps: leading in indoor map information by a smart phone, wherein an indoor map is a vector map; collecting current acceleration information, angular speed information and direction information of the smart phone, and collecting the strength of all indoor WIFI RSS signals; on the basis of PDR, calculating pedestrian steps, pedestrian step lengths and walking directions according to the sampled data; estimating the positions of pedestrians by using a particle filtering algorithm, judging and identifying a swerving scene, a room identification scene and a door detection scene on the basis of WIFI RSS to carry out auxiliary correcting and positioning; and displaying the positions of the pedestrians on the indoor map. The method is high in positioning accuracy and strong in anti-jamming capability, a decimeter-level positioning result can be obtained, the effect on the pedestrian action, caused by the positioning accuracy, is small, the functions of pedestrian swerving, room identification and door detection are effectively achieved, the excessive dependence on the deployment position of a WIFI router is avoided, and the labor consumption in the deployment process is reduced.
Description
Technical field
The invention describes a kind of indoor pedestrian location and tracking based on smart mobile phone.
Background technology
Gps satellite location is the most common way of obtaining positional information at present, but various buildingss block or other factors disturbs because satellite-signal is easily subject to, and GPS location technology is not also suitable for indoor scenarios or built-up complex environment.Along with the development of wireless electron mobile communication technology, indoor positioning technology is supplemented becoming the strong of GPS outdoor positioning, and it can provide critical positions information service (LBS) for various application scenarioss such as indoor rescue, market marketing and the large-scale place navigation such as passenger flow analysing, airport and hospital.
The indoor orientation method of current main-stream can be divided into two classes: indoor positioning technology (inertial navigation location) and the indoor positioning technology based on RSS (wireless receiving signal intensity) based on pedestrian's dead reckoning (PDR).
Inertial navigation localization method is to utilize the sensors such as accelerometer, gyroscope and magnetometer to gather monitoring sensing data, and estimating step length, speed and towards etc. information, and then realize indoor positioning and tracking.In the method implementation process, sensor is easily subject to the impact of various no intention actions in pedestrian's walking process (as arm is shaken, turned round etc.) and causes larger cumulative errors.
Indoor positioning technology based on RSS generally has two kinds: the location technology based on RSS model and the location technology based on RSS fingerprint.Uncertain influence factor based on RSS model indoor positioning is more, and positioning error is larger, and need to obtain the accurate coordinates of WIFI router (AP), localization method based on RSS fingerprint is in the fixing indoor environment in WIFI router (AP) position, by the off-line collection RSS information of coordinate points in batches, learning training draws the mapping library between WIFI RSS signal intensity and indoor coordinate position (distance), and then obtain pedestrian at indoor coordinate position according to the RSS signal intensity real-time query mapping library collecting in walking, the method depends on the accurate deployment coordinate of AP, and positioning precision is subject to the de-stabilising effect of RSS signal intensity larger, RSS signals collecting, off-line training and deployment phase all need larger manpower consumption.
The paper " A Reliable and Accurate Indoor Localization Method Using Phone Inertial Sensors " that famous international conference Ubicomp 2012 delivers in general fit calculation field has adopted particle filter method to utilize cartographic information to proofread and correct the inertial navigation positioning error that smart mobile phone low side inertial sensor brings, and has realized indoor pedestrian location and the tracking precision of mean accuracy between 1.5-2 rice.The present invention is on the basis of this paper method, further indoor radio signal intensity is relatively changed with pedestrian's gait processes in turning, enter the behaviors such as room and set up corresponding relation, for further proofreading and correct the inertial navigation positioning error of gait processes, realize the positioning precision of decimeter grade.
But existing indoor positioning technological orientation precision is not high, and antijamming capability is poor, rely on deployment density and the concrete coordinate position of router, data acquisition and deployment need higher manpower consumption.
Summary of the invention
The object of the invention is to provide a kind of indoor pedestrian location and tracking based on smart mobile phone, the method is taking particle filter as core, relative variation relation based on WIFI network wireless signal intensity (RSS) completes inertial navigation positioning correcting, obtain the hi-Fix result of decimeter grade, thereby overcome the problems such as existing indoor positioning technology acuracy is not high.
Based on indoor pedestrian location and the tracking of smart mobile phone, comprising:
Step 1: smart mobile phone imports indoor cartographic information, described indoor map is map vector;
Step 2: utilize the embedded accelerometer of smart mobile phone, gyroscope, magnetometer sensor to gather the current acceleration information of this smart mobile phone, angular velocity information and directional information, and gather indoor all WIFI RSS signal intensities;
It is characterized in that comprising the following steps as follows:
Step 3: based on PDR (inertial navigation), calculate pedestrian's step, pedestrian's step-length and direction of travel according to the sensor sampled data;
Step 4: the position that utilizes particle filter algorithm estimation pedestrian:
First, pedestrian's step-length, step and the direction of travel calculated based on PDR, the more relative geological information of information, WIFI RSS change in signal strength carries out the distribution of particle weights according to the map, finally completes pedestrian's location estimation by resampling;
Step 5: by pedestrian's position display on indoor map.
The detailed process of above-mentioned steps (4) particle filter algorithm estimation pedestrian's position is as follows:
(4.1) PDR (inertial navigation) is estimated to the pedestrian's step, step-length and the direction of travel information that go out and pass to particle filter;
(4.2) particle is according to the step-length of PDR and direction motion;
(4.3) particle filter obtains the set of current step particle weights, and relative geometrical relation based on WIFI RSS change in signal strength is effectively assisted and proofreaied and correct location;
(4.4) particle filter regenerates new particle.
In above-mentioned steps (4.3), specific as follows based on the auxiliary location of proofreading and correct of WIFI RSS:
(4.3.1) scene is proofreaied and correct in judgement,
If " turning scene ", carries out (4.3.2);
If " room identification scene ", carries out (4.3.3);
If " door detection scene ", carries out (4.3.4);
(4.3.2) operation is turned and is confirmed algorithm;
(4.3.3) operation room recognizer;
(4.3.4) operation door detection algorithm.
Above-mentioned WIFI RSS is auxiliary to be proofreaied and correct in location, and described " turning scene " identification is turned and confirmed that algorithm is specific as follows with operation:
(1), in the time that pedestrian's direction of travel of PDR (inertial navigation) estimation changes than the direction of front step, triggering turns confirms, carries out (2)~(5);
(2) obtain the WIFI RSS vector direction between current step and last step, be defined as RSSDirection1;
(3) obtain the WIFI RSS vector direction between current step and front the second step, be defined as RSSDirection2;
(4) calculate the angle changing between RSSDirection1 and two vector direction of RSSDirection2;
(5) whether the angle changing in judgement (3) is less than predefined left-hand bend threshold value or is greater than right-hand bend threshold value; If angle changing is less than left-hand bend threshold value or is greater than right-hand bend threshold value, think that real touch turn does not occur current step, use the direction of front the second step to replace the direction of current step; Otherwise, think that touch turn has occurred current step really, continue to keep the direction of current step;
Above-mentioned WIFI RSS is auxiliary to be proofreaied and correct in location, and described " room identification scene " identification is specific as follows with operation room recognizer:
(1) particle filter is inferred the pedestrian's step number, step-length and the direction of travel that according to PDR (inertial navigation), and cartographic information, judge whether current step passes through certain door and (above map, have door, whether the prediction run trace that judges current step passes through the door above map, through thinking through certain door, be that detection identification scene in room is to see that whether the track of current step inertial navigation prediction is through certain door, if illustrate that pedestrian enters room through door, which room what trigger that room recognizer judges that pedestrian enters is); If process, illustrates that pedestrian is just entering room, now trigger room recognizer, within the scope of ensuing 3 steps, (2)~(6) are carried out in circulation, exceed 3 step scopes, carry out (7); Otherwise, illustrate that pedestrian does not enter the action behavior in room, keep current step state, carry out (6) (7);
(2) travel through the WIFI RSS signal strength readings of all AP (router) that current step scans, search the AP of WIFI RSS reading maximum, be defined as AP1, and think that temporarily pedestrian has entered the room Room1 at AP1 place;
(3) travel through the WIFI RSS signal strength readings of all AP that current step scans, search the AP of the WIFI RSS reading increment maximum of more last step, orientate AP2 as, the room that simultaneously defines AP2 place is Room2;
(4) if AP2 is identical with AP1, judge that pedestrian has entered the room at AP1 place, keep the state of current particle, carry out (6); Otherwise the room at pedestrian place is reaffirmed in execution (5);
(5) particle filter combining cartographic information, according to the proportionate relationship of WIFI RSS absolute signal intensity corresponding to the AP1 WIFI RSS absolute signal intensity corresponding with AP2, carries out weights distribution to all particles again:
5.1 information according to the map, find the coincidence body of wall at room Room1 and Room2, with it all particles of particle filter are divided into two S set et1 and Set2, wherein Set1 refers to the particle assembly that is positioned at Room1, Set2 refers to the particle assembly that is positioned at Room2;
When the current step of 5.2 definition, WIFI RSS signal intensity corresponding to AP1 is RSS1; WIFI RSS signal intensity corresponding to definition AP2 is RSS2;
In 5.3 definition set Set1, the weights scale-up factor Ratio1 of particle is: (90+RSS1)/and (180+RSS1+RSS2);
The weights scale-up factor Ratio2 of particle is (90+RSS2)/(180+RSS1+RSS2) in 5.4 definition set Set2;
5.5 traversal particle assembly Set1, reset to the weight w of each particle: w*Ratio1;
5.6 traversal particle assembly Set2, reset to the weight w of each particle: w*Ratio2;
(6) particle filter regenerates new particle;
(7) finish algorithm;
Above-mentioned WIFI RSS is auxiliary to be proofreaied and correct in location, and described " door detection scene " identification is specific as follows with operation door detection algorithm:
(1), if pedestrian's accumulation step number is greater than or equal to 3 steps, carry out (2)~(8); Otherwise, carry out (8);
(2) obtain the particle filter predicted position coordinate points of current step and front 3 steps, be defined as successively respectively estPos0, estPos1, estPos2, estPos3;
(3) judge estPos0 and estPos1, whether the distance between estPos1 and estPos2 and estPos2 and estPos3 position coordinates point is all in predefined threshold range, if above three distance values are all in threshold range, and estPos0~estPos3 position coordinates point is all positioned near the edge line (in 0.5 meter) of room wall, carries out (4)~(8); Otherwise carry out (8);
(4) AP of WIFI RSS signal strength readings increment maximum when traversal is searched current step and nearest front the 3rd step;
(5) particle filter creates a particle that weights are 1 in the entrance center position in the room at AP place, and step-length based on nearest three steps and direction of travel (being obtained by PDR) are extrapolated the action vector (run trace) of nearest three steps;
(6) particle filter regenerates new particle;
(7) particle filter is carried out room recognizer, further confirms the residing room of pedestrian's particle;
(8) finish algorithm.
More than turn confirm described in algorithm to obtain WIFI RSS vector direction specific as follows:
(1) the WIFI RSS signal strength readings that smart mobile phone gathers WIFI router-A P is taking timestamp as index stores is in <rss1, rss2, ... rssn, in the data layout of time>, the present invention is called a RSS vector;
(2) travel through the RSS vector in current step moment, search the AP set that in the more last step RSS of RSS reading vector wherein, corresponding RSS reading increases, be defined as Set (increase); Search the AP set that RSS reading corresponding in the more last step RSS of RSS reading vector reduces, be defined as Set (decrease)
(3) positional information based on each room, AP place, calculates respectively the geographical geometric center of Set (increase) and Set (decrease);
(4) calculate the vector direction between the geographical geometric center of Set (increase) and the geographical geometric center of Set (decrease), the RSS vector direction that current step is corresponding.
Described predefined left-hand bend threshold value be (0,90] degree in numerical value; Described right-hand bend threshold value is the numerical value in [270,360] degree.
Between described coordinate points, the threshold range of distance is the arbitrary numerical value in [0,0.5 meter].
The present invention has substantive distinguishing features and marked improvement, solve the deficiency of background technology, utilize the embedded accelerometer of smart mobile phone, gyroscope and magnetometer to carry out detecting pedestrian step, estimate step-length and infer direction of travel, be input to particle filter and carry out pedestrian's position estimation, and then the geological information that information, RSS signal intensity change relatively according to the map carries out the distribution of particle weights, finally complete pedestrian's location estimation by the resampling of particle filter, obtain hi-Fix result.The method effectively solved inertial navigation location be subject to pedestrian move (as arm shake, turned round etc.) affect and the inertial navigation cumulative errors that causes, and effectively realize the functions such as pedestrian's turning, room identification and door detection, avoid the depending on unduly of WIFI router (AP) deployed position, and reduced the manpower consumption of deployment.
Compared with prior art, the present invention has following significant advantage:
A neodoxy of utilizing RSS reading variation tendency to proofread and correct inertial navigation-particle filter method has been proposed; Having designed and Implemented turns confirms algorithm, room recognizer and door detection algorithm; Indoor pedestrian location and the tracking of lightweight, decimeter grade precision on smart mobile phone, are realized.Positioning precision is high, can obtain the positioning precision of decimeter grade.
Antijamming capability is strong, the impact that positioning precision is moved by pedestrian is less, effectively solve inertial navigation location and be subject to pedestrian to move (as arm shake, turned round etc.) impact and the inertial navigation cumulative errors that causes, and effectively realized that pedestrian turns, room is identified and the function such as door detection; Take full advantage of the relative geometrical relation of RSS signal intensity, instead of RSS absolute figure; Reduce the manpower consumption of deployment; Avoid depending on unduly WIFI router (AP) deployed position; Better protect individual's (position) privacy.
Brief description of the drawings
Fig. 1 localization method frame diagram of the present invention.
Fig. 2 localization method process flow diagram of the present invention.
Particle filter process flow diagram in Fig. 3 the inventive method.
In Fig. 4 the inventive method, turn and confirm algorithm flow chart.
Recognizer process flow diagram in room in Fig. 5 the inventive method.
Door detection algorithm process flow diagram in Fig. 6 the inventive method.
Embodiment
As shown in Fig. 1-6, provide following examples in conjunction with the content of the inventive method:
Pedestrian's hand-held intelligent mobile phone is walked in indoor environment, specific as follows:
(1) smart mobile phone loads indoor cartographic information, and definition direct north is the direction that coordinate system 0 is spent, and definition left-hand rotation threshold value is 45, and right-hand rotation threshold value is 315;
(2) embedded accelerometer, gyroscope and the magnetometer sensor of smart mobile phone gathers sensing data, and gathers the WIFI RSS signal strength readings of indoor all-router;
(3) PDR module is according to sensor sample data, detecting pedestrian step, estimates pedestrian's step-length, calculates direction of travel;
(4) step estimating, step-length and direction are inputed to particle filter module by PDR module;
(5) all particles of particle filter are according to the step-length of PDR and direction motion, and based on the effectively auxiliary pedestrian location of proofreading and correct, (6) (7) (8), estimation pedestrian position, is finally presented at position on indoor map in real time;
(6) owing to often thinking pedestrian's action (in fact not having) that occurred to swerve because no intention action (as arm shake, the initiatively action such as turning) causes PDR inertial navigation module in pedestrian's walking process, so pedestrian in the process of walking, if PDR inertial navigation detects pedestrian's direction of travel variation has occurred, particle filter can utilize the positioning correcting function of WIFI module so, carrying out turns confirms algorithm, whether further confirms pedestrian's turning.For example: when current step, PDR detects that variation has occurred direction of travel, calculating corresponding RSSDirection1 angle is 45 degree, calculating RSSDirection2 angle is 80 degree, RSSDirection2 has changed 35 degree compared with RSSDirection1, be less than left-hand rotation threshold value 45, therefore assert that touch turn does not occur pedestrian, keep the particle state of current step, continue to advance.Be 45 degree and work as RSSDirection1 angle corresponding to a certain step, calculating the RSSDirection2 angle that last step obtains is 100 degree, there is the variation of 55 degree in RSS vector corresponding to two steps, be greater than left-hand rotation threshold value, so assert that turning action has occurred pedestrian, current step direction changes the direction of travel of front the second step into
(7) in the time that pedestrian enters indoor a certain room, in order to prevent because the situation that positioning error causes pedestrian to enter wrong room occurs, particle filter utilizes the positioning correcting function of WIFI module, carry out room recognizer, confirm more accurately pedestrian's room location, for example: when current step, particle filter is according to step-length and the directional information of PDR estimation, combining cartographic information is learnt, this pedestrian is just passing the door in certain room, now trigger room recognizer, for example: the AP1 that obtains the WIFI RSS signal intensity maximum that current step is corresponding, and definition room, AP1 place is Room1, obtain the more last step of WIFI RSS signal intensity that current step is corresponding and change maximum AP2, corresponding room is Room2, if AP1 is identical with AP2, think that pedestrian is in Room1 room, otherwise according to the proportionate relationship of WIFI RSS absolute signal intensity corresponding to the AP1 WIFI RSS absolute signal intensity corresponding with AP2, again all particles are carried out to weights distribution, first all particle assemblies that are positioned at Room1 are decided to be to Set1, all particle assemblies in Room2 are decided to be Set2, then all particles in Set1 and Set2 are redistributed respectively to weights, for example: wherein in Set1, the weights of a certain particle are 0.3, in Set2, the weights of a certain particle are 0.1, the WIFI RSS signal intensity that AP1 is corresponding is-70, and WIFI RSS signal intensity corresponding to AP2 is-50, the weights of that particle in Set1 will be re-allocated for so: 03* (90+ (70))/(180+ (70)+(50))=0.3*1/3, the weights of that particle in Set2 are: 0.1* (90+ (50))/(180+ (70)+(50))=0.1*2/3.All the other particles are redistributed respectively weights by same procedure, and final particle filter is estimated pedestrian's position again according to weights set, further confirm the residing room of pedestrian;
(8) when particle filter detects that pedestrian is all the time outside door or hover in wall limit or when long-time transfixion, carry out the door detection algorithm of WIFI module, whether more effective detection pedestrian enters room through door already, for example: in the time of pedestrian's begin column to the four step, obtain four coordinate points corresponding to first three step, be respectively (20, 30), (20.5, 29.5), (20, 30.5) (19.8, 29.2), can be calculated and know that these four coordinate points range difference each other is all no more than 0.5, combining cartographic information again, find that these coordinate points are all positioned on the body of wall edge line in certain room, now traveling through RSS vector obtains front the 3rd step of current step and changes maximum AP, door mouth center in this room, AP place creates a particle (by the whole door mouth position that has been placed on of particle filter) that weights are 1, then by the PDR estimation information (step-length of first three step, step and direction of travel) input to particle filter, thereby particle filter is estimated the run trace of nearest three steps again, meanwhile, particle filter thinks that now pedestrian, just through door, further confirms the residing concrete room of pedestrian therefore start afterwards room recognizer.
Generally speaking, the present invention has following concrete implementation result: 1, positioning precision is high, can obtain decimeter grade positioning result; 2, antijamming capability is strong, and the impact that positioning precision is moved by pedestrian is less; 3, effectively realize the functions such as pedestrian's turning, room identification and door detection; 3, avoided depending on unduly WIFI router (AP) deployed position; 4, reduced the manpower consumption of deployment.
Claims (6)
1. indoor pedestrian location and the tracking based on smart mobile phone, comprising:
Step 1: smart mobile phone imports indoor cartographic information, described indoor map is map vector;
Step 2: utilize the embedded accelerometer of smart mobile phone, gyroscope, magnetometer sensor to gather the current acceleration information of this smart mobile phone, angular velocity information and directional information, and gather indoor all WIFI RSS signal intensities;
It is characterized in that comprising the following steps as follows:
Step 3: based on PDR (inertial navigation), calculate pedestrian's step, pedestrian's step-length and direction of travel according to the sensor sampled data;
Step 4: the position that utilizes particle filter algorithm estimation pedestrian:
First, pedestrian's step-length, step and the direction of travel calculated based on PDR, the more relative geological information of information, WIFI RSS change in signal strength carries out the distribution of particle weights according to the map, finally completes pedestrian's location estimation by resampling;
Step 5: by pedestrian's position display on indoor map.
2. indoor pedestrian location and the tracking based on smart mobile phone as claimed in claim 1, is characterized in that above-mentioned steps (4) particle filter algorithm estimation pedestrian's the detailed process of position is as follows:
(4.1) PDR (inertial navigation) is estimated to the pedestrian's step, step-length and the direction of travel information that go out and pass to particle filter;
(4.2) particle is according to the step-length of PDR and direction motion;
(4.3) particle filter obtains the set of current step particle weights, and relative geometrical relation based on WIFI RSS change in signal strength is effectively assisted and proofreaied and correct location;
(4.4) particle filter regenerates new particle.
3. indoor pedestrian location and the tracking based on smart mobile phone as claimed in claim 2, is characterized in that in above-mentioned steps (4.3), specific as follows based on the auxiliary location of proofreading and correct of WIFI RSS:
(4.3.1) scene is proofreaied and correct in judgement,
If " turning scene ", carries out (4.3.2);
If " room identification scene ", carries out (4.3.3);
If " door detection scene ", carries out (4.3.4);
(4.3.2) operation is turned and is confirmed algorithm;
(4.3.3) operation room recognizer;
(4.3.4) operation door detection algorithm.
Above-mentioned WIFI RSS is auxiliary to be proofreaied and correct in location, and described " turning scene " identification is turned and confirmed that algorithm is specific as follows with operation:
(1), in the time that pedestrian's direction of travel of PDR (inertial navigation) estimation changes than the direction of front step, triggering turns confirms, carries out (2)~(5);
(2) obtain the WIFI RSS vector direction between current step and last step, be defined as RSSDirection1;
(3) obtain the WIFI RSS vector direction between current step and front the second step, be defined as RSSDirection2;
(4) calculate the angle changing between RSSDirection1 and two vector direction of RSSDirection2;
(5) whether the angle changing in judgement (3) is less than predefined left-hand bend threshold value or is greater than right-hand bend threshold value; If angle changing is less than left-hand bend threshold value or is greater than right-hand bend threshold value, think that real touch turn does not occur current step, use the direction of front the second step to replace the direction of current step; Otherwise, think that touch turn has occurred current step really, continue to keep the direction of current step;
Above-mentioned WIFI RSS is auxiliary to be proofreaied and correct in location, and described " room identification scene " identification is specific as follows with operation room recognizer:
(1) particle filter is inferred the pedestrian's step number, step-length and the direction of travel that according to PDR (inertial navigation), and cartographic information, judges whether current step passes through certain door; If process, illustrates that pedestrian is just entering room, now trigger room recognizer, within the scope of ensuing 3 steps, (2)~(6) are carried out in circulation, exceed 3 step scopes, carry out (7); Otherwise, illustrate that pedestrian does not enter the action behavior in room, keep current step state, carry out (6) (7);
(2) travel through the WIFI RSS signal strength readings of all AP (router) that current step scans, search the AP of WIFI RSS reading maximum, be defined as AP1, and think that temporarily pedestrian has entered the room Room1 at AP1 place;
(3) travel through the WIFI RSS signal strength readings of all AP that current step scans, search the AP of the WIFI RSS reading increment maximum of more last step, orientate AP2 as, the room that simultaneously defines AP2 place is Room2;
(4) if AP2 is identical with AP1, judge that pedestrian has entered the room at AP1 place, keep the state of current particle, carry out (6); Otherwise the room at pedestrian place is reaffirmed in execution (5);
(5) particle filter combining cartographic information, according to the proportionate relationship of WIFI RSS absolute signal intensity corresponding to the AP1 WIFI RSS absolute signal intensity corresponding with AP2, carries out weights distribution to all particles again:
5.1 information according to the map, find the coincidence body of wall at room Room1 and Room2, with it all particles of particle filter are divided into two S set et1 and Set2, wherein Set1 refers to the particle assembly that is positioned at Room1, Set2 refers to the particle assembly that is positioned at Room2;
When the current step of 5.2 definition, WIFI RSS signal intensity corresponding to AP1 is RSS1; WIFI RSS signal intensity corresponding to definition AP2 is RSS2;
In 5.3 definition set Set1, the weights scale-up factor Ratio1 of particle is: (90+RSS1)/and (180+RSS1+RSS2);
The weights scale-up factor Ratio2 of particle is (90+RSS2)/(180+RSS1+RSS2) in 5.4 definition set Set2;
5.5 traversal particle assembly Set1, reset to the weight w of each particle: w*Ratio1;
5.6 traversal particle assembly Set2, reset to the weight w of each particle: w*Ratio2;
(6) particle filter regenerates new particle;
(7) finish algorithm;
Above-mentioned WIFI RSS is auxiliary to be proofreaied and correct in location, and described " door detection scene " identification is specific as follows with operation door detection algorithm:
(1), if pedestrian's accumulation step number is greater than or equal to 3 steps, carry out (2)~(8); Otherwise, carry out (8);
(2) obtain the particle filter predicted position coordinate points of current step and front 3 steps, be defined as successively respectively estPos0, estPos1, estPos2, estPos3;
(3) judge estPos0 and estPos1, whether the distance between estPos1 and estPos2 and estPos2 and estPos3 position coordinates point is all in predefined threshold range, if above three distance values are all in threshold range, and estPos0~estPos3 position coordinates point is all positioned near the edge line (in 0.5 meter) of room wall, carries out (4)~(8); Otherwise carry out (8);
(4) AP of WIFI RSS signal strength readings increment maximum when traversal is searched current step and nearest front the 3rd step;
(5) particle filter creates a particle that weights are 1 in the entrance center position in the room at AP place, and step-length based on nearest three steps and direction of travel (being obtained by PDR) are extrapolated the action vector (run trace) of nearest three steps;
(6) particle filter regenerates new particle;
(7) particle filter is carried out room recognizer, further confirms the residing room of pedestrian's particle;
(8) finish algorithm.
4. indoor pedestrian location and the tracking based on smart mobile phone as claimed in claim 3, it is characterized in that above turning confirm described in algorithm to obtain WIFI RSS vector direction specific as follows:
(1) the WIFI RSS signal strength readings that smart mobile phone gathers WIFI router-A P is taking timestamp as index stores is in <rss1, rss2, ... rssn, in the data layout of time>, the present invention is called a RSS vector;
(2) travel through the RSS vector in current step moment, search the AP set that in the more last step RSS of RSS reading vector wherein, corresponding RSS reading increases, be defined as Set (increase); Search the AP set that RSS reading corresponding in the more last step RSS of RSS reading vector reduces, be defined as Set (decrease)
(3) positional information based on each room, AP place, calculates respectively the geographical geometric center of Set (increase) and Set (decrease);
(4) calculate the vector direction between the geographical geometric center of Set (increase) and the geographical geometric center of Set (decrease), the RSS vector direction that current step is corresponding.
5. indoor pedestrian location and the tracking based on smart mobile phone as claimed in claim 3, it is characterized in that described predefined left-hand bend threshold value be (0,90] numerical value in degree; Described right-hand bend threshold value is the numerical value in [270,360] degree.
6. indoor pedestrian location and the tracking based on smart mobile phone as claimed in claim 3, the threshold range that it is characterized in that distance between described coordinate points is the arbitrary numerical value in [0,0.5 meter].
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410438351.0A CN104180805B (en) | 2014-08-29 | 2014-08-29 | Smart phone-based indoor pedestrian positioning and tracking method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410438351.0A CN104180805B (en) | 2014-08-29 | 2014-08-29 | Smart phone-based indoor pedestrian positioning and tracking method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104180805A true CN104180805A (en) | 2014-12-03 |
CN104180805B CN104180805B (en) | 2017-02-01 |
Family
ID=51962016
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410438351.0A Active CN104180805B (en) | 2014-08-29 | 2014-08-29 | Smart phone-based indoor pedestrian positioning and tracking method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104180805B (en) |
Cited By (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104540103A (en) * | 2014-12-08 | 2015-04-22 | 康佳集团股份有限公司 | Indoor positioning method and system for small house |
CN104613961A (en) * | 2015-02-12 | 2015-05-13 | 广东欧珀移动通信有限公司 | Shopping mall store navigation method and shopping mall store navigation device |
CN104613960A (en) * | 2015-02-12 | 2015-05-13 | 广东欧珀移动通信有限公司 | Shopping mall toilet navigation method and shopping mall toilet navigation device |
CN104655137A (en) * | 2015-03-05 | 2015-05-27 | 中国人民解放军国防科学技术大学 | Wi-Fi signal fingerprint positioning algorithm for assisting in speculating flight tracks of pedestrians |
WO2016050081A1 (en) * | 2014-09-29 | 2016-04-07 | 苏州四方万象信息科技有限公司 | System for navigating inside of building and application system therefor |
CN105547285A (en) * | 2016-01-30 | 2016-05-04 | 清华大学 | Virtual reality technology-based in-building navigation system |
CN105588566A (en) * | 2016-01-08 | 2016-05-18 | 重庆邮电大学 | Indoor positioning system and method based on Bluetooth and MEMS (Micro-Electro-Mechanical Systems) fusion |
CN105704652A (en) * | 2016-02-16 | 2016-06-22 | 中国科学院光电研究院 | Method for building and optimizing fingerprint database in WLAN/Bluetooth positioning processes |
CN105716608A (en) * | 2015-11-23 | 2016-06-29 | 南京华苏科技股份有限公司 | Positioning and display method of motion trajectories in building |
CN105737826A (en) * | 2016-02-24 | 2016-07-06 | 中国地质大学(武汉) | Indoor positioning method for pedestrian |
CN105910605A (en) * | 2016-05-30 | 2016-08-31 | 中国科学技术大学苏州研究院 | Indoor navigation dynamic route generation method |
CN106123897A (en) * | 2016-06-14 | 2016-11-16 | 中山大学 | Indoor fusion and positioning method based on multiple features |
CN106228127A (en) * | 2016-07-18 | 2016-12-14 | 乐视控股(北京)有限公司 | Indoor orientation method and device |
WO2016206119A1 (en) * | 2015-06-26 | 2016-12-29 | Intel Corporation | Technologies for pedestrian dead reckoning |
CN106289282A (en) * | 2016-07-18 | 2017-01-04 | 北京方位捷讯科技有限公司 | A kind of indoor map pedestrian's track matching method |
CN106412826A (en) * | 2016-09-07 | 2017-02-15 | 清华大学 | Indoor positioning method and positioning device based on multi-source information fusion |
CN106441279A (en) * | 2016-12-08 | 2017-02-22 | 速感科技(北京)有限公司 | Robot positioning method based on self-positioning and edge searching and system |
CN106448431A (en) * | 2016-08-24 | 2017-02-22 | 电子科技大学 | Mobile phone sensor-based indoor planar graph construction method adopting crowdsourcing mode |
CN106485934A (en) * | 2015-08-25 | 2017-03-08 | 库天下(北京)信息技术有限公司 | A kind of reverse navigation looks for the method and device of target vehicle |
CN106525031A (en) * | 2015-09-11 | 2017-03-22 | 王庆文 | Combined indoor positioning method |
CN106899935A (en) * | 2017-01-18 | 2017-06-27 | 深圳大学 | A kind of indoor orientation method and system based on radio receiver and camera |
CN107094319A (en) * | 2016-02-17 | 2017-08-25 | 王庆文 | A kind of high-precision indoor and outdoor fusion alignment system and method |
CN107219500A (en) * | 2017-06-01 | 2017-09-29 | 成都希盟泰克科技发展有限公司 | Indoor rapid integrated localization method based on WIFI location fingerprint data |
CN107580313A (en) * | 2017-10-17 | 2018-01-12 | 燕山大学 | With reference to bluetooth Beacon and the indoor locating system and its localization method of smart mobile phone |
CN107580294A (en) * | 2017-09-07 | 2018-01-12 | 深圳市易景空间智能科技有限公司 | A kind of indoor hybrid locating method |
WO2018072279A1 (en) * | 2016-10-19 | 2018-04-26 | 华为技术有限公司 | Positioning method and mobile device |
CN107968691A (en) * | 2017-10-12 | 2018-04-27 | 商客通尚景科技江苏有限公司 | The display methods of the signal strength of indoor short-distance wireless communication |
CN108375376A (en) * | 2018-03-08 | 2018-08-07 | 浙江师范大学 | Angle detection method and device |
CN108692730A (en) * | 2018-05-21 | 2018-10-23 | 同济大学 | Pedestrian applied to inertial navigation turns to recognizer |
CN109005503A (en) * | 2018-08-13 | 2018-12-14 | 电子科技大学 | A kind of fusion and positioning method based on WiFi and PDR |
CN109115207A (en) * | 2017-06-23 | 2019-01-01 | 北京方位捷讯科技有限公司 | Pedestrian's foot path detection method, apparatus and system |
CN109164411A (en) * | 2018-09-07 | 2019-01-08 | 中国矿业大学 | A kind of personnel positioning method based on multi-data fusion |
CN109631908A (en) * | 2019-01-31 | 2019-04-16 | 北京永安信通科技股份有限公司 | Object positioning method, device and electronic equipment based on fabric structure data |
CN109922447A (en) * | 2019-03-19 | 2019-06-21 | 福州大学 | A kind of indoor occupant cognitive method based on deep learning |
CN111024075A (en) * | 2019-12-26 | 2020-04-17 | 北京航天控制仪器研究所 | Pedestrian navigation error correction filtering method combining Bluetooth beacon and map |
CN111757244A (en) * | 2019-06-14 | 2020-10-09 | 广东小天才科技有限公司 | Building positioning method and electronic equipment |
CN107289941B (en) * | 2017-06-14 | 2021-01-08 | 湖南格纳微信息科技有限公司 | Inertial navigation-based indoor positioning method and device |
CN112887914A (en) * | 2019-11-30 | 2021-06-01 | 深圳市海思半导体有限公司 | Method and device for positioning between terminals |
CN113093100A (en) * | 2021-03-09 | 2021-07-09 | 惠州Tcl移动通信有限公司 | Positioning method, intelligent terminal and computer readable storage medium |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2769788C (en) * | 2011-03-23 | 2019-08-13 | Trusted Positioning Inc. | Methods of attitude and misalignment estimation for constraint free portable navigation |
CN102419180B (en) * | 2011-09-02 | 2014-01-01 | 无锡智感星际科技有限公司 | Indoor positioning method based on inertial navigation system and WIFI (wireless fidelity) |
CN103175529B (en) * | 2013-03-01 | 2016-01-06 | 上海美迪索科电子科技有限公司 | Based on pedestrian's inertial positioning system that indoor magnetic signature is auxiliary |
CN103476115B (en) * | 2013-09-22 | 2016-03-23 | 中国地质大学(武汉) | A kind of Wi-Fi fingerprint positioning method based on AP collection similarity |
CN103841642B (en) * | 2014-03-10 | 2017-04-19 | 北京工业大学 | Three-dimensional positioning method in a room |
-
2014
- 2014-08-29 CN CN201410438351.0A patent/CN104180805B/en active Active
Cited By (62)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016050081A1 (en) * | 2014-09-29 | 2016-04-07 | 苏州四方万象信息科技有限公司 | System for navigating inside of building and application system therefor |
CN104540103B (en) * | 2014-12-08 | 2019-01-29 | 康佳集团股份有限公司 | Small indoor localization method and its system |
CN104540103A (en) * | 2014-12-08 | 2015-04-22 | 康佳集团股份有限公司 | Indoor positioning method and system for small house |
CN104613961A (en) * | 2015-02-12 | 2015-05-13 | 广东欧珀移动通信有限公司 | Shopping mall store navigation method and shopping mall store navigation device |
CN104613960A (en) * | 2015-02-12 | 2015-05-13 | 广东欧珀移动通信有限公司 | Shopping mall toilet navigation method and shopping mall toilet navigation device |
CN104655137A (en) * | 2015-03-05 | 2015-05-27 | 中国人民解放军国防科学技术大学 | Wi-Fi signal fingerprint positioning algorithm for assisting in speculating flight tracks of pedestrians |
CN104655137B (en) * | 2015-03-05 | 2017-07-14 | 中国人民解放军国防科学技术大学 | The Wi Fi received signals fingerprint location algorithms of pedestrian's flying track conjecture auxiliary |
US10393540B2 (en) | 2015-06-26 | 2019-08-27 | Intel Corporation | Technologies for pedestrian dead reckoning |
WO2016206119A1 (en) * | 2015-06-26 | 2016-12-29 | Intel Corporation | Technologies for pedestrian dead reckoning |
US11199421B2 (en) | 2015-06-26 | 2021-12-14 | Intel Corporation | Technologies for pedestrian dead reckoning |
CN106485934A (en) * | 2015-08-25 | 2017-03-08 | 库天下(北京)信息技术有限公司 | A kind of reverse navigation looks for the method and device of target vehicle |
CN106525031B (en) * | 2015-09-11 | 2019-08-06 | 王庆文 | A kind of combined indoor orientation method |
CN106525031A (en) * | 2015-09-11 | 2017-03-22 | 王庆文 | Combined indoor positioning method |
CN105716608A (en) * | 2015-11-23 | 2016-06-29 | 南京华苏科技股份有限公司 | Positioning and display method of motion trajectories in building |
CN105588566A (en) * | 2016-01-08 | 2016-05-18 | 重庆邮电大学 | Indoor positioning system and method based on Bluetooth and MEMS (Micro-Electro-Mechanical Systems) fusion |
CN105547285B (en) * | 2016-01-30 | 2019-01-15 | 清华大学 | Navigation system in building based on virtual reality technology |
CN105547285A (en) * | 2016-01-30 | 2016-05-04 | 清华大学 | Virtual reality technology-based in-building navigation system |
CN105704652A (en) * | 2016-02-16 | 2016-06-22 | 中国科学院光电研究院 | Method for building and optimizing fingerprint database in WLAN/Bluetooth positioning processes |
CN105704652B (en) * | 2016-02-16 | 2019-01-04 | 中国科学院光电研究院 | Fingerprint base acquisition and optimization method in a kind of positioning of WLAN/ bluetooth |
CN107094319B (en) * | 2016-02-17 | 2021-06-04 | 王庆文 | High-precision indoor and outdoor fusion positioning system and method |
CN107094319A (en) * | 2016-02-17 | 2017-08-25 | 王庆文 | A kind of high-precision indoor and outdoor fusion alignment system and method |
CN105737826A (en) * | 2016-02-24 | 2016-07-06 | 中国地质大学(武汉) | Indoor positioning method for pedestrian |
CN105910605A (en) * | 2016-05-30 | 2016-08-31 | 中国科学技术大学苏州研究院 | Indoor navigation dynamic route generation method |
CN106123897B (en) * | 2016-06-14 | 2019-05-03 | 中山大学 | Indoor fusion and positioning method based on multiple features |
CN106123897A (en) * | 2016-06-14 | 2016-11-16 | 中山大学 | Indoor fusion and positioning method based on multiple features |
CN106289282A (en) * | 2016-07-18 | 2017-01-04 | 北京方位捷讯科技有限公司 | A kind of indoor map pedestrian's track matching method |
CN106228127A (en) * | 2016-07-18 | 2016-12-14 | 乐视控股(北京)有限公司 | Indoor orientation method and device |
CN106448431A (en) * | 2016-08-24 | 2017-02-22 | 电子科技大学 | Mobile phone sensor-based indoor planar graph construction method adopting crowdsourcing mode |
CN106412826B (en) * | 2016-09-07 | 2019-09-17 | 清华大学 | Indoor orientation method and positioning device based on Multi-source Information Fusion |
CN106412826A (en) * | 2016-09-07 | 2017-02-15 | 清华大学 | Indoor positioning method and positioning device based on multi-source information fusion |
CN109564726A (en) * | 2016-10-19 | 2019-04-02 | 华为技术有限公司 | A kind of localization method and mobile device |
US11118913B2 (en) | 2016-10-19 | 2021-09-14 | Huawei Technologies Co., Ltd. | Vehicle positioning correction method and mobile device |
WO2018072279A1 (en) * | 2016-10-19 | 2018-04-26 | 华为技术有限公司 | Positioning method and mobile device |
CN106441279A (en) * | 2016-12-08 | 2017-02-22 | 速感科技(北京)有限公司 | Robot positioning method based on self-positioning and edge searching and system |
CN106899935A (en) * | 2017-01-18 | 2017-06-27 | 深圳大学 | A kind of indoor orientation method and system based on radio receiver and camera |
CN107219500A (en) * | 2017-06-01 | 2017-09-29 | 成都希盟泰克科技发展有限公司 | Indoor rapid integrated localization method based on WIFI location fingerprint data |
CN107219500B (en) * | 2017-06-01 | 2019-12-03 | 成都希盟泰克科技发展有限公司 | The rapid integrated localization method in interior based on WIFI location fingerprint data |
CN107289941B (en) * | 2017-06-14 | 2021-01-08 | 湖南格纳微信息科技有限公司 | Inertial navigation-based indoor positioning method and device |
US11162795B2 (en) | 2017-06-23 | 2021-11-02 | Beijing Fine Way Technology Co., Ltd. | Method and device for detecting pedestrian stride length and walking path |
CN109115207A (en) * | 2017-06-23 | 2019-01-01 | 北京方位捷讯科技有限公司 | Pedestrian's foot path detection method, apparatus and system |
CN113218395A (en) * | 2017-06-23 | 2021-08-06 | 北京方位捷讯科技有限公司 | Pedestrian walking track detection method, device and system |
CN113218395B (en) * | 2017-06-23 | 2024-06-11 | 北京方位捷讯科技有限公司 | Pedestrian walking track detection method, device and system |
CN107580294A (en) * | 2017-09-07 | 2018-01-12 | 深圳市易景空间智能科技有限公司 | A kind of indoor hybrid locating method |
CN107580294B (en) * | 2017-09-07 | 2020-03-24 | 深圳市易景空间智能科技有限公司 | Indoor hybrid positioning method |
CN107968691A (en) * | 2017-10-12 | 2018-04-27 | 商客通尚景科技江苏有限公司 | The display methods of the signal strength of indoor short-distance wireless communication |
CN107580313A (en) * | 2017-10-17 | 2018-01-12 | 燕山大学 | With reference to bluetooth Beacon and the indoor locating system and its localization method of smart mobile phone |
CN107580313B (en) * | 2017-10-17 | 2020-12-29 | 燕山大学 | Indoor positioning system combining Bluetooth Beacon and smart phone and positioning method thereof |
CN108375376A (en) * | 2018-03-08 | 2018-08-07 | 浙江师范大学 | Angle detection method and device |
CN108375376B (en) * | 2018-03-08 | 2020-11-24 | 浙江师范大学 | Rotation angle detection method and device |
CN108692730A (en) * | 2018-05-21 | 2018-10-23 | 同济大学 | Pedestrian applied to inertial navigation turns to recognizer |
CN109005503B (en) * | 2018-08-13 | 2020-05-19 | 电子科技大学 | Fusion positioning method based on WiFi and PDR |
CN109005503A (en) * | 2018-08-13 | 2018-12-14 | 电子科技大学 | A kind of fusion and positioning method based on WiFi and PDR |
CN109164411A (en) * | 2018-09-07 | 2019-01-08 | 中国矿业大学 | A kind of personnel positioning method based on multi-data fusion |
CN109164411B (en) * | 2018-09-07 | 2023-07-11 | 中国矿业大学 | Personnel positioning method based on multi-data fusion |
CN109631908A (en) * | 2019-01-31 | 2019-04-16 | 北京永安信通科技股份有限公司 | Object positioning method, device and electronic equipment based on fabric structure data |
CN109922447A (en) * | 2019-03-19 | 2019-06-21 | 福州大学 | A kind of indoor occupant cognitive method based on deep learning |
CN111757244A (en) * | 2019-06-14 | 2020-10-09 | 广东小天才科技有限公司 | Building positioning method and electronic equipment |
CN111757244B (en) * | 2019-06-14 | 2022-03-25 | 广东小天才科技有限公司 | Building positioning method and electronic equipment |
CN112887914A (en) * | 2019-11-30 | 2021-06-01 | 深圳市海思半导体有限公司 | Method and device for positioning between terminals |
CN111024075A (en) * | 2019-12-26 | 2020-04-17 | 北京航天控制仪器研究所 | Pedestrian navigation error correction filtering method combining Bluetooth beacon and map |
CN111024075B (en) * | 2019-12-26 | 2022-04-12 | 北京航天控制仪器研究所 | Pedestrian navigation error correction filtering method combining Bluetooth beacon and map |
CN113093100A (en) * | 2021-03-09 | 2021-07-09 | 惠州Tcl移动通信有限公司 | Positioning method, intelligent terminal and computer readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN104180805B (en) | 2017-02-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104180805A (en) | Smart phone-based indoor pedestrian positioning and tracking method | |
Poulose et al. | An indoor position-estimation algorithm using smartphone IMU sensor data | |
CN109298389B (en) | Indoor pedestrian combination pose estimation method based on multi-particle swarm optimization | |
CN107389063B (en) | High-precision indoor fusion positioning method based on GSM/MEMS fusion | |
CN110455291B (en) | Method and apparatus for indoor location-finding using magnetic field anomalies | |
CN111491367B (en) | Indoor positioning method based on crowd sensing and multi-fusion technology | |
WO2016126786A1 (en) | Last-mile navigation using smartphones | |
EP3680616A1 (en) | Localization method and apparatus, mobile terminal and computer-readable storage medium | |
CN105241445A (en) | Method and system for acquiring indoor navigation data based on intelligent mobile terminal | |
CN107014375B (en) | Indoor positioning system and method with ultra-low deployment | |
Aly et al. | Robust and ubiquitous smartphone-based lane detection | |
CN111595344B (en) | Multi-posture downlink pedestrian dead reckoning method based on map information assistance | |
CN105674984A (en) | Method for acquiring advancing directions of pedestrians by aid of mobile terminals without constraints | |
CN108020813A (en) | Localization method, positioner and electronic equipment | |
Zhao et al. | Vetrack: Real time vehicle tracking in uninstrumented indoor environments | |
Ren et al. | Movement pattern recognition assisted map matching for pedestrian/wheelchair navigation | |
CN103217154A (en) | Method and device for locating underground personnel in coal mine | |
CN104197935A (en) | Indoor localization method based on mobile intelligent terminal | |
Zhou et al. | DeepVIP: Deep learning-based vehicle indoor positioning using smartphones | |
US20220155402A1 (en) | Transition Detection | |
CN112362044A (en) | Indoor positioning method, device, equipment and system | |
CN108254775A (en) | Onboard navigation system and its implementation | |
JP2014013202A (en) | Inertial navigation device and program | |
Galioto et al. | Sensor fusion localization and navigation for visually impaired people | |
Zhou et al. | A fusion method of pedestrian dead reckoning and pseudo indoor plan based on conditional random field |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |