CN105424026A - Indoor navigation and localization method and system based on point cloud tracks - Google Patents
Indoor navigation and localization method and system based on point cloud tracks Download PDFInfo
- Publication number
- CN105424026A CN105424026A CN201510741200.7A CN201510741200A CN105424026A CN 105424026 A CN105424026 A CN 105424026A CN 201510741200 A CN201510741200 A CN 201510741200A CN 105424026 A CN105424026 A CN 105424026A
- Authority
- CN
- China
- Prior art keywords
- cloud
- tracks
- track
- similarity
- indoor navigation
- 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
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)
Abstract
The invention discloses an indoor navigation and localization method and system based on point cloud tracks. The method includes the steps that the point cloud tracks are captured in the moving process, and a point cloud map is constructed according to the multiple point cloud tracks; a destination is acquired, the current position is localized, and a navigation path is planned according to the point cloud map; whether actual motion deviates relative to the navigation path or not is detected, and if yes, the navigation path is planned again. According to the indoor navigation and localization method and system based on the point cloud tracks, as the point cloud tracks are captured in the moving process to construct the map, it is unnecessary to relay on additional arrangement of specific infrastructures or indoor maps for localization, self-deployment can be achieved, the localization and navigation precision is high, and the robustness to the humans and the environment is high.
Description
Technical field
The present invention relates to wireless communication field, especially, relate to a kind of indoor navigation localization method based on a cloud track and system.
Background technology
The run trace that is the shortest, most convenient arriving destination is found to be that indoor navigation serves bright spot of greatest concern.Such as, user may run into following scene: " in meeting building; how I reach 2016 meeting rooms from current location? " or: " in this shopping center; how I arrive the shop that I admires for a long time from my current position? " however strong demand, the design and implimentation of pervasive accurately indoor navigation system is still have challenging technology.
Indoor navigation system of the prior art designs based on indoor locating system, is roughly divided into two classes: a class depends on infrastructure, and such as, based on the method for received signals fingerprint, the method for visible light communication, its application scenarios is restricted; Another kind of based on indoor map, such as inertial navigation method, computer vision methods.But these systems all depend on specific infrastructure and available indoor map.
Depend on the problem of infrastructure and indoor map for indoor navigation system work in prior art, not yet have effective solution at present.
Summary of the invention
The problem of infrastructure and indoor map is depended on for indoor navigation system work in prior art, the object of the invention is to propose a kind of indoor navigation localization method based on a cloud track and system, normal indoor navigation service can be provided under the environment of foundation-free facility and indoor map.
Based on above-mentioned purpose, technical scheme provided by the invention is as follows:
According to an aspect of the present invention, a kind of indoor navigation localization method based on a cloud track is provided.
Comprise according to a kind of indoor navigation localization method based on a cloud track provided by the invention:
Capture point cloud track in motion process, and build some cloud map according to multiple somes cloud tracks;
Obtain destination, location current location, and according to a cloud map planning guidance path;
Whether detect actual motion to offset relative to guidance path, be again plan guidance path.
Wherein, capture point cloud track in motion process, for catching multiple image by assigned frequency in motion process, and extracts some cloud track from multiple image.
Wherein, build some cloud map according to multiple somes cloud tracks to comprise:
Choose two some cloud tracks, measure the similarity between two some cloud tracks;
According to similarity, two some cloud tracks are merged;
Continue to choose other cloud tracks to merge successively, build some cloud map.
Further, the similarity of measuring between two some cloud tracks comprises:
A cloud track locates turning point;
According to turning point, every bar point cloud track is divided into many some cloud track line segments;
Detect in two some cloud tracks and whether comprise common rail trace segments;
The similarity between two some cloud tracks is measured according to common rail trace segments.
Further, according to similarity, two some cloud tracks merging are comprised:
The relatively length of common rail trace segments on the some cloud track line segment of two some cloud tracks;
When the length of common rail trace segments on the some cloud track line segment of two some cloud tracks is equal, the same position of two some cloud track line segments specifies multiple point, the similarity of multiple designated point on the some cloud track line segment contrasting two some cloud tracks, and according to similarity, two some cloud tracks are merged;
When the length of common rail trace segments on the some cloud track line segment of two some cloud tracks does not wait, longer some cloud track line segment intercepts moving window by the length of shorter some cloud track line segment, and in each moving window, contrast the similarity of each point according to previous step, and according to similarity, two some cloud tracks are merged.
Further, according to similarity, two some cloud tracks merging are comprised:
When similarity is higher than upper bound threshold value, judges that two some cloud track line segments are similar, carry out track merging;
When similarity is lower than lower bound threshold value, judges that two some cloud track line segments are dissimilar, do not carry out track merging;
When similarity is between upper bound threshold value and lower bound threshold value, do not judge the similar situation of two some cloud track line segments, increase the quantity that is designated point and the similarity of multiple designated point on the some cloud track line segment again contrasting two some cloud tracks.
Meanwhile, location current location, for using trilateration location current location, comprising:
Choose a some cloud location current location;
Choose another cloud location current location, and use gravity model appoach to upgrade current location to two current locations;
Iteration carries out previous step, until be less than error threshold to the correction of current location.
Further, detect actual motion whether to comprise relative to guidance path generation skew:
By assigned frequency location current location in actual motion;
Judge whether to be positioned on guidance path according to current location, if not then next step;
Judge whether to occur without coupling according to the historical path of actual motion, then judge that actual motion offsets relative to guidance path if not.
In addition, also inform with information while again planning guidance path.
According to another aspect of the present invention, a kind of indoor navigation positioning system based on a cloud track is additionally provided.
Described above according to a kind of indoor navigation positioning system based on a cloud track provided by the invention.
As can be seen from above, technical scheme provided by the invention builds map by using capture point cloud track at the volley, do not need to rely on and extra certain infrastructure is set with indoor map positions, and can high, the strong robustness to human and environment of oneself's deployment, position & navigation precision.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the process flow diagram of a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention;
Fig. 2 is the structural relation figure of a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention;
Fig. 3 is in a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention, the capture point cloud under different attitude and number thereof;
Fig. 4 is in a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention, captures the mass distribution situation histogram of 375 some clouds in office and market;
Fig. 5 is in a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention, equipment attitude and the correlativity broken line graph putting cloud quality;
Fig. 6 is in a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention, public sub-trajectory line segment combination situation schematic diagram;
Fig. 7 is in a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention, the relation histogram between some cloud computing time and accuracy;
Fig. 8 is in a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention, Trilateration methods and centralized positioning schematic diagram;
Fig. 9 is the broken line graph offset without coupling according to the some cloud of a kind of indoor navigation localization method based on a cloud track of the embodiment of the present invention;
Figure 10 is in a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention, at office and the scene map in shopping center and four test trails figure of each scene;
Figure 11 is in a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention, the maximum tracking error in scene map and average tracking error statistical graph;
Figure 12 is in a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention, the correlativity histogram in scene map between move distance and tracking error;
Figure 13 is in a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention, the correlativity histogram between scene map midpoint detection precision and some cloud;
Figure 14 is in a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention, with or without the collection point cloud quantity broken line graph under Attitude estimation in scene map;
Figure 15 is in a kind of indoor navigation localization method based on a cloud track according to the embodiment of the present invention, scene map point cloud quantity and the correlativity histogram putting the cloud accuracy of map.
Embodiment
Clearly understand for making the object, technical solutions and advantages of the present invention, below in conjunction with the accompanying drawing in the embodiment of the present invention, to the technical scheme in the embodiment of the present invention carry out further clear, complete, describe in detail, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain, all belongs to the scope of protection of the invention.
The prosperity and development of mobile computing have promoted indoor navigation service as attracting, a promising application.The indoor navigation system of traditional design or depend on infrastructure, or depend on indoor map.The present invention has promoted indoor navigation system from five aspects and has moved towards pervasive: oneself can dispose, high navigation accuracy, to the robustness of environment dynamic change and personnel, without the need to infrastructure and start online.Based on the some cloud localization method position of consumer positioning on a cloud map accurately of innovation, technical scheme of the present invention navigation user can arrive indoor impact point in the mode started online.Further, run trace can also be extracted from cloud data, run trace and cloud data combined structure point cloud map.In addition, in order to improve the robustness of system to environmental dynamics and personnel, go to catch high-quality some cloud by the attitude of estimating apparatus.Under office and shopping mall scenario, a large amount of experimental verifications outstanding navigation performance.
According to one embodiment of present invention, a kind of indoor navigation localization method based on a cloud track is provided.
As shown in Figure 1, the indoor navigation localization method based on a cloud track provided according to the embodiment of the present invention comprises:
Step S101, capture point cloud track in motion process, and build some cloud map according to multiple somes cloud tracks;
Step S103, obtains destination, location current location, and according to a cloud map planning guidance path;
Whether step S105, detecting actual motion and offset relative to guidance path, is again plan guidance path.
Wherein, capture point cloud track in motion process, for catching multiple image by assigned frequency in motion process, and extracts some cloud track from multiple image.
Wherein, build some cloud map according to multiple somes cloud tracks to comprise:
Choose two some cloud tracks, measure the similarity between two some cloud tracks;
According to similarity, two some cloud tracks are merged;
Continue to choose other cloud tracks to merge successively, build some cloud map.
Further, the similarity of measuring between two some cloud tracks comprises:
A cloud track locates turning point;
According to turning point, every bar point cloud track is divided into many some cloud track line segments;
Detect in two some cloud tracks and whether comprise common rail trace segments;
The similarity between two some cloud tracks is measured according to common rail trace segments.
Further, according to similarity, two some cloud tracks merging are comprised:
The relatively length of common rail trace segments on the some cloud track line segment of two some cloud tracks;
When the length of common rail trace segments on the some cloud track line segment of two some cloud tracks is equal, the same position of two some cloud track line segments specifies multiple point, the similarity of multiple designated point on the some cloud track line segment contrasting two some cloud tracks, and according to similarity, two some cloud tracks are merged;
When the length of common rail trace segments on the some cloud track line segment of two some cloud tracks does not wait, longer some cloud track line segment intercepts moving window by the length of shorter some cloud track line segment, and in each moving window, contrast the similarity of each point according to previous step, and according to similarity, two some cloud tracks are merged.
Further, according to similarity, two some cloud tracks merging are comprised:
When similarity is higher than upper bound threshold value, judges that two some cloud track line segments are similar, carry out track merging;
When similarity is lower than lower bound threshold value, judges that two some cloud track line segments are dissimilar, do not carry out track merging;
When similarity is between upper bound threshold value and lower bound threshold value, do not judge the similar situation of two some cloud track line segments, increase the quantity that is designated point and the similarity of multiple designated point on the some cloud track line segment again contrasting two some cloud tracks.
Meanwhile, location current location, for using trilateration location current location, comprising:
Choose a some cloud location current location;
Choose another cloud location current location, and use gravity model appoach to upgrade current location to two current locations;
Iteration carries out previous step, until be less than error threshold to the correction of current location.
Further, detect actual motion whether to comprise relative to guidance path generation skew:
By assigned frequency location current location in actual motion;
Judge whether to be positioned on guidance path according to current location, if not then next step;
Judge whether to occur without coupling according to the historical path of actual motion, then judge that actual motion offsets relative to guidance path if not.
In addition, also inform with information while again planning guidance path.
Technical scheme of the present invention is set forth further below according to specific embodiment.
Shown in Fig. 2 is the structural relation of indoor navigation of the present invention (being named as pcNavi system).As shown in Figure 2, indoor navigation system forms primarily of 3 parts: mobile client, Cloud Server and navigation user.
The sensor record of mobile client they at the track data of the daily life of the interior space.Specifically, pcNavi system uses relevant some cloud sequence to calculate the run trace of user.Meanwhile, the run trace that a cloud computing goes out by this system is associated with some cloud.The more important thing is, mobile client catches high-quality some cloud by the attitude detecting mobile device, and reduction assesses the cost.The track of the some cloud produced, uploads to Cloud Server and does further process.
Cloud Server comprises some cloud map structuring module and a navigation module.We measure the similarity between track by the similarity between calculation level cloud, build some cloud map by merging many tracks.Once receive the navigation requests from user, first Cloud Server calculates the position of user on a cloud map, and uses this position as the starting point of navigation path.By predefined destination, high in the clouds planning guidance path.When user walks to destination, the real-time acceptance in high in the clouds, from the cloud data of mobile client, carries out the tracking of navigation process, offset detection.When user departs from navigation path, system provides warning, new planning walking path of laying equal stress on.
Unique task of navigation user inputs destination exactly to system, then under the guide of system, navigates to destination.
Mobile client catches multiple image by assigned frequency in motion process, and from multiple image, extract some cloud track.Because some cloud is captured in the process of walking, the quality of the some cloud obtained is different.Such as, when equipment is second-rate facing to the some cloud of catching when floor or ceiling, and the quality facing toward the some cloud that entity is caught is higher.The unique point number of the capture point cloud under different attitude as shown in Figure 3.General, we utilize the unique point of extraction to carry out the quality of metric point cloud.Shown in Fig. 4 is the mass distribution situation capturing 375 some clouds in office and market, and market is caught invocation point cloud quality more than office and wanted high, unique point redundant character unconspicuous some cloud that abundant some cloud has.In addition, when equipment picture head upwards downwards time, what catch is the some cloud on ceiling and floor, and feature is not obvious comparatively speaking.What other angle was mostly caught is that feature significantly puts cloud (except pure facing to except wall).Equipment attitude shown in Fig. 5 demonstrates this point with the correlativity putting cloud quality.
Significantly put cloud to catch feature, we can carry out a cloud with high frame per second and catch, and are filtering feature unconspicuous some cloud.But so, just make energy consumption increase.We pass through the relation between the attitude of facilities for observation capture point cloud and some cloud quality, devise simple and effective high-quality point cloud catching method, do not increase energy consumption simultaneously.
Our defining point cloud capturing events is f, is a binary class problem, namely catches or not capture point cloud.We adopt logistic to return and predict equipment attitude.Here, have six independents variable, i.e. travel distance (γ d), three attitude angle, Fibre Optical Sensor, proximity transducer, i.e. X={a, p, r, sl, sp, Δ (d) }, parameter sets is defined as θ.Logistic regression equation as shown in the formula:
f＝θ
TX
Further, equation adopts Sigmoid function to be rewritten as:
Its cost function is:
Our target minimizes cost function.We adopt gradient descent method to solve, and obtain:
Wherein,
In addition, if in the process of walking, within a step, system is not caught and is obtained a cloud, will continue the request sending capture point cloud.
For the some cloud obtained, we utilize existing algorithm to calculate run trace from a cloud sequence, are defined as r, r={x, y, pc}.We use a some cloud to measure similarity between track, are that to utilize turning point to divide track be track line segment, and the similarity between track is measured on the basis of trace segments in-orbit.Key issue is a tolerance of cloud similarity.We conducted a large amount of experiments, if find that the similitude between two some clouds is greater than at least 80, can think that two some clouds are similar.
Point cloud map is the set of the position relationship between the some cloud of indoor location entity.We utilize many some cloud tracks to merge a cloud map, and the principle of merging minimizes the diversity between a cloud track.In order to merge two tracks, first we calculate public sub-trajectory line segment.Fig. 6 is by public sub-trajectory line segment
with
be relatively divided into two kinds of situations, other situations can reduction be both of these case.
Situation 1:
namely the CaseA in Fig. 6.The simplest method is that the some cloud on two orbit segments calculates similarity one by one, but so process is consuming time.We devise random point cloud number selection algorithm (RPM) and reduce computational complexity.Concretism is Stochastic choice a certain proportion of some cloud, carries out comparison between two.If the number of similar some cloud is greater than previous, think that two strip track line segments are similar.How similar the number of some cloud, lower than lower bound, think that two track line segments are dissimilar.If the number of similar some cloud is between bound, think that two track line segments are uncertain dissimilar mutually, also need to increase some cloud ratio and carry out extra calculating.In a worst case scenario, be that all some clouds are all calculated similarity.
Situation 2:
namely the CaseB in Fig. 6.The sub-line segment course length that two users walk is unequal, and we choose short sub-line segment track is benchmark, adopts the mode of moving window to calculate similarity, until find similar track line segment.
In order to determine the ratio value of selected point cloud number, We conducted a large amount of experiments.We define two measurement indexs: one is accuracy, and another is time ratio.Shown in Fig. 7 is a relation between cloud computing time and accuracy, as shown in Figure 7, with accuracy and time than time ratio value for benchmark, be chosen between [0.6,0.8] optimum.
Once the public sub-trajectory Line segment detection of sufficient amount out, we apply RPM algorithm and build some cloud map.In the process, in order to speed-up computation speed, we adopt VF2 algorithm.Under the coordinate changing different tracks is tied to unified coordinate system, we adopt BursaWolf model.Meanwhile, in order to improve the performance of RPM algorithm, we adopt ICP algorithm to accelerate.
After completing a cloud map, we the position of consumer positioning can calculate navigation path as starting point and according to the indoor destination of navigation user.If navigation path is not unique, pcNavi calculates an optimal trajectory.PcNavi also has offset detection function, and when user offsets correct navigation path, system can provide prompting, simultaneously plans a new guidance path based on the current location of user.
Embodiments of the invention adopt the method based on trilateration to carry out the location of user.Due to the complicacy of indoor environment, there will be that multiple position to put cloud very similar, we are called pinpoint problem.In order to solve this problem, solution increases an acquisition for cloud quantity the most intuitively.Therefore we devise PCLA location algorithm.For given cloud data, adopt following Trilateration methods to get final product the position of consumer positioning, as shown in Figure 8, its customer location O is:
O＝T
-1B
Wherein,
Because the some cloud of catching is in camera coordinates system, we can utilize the coordinate of a cloud directly to carry out the location of user.Computing formula is:
A given n cloud data, our optimization aim is that the position that calculated by PCLA algorithm and physical location offset error are minimized.We define optimization aim:
s.t.ni＝rij×nj，rij∈R，i≠j，
Optimization Steps is as shown in Figure 8:
Initial, choose the position of a some cloud consumer positioning.
In the position of the some cloud consumer positioning do not chosen, choose the position of gravity model appoach as final user.
Iteration previous step, until the position determined of current gravity model appoach with the position determined of a step gravity model appoach be less than threshold value, stop.
Wherein, threshold value we be set as 0.1 meter by experiment.Optimization Steps like this, the position on the some cloud map at the current place of determination user that we can be unique fast.
We utilize the determination of the existing real time position of a mysorethorn to carry out the process of track user navigation.For offset detection, we are divided into two kinds of situations and process: first point cloud is without mating the skew that causes, and it two is user's actual shifts.
Shown in Fig. 9 is the broken line graph of a cloud without coupling skew.The historical track that we utilize user to walk, setting threshold test point cloud whether error hiding.
The position of locating out as fruit dot cloud exceedes certain threshold value (such as 3 steps are far away) and then thinks a skew that cloud error hiding causes.So, system will ask cloud data again, carry out the secondary location of user.
Offset if user is actual, pcNavi can reminding user, and plans a new path.
Meanwhile, we adopt Dijstra ' s algorithm to calculate optimal path.
Below the effect of sort method of the present invention is evaluated.
Shown in Figure 10 is four test trails that we choose respectively under office and two, shopping center scene.
In office block, four volunteers are required to walk along A, B, C, D tetra-lines, and each track is recorded at least 20 takes turns.The length of these tracks is 30 meters, 40 meters, 65 meters, 90 meters.In our experiment, all volunteers can arrive destination by the track along the best under pcNavi instructs smoothly.As shown in Figure 11 (a), the maximum tracking error of pcNavi is 1.41 meters, and average tracking error is 1.35 meters.This pcNavi system deviation is less than the tracking error (being generally 0.75m mono-step) that 2 steps reach less, this is because compared to two dimensional image, change and the crowd of pcNavi point cloud environment are more responsive.
At the mall, the track of four walkings is respectively M1, M2, M3, M4, and length is respectively 30 meters, 60 meters, 90 meters, 120 meters, and per pass track at least records 20 and takes turns.In our experiment, all volunteers successfully can arrive destination.As shown in Figure 11 (b), the maximum tracking error of pcNavi experience is at 1.20 meters, and average tracking error is 1.04 meters.Tracking error at the mall than less at office building be because the some cloud in shopping center enriches, and the some cloud of office building is less.
In addition, we can see, tracking error slightly increases with the increase of walking distance, the relation therefore further between experiment test tracking error and walking distance.Every volunteer be required office building and shopping center walking, and the tracking error recorded under different travel distance, walking distance becomes 360 meters from 0 and often takes turns test, experiment repetition 10 times, its result is as shown in Figure 12 (a) Yu 12 (b).Experimental result shows, and the navigation skew that pcNavi can detect is 2.85 meters, and actual deviation is 2.80 meters simultaneously.We find, the increase of the walking distance that tracking error does not increase.This is because the tracking drift caused often can be positioned in a location position of cloud graphical user and eliminate.
Therefore, tracking error detect accuracy and deviation can meet indoor navigation system.In practice, high precision navigation also and inessential because user with the naked eye can find destination easily.In addition, we analyse in depth influence factor and separate-blas estimation tracking error.
The positioning precision of some cloud map to tracking and separate-blas estimation most important.We assess in the critical point detection precision in office and building, market, and from 1 to 6 not etc., from 80 to 100 not etc., Figure 13 (a) and Figure 13 (b) are experimental result for the number of respective point for the number of the some cloud on a position.We find, some accuracy of detection increases with the quantity of a cloud.When the number of a cloud is increased to 5, critical point detection precision almost reaches 100%.In addition, when positioning precision layer point cloud number is 5, reduce as the positioning error increased for a cloud quantity.Obviously, a small amount of some cloud is that enough pcNavi are promptly and accurately positioned at a position for cloud graphical user.This result also shows, the optimum configurations of deduction is PCLA is quite accurately.
The impact of the feature point pairs point cloud matching precision of capture point cloud is the factor of a restriction pcNavi navigation accuracy.Volunteer have collected 200 groups of cloud datas, and respectively according to having Attitude estimation and processing without Attitude estimation two kinds of modes, its result as shown in figure 14.Can find out, put cloud unique point quantity under having Attitude estimation all the time higher than without Attitude estimation.Therefore, attitude estimates that the function really contributing to enriching catches some cloud.
The impact of the navigation accuracy of the some cloud map of the accuracy that we assess further.Four volunteers are required to consume over three days at office building and shopping center to build a some cloud map, have collected nearly 3000 groups of cloud datas.We weigh the impact of a some cloud accuracy of map, adopt root-mean-square error (RMSE).The two-dimensional position coordinate SPC of given n some cloud, computing formula is
Its result as shown in figure 15, the very little office of (such as ,≤0.56m) of RMSEs point cloud map and the situation in market.Clearly, along with the increase of number of users, the precision of some cloud map also increases thereupon.
According to another embodiment of the invention, a kind of indoor navigation positioning system based on a cloud track is provided.
Described above according to the indoor navigation positioning system based on a cloud track that the embodiment of the present invention provides.
In sum, by means of technique scheme of the present invention, map is built by using capture point cloud track at the volley, do not need to rely on and extra certain infrastructure be set and indoor map positions, promoted indoor navigation system from five aspects and moved towards pervasive: oneself can dispose, high navigation accuracy, to the robustness of environment dynamic change and personnel, without the need to infrastructure and start online.Based on the some cloud localization method position of consumer positioning on a cloud map accurately of innovation, system navigation user can arrive indoor impact point in the mode started online; In addition, also can extract run trace from cloud data, run trace and cloud data combined structure point cloud map; In order to improve the robustness of system to environmental dynamics and personnel, he goes to catch high-quality some cloud by the attitude of estimating apparatus; Under office and shopping mall scenario, our system of a large amount of experimental verifications outstanding navigation performance.
Those of ordinary skill in the field are to be understood that: the foregoing is only specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any amendment made, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1., based on an indoor navigation localization method for a cloud track, it is characterized in that, comprising:
Capture point cloud track in motion process, and build some cloud map according to multiple somes cloud tracks;
Obtain destination, location current location, and according to described some cloud map planning guidance path;
Whether detect actual motion to offset relative to guidance path, be again plan guidance path.
2. a kind of indoor navigation localization method based on a cloud track according to claim 1, it is characterized in that, described in motion process capture point cloud track, for catching multiple image by assigned frequency in motion process, and from described multiple image, extract a some cloud track.
3. a kind of indoor navigation localization method based on a cloud track according to claim 1, is characterized in that, describedly builds some cloud maps according to multiple somes cloud tracks and comprises:
Choose two some cloud tracks, measure the similarity between two some cloud tracks;
According to described similarity, two some cloud tracks are merged;
Continue to choose other cloud tracks to merge successively, build some cloud map.
4. a kind of indoor navigation localization method based on a cloud track according to claim 3, is characterized in that, the similarity between described tolerance two some cloud tracks comprises:
Described some cloud track locates turning point;
Many some cloud track line segments are divided into by putting cloud track described in every bar according to described turning point;
Detect in described two some cloud tracks and whether comprise common rail trace segments;
The similarity between two some cloud tracks is measured according to described common rail trace segments.
5. a kind of indoor navigation localization method based on a cloud track according to claim 4, is characterized in that, two some cloud tracks merging is comprised according to described similarity:
The length of more described common rail trace segments on the some cloud track line segment of described two some cloud tracks;
When the length of described common rail trace segments on the some cloud track line segment of described two some cloud tracks is equal, the same position of described two some cloud track line segments specifies multiple point, the similarity of multiple designated point on the some cloud track line segment contrasting described two some cloud tracks, and according to described similarity, two some cloud tracks are merged;
When the length of described common rail trace segments on the some cloud track line segment of described two some cloud tracks does not wait, longer some cloud track line segment intercepts moving window by the length of shorter some cloud track line segment, and in each moving window, contrast the similarity of each point according to previous step, and according to described similarity, two some cloud tracks are merged.
6. a kind of indoor navigation localization method based on a cloud track according to claim 5, is characterized in that, two some cloud tracks merging is comprised according to described similarity:
When similarity is higher than upper bound threshold value, judges that two some cloud track line segments are similar, carry out track merging;
When similarity is lower than lower bound threshold value, judges that two some cloud track line segments are dissimilar, do not carry out track merging;
When similarity is between upper bound threshold value and lower bound threshold value, do not judge the similar situation of two some cloud track line segments, increase the quantity that is designated point and the similarity of multiple designated point on the some cloud track line segment again contrasting described two some cloud tracks.
7. a kind of indoor navigation localization method based on a cloud track according to claim 1, is characterized in that, described location current location, for using trilateration location current location, comprising:
Choose a some cloud location current location;
Choose another cloud location current location, and use gravity model appoach to upgrade current location to described two current locations;
Iteration carries out previous step, until be less than error threshold to the correction of current location.
8. a kind of indoor navigation localization method based on a cloud track according to claim 7, is characterized in that, whether described detection actual motion comprises relative to guidance path generation skew:
By assigned frequency location current location in actual motion;
Judge whether to be positioned on guidance path according to described current location, if not then next step;
Judge whether to occur without coupling according to the historical path of actual motion, then judge that actual motion offsets relative to guidance path if not.
9. a kind of indoor navigation localization method based on a cloud track according to claim 1, is characterized in that, also inform with information while again planning guidance path.
10. based on an indoor navigation positioning system for a cloud track, it is characterized in that, employ as the indoor navigation localization method based on a cloud track in claim 1-9 as described in any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510741200.7A CN105424026B (en) | 2015-11-04 | 2015-11-04 | A kind of indoor navigation localization method and system based on a cloud track |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510741200.7A CN105424026B (en) | 2015-11-04 | 2015-11-04 | A kind of indoor navigation localization method and system based on a cloud track |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105424026A true CN105424026A (en) | 2016-03-23 |
| CN105424026B CN105424026B (en) | 2017-07-07 |
Family
ID=55502400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510741200.7A Active CN105424026B (en) | 2015-11-04 | 2015-11-04 | A kind of indoor navigation localization method and system based on a cloud track |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105424026B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105955267A (en) * | 2016-05-11 | 2016-09-21 | 上海慧流云计算科技有限公司 | Motion control method and motion control system |
| CN106338292A (en) * | 2016-09-30 | 2017-01-18 | 百度在线网络技术（北京）有限公司 | Walking path processing method and device |
| CN107091639A (en) * | 2017-05-12 | 2017-08-25 | 北京航空航天大学 | A kind of total trajectory length based on adaptive average window length determines method |
| CN107204014A (en) * | 2017-05-24 | 2017-09-26 | 京东方科技集团股份有限公司 | Localization method, device and the intelligent terminal of intelligent terminal |
| CN108700947A (en) * | 2016-05-18 | 2018-10-23 | 谷歌有限责任公司 | For concurrent ranging and the system and method for building figure |
| CN109066857A (en) * | 2018-08-15 | 2018-12-21 | 深圳市烽焌信息科技有限公司 | The method and charging robot charge to patrol robot |
| CN109147044A (en) * | 2017-09-19 | 2019-01-04 | 上海华测导航技术股份有限公司 | A kind of system that power transmission tower and wireline inspection are carried out based on point cloud data |
| CN109143256A (en) * | 2017-09-19 | 2019-01-04 | 上海华测导航技术股份有限公司 | A method of power transmission tower and wireline inspection are carried out based on point cloud data |
| CN109146836A (en) * | 2017-09-19 | 2019-01-04 | 上海华测导航技术股份有限公司 | A kind of system and method carrying out power transmission tower and wireline inspection based on point cloud data |
| CN110515089A (en) * | 2018-05-21 | 2019-11-29 | 华创车电技术中心股份有限公司 | Driving householder method based on optical radar |
| CN110780678A (en) * | 2019-10-29 | 2020-02-11 | 无锡汉咏科技股份有限公司 | Unmanned aerial vehicle visual navigation control method based on point cloud data |
| CN110857861A (en) * | 2018-08-22 | 2020-03-03 | 和硕联合科技股份有限公司 | Trajectory planning method and system |
| CN111721283A (en) * | 2019-03-18 | 2020-09-29 | 深圳市速腾聚创科技有限公司 | Precision detection method and device of positioning algorithm, computer equipment and storage medium |
| CN111798517A (en) * | 2020-07-01 | 2020-10-20 | 小狗电器互联网科技（北京）股份有限公司 | Method and device for determining travel track, readable medium and electronic equipment |
| US10890600B2 (en) | 2016-05-18 | 2021-01-12 | Google Llc | Real-time visual-inertial motion tracking fault detection |
| CN112399165A (en) * | 2019-08-14 | 2021-02-23 | 腾讯美国有限责任公司 | Decoding method and device, computer equipment and storage medium |
| CN112764074A (en) * | 2020-12-30 | 2021-05-07 | 深圳中科讯联科技股份有限公司 | Method and device for positioning navigation track and electronic equipment |
| US11017610B2 (en) | 2016-05-18 | 2021-05-25 | Google Llc | System and method for fault detection and recovery for concurrent odometry and mapping |
| CN116534059A (en) * | 2023-07-04 | 2023-08-04 | 深圳海星智驾科技有限公司 | Adaptive perception path decision method, device, computer equipment and storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111323035A (en) * | 2019-12-18 | 2020-06-23 | 北京嘀嘀无限科技发展有限公司 | Detection method and detection device for driving yaw and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101526356A (en) * | 2008-03-07 | 2009-09-09 | 佛山市顺德区顺达电脑厂有限公司 | Method for programming pedestrian navigation path |
| CN102306300A (en) * | 2011-08-25 | 2012-01-04 | 光庭导航数据（武汉）有限公司 | Curve model-based method for identifying road with lossy shape |
| US20140088855A1 (en) * | 2012-09-27 | 2014-03-27 | Google Inc. | Determining changes in a driving environment based on vehicle behavior |
| CN103884330A (en) * | 2012-12-21 | 2014-06-25 | 联想(北京)有限公司 | Information processing method, mobile electronic device, guidance device, and server |
| CN104536445A (en) * | 2014-12-19 | 2015-04-22 | 深圳先进技术研究院 | Mobile navigation method and system |
-
2015
- 2015-11-04 CN CN201510741200.7A patent/CN105424026B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101526356A (en) * | 2008-03-07 | 2009-09-09 | 佛山市顺德区顺达电脑厂有限公司 | Method for programming pedestrian navigation path |
| CN102306300A (en) * | 2011-08-25 | 2012-01-04 | 光庭导航数据（武汉）有限公司 | Curve model-based method for identifying road with lossy shape |
| US20140088855A1 (en) * | 2012-09-27 | 2014-03-27 | Google Inc. | Determining changes in a driving environment based on vehicle behavior |
| CN103884330A (en) * | 2012-12-21 | 2014-06-25 | 联想(北京)有限公司 | Information processing method, mobile electronic device, guidance device, and server |
| CN104536445A (en) * | 2014-12-19 | 2015-04-22 | 深圳先进技术研究院 | Mobile navigation method and system |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105955267A (en) * | 2016-05-11 | 2016-09-21 | 上海慧流云计算科技有限公司 | Motion control method and motion control system |
| US11017610B2 (en) | 2016-05-18 | 2021-05-25 | Google Llc | System and method for fault detection and recovery for concurrent odometry and mapping |
| CN108700947A (en) * | 2016-05-18 | 2018-10-23 | 谷歌有限责任公司 | For concurrent ranging and the system and method for building figure |
| CN108700947B (en) * | 2016-05-18 | 2021-11-16 | 谷歌有限责任公司 | System and method for concurrent ranging and mapping |
| US11734846B2 (en) | 2016-05-18 | 2023-08-22 | Google Llc | System and method for concurrent odometry and mapping |
| US10890600B2 (en) | 2016-05-18 | 2021-01-12 | Google Llc | Real-time visual-inertial motion tracking fault detection |
| CN106338292A (en) * | 2016-09-30 | 2017-01-18 | 百度在线网络技术（北京）有限公司 | Walking path processing method and device |
| CN107091639B (en) * | 2017-05-12 | 2019-11-12 | 北京航空航天大学 | A kind of total trajectory length long based on adaptive average window determines method |
| CN107091639A (en) * | 2017-05-12 | 2017-08-25 | 北京航空航天大学 | A kind of total trajectory length based on adaptive average window length determines method |
| US11257244B2 (en) | 2017-05-24 | 2022-02-22 | Boe Technology Group Co., Ltd. | Method and device for positioning intelligent terminal apparatus, as well as intelligent terminal apparatus associated therewith |
| WO2018214605A1 (en) * | 2017-05-24 | 2018-11-29 | 京东方科技集团股份有限公司 | Positioning method and apparatus for intelligent terminal device, and associated intelligent terminal device |
| CN107204014A (en) * | 2017-05-24 | 2017-09-26 | 京东方科技集团股份有限公司 | Localization method, device and the intelligent terminal of intelligent terminal |
| CN109146836A (en) * | 2017-09-19 | 2019-01-04 | 上海华测导航技术股份有限公司 | A kind of system and method carrying out power transmission tower and wireline inspection based on point cloud data |
| CN109143256A (en) * | 2017-09-19 | 2019-01-04 | 上海华测导航技术股份有限公司 | A method of power transmission tower and wireline inspection are carried out based on point cloud data |
| CN109147044A (en) * | 2017-09-19 | 2019-01-04 | 上海华测导航技术股份有限公司 | A kind of system that power transmission tower and wireline inspection are carried out based on point cloud data |
| CN110515089A (en) * | 2018-05-21 | 2019-11-29 | 华创车电技术中心股份有限公司 | Driving householder method based on optical radar |
| CN109066857B (en) * | 2018-08-15 | 2021-12-24 | 重庆七腾科技有限公司 | Method for charging patrol robot and charger robot |
| CN109066857A (en) * | 2018-08-15 | 2018-12-21 | 深圳市烽焌信息科技有限公司 | The method and charging robot charge to patrol robot |
| CN110857861A (en) * | 2018-08-22 | 2020-03-03 | 和硕联合科技股份有限公司 | Trajectory planning method and system |
| CN110857861B (en) * | 2018-08-22 | 2023-06-13 | 和硕联合科技股份有限公司 | Track planning method and system |
| CN111721283B (en) * | 2019-03-18 | 2023-08-15 | 深圳市速腾聚创科技有限公司 | Precision detection method and device for positioning algorithm, computer equipment and storage medium |
| CN111721283A (en) * | 2019-03-18 | 2020-09-29 | 深圳市速腾聚创科技有限公司 | Precision detection method and device of positioning algorithm, computer equipment and storage medium |
| CN112399165B (en) * | 2019-08-14 | 2022-03-25 | 腾讯美国有限责任公司 | Decoding method and device, computer equipment and storage medium |
| CN112399165A (en) * | 2019-08-14 | 2021-02-23 | 腾讯美国有限责任公司 | Decoding method and device, computer equipment and storage medium |
| CN110780678A (en) * | 2019-10-29 | 2020-02-11 | 无锡汉咏科技股份有限公司 | Unmanned aerial vehicle visual navigation control method based on point cloud data |
| CN111798517A (en) * | 2020-07-01 | 2020-10-20 | 小狗电器互联网科技（北京）股份有限公司 | Method and device for determining travel track, readable medium and electronic equipment |
| CN112764074A (en) * | 2020-12-30 | 2021-05-07 | 深圳中科讯联科技股份有限公司 | Method and device for positioning navigation track and electronic equipment |
| CN112764074B (en) * | 2020-12-30 | 2024-01-12 | 深圳中科讯联科技股份有限公司 | Method and device for positioning navigation track and electronic equipment |
| CN116534059A (en) * | 2023-07-04 | 2023-08-04 | 深圳海星智驾科技有限公司 | Adaptive perception path decision method, device, computer equipment and storage medium |
| CN116534059B (en) * | 2023-07-04 | 2023-09-08 | 深圳海星智驾科技有限公司 | Adaptive perception path decision method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105424026B (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105424026A (en) | Indoor navigation and localization method and system based on point cloud tracks | |
| Renaudin et al. | Evaluating indoor positioning systems in a shopping mall: The lessons learned from the IPIN 2018 competition | |
| Wang et al. | Vision-based framework for automatic progress monitoring of precast walls by using surveillance videos during the construction phase | |
| Hilsenbeck et al. | Graph-based data fusion of pedometer and WiFi measurements for mobile indoor positioning | |
| Park et al. | Self-corrective knowledge-based hybrid tracking system using BIM and multimodal sensors | |
| CN102576064B (en) | Method and apparatus for identification of points of interest within a predefined area | |
| Shu et al. | Magicol: Indoor localization using pervasive magnetic field and opportunistic WiFi sensing | |
| EP2885609B1 (en) | Crowd-sourcing indoor locations | |
| Potortì et al. | Off-line evaluation of indoor positioning systems in different scenarios: The experiences from IPIN 2020 competition | |
| US20160371394A1 (en) | Indoor localization using crowdsourced data | |
| Taneja et al. | Analysis of three indoor localization technologies for supporting operations and maintenance field tasks | |
| US20120044355A1 (en) | Calibration of Wi-Fi Localization from Video Localization | |
| JP2016180980A (en) | Information processing device, program, and map data updating system | |
| CN106574975A (en) | Trajectory matching using peripheral signal | |
| JP2015531053A (en) | System, method, and computer program for dynamically creating a radio map | |
| JP6820967B2 (en) | Indoor positioning systems and methods based on geomagnetic signals combined with computer vision | |
| EP2965041A1 (en) | Crowd sourced pathway maps | |
| TW201425971A (en) | Map matching device, system and method | |
| Papaioannou et al. | Tracking people in highly dynamic industrial environments | |
| Radaelli et al. | Using cameras to improve wi-fi based indoor positioning | |
| US10104494B2 (en) | Marker based activity transition models | |
| Elhamshary et al. | JustWalk: A crowdsourcing approach for the automatic construction of indoor floorplans | |
| CN110909873B (en) | Method and device for denoising passive RFID (radio frequency identification) mobile ranging data and computer equipment | |
| Takafuji et al. | Indoor localization utilizing tracking scanners and motion sensors | |
| CA2894863A1 (en) | Indoor localization using crowdsourced data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |