CN110146083A - A kind of crowded off-the-air picture identification cloud navigation system - Google Patents
A kind of crowded off-the-air picture identification cloud navigation system Download PDFInfo
- Publication number
- CN110146083A CN110146083A CN201910396992.7A CN201910396992A CN110146083A CN 110146083 A CN110146083 A CN 110146083A CN 201910396992 A CN201910396992 A CN 201910396992A CN 110146083 A CN110146083 A CN 110146083A
- Authority
- CN
- China
- Prior art keywords
- map
- shop
- mobile terminal
- crowded
- navigation system
- 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.)
- Pending
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
- G01C21/20—Instruments for performing navigational calculations
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
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 belongs to cloud field of navigation technology and disclose a kind of crowded off-the-air picture identification cloud navigation system, it can be realized the map structuring of maintenance-free self duplication, after constructing map, entire map system is collected into visual signature point 8971, with the progress of navigation, system can automatically record emerging visual signature according to threshold value, after carrying out navigation in one week clockwise, the characteristic point quantity of system record has reached 12482, therefore system being capable of map automatic updating relevant knowledge, navigation discrimination reaches 87.6% at this time, accuracy of identification 96.1%.
Description
Technical field
The present invention relates to cloud field of navigation technology more particularly to a kind of crowded off-the-air picture to identify cloud navigation system.
Background technique
Compared to highly developed outdoor positioning technology (GPS, dipper system, A-GPS etc.), indoor positioning is still at present
Budding period, there are no be used widely.But as the important supplement of outdoor airmanship, indoor navigation technology carries navigation
Position the vital task of " last rice ".The mainstream technology of indoor navigation has at present:
1, based on the indoor positioning of special equipment: by indoors specify a large amount of specialized hardware facility of regional deployment (ultrasonic wave,
Infrared sensing), while making user's wearable device, realize positioning.
2, be based on Wi-Fi signal ranging: the signal strength of Wi-Fi decays as distance becomes larger.By attenuation model and
The positioning of three sides can determine user location.
3, the positioning based on Wi-Fi fingerprint: this method is the current most common solution.In position, A measures routing
The signal strength of device 1,2,3,4,5 is a, b, c, d, e, you are usually different in the intensity that another location B is measured.Often
The signal strength that primary each router is surveyed every several meters, is stored to a data as a data (we term it Wi-Fi fingerprints)
In library, for the input value on certain position next time, it is highest cosine similarity need to be found.Indoor generally too busy to get away Wi- after all
Fi。
4, the positioning of view-based access control model information: the positioning of view-based access control model information is a kind of new method of indoor positioning, this kind of side
Method carries out closed loop detection (loop-closure detecting) based on the matching of characteristics of image, and feature is that cost is relatively low.
Summary of the invention
The technical problem to be solved by the present invention is to overcome the existing defects, provides a kind of crowded off-the-air picture identification cloud navigation
System can be realized the map structuring of maintenance-free self duplication, and after constructing map, entire map system is collected into vision
Characteristic point 8971, with the progress of navigation, system can automatically record emerging visual signature according to threshold value, carry out up time
After needle navigation in one week, the characteristic point quantity of system record has reached 12482, therefore system being capable of map automatic updating correlation
Knowledge, the discrimination that navigates at this time reach 87.6%, and accuracy of identification 96.1% can effectively solve the problems in background technique.
In order to solve the above-mentioned technical problems, the present invention provides the following technical solutions:
The present invention provides a kind of crowded off-the-air picture identification cloud navigation system, comprising:
Mobile terminal and server end；
Mobile terminal connects server end, if successful connection, server sends abstract cartographic information to mobile terminal, is abstracted cartographic information
Including map.csv, are as follows:
0,0,0
1,0,0
…
100,5,0
…
500,5,1
…
Stable characteristic point, which is extracted, from the sequence of pictures that mobile terminal shoots current pedestrian visual angle is sent to server-side；
The invariant feature point information matches that server end is sent according to mobile terminal are stored in the characteristic point in map, obtain matching degree
Highest and matching degree are higher than the picture number of the threshold value rule of thumb set；
Due to the known and immediate picture number of photographer, therefore the position of current photographer can be learnt according to map.csv information
With visual angle；
According to the information of the position of current photographer and visual angle, number from the nearest shop of photographer, destination are comprehensively considered
Shop sum, the current direction of photographer, calculate shortest path using algorithm one in mobile terminal, provide navigation in number, map
It is recommended that.
As a preferred technical solution of the present invention, the map.csv first is classified as the picture number in map, and second
It is classified as store code, third is classified as the direction of the picture,
Wherein, 0 be it is clockwise, 1 be it is counterclockwise,
Another map.csv has recorded the shop title that each shop number represents.
As a preferred technical solution of the present invention, the mobile terminal is shot for interval 500ms and shoots one, shoots altogether
It is 4,2 seconds time-consuming.
As a preferred technical solution of the present invention, the stable characteristic point, which refers to, eliminates pedestrian's motive objects soma
The environmental characteristic point disturbed.
It is described to suggest including two classes as a preferred technical solution of the present invention:
1. passing through n1 along current path, the shop n2.. can be arrived at the destination；
2. turning round by way of by n1, the shop n2.. can be arrived at the destination.
One or more technical solution provided in the present invention, at least has the following technical effect that or advantage:
1, configuration is easy, human cost is low, and this project only need to operate mobile Simple robot to ring before one place use
Border study is primary, since map can update to self duplication, so not needing subsequent maintenance after primary study, therefore
This project can greatly save the human cost of indoor navigation system system maintenance.
2, potential user's amount is huge, in mobile internet era, the popularity rate of smart phone it is very high (whole nation has reached 58%,
The city is higher), this project does not need additional hardware support, it is only necessary to the camera function and network function that all smart phones are provided with
Energy, all smart phone users can enjoy the convenient life of this project bring, so the potential user of this project measures
It is huge.
It 3, can be in the study and navigation under crowded environment: dynamic environment can be efficiently extracted using innovation patent technology
Middle stable visual characteristic, and then realize study and navigation in crowded environment.So this project can section at any time
Learnt or navigated, is particularly suitable for the numerous dynamic environment of personnel.
4, cloud is handled, and this project is innovatively to the maximum extent transferred to heavy calculating task using cloud computing technology
Configure powerful cloud server end.It can be not required to the excessive electric power of consumption smart phone in this way, and be able to achieve response speed faster
Degree promotes user experience.
Specific embodiment
The embodiment of the present application solves existing in the prior art by a kind of crowded off-the-air picture identification cloud navigation system
Problem.
Above-mentioned technical proposal in order to better understand, below specific embodiment to above-mentioned technical proposal carry out specifically
It is bright.
Embodiment one:
A kind of crowded off-the-air picture of the present invention identifies cloud navigation system, comprising:
Mobile terminal and server end；
Mobile terminal connects server end, if successful connection, server sends abstract cartographic information to mobile terminal, is abstracted cartographic information
Including map.csv, are as follows:
0,0,0
1,0,0
…
100,5,0
…
500,5,1
…
Wherein map.csv first is classified as the picture number in map, and second is classified as store code, and third is classified as the court of the picture
To, wherein 0 be it is clockwise, 1 is counterclockwise；
Such as 500,5,1 meanings are that the 500th picture position takes pictures near the 5th shop and is oriented the inverse time in the map of cloud
Needle；
Another map.csv has recorded the shop title that each shop number represents；
Utilize patented technology (Osamu Hasegawa, Gangchen Hua, FEATURE VALUE EXTRACTION DEVICE
AND LOCATION INFERENCE DEVICE. (PCT Patent, International Intellectual Property Organization patent of invention number:
WO2014073204 A1)), stable characteristic point is extracted from the sequence of pictures that mobile terminal shoots current pedestrian visual angle
It is sent to server-side；
The invariant feature point information matches that server end is sent according to mobile terminal are stored in the characteristic point in map, and (matching process is still
So it is based on WO2014073204 A1), show that matching degree highest and matching degree are higher than a figure of the threshold value rule of thumb set
Piece numbers (such as 500), returns to (3) if it cannot get this number and retries, and mobile terminal is shot for interval 500ms shooting one
, 4 are shot altogether, and 2 seconds time-consuming, stable characteristic point refers to the environmental characteristic point for eliminating the interference of the mobile objects such as pedestrian；
Due to the known and immediate picture number of photographer, therefore the position of current photographer can be learnt according to map.csv information
With visual angle；Such as knows and just can know that photographer current location in the 5th shop for 500 with the immediate picture number of photographer
Near, it is oriented counterclockwise；
According to the information of the position of current photographer and visual angle, number from the nearest shop of photographer, destination are comprehensively considered
Shop sum, the current direction of photographer, calculate shortest path using algorithm one in mobile terminal, provide navigation in number, map
It is recommended that；
It is recommended that including two classes:
1. passing through n1 along current path, the shop n2.. can be arrived at the destination；
2. turning round by way of by n1, the shop n2.. can be arrived at the destination；
Wherein, algorithm one are as follows:
The number in the current nearest shop of current_index photographer, by learning current photographer according to map.csv information
Position obtained with visual angle:
The number of the destination objective_index, user are specified；
The absolute value of distance objective_index-current_index；
Shop sum in shop_amount map；
The current direction of orentation user, by learning that the position of current photographer is obtained with visual angle according to map.csv information
Arrive, 0 be it is clockwise, 1 is counterclockwise.
Concrete operations are as follows:
if (current_index < objective_index) {
if (distance <= shop_amount / 2) {
If (orentation==0) { prompt user passes through n1 along current path, and the shop n2.. can arrive at the destination }
Else { prompt user turns round by way of by n1, and the shop n2.. can arrive at the destination } }
Else if (orentation==1) { prompt user passes through n1 along current path, and the shop n2.. can arrive at the destination }
Else { prompt user turns round by way of by n1, and the shop n2.. can arrive at the destination } } }
else{if (distance <= shop_amount / 2) {if(orentation == 1){
User is prompted to pass through n1 along current path, the shop n2.. can arrive at the destination }
Else { prompt user turns round by way of by n1, and the shop n2.. can arrive at the destination } }
Else if (orentation==0) { prompt user passes through n1 along current path, and the shop n2.. can arrive at the destination }
Else { prompt user turns round by way of by n1, and the shop n2.. can arrive at the destination } } }.
Finally, it should be noted that the foregoing is only a preferred embodiment of the present invention, it is not intended to restrict the invention,
Although the present invention is described in detail referring to the foregoing embodiments, for those skilled in the art, still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features.
All within the spirits and principles of the present invention, any modification, equivalent replacement, improvement and so on should be included in of the invention
Within protection scope.
Claims (5)
1. a kind of crowded off-the-air picture identifies cloud navigation system, it is characterised in that: include:
Mobile terminal and server end；
Mobile terminal connects server end, if successful connection, server sends abstract cartographic information to mobile terminal, is abstracted cartographic information
Including map.csv, are as follows:
0,0,0
1,0,0
…
100,5,0
…
500,5,1
…
Stable characteristic point, which is extracted, from the sequence of pictures that mobile terminal shoots current pedestrian visual angle is sent to server-side；
The invariant feature point information matches that server end is sent according to mobile terminal are stored in the characteristic point in map, obtain matching degree
Highest and matching degree are higher than the picture number of the threshold value rule of thumb set；
Due to the known and immediate picture number of photographer, therefore the position of current photographer can be learnt according to map.csv information
With visual angle；
According to the information of the position of current photographer and visual angle, number from the nearest shop of photographer, destination are comprehensively considered
Shop sum, the current direction of photographer, calculate shortest path using algorithm one in mobile terminal, provide navigation in number, map
It is recommended that.
2. a kind of crowded off-the-air picture according to claim 1 identifies cloud navigation system, it is characterised in that: described
Map.csv first is classified as the picture number in map, and second is classified as store code, and third is classified as the direction of the picture,
Wherein, 0 be it is clockwise, 1 be it is counterclockwise,
Another map.csv has recorded the shop title that each shop number represents.
3. a kind of crowded off-the-air picture according to claim 1 identifies cloud navigation system, it is characterised in that: the mobile terminal
It is shot for interval 500ms and shoots one, shoot 4 altogether, time-consuming 2 seconds.
4. a kind of crowded off-the-air picture according to claim 1 identifies cloud navigation system, it is characterised in that: described stable
Characteristic point refers to the environmental characteristic point for eliminating the interference of pedestrian's mobile object.
5. a kind of crowded off-the-air picture according to claim 1 identifies cloud navigation system, it is characterised in that: the suggestion packet
Include two classes:
1. passing through n1 along current path, the shop n2.. can be arrived at the destination；
2. turning round by way of by n1, the shop n2.. can be arrived at the destination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910396992.7A CN110146083A (en) | 2019-05-14 | 2019-05-14 | A kind of crowded off-the-air picture identification cloud navigation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910396992.7A CN110146083A (en) | 2019-05-14 | 2019-05-14 | A kind of crowded off-the-air picture identification cloud navigation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110146083A true CN110146083A (en) | 2019-08-20 |
Family
ID=67595319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910396992.7A Pending CN110146083A (en) | 2019-05-14 | 2019-05-14 | A kind of crowded off-the-air picture identification cloud navigation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110146083A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103398717A (en) * | 2013-08-22 | 2013-11-20 | 成都理想境界科技有限公司 | Panoramic map database acquisition system and vision-based positioning and navigating method |
| CN104899603A (en) * | 2015-06-03 | 2015-09-09 | 孙思宇 | Optimization algorithm based on image matching indoor positioning |
| CN104897165A (en) * | 2014-03-06 | 2015-09-09 | 苏州工业园区新国大研究院 | Shot scenery-based navigation method and system thereof |
| CN106940186A (en) * | 2017-02-16 | 2017-07-11 | 华中科技大学 | A kind of robot autonomous localization and air navigation aid and system |
| CN107806872A (en) * | 2017-09-18 | 2018-03-16 | 东莞新吉凯氏测量技术有限公司 | Augmented reality air navigation aid based on machine vision |
| CN108020225A (en) * | 2016-10-28 | 2018-05-11 | 大辅科技（北京）有限公司 | Map system and air navigation aid based on image recognition |
| CN109029444A (en) * | 2018-06-12 | 2018-12-18 | 深圳职业技术学院 | One kind is based on images match and sterically defined indoor navigation system and air navigation aid |
| CN109520510A (en) * | 2018-12-26 | 2019-03-26 | 安徽智恒信科技有限公司 | A kind of indoor navigation method and system based on virtual reality technology |
-
2019
- 2019-05-14 CN CN201910396992.7A patent/CN110146083A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103398717A (en) * | 2013-08-22 | 2013-11-20 | 成都理想境界科技有限公司 | Panoramic map database acquisition system and vision-based positioning and navigating method |
| CN104897165A (en) * | 2014-03-06 | 2015-09-09 | 苏州工业园区新国大研究院 | Shot scenery-based navigation method and system thereof |
| CN104899603A (en) * | 2015-06-03 | 2015-09-09 | 孙思宇 | Optimization algorithm based on image matching indoor positioning |
| CN108020225A (en) * | 2016-10-28 | 2018-05-11 | 大辅科技（北京）有限公司 | Map system and air navigation aid based on image recognition |
| CN106940186A (en) * | 2017-02-16 | 2017-07-11 | 华中科技大学 | A kind of robot autonomous localization and air navigation aid and system |
| CN107806872A (en) * | 2017-09-18 | 2018-03-16 | 东莞新吉凯氏测量技术有限公司 | Augmented reality air navigation aid based on machine vision |
| CN109029444A (en) * | 2018-06-12 | 2018-12-18 | 深圳职业技术学院 | One kind is based on images match and sterically defined indoor navigation system and air navigation aid |
| CN109520510A (en) * | 2018-12-26 | 2019-03-26 | 安徽智恒信科技有限公司 | A kind of indoor navigation method and system based on virtual reality technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106651916B (en) | A kind of positioning and tracing method and device of target | |
| US20210201590A1 (en) | Systems, devices, and methods for augmented reality | |
| Qiu et al. | Kestrel: Video analytics for augmented multi-camera vehicle tracking | |
| CN105654512B (en) | A kind of method for tracking target and device | |
| Strasdat et al. | Scale Drift-Aware Large Scale Monocular SLAM. | |
| CN110163889A (en) | Method for tracking target, target tracker, target following equipment | |
| CN110672111B (en) | Vehicle driving path planning method, device, system, medium and equipment | |
| CN104378735B (en) | Indoor orientation method, client and server | |
| Gao et al. | Robust RGB-D simultaneous localization and mapping using planar point features | |
| US10949999B2 (en) | Location determination using street view images | |
| WO2020093829A1 (en) | Method and device for real-time statistical analysis of pedestrian flow in open space | |
| CN112101339B (en) | Map interest point information acquisition method and device, electronic equipment and storage medium | |
| CN110434853A (en) | A kind of robot control method, device and storage medium | |
| JP2016035775A (en) | Head pose estimation using RGBD camera | |
| CN109073385A (en) | A kind of localization method and aircraft of view-based access control model | |
| CN105931269A (en) | Tracking method for target in video and tracking device thereof | |
| CN104794468A (en) | Human face detection and tracking method based on unmanned aerial vehicle mobile platform | |
| CN109141453A (en) | A kind of route guiding method and system | |
| CN110321885A (en) | A kind of acquisition methods and device of point of interest | |
| US11657085B1 (en) | Optical devices and apparatuses for capturing, structuring, and using interlinked multi-directional still pictures and/or multi-directional motion pictures | |
| CN104897165A (en) | Shot scenery-based navigation method and system thereof | |
| WO2021077941A1 (en) | Method and device for robot positioning, smart robot, and storage medium | |
| KR100970121B1 (en) | Method, system, and computer-readable recording medium for performing image matching adaptively according to various conditions | |
| CN110428449A (en) | Target detection tracking method, device, equipment and storage medium | |
| CN107223082A (en) | A kind of robot control method, robot device and robot device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190820 |