CN109357679A - A kind of indoor orientation method based on significant characteristics identification - Google Patents
A kind of indoor orientation method based on significant characteristics identification Download PDFInfo
- Publication number
- CN109357679A CN109357679A CN201811364650.9A CN201811364650A CN109357679A CN 109357679 A CN109357679 A CN 109357679A CN 201811364650 A CN201811364650 A CN 201811364650A CN 109357679 A CN109357679 A CN 109357679A
- Authority
- CN
- China
- Prior art keywords
- image
- indoor
- intelligent movable
- app
- positioning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 239000000284 extract Substances 0.000 claims abstract description 16
- 238000000547 structure data Methods 0.000 claims abstract description 3
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000006835 compression Effects 0.000 claims description 3
- 238000007906 compression Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000013135 deep learning Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/02—Systems using the reflection of electromagnetic waves other than radio waves
- G01S17/06—Systems determining position data of a target
- G01S17/08—Systems determining position data of a target for measuring distance only
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Studio Devices (AREA)
Abstract
The present invention provides a kind of indoor orientation method based on significant characteristics identification, it is related to conspicuousness target detection, deep learning and indoor positioning technologies field, the present invention completes indoor panoramic table using high definition camera cooperation laser radar and models, and saliency feature is extracted using computer vision technique, be trained by a large amount of real scene images, correct and processing formed model, take pictures eventually by smart machine outdoor scene carry out images match extract space structure data realize precise positioning.It solves the problems, such as that indoor-GPS signal is weak, and eliminates the influence that dynamic object movement generates, ensure that the real-time of real scene image scene, improve the accuracy of image recognition, and then improve the precision of indoor positioning.
Description
Technical field
The present invention relates to conspicuousness target detection, deep learning and indoor positioning technologies, more particularly to one kind is based on significant
Property feature identification indoor orientation method.
Background technique
With the development that precision marketing, indoor navigation service etc. are applied by force, more and more attention has been paid in machine for indoor positioning
The multiple indoors scene such as field, railway station, market, factory, school has extensive application case.Indoor positioning refers to environment indoors
In position positioning, due to being limited by environment, it is fixed easily to be realized in outdoor intelligent mobile phone using GPS sensor
Position, but enter the room, smart machine often can not just receive GPS signal, be difficult to realize precise positioning.
Traditional indoor mode is to utilize base using wireless communication techniques such as indoor WiFi, bluetooth, RFID in the industry at present
It stands firm position, relative position is calculated by the signal strength that multiple wireless transmitters acquire, it is final to realize that personnel or object etc. exist
Positioning in the interior space.Traditional mode greatly relies on the construction of infrastructure, to WiFi or Bluetooth signal transmitter
The stability requirement of signal strength is higher, especially in the more scene in flow of personnel compact district or dynamic object, Wu Fabao
The stability for demonstrate,proving its signal causes the precision of indoor positioning and actual bit to be equipped with very big deviation, is unable to satisfy actual application
Demand.
In recent years, with the development of deep learning and computer vision technique, the precision and speed of machine recognition image are big
Width improves, and carries out position positioning by analysis shoot on location image and is possibly realized, on the other hand, the intelligence degree of mobile device
It is being continuously improved, processing capacity can satisfy the requirement of application.In this case, how computer vision is effectively utilized
Technology, and a variety of sensing technologies are combined, realize that indoor precise positioning becomes a urgent problem needed to be solved.
Summary of the invention
In order to solve the above technical problems, the invention proposes a kind of indoor positioning sides based on significant characteristics identification
Method solves the problems, such as that indoor-GPS signal is weak, improves the precision of indoor positioning.
The technical scheme is that
A kind of indoor orientation method based on significant characteristics identification first completes indoor panoramic table modeling, and utilizes computer
Vision technique extracts saliency feature, is trained, is corrected and processing forms model by a large amount of real scene images, final logical
Cross smart machine outdoor scene take pictures carry out images match extract space structure data realize precise positioning.
Using panoramic picture in high definition camera collection room, and the point cloud data of laser radar is cooperated to complete ranging, based on complete
Scape map carries out significant characteristics identification, image segmentation, then the shoot on location by the practical mobile photographing device of different time sections
Image is corrected and handles, and forms panorama location model rule base, and compress to model and rule base, is placed into band and claps
According in the intelligent movable equipment of function；Intelligent movable equipment shoots the outdoor scene of multiple different directions in fixed point, carries out image
Match, extracts image space structural information and carry out intersecting comparison positioning.In addition, intelligent movable equipment can also be by wifi, bluetooth
Etc. modes reduce search range, with real scene image positioning be mutually authenticated.Wherein,
The high definition camera is used for the acquisition of indoor panoramic image data, the laser radar cooperation high definition camera
It takes pictures, records point cloud data, determine shooting point at a distance from surrounding enviroment object, realize that panoramic picture shoots point location；
The positioning and model rule base is the computing resource assembled by cloud center, is learnt using image processing algorithm and is analyzed
It obtains, and forms running fix App, be put into intelligent movable equipment；The intelligent movable equipment has camera function, and
With certain computing capability, running fix App can be executed；The wifi and Bluetooth signal generator is indoor offer
The connection of the wireless communication of wifi and bluetooth.
The present invention provides a kind of indoor orientation methods based on significant characteristics identification, the room for intelligent movable equipment
Interior positioning, comprising:
Step 101, the laser radar cooperation high definition camera are to indoor shot distant view photograph, by the laser thunder
Up to acquisition point cloud data, identification record shooting point is at a distance from surrounding enviroment object；
The image, point cloud data and range data of acquisition are uploaded to cloud by step 102, are pre-processed, and data structure is completed
Change；
The panoramic picture repeatedly shot is carried out super-pixel segmentation by step 103, obtains initial notable figure；
The panoramic view data that step 104, basis are repeatedly shot fully considers that the variation of hiding relation and dynamic object, identification are significant
Property stationary body target；
Image and stationary body characteristic area after step 105, fusion segmentation, by the significant graph region of determination；
Step 106 extracts spatial structural form, determines position according to image resolution ratio and camera site in conjunction with point cloud data ranging
It sets；
Step 107 repeats step 103 to step 106, completes the model and rule base of indoor panorama；
Step 108 carries out compression processing for model and rule base, and combines indoor panoramic table, forms running fix APP,
It is put into cloud；
Step 109, the intelligent movable equipment download running fix APP from cloud；
The picture that step 110, the intelligent movable equipment shoot the outdoor scene of multiple different directions, and will acquire in fixed point into
Row pretreatment extracts it and shoots metadata, including aperture, shutter, focal length, pixel, shooting time etc.；
The running fix APP of intelligent movable equipment described in step 111, (optional) can connect wifi, bluetooth etc., and other are fixed
Position device, obtains position range；
The running fix APP extraction characteristics of image of step 112, the intelligent movable equipment, carries out images match, determines panorama
The position of image；
Step 113, according to shooting image metadata, image is projected on panoramic picture, extract image space structure
Information, which intersect, compares positioning, determines intelligent movable device location and is labeled display by App；
Step 114, the intelligent movable equipment utilization running fix APP are corrected labeling position, and will shoot image
Cloud is uploaded to together；
Step 115, cloud receive the data of user's upload, its App of Continuous optimization identifies location model, improve positioning accuracy.
The beneficial effects of the invention are as follows
The present invention realizes positioning using computer vision technique, greatly solves the problems, such as that indoor-GPS signal is weak, and disappear
In addition to the influence that dynamic object movement generates, the indoor positioning of degree of precision may be implemented, be suitable for plurality of application scenes；By
The modes such as wifi, bluetooth reduce search range, improve matching speed, and be mutually authenticated with real scene image positioning.In addition, effective
Using mobile APP persistent collection live-action data and amendment positioning, the real-time of real scene image scene ensure that, improve image knowledge
Other accuracy, and then improve the precision of indoor positioning.
Detailed description of the invention
Fig. 1 is indoor locating system composition schematic diagram；
Fig. 2 is the indoor positioning flow chart of intelligent movable equipment.
Specific embodiment
More detailed elaboration is carried out to the contents of the present invention with reference to the accompanying drawing:
As shown in fig. 1, using panoramic picture in high definition camera collection room, and the point cloud data of laser radar is cooperated to complete to survey
Away from carrying out significant characteristics identification, image segmentation based on panoramic table, then move photographing device by the way that different time sections are practical
Shoot on location image is corrected and handles, and forms panorama location model rule base, and compress to model and rule base, puts
It sets in the intelligent movable equipment with camera function；Intelligent movable equipment shoots the outdoor scene of multiple different directions in fixed point, into
Row images match extracts image space structural information and carries out intersecting comparison positioning.In addition, intelligent movable equipment can also be by
The modes such as wifi, bluetooth reduce search range, are mutually authenticated with real scene image positioning.
Wherein,
The high definition camera is used for the acquisition of indoor panoramic image data, the laser radar cooperation high definition camera
It takes pictures, records point cloud data, determine shooting point at a distance from surrounding enviroment object, realize that panoramic picture shoots point location；
The positioning and model rule base is the computing resource assembled by cloud center, using image processing algorithm study and
Analysis obtains, and forms running fix App, is put into intelligent movable equipment；
The intelligent movable equipment has camera function, and has certain computing capability, can execute running fix App；
The wifi is that the wifi of indoor offer and the wireless communication of bluetooth connect with Bluetooth signal generator.
Clear in order to describe, the characteristics of image recognizer in following instance uses R-CNN, conspicuousness algorithm of target detection
Using SLRC algorithm, feature extraction uses HOG+SVM algorithm.It will be appreciated by those skilled in the art that in addition to using with worthwhile
Except that, the construction of embodiment according to the present invention can also apply on other algorithms method.
As described in Figure 2, intelligent movable equipment indoor positioning the following steps are included:
Step 101, the laser radar cooperation high definition camera are to indoor shot distant view photograph, by the laser thunder
Up to acquisition point cloud data, identification record shooting point is at a distance from surrounding enviroment object；
The image, point cloud data and range data of acquisition are uploaded to cloud by step 102, are pre-processed, and data structure is completed
Change；
The panoramic picture repeatedly shot is carried out super-pixel segmentation by step 103, obtains initial notable figure；
The panoramic view data that step 104, basis are repeatedly shot fully considers that the variation of hiding relation and dynamic object, identification are significant
Property stationary body target；
Image and stationary body characteristic area after step 105, fusion segmentation, by the significant graph region of determination；
Step 106 extracts spatial structural form, determines position according to image resolution ratio and camera site in conjunction with point cloud data ranging
It sets；
Step 107 repeats step 103 to step 106, completes the model and rule base of indoor panorama；
Step 108 carries out compression processing for model and rule base, and combines indoor panoramic table, forms running fix APP,
It is put into cloud；
Step 109, the intelligent movable equipment download running fix APP from cloud；
The picture that step 110, the intelligent movable equipment shoot the outdoor scene of multiple different directions, and will acquire in fixed point into
Row pretreatment extracts it and shoots metadata, including aperture, shutter, focal length, pixel, shooting time etc.；
Step 111, the intelligent movable equipment running fix APP can connect other positioning devices such as wifi, bluetooth, obtain
Take position range；
The running fix APP extraction characteristics of image of step 112, the intelligent movable equipment, carries out images match, determines panorama
The position of image；
Step 113, according to shooting image metadata, image is projected on panoramic picture, extract image space structure
Information, which intersect, compares positioning, determines intelligent movable device location and is labeled display by App；
Step 114, the intelligent movable equipment utilization running fix APP are corrected labeling position, and will shoot image
Cloud is uploaded to together；
Step 115, cloud receive the data of user's upload, its App of Continuous optimization identifies location model, improve positioning accuracy.
Embodiment described above, only one kind of the specific embodiment of the invention, those skilled in the art is in this hair
The usual variations and alternatives carried out in bright technical proposal scope should be all included within the scope of the present invention.
Claims (9)
1. a kind of indoor orientation method based on significant characteristics identification, which is characterized in that
Indoor panoramic table modeling is first completed, recycles computer vision technique to extract saliency feature, passes through realistic picture
As be trained, correct and processing formed model, take pictures eventually by smart machine outdoor scene carry out images match extract space knot
Structure data realize precise positioning.
2. the method according to claim 1, wherein
Panoramic picture in collection room, and the point cloud data of laser radar is cooperated to complete ranging, conspicuousness is carried out based on panoramic table
Feature identification, image segmentation, then be corrected and locate by the shoot on location image of the practical mobile photographing device of different time sections
Reason forms panorama location model rule base, and compresses to model and rule base, is placed into the intelligent movable with camera function
In equipment；Intelligent movable equipment shoots the outdoor scene of multiple different directions in fixed point, carries out images match, extracts image space knot
Structure information, which intersect, compares positioning.
3. according to the method described in claim 2, it is characterized in that,
In addition, intelligent movable equipment can also reduce search range by wifi, bluetooth, it is mutually authenticated with real scene image positioning.
4. according to the method described in claim 2, it is characterized in that,
Be used for the acquisition of indoor panoramic image data by high definition camera, the laser radar cooperation high definition camera into
Row is taken pictures, and point cloud data is recorded, and determines shooting point at a distance from surrounding enviroment object, realizes that panoramic picture shoots point location.
5. according to the method described in claim 2, it is characterized in that,
The positioning and model rule base is the computing resource assembled by cloud center, using image processing algorithm study and
Analysis obtains, and forms running fix App, is put into intelligent movable equipment.
6. according to the method described in claim 2, it is characterized in that,
The intelligent movable equipment has camera function, and has computing capability, can execute running fix App.
7. according to the method described in claim 3, it is characterized in that,
The wifi is that the wifi of indoor offer and the wireless communication of bluetooth connect with Bluetooth signal generator.
8. according to the method described in claim 2, it is characterized in that,
Concrete operation step includes:
Step 101, the laser radar cooperation high definition camera are to indoor shot distant view photograph, by the laser thunder
Up to acquisition point cloud data, identification record shooting point is at a distance from surrounding enviroment object；
The image, point cloud data and range data of acquisition are uploaded to cloud by step 102, are pre-processed, and data structure is completed
Change；
The panoramic picture repeatedly shot is carried out super-pixel segmentation by step 103, obtains initial notable figure；
The panoramic view data that step 104, basis are repeatedly shot fully considers that the variation of hiding relation and dynamic object, identification are significant
Property stationary body target；
Image and stationary body characteristic area after step 105, fusion segmentation, by the significant graph region of determination；
Step 106 extracts spatial structural form, determines position according to image resolution ratio and camera site in conjunction with point cloud data ranging
It sets；
Step 107 repeats step 103 to step 106, completes the model and rule base of indoor panorama；
Step 108 carries out compression processing for model and rule base, and combines indoor panoramic table, forms running fix APP,
It is put into cloud；
Step 109, the intelligent movable equipment download running fix APP from cloud；
The picture that step 110, the intelligent movable equipment shoot the outdoor scene of multiple different directions, and will acquire in fixed point into
Row pretreatment extracts it and shoots metadata, including aperture, shutter, focal length, pixel, shooting time etc.；
The running fix APP extraction characteristics of image of step 111, the intelligent movable equipment, carries out images match, determines panorama
The position of image；
Step 112, according to shooting image metadata, image is projected on panoramic picture, extract image space structure
Information, which intersect, compares positioning, determines intelligent movable device location and is labeled display by App；
Step 113, the intelligent movable equipment utilization running fix APP are corrected labeling position, and will shoot image
Cloud is uploaded to together；
Step 114, cloud receive the data of user's upload, its App of Continuous optimization identifies location model, improve positioning accuracy.
9. according to the method described in claim 8, it is characterized in that,
The running fix APP of the intelligent movable equipment can connect wifi, bluetooth, obtain position range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811364650.9A CN109357679B (en) | 2018-11-16 | 2018-11-16 | Indoor positioning method based on significance characteristic recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811364650.9A CN109357679B (en) | 2018-11-16 | 2018-11-16 | Indoor positioning method based on significance characteristic recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109357679A true CN109357679A (en) | 2019-02-19 |
| CN109357679B CN109357679B (en) | 2022-04-19 |
Family
ID=65345498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811364650.9A Active CN109357679B (en) | 2018-11-16 | 2018-11-16 | Indoor positioning method based on significance characteristic recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109357679B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109916408A (en) * | 2019-02-28 | 2019-06-21 | 深圳市鑫益嘉科技股份有限公司 | Robot indoor positioning and air navigation aid, device, equipment and storage medium |
| CN110070127A (en) * | 2019-04-19 | 2019-07-30 | 南京邮电大学 | The optimization method finely identified towards family product |
| CN110298320A (en) * | 2019-07-01 | 2019-10-01 | 北京百度网讯科技有限公司 | A kind of vision positioning method, device and storage medium |
| CN110427936A (en) * | 2019-07-04 | 2019-11-08 | 深圳市新潮酒窖文化传播有限公司 | A kind of the cellar management method and system in wine cellar |
| CN112242002A (en) * | 2020-10-09 | 2021-01-19 | 同济大学 | Object identification and panoramic roaming method based on deep learning |
| CN113137963A (en) * | 2021-04-06 | 2021-07-20 | 上海电科智能系统股份有限公司 | Passive indoor high-precision comprehensive positioning and navigation method for people and objects |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130222369A1 (en) * | 2012-02-23 | 2013-08-29 | Charles D. Huston | System and Method for Creating an Environment and for Sharing a Location Based Experience in an Environment |
| CN103646420A (en) * | 2013-12-12 | 2014-03-19 | 浪潮电子信息产业股份有限公司 | Intelligent 3D scene reduction method based on self learning algorithm |
| WO2014073841A1 (en) * | 2012-11-07 | 2014-05-15 | 한국과학기술연구원 | Method for detecting image-based indoor position, and mobile terminal using same |
| CN105716609A (en) * | 2016-01-15 | 2016-06-29 | 浙江梧斯源通信科技股份有限公司 | Indoor robot vision positioning method |
| CN106447585A (en) * | 2016-09-21 | 2017-02-22 | 武汉大学 | Urban area and indoor high-precision visual positioning system and method |
| CN107131883A (en) * | 2017-04-26 | 2017-09-05 | 中山大学 | The full-automatic mobile terminal indoor locating system of view-based access control model |
| CN107167144A (en) * | 2017-07-07 | 2017-09-15 | 武汉科技大学 | A kind of mobile robot indoor environment recognition positioning method of view-based access control model |
| US20180061126A1 (en) * | 2016-08-26 | 2018-03-01 | Osense Technology Co., Ltd. | Method and system for indoor positioning and device for creating indoor maps thereof |
| CN107833220A (en) * | 2017-11-28 | 2018-03-23 | 河海大学常州校区 | Fabric defect detection method based on depth convolutional neural networks and vision significance |
| WO2018093438A1 (en) * | 2016-08-26 | 2018-05-24 | William Marsh Rice University | Camera-based positioning system using learning |
-
2018
- 2018-11-16 CN CN201811364650.9A patent/CN109357679B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130222369A1 (en) * | 2012-02-23 | 2013-08-29 | Charles D. Huston | System and Method for Creating an Environment and for Sharing a Location Based Experience in an Environment |
| WO2014073841A1 (en) * | 2012-11-07 | 2014-05-15 | 한국과학기술연구원 | Method for detecting image-based indoor position, and mobile terminal using same |
| CN103646420A (en) * | 2013-12-12 | 2014-03-19 | 浪潮电子信息产业股份有限公司 | Intelligent 3D scene reduction method based on self learning algorithm |
| CN105716609A (en) * | 2016-01-15 | 2016-06-29 | 浙江梧斯源通信科技股份有限公司 | Indoor robot vision positioning method |
| US20180061126A1 (en) * | 2016-08-26 | 2018-03-01 | Osense Technology Co., Ltd. | Method and system for indoor positioning and device for creating indoor maps thereof |
| WO2018093438A1 (en) * | 2016-08-26 | 2018-05-24 | William Marsh Rice University | Camera-based positioning system using learning |
| CN106447585A (en) * | 2016-09-21 | 2017-02-22 | 武汉大学 | Urban area and indoor high-precision visual positioning system and method |
| CN107131883A (en) * | 2017-04-26 | 2017-09-05 | 中山大学 | The full-automatic mobile terminal indoor locating system of view-based access control model |
| CN107167144A (en) * | 2017-07-07 | 2017-09-15 | 武汉科技大学 | A kind of mobile robot indoor environment recognition positioning method of view-based access control model |
| CN107833220A (en) * | 2017-11-28 | 2018-03-23 | 河海大学常州校区 | Fabric defect detection method based on depth convolutional neural networks and vision significance |
Non-Patent Citations (2)
| Title |
|---|
| HISATO KAWAJI等: "Image-based indoor positioning system: fast image matching using omnidirectional panoramic images", 《PROCEEDINGS OF THE 1ST ACM INTERNATIONAL WORKSHOP ON MULTIMODAL PERVASIVE VIDEO ANALYSIS》 * |
| 曹天扬 等: "结合图像内容匹配的机器人视觉导航定位与全局地图构建系统", 《光学精密工程》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109916408A (en) * | 2019-02-28 | 2019-06-21 | 深圳市鑫益嘉科技股份有限公司 | Robot indoor positioning and air navigation aid, device, equipment and storage medium |
| CN110070127A (en) * | 2019-04-19 | 2019-07-30 | 南京邮电大学 | The optimization method finely identified towards family product |
| CN110298320A (en) * | 2019-07-01 | 2019-10-01 | 北京百度网讯科技有限公司 | A kind of vision positioning method, device and storage medium |
| CN110427936A (en) * | 2019-07-04 | 2019-11-08 | 深圳市新潮酒窖文化传播有限公司 | A kind of the cellar management method and system in wine cellar |
| CN110427936B (en) * | 2019-07-04 | 2022-09-30 | 深圳市新潮酒窖文化传播有限公司 | Wine storage management method and system for wine cellar |
| CN112242002A (en) * | 2020-10-09 | 2021-01-19 | 同济大学 | Object identification and panoramic roaming method based on deep learning |
| CN112242002B (en) * | 2020-10-09 | 2022-07-08 | 同济大学 | Object identification and panoramic roaming method based on deep learning |
| CN113137963A (en) * | 2021-04-06 | 2021-07-20 | 上海电科智能系统股份有限公司 | Passive indoor high-precision comprehensive positioning and navigation method for people and objects |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109357679B (en) | 2022-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109357679A (en) | A kind of indoor orientation method based on significant characteristics identification | |
| US10740975B2 (en) | Mobile augmented reality system | |
| CN108965687B (en) | Shooting direction identification method, server, monitoring method, monitoring system and camera equipment | |
| US10664708B2 (en) | Image location through large object detection | |
| CN107133325B (en) | Internet photo geographic space positioning method based on street view map | |
| CN109520500B (en) | Accurate positioning and street view library acquisition method based on terminal shooting image matching | |
| CN104376118A (en) | Panorama-based outdoor movement augmented reality method for accurately marking POI | |
| CN112166459A (en) | Three-dimensional environment modeling based on multi-camera convolver system | |
| TW202208879A (en) | Pose determination method, electronic device and computer readable storage medium | |
| CN102157011A (en) | Method for carrying out dynamic texture acquisition and virtuality-reality fusion by using mobile shooting equipment | |
| CN105023266A (en) | Method and device for implementing augmented reality (AR) and terminal device | |
| CN112161618A (en) | Storage robot positioning and map construction method, robot and storage medium | |
| CN108955682A (en) | Mobile phone indoor positioning air navigation aid | |
| CN104573617A (en) | Video shooting control method | |
| Feng et al. | Visual map construction using RGB-D sensors for image-based localization in indoor environments | |
| CN109523499A (en) | A kind of multi-source fusion full-view modeling method based on crowdsourcing | |
| KR102072796B1 (en) | Method, system and non-transitory computer-readable recording medium for calculating spatial coordinates of a region of interest | |
| KR102300570B1 (en) | Assembly for omnidirectional image capture and method performing by the same | |
| WO2023160722A1 (en) | Interactive target object searching method and system and storage medium | |
| CN112348887A (en) | Terminal pose determining method and related device | |
| CN105245845A (en) | Method for controlling camera to follow and shoot automatically based on gathering trend in match field | |
| KR102029741B1 (en) | Method and system of tracking object | |
| Zhao et al. | CrowdOLR: Toward object location recognition with crowdsourced fingerprints using smartphones | |
| WO2023103883A1 (en) | Automatic object annotation method and apparatus, electronic device and storage medium | |
| CN110473256A (en) | A kind of vehicle positioning method and system |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220324 Address after: 250100 building S02, No. 1036, Langchao Road, high tech Zone, Jinan City, Shandong Province Applicant after: Shandong Inspur Scientific Research Institute Co.,Ltd. Address before: 250100 First Floor of R&D Building 2877 Kehang Road, Sun Village Town, Jinan High-tech Zone, Shandong Province Applicant before: JINAN INSPUR HIGH-TECH TECHNOLOGY DEVELOPMENT Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |