CN109521398A - A kind of positioning system and localization method based on multi-vision visual - Google Patents
A kind of positioning system and localization method based on multi-vision visual Download PDFInfo
- Publication number
- CN109521398A CN109521398A CN201811477135.1A CN201811477135A CN109521398A CN 109521398 A CN109521398 A CN 109521398A CN 201811477135 A CN201811477135 A CN 201811477135A CN 109521398 A CN109521398 A CN 109521398A
- Authority
- CN
- China
- Prior art keywords
- fork truck
- goods
- positioning system
- vision
- image
- 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
- 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
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/16—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using electromagnetic waves other than radio waves
- G01S5/163—Determination of attitude
Landscapes
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Forklifts And Lifting Vehicles (AREA)
- Image Processing (AREA)
Abstract
A kind of positioning system based on multi-vision visual is made of more mesh camera units, interchanger and vision positioning system；Wherein, more mesh camera units are the cellular constructions that at least two mesh cameras are constituted；Belong to embedded development, volume very little, algorithm interface are standard interface；Fork truck can be guided to carry out accurately forking goods bat according to the pose of cargo；It has the advantages of simple structure and easy realization, the unmanned fork lift suitable for Intelligent storage system inserts goods bat automatically.
Description
Technical field
It stores in a warehouse correlative technology field the invention belongs to intelligence, especially a kind of positioning system based on multi-vision visual and fixed
Position method.
Background technique
Intelligent storage system and unmanned warehousing system are just increasingly valued by people currently on the market, wherein without
It is a very important sport technique segment that picking object is inserted in the automation of people's fork truck, and technological difficulties are how to guide fork truck accurate
Slotting fetch bit is set unfixed goods and is clapped.Solving the more commonly used method of this problem at present is using single camera system and in goods bat
The mode that cooperative target combines is pasted to realize, but the shortcomings that this mode is, the same position to clap in each goods
Cooperative target is pasted, system accuracy is greatly influenced by the precision that cooperative target claps relative positional relationship with goods.Therefore, it is
Reach very high precision cooperative target and positional relationship that goods is clapped will be demarcated in advance.And goods bat type is very more, behaviour
Make to get up pretty troublesome.This leads to that good control effect is all not achieved in the occasion much applied.
Summary of the invention
The purpose of the present invention is to provide a kind of positioning system and localization method based on multi-vision visual, it can make up existing
There is the deficiency of technology, is that a kind of structure is simple, localization method multi-vision visual image location system easy to accomplish.
Technical solution of the present invention: a kind of positioning system based on multi-vision visual, including fork truck control system, by embedded
Control system, servo motor driving system, the standard communication interface of network interface and USB port and other miscellaneous function units are constituted,
It is characterized in that it is made of more mesh camera units, interchanger and vision positioning system；Wherein, more mesh camera units be to
The cellular construction that rare two mesh camera is constituted is clapped between image information, with interchanger for acquiring fork truck and goods in bi-directional data
Connection；The vision positioning system includes control core plate unit；In two-way between the interchanger and control core plate unit
Data connection；It is connected in bi-directional data between the control core plate unit and interchanger and fork truck control system, for real
Coordinate system calibration processing now is carried out to the collected fork truck image information of more mesh camera units, to obtain object in fork truck coordinate system
Under pose, find out the position deviation between standard pose, and deviation signal is returned into fork truck control system, reach control
The purpose that fork truck correctly acts.
It is connected according to gigabit ethernet interface in bi-directional data between the control core plate unit and interchanger；The control
It is connected by USB interface in bi-directional data between core plate unit and fork truck control system.
A kind of positioning system based on multi-vision visual further includes control light source, passes through I/O interface and vision positioning system
Control core plate unit in being bi-directionally connected.
The interchanger is industrial switch.
More mesh camera units are binocular camera units, consistent with specifications parameter using brand with camera lens by two cameras
Industrial camera is constituted.
The binocular camera unit is loaded on the headstock position immediately ahead of fork truck, and the foundation of installation site adjustment is with unobstructedly
Subject to seeing that goods is clapped；The headstock position is equipped with a horizontal bracket, the camera and camera lens all framves of the binocular camera unit
It is located on the horizontal bracket；The size of centerlines and testee between two cameras of the binocular camera unit and
Testing distance is related, can fully appear in simultaneously in the visual field of two cameras according to guarantee object, and size is entire picture
1/3 pair of centerlines be adjusted.
The positioning system based on multi-vision visual is a set of computing system for meeting X86 structure, using embedded core
CPU board is control core, can install Windows/Linux system.
A kind of localization method based on multi-vision visual, it is characterised in that it the following steps are included:
Step 1: acquiring fork truck and goods bat position progress image information by more mesh camera units, and image is believed by interchanger
Breath uploads to control core plate unit, at this point, the fork truck image information that control core plate unit obtains more mesh camera units
Combined calibrating is carried out with the fork truck image information for having stored in control core plate unit, obtains transition matrix, it is therefore an objective to will regard
The coordinate system of feel system unitizes with fork truck coordinate system；
Step 2: can go out object after calibration by transform matrix calculations by value of the analysis fork truck under image coordinate system and exist
Pose under fork truck coordinate system；Complete system calibrating work；
Step 3: being clapped by more mesh camera units goods in the case where fork truck and goods clap normal place relationship and carrying out Image Acquisition, and will
Goods in this image claps direct picture and is set as template, using the pose of fork truck under the present situation as with reference to pose；
Step 4: fork truck is started to work, after fork truck movement arrival claps the position in 1.6 meters -2 meters of front, detected by binocular image
It is single to carry out image data acquiring, and control core plate unit is uploaded to, image is clapped to the goods in image by control core plate unit
Data carry out feature point extraction, and the goods beat template picture obtained with third step compares, and then calculate current goods and clap
Pose under fork truck coordinate system；
Step 5: the goods that the 4th step is obtained claps the posture information under fork truck coordinate system with the format of (X, Y, Z, Rx, Ry, Rz)
Fork truck control system is sent to by USB interface；Wherein, X, Y, Z are the location information of object under three-dimensional system of coordinate, X, Y, Z table
Show that a coordinate points respectively indicate a point X-axis, the value of Y-axis and Z-direction under three-dimensional system of coordinate；Rx, Ry, Rz are that object exists
Rotation amount under each reference axis, this six parameters are referred to as position and the posture information of object；
Step 6: fork truck control system then carries out difference according to the canonical reference pose and currently available pose demarcated in advance
Compare, can calculate offset and rotation amount required for fork truck, fork truck according to these calculated values carry out corresponding movement come
Achieve the purpose that accurately to insert.
The working principle of the invention: being a based on multi-vision visual image location system, high to guide unmanned fork lift to complete
Precision inserting.It, which is the mode based on template matching, establishes template for goods bat front, passes through multi-vision visual system identification and analysis
Goods claps the characteristic point of side and claps the pose under camera coordinates system to parse current goods.Because of camera coordinates system and fork truck coordinate
Calibration finishes in advance for system, so can clap the position under fork truck coordinate system by the pose under camera coordinates system with inverse shipment
Appearance, so as to guide fork truck to carry out corresponding position adjustment.It can be compatible with the overwhelming majority in the case where not pasting index point
Goods is clapped.Therefore, it considerably increases the flexibility degree of equipment, and application range also expands therewith.
Superiority of the invention: 1, being integrated with the vision guide control algolithm of complete set, can need to obtain according to user
Different goods are taken to clap posture information of the cargo under different coordinates under type；2, this system is embedded development, and volume very little is calculated
Method interface is standard interface；3, high-precision vision measuring technique and unmanned fork lift control technology are combined together, by more
Mesh system-computed goes out current goods and claps pose, and pose feeds back to the control system of unmanned fork lift to guide fork truck to carry out accurately
Fork goods bat；4, it has the advantages of simple structure and easy realization, the unmanned fork lift suitable for Intelligent storage system inserts goods bat automatically.
Figure of description
Fig. 1 is a kind of overall structure block diagram of the positioning system based on multi-vision visual involved by the present invention.
Specific embodiment
Embodiment: a kind of positioning system based on multi-vision visual, including fork truck control system, by embedded control system,
Servo motor driving system, the standard communication interface of network interface and USB port and other miscellaneous function units are constituted, as shown, its
It is characterized in that it is made of more mesh camera units, interchanger and vision positioning system；Wherein, more mesh camera units be to
The cellular construction that rare two mesh camera is constituted is clapped between image information, with interchanger for acquiring fork truck and goods in bi-directional data
Connection；The vision positioning system includes control core plate unit；In two-way between the interchanger and control core plate unit
Data connection；It is connected in bi-directional data between the control core plate unit and interchanger and fork truck control system, for real
Coordinate system calibration processing now is carried out to the collected fork truck image information of more mesh camera units, to obtain object in fork truck coordinate system
Under pose, find out the position deviation between standard pose, and deviation signal is returned into fork truck control system, reach control
The purpose that fork truck correctly acts.
As shown, connecting according to gigabit ethernet interface in bi-directional data between the control core plate unit and interchanger
It connects；It is connected by USB interface in bi-directional data between the control core plate unit and fork truck control system.
As shown, a kind of positioning system based on multi-vision visual further includes control light source, pass through I/O interface and view
The control core plate unit for feeling positioning system is in be bi-directionally connected.
The interchanger is industrial switch.
As shown, more mesh camera units are binocular camera units, brand and rule are used by two cameras and camera lens
The consistent industrial camera of lattice parameter is constituted.
The binocular camera unit is loaded on the headstock position immediately ahead of fork truck, and the foundation of installation site adjustment is with unobstructedly
Subject to seeing that goods is clapped；The headstock position is equipped with a horizontal bracket, the camera and camera lens all framves of the binocular camera unit
It is located on the horizontal bracket；The size of centerlines and testee between two cameras of the binocular camera unit and
Testing distance is related, can fully appear in simultaneously in the visual field of two cameras according to guarantee object, and size is entire picture
1/3 pair of centerlines be adjusted.
The vision positioning system is a set of computing system for meeting X86 structure, uses embedded core CPU plate for control
Core can install Windows/Linux system.
A kind of localization method based on multi-vision visual, it is characterised in that it the following steps are included:
Step 1: acquiring fork truck and goods bat position progress image information by more mesh camera units, and image is believed by interchanger
Breath uploads to control core plate unit, at this point, the fork truck image information that control core plate unit obtains more mesh camera units
Combined calibrating is carried out with the fork truck image information for having stored in control core plate unit, obtains transition matrix, it is therefore an objective to will regard
The coordinate system of feel system unitizes with fork truck coordinate system；
Step 2: can go out object after calibration by transform matrix calculations by value of the analysis fork truck under image coordinate system and exist
Pose under fork truck coordinate system；Complete system calibrating work；
Step 3: being clapped by more mesh camera units goods in the case where fork truck and goods clap normal place relationship and carrying out Image Acquisition, and will
Goods in this image claps direct picture and is set as template, using the pose of fork truck under the present situation as with reference to pose；
Step 4: fork truck is started to work, after fork truck movement arrival claps the position in 1.6 meters -2 meters of front, detected by binocular image
It is single to carry out image data acquiring, and control core plate unit is uploaded to, image is clapped to the goods in image by control core plate unit
Data carry out feature point extraction, and the goods beat template picture obtained with third step compares, and then calculate current goods and clap
Pose under fork truck coordinate system；
Step 5: the goods that the 4th step is obtained claps the posture information under fork truck coordinate system with the format of (X, Y, Z, Rx, Ry, Rz)
Fork truck control system is sent to by USB interface；Wherein, X, Y, Z are the location information of object under three-dimensional system of coordinate, X, Y, Z table
Show that a coordinate points respectively indicate a point X-axis, the value of Y-axis and Z-direction under three-dimensional system of coordinate；Rx, Ry, Rz are that object exists
Rotation amount under each reference axis, this six parameters are referred to as position and the posture information of object；
Step 6: fork truck control system then carries out difference according to the canonical reference pose and currently available pose demarcated in advance
Compare, can calculate offset and rotation amount required for fork truck, fork truck according to these calculated values carry out corresponding movement come
Achieve the purpose that accurately to insert.
For the description the objectives, technical solutions, and advantages of the present invention further clearly understood, in conjunction with attached drawing and implementation
Case is described in detail.Case study on implementation described herein is a part of the invention.
When system components operation enters automatic mode, unmanned fork lift moves arrival under the guide that SLAM system is navigated
Clap front, but since posture that goods is clapped has a very big uncertainty, and the positioning accuracy of fork truck is in ± 5cm range,
So last adjustment must just be carried out by this vision positioning system by accurately inserting picking object to fork truck.
Step 1: this vision positioning system, loaded on the headstock position immediately ahead of fork truck, specific installation site will be adjusted to
Subject to can unobstructedly seeing that goods is clapped.Step 2: multicamera system will carry out combined calibrating with fork truck, transition matrix is obtained,
Purpose is that the coordinate system of vision system and fork truck coordinate system unitize.After calibration, by object analysis in image coordinate
Value under system can calculate pose of the object under fork truck coordinate system by transition matrix.Step 3: the system of progress mark
It can be carried out work after fixed.Goods bat is carried out adopting figure in the case where fork truck and goods clap normal place relationship, and will be in this image
Goods clap direct picture and be set as template, the pose of fork truck under the present situation is used as with reference to pose.Fork truck after-vision system in place
System carries out image data acquiring first, then claps the goods in image and carries out feature point extraction, and compares with template picture,
And then it calculates current goods and claps the pose under fork truck coordinate system, and by the posture information with the format of (X, Y, Z, Rx, Ry, Rz)
Fork truck control system is sent to by USB interface.Fork truck system carries out difference ratio according to reference pose and currently available pose
Compared with that can calculate offset and rotation amount required for fork truck, fork truck carries out corresponding movement according to these calculated values to reach
The purpose accurately inserted.
Although above-mentioned have been described in the embodiment of the present invention, to those of ordinary skill in the art, in this principle and
A variety of variations can be carried out to embodiment under spirit belong to protection of the invention under the premise of not making creative labor
Within the scope of.
Claims (8)
1. a kind of positioning system based on multi-vision visual, including fork truck control system are driven by embedded control system, servo motor
Dynamic system, the standard communication interface of network interface and USB port and other miscellaneous function units are constituted, it is characterised in that it is by more mesh phases
Machine unit, interchanger and vision positioning system are constituted；Wherein, more mesh camera units are the lists that at least two mesh cameras are constituted
Meta structure is clapped image information for acquiring fork truck and goods, is connect between interchanger in bi-directional data；The vision positioning system
Including control core plate unit；It is connected between the interchanger and control core plate unit in bi-directional data；The control core
It connects in bi-directional data between plate unit and interchanger and fork truck control system, is collected for realizing to more mesh camera units
Fork truck image information carry out coordinate system calibration processing, to obtain pose of the object under fork truck coordinate system, find out and normal bit
Position deviation between appearance, and deviation signal is returned into fork truck control system, achieve the purpose that controlling fork truck correctly acts.
2. a kind of positioning system based on multi-vision visual according to claim 1, it is characterised in that the control core plate list
It is connected according to gigabit ethernet interface in bi-directional data between member and interchanger；The control core plate unit and fork truck control system
Between by USB interface in bi-directional data connection.
3. a kind of positioning system based on multi-vision visual according to claim 1, it is characterised in that described to be based on multi-vision visual
Positioning system further include control light source, by I/O interface and the control core plate unit of vision positioning system in being bi-directionally connected.
4. a kind of positioning system based on multi-vision visual according to claim 1, it is characterised in that the interchanger is industry
Interchanger.
5. a kind of positioning system based on multi-vision visual according to claim 1, it is characterised in that more mesh camera units
It is binocular camera unit, is constituted by two cameras with camera lens using brand industrial camera consistent with specifications parameter.
6. a kind of positioning system based on multi-vision visual according to claim 5, it is characterised in that the binocular camera unit
Loaded on the headstock position immediately ahead of fork truck, the foundation of installation site adjustment, which is subject to, unobstructedly sees that goods is clapped；The headstock position
It sets and a horizontal bracket is installed, the camera and camera lens of the binocular camera unit are all erected on the horizontal bracket；It is described double
Centerlines between two cameras of mesh camera unit are related with the size of testee and testing distance, according to guarantee object
Body can fully appear in simultaneously in the visual field of two cameras, and size is that 1/3 pair of centerlines of entire picture are adjusted
Section.
7. a kind of positioning system based on multi-vision visual according to claim 1, it is characterised in that the vision positioning system
It is a set of computing system for meeting X86 structure, uses embedded core CPU plate for control core, Windows/ can be installed
Linux system.
8. a kind of localization method based on multi-vision visual, it is characterised in that it the following steps are included:
Step 1: acquiring fork truck and goods bat position progress image information by more mesh camera units, and image is believed by interchanger
Breath uploads to control core plate unit, at this point, the fork truck image information that control core plate unit obtains more mesh camera units
Combined calibrating is carried out with the fork truck image information for having stored in control core plate unit, obtains transition matrix, it is therefore an objective to will regard
The coordinate system of feel system unitizes with fork truck coordinate system；
Step 2: can go out object after calibration by transform matrix calculations by value of the analysis fork truck under image coordinate system and exist
Pose under fork truck coordinate system；Complete system calibrating work；
Step 3: being clapped by more mesh camera units goods in the case where fork truck and goods clap normal place relationship and carrying out Image Acquisition, and will
Goods in this image claps direct picture and is set as template, using the pose of fork truck under the present situation as with reference to pose；
Step 4: fork truck is started to work, after fork truck movement arrival claps the position in 1.6 meters -2 meters of front, detected by binocular image
It is single to carry out image data acquiring, and control core plate unit is uploaded to, image is clapped to the goods in image by control core plate unit
Data carry out feature point extraction, and the goods beat template picture obtained with third step compares, and then calculate current goods and clap
Pose under fork truck coordinate system；
Step 5: the goods that the 4th step is obtained claps the posture information under fork truck coordinate system with the format of (X, Y, Z, Rx, Ry, Rz)
Fork truck control system is sent to by USB interface；Wherein, X, Y, Z are the location information of object under three-dimensional system of coordinate, X, Y, Z table
Show that a coordinate points respectively indicate a point X-axis, the value of Y-axis and Z-direction under three-dimensional system of coordinate；Rx, Ry, Rz are that object exists
Rotation amount under each reference axis, this six parameters are referred to as position and the posture information of object；
Step 6: fork truck control system then carries out difference according to the canonical reference pose and currently available pose demarcated in advance
Compare, can calculate offset and rotation amount required for fork truck, fork truck according to these calculated values carry out corresponding movement come
Achieve the purpose that accurately to insert.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811477135.1A CN109521398A (en) | 2018-12-05 | 2018-12-05 | A kind of positioning system and localization method based on multi-vision visual |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811477135.1A CN109521398A (en) | 2018-12-05 | 2018-12-05 | A kind of positioning system and localization method based on multi-vision visual |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109521398A true CN109521398A (en) | 2019-03-26 |
Family
ID=65794168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811477135.1A Pending CN109521398A (en) | 2018-12-05 | 2018-12-05 | A kind of positioning system and localization method based on multi-vision visual |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109521398A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111807265A (en) * | 2020-06-16 | 2020-10-23 | 季华实验室 | Goods taking position adjusting method and device, mobile robot system and electronic equipment |
| CN113313444A (en) * | 2021-04-19 | 2021-08-27 | 安吉智能物联技术有限公司 | Forklift real-time positioning system and method for logistics warehouse |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103706568A (en) * | 2013-11-26 | 2014-04-09 | 中国船舶重工集团公司第七一六研究所 | System and method for machine vision-based robot sorting |
| CN104331894A (en) * | 2014-11-19 | 2015-02-04 | 山东省科学院自动化研究所 | Robot unstacking method based on binocular stereoscopic vision |
| CN106695784A (en) * | 2016-12-02 | 2017-05-24 | 中国东方电气集团有限公司 | Visual control system for robot |
| CN106885601A (en) * | 2017-01-09 | 2017-06-23 | 北京理工大学 | Unmanned vehicle multi-sensor data synchronous |
| CN108012325A (en) * | 2017-10-30 | 2018-05-08 | 上海神添实业有限公司 | A kind of navigation locating method based on UWB and binocular vision |
| CN208999804U (en) * | 2018-12-05 | 2019-06-18 | 普达迪泰（天津）智能装备科技有限公司 | A kind of high-precision intelligent equipment based on multi-vision visual positioning system |
-
2018
- 2018-12-05 CN CN201811477135.1A patent/CN109521398A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103706568A (en) * | 2013-11-26 | 2014-04-09 | 中国船舶重工集团公司第七一六研究所 | System and method for machine vision-based robot sorting |
| CN104331894A (en) * | 2014-11-19 | 2015-02-04 | 山东省科学院自动化研究所 | Robot unstacking method based on binocular stereoscopic vision |
| CN106695784A (en) * | 2016-12-02 | 2017-05-24 | 中国东方电气集团有限公司 | Visual control system for robot |
| CN106885601A (en) * | 2017-01-09 | 2017-06-23 | 北京理工大学 | Unmanned vehicle multi-sensor data synchronous |
| CN108012325A (en) * | 2017-10-30 | 2018-05-08 | 上海神添实业有限公司 | A kind of navigation locating method based on UWB and binocular vision |
| CN208999804U (en) * | 2018-12-05 | 2019-06-18 | 普达迪泰（天津）智能装备科技有限公司 | A kind of high-precision intelligent equipment based on multi-vision visual positioning system |
Non-Patent Citations (2)
| Title |
|---|
| 李瑞峰: "《工业机器人设计与应用》", 31 January 2017 * |
| 马蕾: "基于双目立体视觉的集装箱识别与定位技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111807265A (en) * | 2020-06-16 | 2020-10-23 | 季华实验室 | Goods taking position adjusting method and device, mobile robot system and electronic equipment |
| CN113313444A (en) * | 2021-04-19 | 2021-08-27 | 安吉智能物联技术有限公司 | Forklift real-time positioning system and method for logistics warehouse |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104217439B (en) | Indoor visual positioning system and method | |
| US20190371003A1 (en) | Monocular vision tracking method, apparatus and non-volatile computer-readable storage medium | |
| CN108536145A (en) | A kind of robot system intelligently followed using machine vision and operation method | |
| CN110033489B (en) | Method, device and equipment for evaluating vehicle positioning accuracy | |
| CN106168805A (en) | The method of robot autonomous walking based on cloud computing | |
| KR20140049361A (en) | Multiple sensor system, and apparatus and method for three dimensional world modeling using the same | |
| CN110517216A (en) | A kind of SLAM fusion method and its system based on polymorphic type camera | |
| CN206990800U (en) | A kind of alignment system | |
| CN109521398A (en) | A kind of positioning system and localization method based on multi-vision visual | |
| WO2021036587A1 (en) | Positioning method and system for electric power patrol scenario | |
| WO2022000713A1 (en) | Augmented reality self-positioning method based on aviation assembly | |
| CN109387194A (en) | A kind of method for positioning mobile robot and positioning system | |
| KR20120099952A (en) | Sensor system, and system and method for preparing environment map using the same | |
| CN111242994A (en) | Semantic map construction method and device, robot and storage medium | |
| CN112212784B (en) | Method and system for fusing coordinates of point laser displacement sensor and binocular camera | |
| CN109407115A (en) | A kind of road surface extraction system and its extracting method based on laser radar | |
| CN105929820A (en) | Intelligent robot positioning method | |
| CN114800524B (en) | System and method for actively preventing collision of man-machine interaction cooperative robot | |
| CN208999804U (en) | A kind of high-precision intelligent equipment based on multi-vision visual positioning system | |
| CN112050814A (en) | Unmanned aerial vehicle visual navigation system and method for indoor transformer substation | |
| CN116907469A (en) | Synchronous positioning and mapping method and system for multi-mode data combined optimization | |
| Maxim et al. | UAV Guidance with robotic total station for architectural fabrication processes | |
| Little et al. | Selecting stable image features for robot localization using stereo | |
| CN112556695A (en) | Indoor positioning and three-dimensional modeling method and system, electronic equipment and storage medium | |
| Jingjing et al. | Research on autonomous positioning method of UAV based on binocular vision |
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: 20190326 |