CN108814912A - A kind of intelligent barrier avoiding system based on multi-vision visual measurement - Google Patents
A kind of intelligent barrier avoiding system based on multi-vision visual measurement Download PDFInfo
- Publication number
- CN108814912A CN108814912A CN201810369198.9A CN201810369198A CN108814912A CN 108814912 A CN108814912 A CN 108814912A CN 201810369198 A CN201810369198 A CN 201810369198A CN 108814912 A CN108814912 A CN 108814912A
- Authority
- CN
- China
- Prior art keywords
- module
- photographing module
- photographing
- visual
- distance
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H3/00—Appliances for aiding patients or disabled persons to walk about
- A61H3/06—Walking aids for blind persons
- A61H3/061—Walking aids for blind persons with electronic detecting or guiding means
Landscapes
- Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Pain & Pain Management (AREA)
- Physical Education & Sports Medicine (AREA)
- Rehabilitation Therapy (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of intelligent barrier avoiding systems based on multi-vision visual measurement, including:First photographing module, second photographing module, third photographing module, processing module, processing module is separately connected the first photographing module, second photographing module and third photographing module, first photographing module, second photographing module, third photographing module shoots Front image from different perspectives respectively, first photographing module, second photographing module and third photographing module separately include two photographic devices, the corresponding photographic device of same photographing module corresponds to the visual pattern of shooting angle according to the binocular vision theoretical modeling photographing module, processing module is by the first photographing module, the visual pattern of second photographing module and third photographing module, which combines, generates final three-dimensional image, processing module determines barrier according to final three stereo-pictures and generates best avoidance route.
Description
Technical field
The present invention relates to obstacle avoidance system more particularly to a kind of intelligent barrier avoiding systems based on multi-vision visual measurement.
Background technique
With the progress of social civilization, the life matter of the disadvantaged group such as the elderly and physical disabilities is ensured and improved
Amount has increasingly received the concern of society.A large number of studies show that the ability to act of effectively enhancing the elderly and physical disabilities,
Their daily life is not only made to become convenient, but also the mental health to them, self-assessment, the state of mind also have depth
Remote influence.Therefore, one kind providing wheelchair of easily riding instead of walk for above-mentioned crowd and comes into being.Traditional wheelchair be manually, by
People rotates handwheel and advances, this needs to expend a large amount of physical strength, is not suitable for the elderly and physical disabilities use.Nowadays there is Electric Motor Wheel
Chair, this electric wheelchair generally comprise car body, and front and back wheel, driving motor, control stick and motor driver, driving motor is by electric power storage
Pond power supply, driving rear-wheel advance, and the people being sitting on wheelchair only needs thumb-operated control stick, can be realized the advance of wheelchair, retreat with
And turning.For some self-care abilities are not good people, their the bad operations of general electric wheelchair;And for one
For the people or some the elderlys to go out once in a while that fracture a bit, this wheelchair is just at a kind of additional expense.In addition, for
Physical disabilities often cause traveling process to become difficult during action tool is advanced because encountering barrier, because
This, needs to develop a kind of intelligent barrier avoiding system that can be implanted into all kinds of mobile tools.
Summary of the invention
Goal of the invention:
Need to develop it is a kind of can be implanted into the intelligent barrier avoiding system of all kinds of mobile tools aiming at the problem that, the present invention provides a kind of base
In the intelligent barrier avoiding system of multi-vision visual measurement.
Technical solution:
A kind of intelligent barrier avoiding system based on multi-vision visual measurement, including:First photographing module, the second photographing module, third are taken the photograph
As module, processing module, the processing module is separately connected first photographing module, the second photographing module and third camera shooting
Module, first photographing module, the second photographing module, third photographing module shoot Front image from different perspectives respectively, institute
It states the first photographing module, the second photographing module and third photographing module and separately includes two photographic devices, same photographing module
Corresponding photographic device corresponds to the visual pattern of shooting angle, the processing mould according to the binocular vision theoretical modeling photographing module
Block, which combines the visual pattern of first photographing module, the second photographing module and third photographing module, generates finally three-dimensional stand
Body image, the processing module determine barrier according to final three stereo-pictures and generate best avoidance route.
As a kind of preferred embodiment of the invention, the processing module includes node acquisition submodule, combination submodule, institute
It states processing module and is also used to confirm reference mode, the node acquisition submodule is used to be based on first photographing module, second
Photographing module and third photographing module carry out the selection of reference mode respectively, and the submodule that combines is according to the reference node of selection
The visual pattern that first photographing module, the second photographing module and third photographing module are shot is combined into final three-dimensional by point
Stereo-picture.
It further include Angle Measurement Module as a kind of preferred embodiment of the invention, the Angle Measurement Module is used for basis
Different photographing modules is corresponded on the same visual node carries out photographing module in the survey of the visual node photographs angle
Amount.
It further include the first computing module as a kind of preferred embodiment of the invention, first computing module is used for basis
Distance in shooting angle and the visual node on the visual node between corresponding photographing module calculates the visual node
Corresponding linear distance, the linear distance are the distance apart from barrier.
It further include the second computing module as a kind of preferred embodiment of the invention, second computing module is used for basis
Each photographing module carries out the calculating of distalmost end distance and most proximal end distance to the boundary position that barrier is shot.
Further include drive module as a kind of preferred embodiment of the invention, be provided with pre-determined distance in the processing module,
When the processing module judges the linear distance no more than the pre-determined distance, the processing module sends out the drive module
Commutation instruction, the drive module commutate out.
As a kind of preferred embodiment of the invention, the processing module is also by the linear distance and the most proximal end distance
It is compared, if judging, the linear distance is less than the most proximal end distance, and the processing module judgement terminates avoidance, the place
It manages module and issues release command to the drive module, traffic direction is become again original traffic direction by the drive module.
The present invention realizes following beneficial effect:
Three-dimensional live is handled using the technology that multi-vision visual measures, the visual angle for simulating user of high degree, and root
The judgement and the judgement of best steering direction of obstacle distance are carried out, according to the method for data analysis convenient for making most effective avoidance
Judgement.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and consistent with the instructions for explaining the principles of this disclosure.
Fig. 1 is system module frame diagram.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.
Embodiment one:
It is Fig. 1 with reference to figure.A kind of intelligent barrier avoiding system based on multi-vision visual measurement, including:First photographing module 1, second are taken the photograph
As module 2, third photographing module 3, processing module 4, the processing module 4 is separately connected first photographing module 1, second takes the photograph
As module 2 and third photographing module 3, first photographing module 1, the second photographing module 2, third photographing module 3 respectively from
Different angle shoots Front image, and first photographing module 1, the second photographing module 2 and third photographing module 3 separately include
Two photographic devices, the corresponding photographic device of same photographing module are shot according to the binocular vision theoretical modeling photographing module is corresponding
The visual pattern of angle, the processing module 4 is by first photographing module 1, the second photographing module 2 and third photographing module
3 visual pattern, which combines, generates final three-dimensional image, and the processing module 4 is determined according to final three stereo-pictures
Barrier simultaneously generates best avoidance route.
As a kind of preferred embodiment of the invention, the processing module 4 includes node acquisition submodule 41, combination submodule
42, the processing module 4 is also used to confirm reference mode, and the node acquisition submodule 41 is used for based on the first camera shooting mould
Block 1, the second photographing module 2 and third photographing module 3 carry out the selection of reference mode, 42 basis of combination submodule respectively
The vision figure that the reference mode of selection shoots first photographing module 1, the second photographing module 2 and third photographing module 3
As being combined into final three-dimensional image.
It further include Angle Measurement Module 5 as a kind of preferred embodiment of the invention, the Angle Measurement Module 5 is used for root
Photographing module is carried out in the visual node photographs angle according to different photographing modules is corresponded on the same visual node
Measurement.
It further include the first computing module 6 as a kind of preferred embodiment of the invention, first computing module 6 is used for root
According on the visual node shooting angle and the visual node on distance between corresponding photographing module calculate the vision section
The corresponding linear distance of point, the linear distance are the distance apart from barrier.
It further include the second computing module 7 as a kind of preferred embodiment of the invention, second computing module 7 is used for root
The calculating of distalmost end distance and most proximal end distance is carried out to the boundary position that barrier is shot according to each photographing module.
Further include drive module 8 as a kind of preferred embodiment of the invention, be provided in the processing module 4 it is default away from
From when the processing module 4 judges the linear distance no more than the pre-determined distance, the processing module 4 is to the driving
Module 8 issues commutation instruction, and the drive module 8 commutates.
As a kind of preferred embodiment of the invention, the processing module 4 also by the linear distance and the most proximal end away from
From being compared, if judging, the linear distance is less than the most proximal end distance, and the judgement of processing module 4 terminates avoidance, institute
It states processing module 4 and issues release command to the drive module 8, traffic direction is become again original operation by the drive module 8
Direction.
In the specific implementation process, the first photographing module 1, the second photographing module 2, third photographing module 3 are respectively with difference
Angle shot Front image, complete shooting after, processing module 4 selects several reference modes in the second photographing module 2, place
Reference mode is projected position corresponding with the first photographing module 1 and third photographing module 3 by reason module 4 respectively, and same
The image for shooting the first photographing module 1, the second photographing module 2 and third photographing module 3 in spatial dimension is with reference mode
The mode of coincidence carries out the overlapping of image, and in overlay process, the first photographing module 1, the second photographing module 2, third image mould
Block 3 keeps respective shooting angle respectively to finally synthesize three-dimensional image.For image overlap, the second photographing module 2
Shooting angle be 90 °, 1 shooting angle of the first photographing module is equal with the sine value of 3 shooting angle of third photographing module, with seat
For the process that target form is overlapped, it is assumed that A point serving as reference point is selected in the image of the second photographing module 2 shooting, it is right
Remained unchanged in the ordinate of each photographing module, A point, the abscissa of A point in the image that the first photographing module 1 is shot and
All take abscissa to the cosecant value of shooting angle in the image that third photographing module 3 is shot, thus by the first photographing module 1 or the
Coordinate value in the image of three photographing modules 3 shooting becomes the coordinate value in the image of the second photographing module 2 shooting, processing module
4 carry out the overlapping of image according to the coordinate value of each photographing module, are combined into final three-dimensional image.Due to angle measurement mould
First photographing module 1 and the second photographing module 2, the second photographing module 2 are imaged mould with third photographing module 3 and first by block 5
Block 1 is finished with shooting angle measurement of the third photographing module 3 on the same visual node, therefore, known multiple angles with
And in the case where being spaced between each photographing module, the visual node is calculated by the cosine law in the first computing module 6
Linear distance, the distance of same plane of the linear distance where each photographing module to the visual node, therefore, the straight line
Distance i.e. obstacle distance.For each photographing module, there is the maximum region in shooting, processing module 4 is in the maximum region
The middle visual node for extracting most boundary, the second computing module 7 calculate separately each photographing module to most boundary visual node away from
From, and respectively to each photographing module mark distalmost end distance and most proximal end distance, be provided in processing module 4 it is default away from
From when processing module 4 judges linear distance no more than pre-determined distance, processing module 4 issues commutation instruction to drive module 8, drives
Dynamic model block 8 commutates, and linear distance is also compared by processing module 4 with most proximal end distance, if judging, linear distance is less than
Most proximal end distance, the judgement of processing module 4 terminate avoidance, and processing module 4 issues release command to drive module 8, and drive module 8 will
Traffic direction becomes original traffic direction again.
The above embodiments merely illustrate the technical concept and features of the present invention, and the purpose is to allow the skill for being familiar with the technical field
Art personnel can understand the content of the present invention and implement it accordingly, and can not be limited the scope of the invention with this.All bases
Equivalent changes or modifications made by spirit of the invention, should be covered by the protection scope of the present invention.
Claims (7)
1. a kind of intelligent barrier avoiding system based on multi-vision visual measurement, including:First photographing module, the second photographing module, third
Photographing module, processing module, the processing module are separately connected first photographing module, the second photographing module and third and take the photograph
As module, first photographing module, the second photographing module, third photographing module shoot Front image from different perspectives respectively,
It is characterized in that:First photographing module, the second photographing module and third photographing module separately include two photographic devices,
The corresponding photographic device of same photographing module corresponds to the vision figure of shooting angle according to the binocular vision theoretical modeling photographing module
Picture, the processing module combine the visual pattern of first photographing module, the second photographing module and third photographing module
Final three-dimensional image is generated, the processing module determines barrier according to final three stereo-pictures and generates best
Avoidance route.
2. a kind of intelligent barrier avoiding system based on multi-vision visual measurement according to claim 1, it is characterised in that:The place
Reason module includes node acquisition submodule, combination submodule, and the processing module is also used to confirm that reference mode, the node obtain
Take submodule for carrying out reference mode respectively based on first photographing module, the second photographing module and third photographing module
Selection, the combination submodule is according to the reference mode of selection by first photographing module, the second photographing module and the
The visual pattern of three photographing modules shooting is combined into final three-dimensional image.
3. a kind of intelligent barrier avoiding system based on multi-vision visual measurement according to claim 2, it is characterised in that:Further include
Angle Measurement Module, the Angle Measurement Module are used for basis and correspond to different photographing module progress on the same visual node
Measurement of the photographing module in the visual node photographs angle.
4. a kind of intelligent barrier avoiding system based on multi-vision visual measurement according to claim 3, it is characterised in that:Further include
First computing module, first computing module are used for according to the shooting angle and the visual node on the visual node
Distance between corresponding photographing module calculates the corresponding linear distance of the visual node, and the linear distance is i.e. apart from barrier
Distance.
5. a kind of intelligent barrier avoiding system based on multi-vision visual measurement according to claim 4, it is characterised in that:Further include
Second computing module, second computing module are used to carry out most the boundary position that barrier is shot according to each photographing module
The calculating of distal end distance and most proximal end distance.
6. a kind of intelligent barrier avoiding system based on multi-vision visual measurement according to claim 5, it is characterised in that:Further include
Drive module, pre-determined distance is provided in the processing module, and the processing module judges the linear distance no more than described
When pre-determined distance, the processing module issues commutation instruction to the drive module, and the drive module commutates.
7. a kind of intelligent barrier avoiding system based on multi-vision visual measurement according to claim 6, it is characterised in that:The place
The linear distance is also compared by reason module with the most proximal end distance, if it is described nearest to judge that the linear distance is less than
Distance is held, the processing module judgement terminates avoidance, and the processing module issues release command, the drive to the drive module
Traffic direction is become again original traffic direction by dynamic model block.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810369198.9A CN108814912B (en) | 2018-04-23 | 2018-04-23 | Intelligent obstacle avoidance system based on multi-view vision measurement |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810369198.9A CN108814912B (en) | 2018-04-23 | 2018-04-23 | Intelligent obstacle avoidance system based on multi-view vision measurement |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108814912A true CN108814912A (en) | 2018-11-16 |
CN108814912B CN108814912B (en) | 2021-04-09 |
Family
ID=64154634
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810369198.9A Active CN108814912B (en) | 2018-04-23 | 2018-04-23 | Intelligent obstacle avoidance system based on multi-view vision measurement |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108814912B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109730910A (en) * | 2018-11-30 | 2019-05-10 | 深圳市智瞻科技有限公司 | Vision-aided system and its ancillary equipment, method, the readable storage medium storing program for executing of trip |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105005999A (en) * | 2015-08-12 | 2015-10-28 | 北京航空航天大学 | Obstacle detection method for blind guiding instrument based on computer stereo vision |
JP2016067855A (en) * | 2014-09-22 | 2016-05-09 | 達鋭 橋本 | Walking guide device for sight disabled person |
CN105761242A (en) * | 2016-01-27 | 2016-07-13 | 北京航空航天大学 | Blind person walking positioning method based on computer binocular vision and inertial measurement |
CN105787447A (en) * | 2016-02-26 | 2016-07-20 | 深圳市道通智能航空技术有限公司 | Method and system of unmanned plane omnibearing obstacle avoidance based on binocular vision |
CN106214437A (en) * | 2016-07-22 | 2016-12-14 | 杭州视氪科技有限公司 | A kind of intelligent blind auxiliary eyeglasses |
CN107684493A (en) * | 2017-10-17 | 2018-02-13 | 苏州诚满信息技术有限公司 | A kind of cloud for wheelchair simulates intelligent barrier avoiding system |
-
2018
- 2018-04-23 CN CN201810369198.9A patent/CN108814912B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016067855A (en) * | 2014-09-22 | 2016-05-09 | 達鋭 橋本 | Walking guide device for sight disabled person |
CN105005999A (en) * | 2015-08-12 | 2015-10-28 | 北京航空航天大学 | Obstacle detection method for blind guiding instrument based on computer stereo vision |
CN105761242A (en) * | 2016-01-27 | 2016-07-13 | 北京航空航天大学 | Blind person walking positioning method based on computer binocular vision and inertial measurement |
CN105787447A (en) * | 2016-02-26 | 2016-07-20 | 深圳市道通智能航空技术有限公司 | Method and system of unmanned plane omnibearing obstacle avoidance based on binocular vision |
CN106214437A (en) * | 2016-07-22 | 2016-12-14 | 杭州视氪科技有限公司 | A kind of intelligent blind auxiliary eyeglasses |
CN107684493A (en) * | 2017-10-17 | 2018-02-13 | 苏州诚满信息技术有限公司 | A kind of cloud for wheelchair simulates intelligent barrier avoiding system |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109730910A (en) * | 2018-11-30 | 2019-05-10 | 深圳市智瞻科技有限公司 | Vision-aided system and its ancillary equipment, method, the readable storage medium storing program for executing of trip |
Also Published As
Publication number | Publication date |
---|---|
CN108814912B (en) | 2021-04-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8971597B2 (en) | Efficient vision and kinematic data fusion for robotic surgical instruments and other applications | |
US11806102B2 (en) | Providing information of tools by filtering image areas adjacent to or on displayed images of the tools | |
US20240016556A1 (en) | Estimation of a position and orientation of a frame used in controlling movement of a tool | |
EP2977844B1 (en) | Method for cleaning or processing a room using an automatically moved device | |
CN104680582B (en) | A kind of three-dimensional (3 D) manikin creation method of object-oriented customization | |
CN103810685B (en) | A kind of super-resolution processing method of depth map | |
CN101384402B (en) | Mobile robot | |
US6891518B2 (en) | Augmented reality visualization device | |
CN106327587A (en) | Laparoscope video precision fusion method for enhancing real surgical navigation | |
CN109333506A (en) | A kind of humanoid intelligent robot system | |
CN112263332B (en) | System, method, medium, and terminal for adjusting surgical robot | |
CN106846417A (en) | The monocular infrared video three-dimensional rebuilding method of view-based access control model odometer | |
WO2015110859A1 (en) | Method for implant surgery using augmented visualization | |
CN103209656A (en) | Visualization of registered subsurface anatomy reference to related applications | |
EP1394743A3 (en) | Device for detecting position/orientation of object from stereo images | |
WO2023071834A1 (en) | Alignment method and alignment apparatus for display device, and vehicle-mounted display system | |
JP7375456B2 (en) | Toe position estimation device and fingertip position estimation device | |
CN105843166B (en) | A kind of special type multiple degrees of freedom automatic butt jointing device and its working method | |
CN103743394A (en) | Light-stream-based obstacle avoiding method of mobile robot | |
CN108814912A (en) | A kind of intelligent barrier avoiding system based on multi-vision visual measurement | |
CN109724537A (en) | A kind of binocular three-dimensional imaging method and system | |
Noonan et al. | The design and initial calibration of an optical tracking system using the microsoft kinect | |
CN110192224A (en) | Device for estimating state of driver and estimating state of driver method | |
CN101849849B (en) | Device for intellectualized monitoring of surgical grinding tool | |
US20190060013A1 (en) | Method and apparatus to project light pattern to determine distance in a surgical scene |
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: 20210323 Address after: No.120 liangle Road, Gujian village committee, Daliang sub district office, Shunde District, Foshan City, Guangdong Province, 528399 Applicant after: Foshan Linfu Machinery Manufacturing Co.,Ltd. Address before: Room 17, No. 93, Shanan East Road, Shaxi Town, Taicang City, Suzhou City, Jiangsu Province Applicant before: SUZHOU DENGYANG INFORMATION TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |