CN106197452A - A kind of visual pattern processing equipment and system - Google Patents
A kind of visual pattern processing equipment and system Download PDFInfo
- Publication number
- CN106197452A CN106197452A CN201610581601.5A CN201610581601A CN106197452A CN 106197452 A CN106197452 A CN 106197452A CN 201610581601 A CN201610581601 A CN 201610581601A CN 106197452 A CN106197452 A CN 106197452A
- Authority
- CN
- China
- Prior art keywords
- view data
- information
- visual
- threedimensional model
- processing equipment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/3415—Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
-
- 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
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3605—Destination input or retrieval
- G01C21/3608—Destination input or retrieval using speech input, e.g. using speech recognition
-
- 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
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3626—Details of the output of route guidance instructions
- G01C21/3629—Guidance using speech or audio output, e.g. text-to-speech
-
- 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
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/02—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems using reflection of acoustic waves
- G01S15/06—Systems determining the position data of a target
- G01S15/08—Systems for measuring distance only
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention provides a kind of visual pattern processing equipment and system, including: multidimensional image harvester, dynamic continuous print view data in being used for obtaining its visual range, all of view data is all preset frame rate with first and sends to front-end image processing means;Front-end image processing means, is used for receiving above-mentioned dynamic continuous print view data, carries out three-dimensional modeling process according to above-mentioned view data, obtains threedimensional model, and obtains the spatial positional information that view data is corresponding from threedimensional model;It can obtain visual image information in real time and carry out real-time signal analysis in front end, thus realize real-time acquisition three dimensional local information model, obtain the information such as such as three-dimensional point cloud atlas, distance, directional image segmentation result, and obtain obstacle information accordingly, lay equal stress on new planning guidance path, to implement avoidance;Further, without requiring transmission speed in above-mentioned front-end processing, it is possible to ensure integrity and the accuracy of data, also make real-time preferable simultaneously.
Description
Technical field
The present invention relates to technical field of image processing, in particular to a kind of visual pattern processing equipment and system.
Background technology
In recent years, artificial intelligence is widely used to the fields such as industry, security protection, traffic, household and wearable device, makes people
The life of class there occurs earth-shaking change, such as unmanned plane, robot.Along with the raising of Intellectual Analysis Technology, equally to ring
Border cognition technology is had higher requirement.The same with the mankind, from the point of view of vision is for machine, also it is most important aware space ring
Border, the channel of acquisition information.Therefore, current intelligent machine is provided with visual information acquisition system, for aware space
Environment also carries out acquisition of information.
At present, the visual information acquisition system on intelligent machine is all dependent on back-end processing, is i.e. gathered by visual information
System senses spatial environments also carries out acquisition of information, the long-range the control then information obtained sent to intelligent robot rear end
End processed, is analyzed, to obtain information needed the above-mentioned information obtained by rear end remote control terminal.At present, visual information is adopted
The front end processing techniques of collecting system, due to the limitation of disposal ability, analysis method etc., there is presently no and is used widely.
Inventor finds under study for action, and visual information acquisition system of the prior art must be based on rear end remote control terminal
The information obtained is processed, and background process has higher requirements for information transfer rate, otherwise arise that information lacks
The problems such as mistake, time delay, transmission distortion.
Summary of the invention
In view of this, the purpose of the embodiment of the present invention is to provide a kind of visual pattern processing equipment and system, it is possible to
Front end is to obtaining visual image information and processing, it is not necessary to require transmission speed, it is possible to ensure that the integrity of data is with accurate
Property, also make real-time preferable simultaneously.
First aspect, embodiments provides a kind of visual pattern processing equipment, it is characterised in that including: multidimensional
Image collecting device and front-end image processing means;
Described multidimensional image harvester, dynamic continuous print view data in being used for obtaining its visual range, by all of
View data is all preset frame rate with first and is sent to front-end image processing means;
Described front-end image processing means, is used for receiving described dynamic continuous print view data, to described dynamic continuous print
View data carries out three-dimensional modeling process, obtains threedimensional model, and it is corresponding to obtain described view data from described threedimensional model
Spatial positional information.
In conjunction with first aspect, embodiments provide the first possible embodiment of first aspect, wherein, institute
The visual pattern processing equipment stated, also includes high accuracy assistant images harvester;
Described high accuracy assistant images harvester, for gathering the high accuracy video image number in described visual range
According to, described high accuracy vedio data is preset frame rate with second and sends to described front-end image processing means;
Described front-end image processing means is additionally operable to, and receives described high accuracy vedio data, according to described high accuracy
Vedio data carries out calibration process to described threedimensional model, the threedimensional model after being calibrated, and after described calibration
Threedimensional model obtains the spatial positional information that described view data is corresponding.
In conjunction with the first possible embodiment of first aspect, embodiments provide the second of first aspect
Possible embodiment, wherein, described multidimensional image harvester includes monocular camera lens;
Described monocular camera lens, dynamic continuous print view data in being used for gathering its visual range, by all of view data
All preset frame rate with first to send to front-end image processing means.
In conjunction with the first possible embodiment of first aspect, embodiments provide the third of first aspect
Possible embodiment, wherein, described multidimensional image harvester includes binocular head;Described binocular head includes: first group
Gather camera lens and second group of collection camera lens;
Described first group of collection camera lens and described second group of collection camera lens are used to, and dynamically connect in gathering respective visual range
Continuous view data, all presets frame rate with first by all of view data and sends to front-end image processing means.
In conjunction with the embodiment that the second of first aspect is possible, or the third possible embodiment party of first aspect
Formula, embodiments provides the 4th kind of possible embodiment of first aspect, wherein, described front-end image processing means
Including: control device and special visual processing apparatus;
Described control device, for controlling the algorithm in described special visual processing apparatus processing procedure, and with described
The result that algorithm is corresponding;
Described special visual processing apparatus, under the control of described control device, receives described dynamic continuous print figure
As data, described dynamic continuous print view data is carried out three-dimensional modeling process, obtains threedimensional model, and from described threedimensional model
The spatial positional information that the described view data of middle acquisition is corresponding;And/or, receive described high accuracy vedio data, according to institute
State high accuracy vedio data and described threedimensional model is carried out calibration process, the threedimensional model after being calibrated, and from described
Threedimensional model after calibration obtains the spatial positional information that described view data is corresponding.
In conjunction with the 4th kind of possible embodiment of first aspect, embodiments provide the 5th kind of first aspect
Possible embodiment, wherein, described front-end image processing means also includes memorizer;
Described control device is additionally operable to, and controls the data stream of described memorizer storage and corresponding data flow circuit;
Described memorizer, under the control of described control device, stores what described multidimensional image harvester sent
Dynamically continuous print view data, and/or, high accuracy vedio data that described high accuracy assistant images harvester sends,
Described threedimensional model, and/or, threedimensional model after described calibration and spatial positional information corresponding to described view data.
In conjunction with the 5th kind of possible embodiment of first aspect, embodiments provide the 6th kind of first aspect
Possible embodiment, wherein, described special visual processing apparatus includes: supersonic detector and use processing device;
Described supersonic detector, for detecting the range information of described barrier, described in described distance information transmission
Use processing device;
According to described video image and described range information, described use processing device, for determining that described barrier is believed
Breath, and export described obstacle information.
In conjunction with the 6th kind of possible embodiment of first aspect, embodiments provide the 7th kind of first aspect
Possible embodiment, wherein, described first group of collection camera lens and described second group of collection camera lens all include a monocular camera lens
Or multiple monocular camera lens;Described high accuracy assistant images harvester includes photographic head.
In conjunction with the 7th kind of possible embodiment of first aspect, embodiments provide the 8th kind of first aspect
Possible embodiment, wherein, described front-end image processing means also includes: speech recognition synthesizer and path planning subsystem
System;
Described speech recognition synthesizer, for receiving the voice messaging that user sends, knows described voice messaging
Other places are managed, and obtain the destination address of correspondence;And, according to described destination address and described obstacle information, synthesis and described mesh
Suggestion voice corresponding to address, export described suggestion voice to point out;
Described path planning subsystem, for being adjusted or weight original guidance path according to described obstacle information
Newly-generated guidance path.
Second aspect, the embodiment of the present invention additionally provides a kind of visual pattern processing system, including: including: aforesaid right
Require the visual pattern processing equipment described in any one of first aspect;Also include: intelligent machine and remote control terminal;
Described visual pattern processing equipment embeds in described intelligent machine, detects described intelligent machine front in real time
Obstacle information, and described obstacle information is sent to described remote control terminal;
Described remote control terminal, is used for receiving described obstacle information, monitors described in real time according to described obstacle information
The walking states of intelligent machine, and under the control of staff, the control that the walking states of described intelligent machine is mated
System.
A kind of visual pattern processing equipment that the embodiment of the present invention provides and system, including: multidimensional image harvester and
Front-end image processing means;Multidimensional image harvester, is used for obtaining dynamic continuous print view data in it takes visual range, by institute
Some view data are all preset frame rate with first and are sent to front-end image processing means;Front-end image processing means, is used for connecing
Receive dynamic continuous print view data and carry out three-dimensional modeling process, obtaining threedimensional model, and from threedimensional model, obtain picture number
According to corresponding spatial positional information;With background process of the prior art, information transfer rate is had higher requirements, the most just
There will be the problems such as loss of learning, time delay, transmission distortion to compare, it can obtain visual image information in real time in front end, and right
This visual image information carries out real-time signal analysis, thus realizes real-time acquisition three dimensional local information model, obtains such as three
The information such as dimension point cloud chart, distance, directional image segmentation result, and obtain obstacle information accordingly, to implement avoidance;Further, on
State in front-end processing without requiring transmission speed, it is possible to ensure integrity and the accuracy of data, also make real-time relatively simultaneously
Good.
For making the above-mentioned purpose of the present invention, feature and advantage to become apparent, preferred embodiment cited below particularly, and coordinate
Appended accompanying drawing, is described in detail below.
Accompanying drawing explanation
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, below by embodiment required use attached
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, and it is right to be therefore not construed as
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to according to this
A little accompanying drawings obtain other relevant accompanying drawings.
Fig. 1 shows the structural representation of a kind of visual pattern processing equipment that the embodiment of the present invention provided;
Fig. 2 shows the structural representation of the another kind of visual pattern processing equipment that the embodiment of the present invention provided;
Fig. 3 shows special visual processing apparatus in a kind of visual pattern processing equipment that the embodiment of the present invention is provided
Structural representation;
Fig. 4 shows front-end image processing means in a kind of visual pattern processing equipment that the embodiment of the present invention is provided
Structural representation;
Fig. 5 shows the structural representation of a kind of visual pattern processing system that the embodiment of the present invention provided.
Major Symbol explanation;
1, visual pattern processing equipment;2, intelligent machine;3, remote control terminal;10, multidimensional image harvester;20, front
End image processing apparatus;30, assistant images harvester in high precision;101, first group gathers camera lens;102, second group gathers mirror
Head;201, device is controlled;202, special visual processing apparatus;203, memorizer;204, speech recognition synthesizer;205, path
Planning subsystem.
Detailed description of the invention
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with the embodiment of the present invention
Middle accompanying drawing, is clearly and completely described the technical scheme in the embodiment of the present invention, it is clear that described embodiment is only
It is a part of embodiment of the present invention rather than whole embodiments.Generally real with the present invention illustrated described in accompanying drawing herein
The assembly executing example can be arranged with various different configurations and design.Therefore, below to the present invention's provided in the accompanying drawings
The detailed description of embodiment is not intended to limit the scope of claimed invention, but is merely representative of the selected reality of the present invention
Execute example.Based on embodiments of the invention, the institute that those skilled in the art are obtained on the premise of not making creative work
There are other embodiments, broadly fall into the scope of protection of the invention.
Rear end remote control terminal (i.e. back-end services is must be based in view of visual information acquisition system of the prior art
Device) information obtained is processed, and background process has higher requirements for information transfer rate, otherwise arises that information
The problems such as disappearance, time delay, transmission distortion.Based on this, embodiments provide a kind of visual pattern processing equipment and system,
It is described by embodiment below in conjunction with Fig. 1, Fig. 2, Fig. 3, Fig. 4 and Fig. 5.
With reference to Fig. 1, embodiments provide a kind of visual pattern processing equipment, including: multidimensional image harvester
10 and front-end image processing means 20;
Multidimensional image harvester 10, dynamic continuous print view data in being used for obtaining its visual range, by all of figure
All preset frame rate with first as data to send to front-end image processing means 20;
Front-end image processing means 20, is used for receiving above-mentioned dynamic continuous print view data, to dynamic continuous print picture number
According to carrying out three-dimensional modeling process, obtain threedimensional model, and from threedimensional model, obtain the spatial positional information that view data is corresponding.
Concrete, the visual pattern processing equipment that the embodiment of the present invention provides, as an entirety, is adopted including multidimensional image
Acquisition means 10 and these two parts of front-end image processing means 20, above-mentioned entirety can apply on intelligent machine, itself and intelligent machine
The connected mode of device is as follows: be provided with connecting-disconnecting interface on intelligent machine, and above-mentioned visual pattern processing equipment can be directly by upper
State connecting-disconnecting interface to access on above-mentioned intelligent machine;Or, above-mentioned visual pattern processing equipment is by data wire and intelligent machine
Connecting-disconnecting interface electrical connection;It is logical with the data of intelligent machine that above two mounting means all can realize visual pattern processing equipment
Letter, visual pattern processing equipment can gather the dynamic consecutive image data in visual range, carry out the data gathered simultaneously
Process, the spatial positional information corresponding to obtain view data.
Wherein, above-mentioned multidimensional image harvester 10 can be binocular head, and binocular head is to there being certain vision model
Enclosing, this binocular head can obtain dynamic continuous print view data, the image that then will get in the visual range of oneself
Data are all preset frame rate with first and are sent to front-end image processing means 20.Wherein, above-mentioned first preset frame rate can be pre-
First it is configured, as arranged 30 frames per second;Above-mentioned first setting presetting frame rate is not done concrete limit by the embodiment of the present invention
System.
Space can be carried out difference real-time image information collection, wherein, above-mentioned binocular head by above-mentioned binocular head
Including two groups of camera lenses, its each group of camera lens can use one or more photographic head to carry out video image acquisition.
And above-mentioned front-end image processing means 20 itself has data processing function, first it receive dynamic continuous print image
Data, then carry out three-dimensional modeling process according to all of view data received, and obtain corresponding dynamically continuous print picture number
According to threedimensional model;Then according to this threedimensional model set up, space bit confidence corresponding in view data can therefrom be obtained
Breath;Above-mentioned spatial positional information at least includes: the information such as relative position, direction and distance between three-dimensional point cloud atlas, object.
A kind of visual pattern processing equipment that the embodiment of the present invention provides, with background process of the prior art for information
Transmission speed has higher requirements, and otherwise arises that the problems such as loss of learning, time delay, transmission distortion are compared, and it can be in front end
Obtain visual image information in real time, and this visual image information is carried out real-time signal analysis, thus realize real-time acquisition three
Dimension positional information model, obtains the information such as such as three-dimensional point cloud atlas, distance, directional image segmentation result, and obtains obstacle accordingly
Thing information, to implement avoidance;Further, without requiring transmission speed in above-mentioned front-end processing, it is possible to ensure data integrity and
Accuracy, also makes real-time preferable simultaneously.
Unsharp part may be there is, to this, according to this in the image gathered in view of multidimensional image harvester 10
The threedimensional model that image is set up may position inaccurate, and to this, with reference to Fig. 1, the visual pattern of the embodiment of the present invention processes and sets
In Bei, also include high accuracy assistant images harvester 30;
Assistant images harvester 30 in high precision, for gathering the high accuracy vedio data in visual range, by height
Precision vedio data is preset frame rate with second and is sent to front-end image processing means 20;Wherein, second herein is preset
Frame rate with above-mentioned first preset frame rate can be identical, it is also possible to different;In the embodiment of the present invention, arrange above-mentioned second and preset
It is different that frame rate presets frame rate from above-mentioned first.
Front-end image processing means 20 is additionally operable to, and extracts second and presets the high accuracy vedio data in picture, according to
Vedio data carries out calibration process to threedimensional model in high precision, the threedimensional model after being calibrated, and three after calibration
Dimension module obtains the spatial positional information that view data is corresponding.
Concrete, by above-mentioned high accuracy assistant images harvester 30 Real-time Collection, cover multidimensional image harvester
The high accuracy vedio data of the visual range of 10;Front-end image processing means 20 is then according to above-mentioned high accuracy video image number
According to, the threedimensional model setting up the view data gathered according to multidimensional image harvester 10 carries out calibration process, the school obtained
Threedimensional model after standard;And the threedimensional model after calibrating more can accurately show in multidimensional image harvester 10 visual range
Overall space positional information.
In the embodiment of the present invention, above-mentioned high accuracy assistant images harvester 30 can be high accuracy photographic head, this shooting
Head can be with auto-focusing, and it is for by focusing parameter, to binocular difference image information, (i.e. multidimensional image harvester 10 gathers
High precision image data) process carry out correcting and supplementing, additionally can also to gather fine definition (the most high-precision for this system
Degree) video image or picture;Make up what multidimensional image harvester 10 gathered by the high precision image data gathered
The deficiency of view data, to set up threedimensional model more accurately.
Further, in above-mentioned visual pattern processing equipment, multidimensional image harvester includes monocular camera lens;Monocular instrumnent
Head, dynamic continuous print view data in being used for gathering its visual range, all of view data is all preset frame rate with first
Send to front-end image processing means.
Further, with reference to Fig. 2, in above-mentioned visual pattern processing equipment, multidimensional image harvester 10 includes binocular
Head;Binocular head includes: first group gathers camera lens 101 and second group of collection camera lens 102;
First group of collection camera lens 101 and second group of collection camera lens 102 are used to, the most continuous in gathering respective visual range
View data, by all of view data all with first preset frame rate send to front-end image processing means.
Concrete, two groups of collection camera lenses that above-mentioned binocular head includes are used to gather dynamically connecting in self visual range
Continuous view data, and preset frame frequency with first the view data of collection is sent successively to front-end image processing means 20.
Wherein, above-mentioned first group of collection camera lens 101 and second group of collection camera lens 102 all include a monocular camera lens or multiple
Monocular camera lens.
Further, with reference to Fig. 2, in above-mentioned visual pattern processing equipment, front-end image processing means 20 includes: control dress
Put 201 and special visual processing apparatus 202;
Control device 201, for the algorithm controlling in special visual processing apparatus 202 processing procedure, and with algorithm pair
The result answered;
Special visual processing apparatus 202, for, under the control controlling device 201, receiving dynamic continuous print view data,
Dynamic continuous print view data is carried out three-dimensional modeling process, obtains threedimensional model, and from threedimensional model, obtain view data
Corresponding spatial positional information;And/or, extract second and preset the high accuracy vedio data in picture, regard according to high accuracy
Frequently view data carries out calibration process to threedimensional model, the threedimensional model after being calibrated, and from the threedimensional model after calibration
Obtain the spatial positional information that view data is corresponding.
Concrete, in front-end image processing means 20, special visual processing apparatus 202 implement real computing
Journey, is controlled, by controlling device 201, algorithm and the corresponding operation result that special visual processing apparatus 202 is implemented.
Further, with reference to Fig. 2, in above-mentioned visual pattern processing equipment, front-end image processing means 20 also includes storage
Device 203;
Control device 201 to be additionally operable to, control the data stream of memorizer 203 storage and corresponding data flow circuit;
Memorizer 203, under the control controlling device 201, it is dynamic that storage multidimensional image harvester 10 sends
Continuous print view data, and/or, the high accuracy vedio data that assistant images harvester 30 sends in high precision, three-dimensional mould
Type, and/or, threedimensional model after calibration and spatial positional information corresponding to view data.
Concrete, in front-end image processing means 20, also include memorizer 203;The storage merit implemented by memorizer 203
Can, controlled, by controlling device 201, path and the data stream that memorizer 203 carries out storing.
Further, with reference to Fig. 3, in above-mentioned visual pattern processing equipment, special visual processing apparatus 202 includes: ultrasonic
Ripple detector 2021 and use processing device 2022;
Supersonic detector 2021, for detecting the range information of barrier, by distance information transmission use processing
Device;
Use processing device 2022, for determining obstacle information according to range information at information fusion, and exports barrier
Hinder thing information.
Further, with reference to Fig. 4, in above-mentioned visual pattern processing equipment, front-end image processing means 20 also includes: voice
Identify synthesizer 204 and path planning subsystem 205;
Speech recognition synthesizer 204, for receiving the voice messaging that user sends, is identified place to voice messaging
Reason, obtains the destination address of correspondence;And, according to destination address and obstacle information, synthesize the prompting corresponding with destination address
Voice, output suggestion voice is to point out;
Path planning subsystem 205, for being adjusted original guidance path according to obstacle information or again giving birth to
Become guidance path.
In the embodiment of the present invention, user directly can say this visual pattern by speech recognition synthesizer 204 and process
The destination address of its embedded intelligent machine 2 of equipment 1, i.e. sends to above-mentioned visual pattern processing equipment 1 and includes above-mentioned purpose
The voice messaging of address;Speech recognition synthesizer 204 then synthesizes corresponding destination address, and root according to the voice messaging of user
According to destination address and obstacle information, synthesize the suggestion voice corresponding with destination address, output suggestion voice to point out, than
As, prompting intelligent machine 2 carries out left-hand rotation etc..
Concrete, path planning subsystem 205 is for according to the obstacle information received, adjusting original guidance path
Whole or regenerate guidance path, carry out Real Time Obstacle Avoiding with the intelligent machine 2 realizing visual pattern processing equipment 1 is embedded.
A kind of visual pattern processing equipment that the embodiment of the present invention provides, with background process of the prior art for information
Transmission speed has higher requirements, and otherwise arises that the problems such as loss of learning, time delay, transmission distortion are compared, and it can be in front end
Obtain visual image information in real time, and this visual image information is carried out real-time signal analysis, thus realize real-time acquisition three
Dimension positional information model, obtains the information such as such as three-dimensional point cloud atlas, distance, directional image segmentation result, and obtains obstacle accordingly
Thing information, to implement avoidance;Further, without requiring transmission speed in above-mentioned front-end processing, it is possible to ensure data integrity and
Accuracy, also makes real-time preferable simultaneously.
Embodiments provide a kind of visual pattern processing system, with reference to Fig. 5, including: above-mentioned visual pattern processes
Equipment 1;Also include: intelligent machine 2 and remote control terminal 3;
Visual pattern processing equipment 1 embeds in intelligent machine 2, for the barrier letter in detection intelligent machine 2 front in real time
Breath, and obstacle information is sent to remote control terminal 3;
Remote control terminal 3, is used for receiving obstacle information, according to the walking of obstacle information real-time monitoring intelligent machine 2
State, and under the control of staff, the control that the walking states of intelligent machine 2 is mated.
Visual pattern processing equipment 1 in the embodiment of the present invention can be applied on intelligent machine 2, itself and intelligent machine 2
Connected mode as follows: being provided with connecting-disconnecting interface on intelligent machine 2, above-mentioned visual pattern processing equipment 1 can be directly by upper
State connecting-disconnecting interface to access on above-mentioned intelligent machine 2;Or, above-mentioned visual pattern processing equipment 1 is by data wire and intelligent machine 2
On connecting-disconnecting interface electrical connection;Above two mounting means all can realize the data of visual pattern processing equipment 1 and intelligent machine 2
Communication.
Above-mentioned visual pattern processing equipment 1 can gather the dynamic continuous print view data in self visual range, simultaneously
The above-mentioned dynamic continuous print view data gathered is carried out three-dimensional modeling process, obtains threedimensional model, then from threedimensional model
Obtain the spatial positional information that view data is corresponding, and obtain the barrier letter in this environment according to above-mentioned spatial positional information
Breath, finally can adjust the original walking path of intelligent machine 2 according to this obstacle information or again plan intelligent machine 2
Walking path, avoidance implemented by the intelligent machine 2 embedded to control visual pattern processing equipment 1;Wherein, above-mentioned spatial positional information
At least include: the information such as relative position, direction and distance between three-dimensional point cloud atlas, object.
Above-mentioned remote control terminal 3 is the back-end processing software in visual pattern processing system, can be server, and it receives
The spatial positional information that the visual pattern processing equipment 1 of front end sends, and it can also obtain according to the positional information in this space
Know the obstacle information affecting intelligent machine 2 walking, and the distance of the barrier in computational intelligence machine 2 relative dimensional model,
Then, plan the walking path of described intelligent machine 2 avoiding barrier according to the result calculated, then supervise according to this walking path
Whether survey visual pattern processing equipment 1 controls intelligent machine 2 is walked according to this walking path;Or, directly control intelligent machine 2
Walk according to above-mentioned calculated walking path, implement avoidance controlling intelligent machine 2.
Wherein, above-mentioned intelligent machine can be car, as a example by intelligent machine is as car, by above-mentioned visual pattern processing equipment 2
(hereinafter referred to as vision card) is loaded on the vehicle, and can realize data communication with car;Such as in a parking lot, by this
The visual pattern processing equipment that bright embodiment provides has carried out scan process to the vedio data in whole parking lot, and according to
Vedio data sets up threedimensional model, then the car being loaded with vision card just can be accurately positioned oneself in the threedimensional model set up
Location;Then, visual pattern processing equipment self with the obstacle information of monitoring car, and can plan the navigation of car accordingly
Path;Then, the obstacle information detected is sent to backstage by wireless communication module by visual pattern processing equipment in real time
Remote control terminal, by backstage remote control terminal according to the obstacle information received, calculates the car distance relative to peripheral obstacle, and
According to the travel route of the result planning car calculated, finally directly control car according to this traveling road with calculated travel route
Line travels, it is also possible to calculated travel route to visual pattern processing equipment implementing monitoring.
A kind of visual pattern processing system that the embodiment of the present invention provides, with background process of the prior art for information
Transmission speed has higher requirements, and otherwise arises that the problems such as loss of learning, time delay, transmission distortion are compared, and it can be by regarding
Feel that image processing equipment 1 obtains visual image information in real time in front end, and this visual image information carried out real-time signal analysis,
Thus realize real-time acquisition three dimensional local information model, obtain such as three-dimensional point cloud atlas, distance, directional image segmentation result etc.
Information, then the walking path of information planning intelligent machine 2 avoidance that rear end remote control terminal 3 obtains according to front end, finally controls
Intelligent machine 2 processed is according to the walking path walking of planning;Or, information planning intelligent machine 2 avoidance obtained according to front end
Walking path, and accordingly the controlled state of visual pattern processing equipment 1 is monitored;Further, in above-mentioned front-end processing without
Require transmission speed, it is possible to ensure integrity and the accuracy of data, also make real-time preferable simultaneously.
In embodiment provided by the present invention, it should be understood that disclosed equipment and system, can be by other side
Formula realizes.Device embodiment described above is only that schematically such as, the division of described unit, the most only one are patrolled
Volume function divides, and actual can have other dividing mode when realizing, the most such as, multiple unit or assembly can in conjunction with or can
To be integrated into another system, or some features can be ignored, or does not performs.Another point, shown or discussed each other
Coupling direct-coupling or communication connection can be the INDIRECT COUPLING by some communication interfaces, device or unit or communication link
Connect, can be electrical, machinery or other form.
The described unit illustrated as separating component can be or may not be physically separate, shows as unit
The parts shown can be or may not be physical location, i.e. may be located at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected according to the actual needs to realize the mesh of the present embodiment scheme
's.
It addition, each functional unit in the embodiment that the present invention provides can be integrated in a processing unit, it is possible to
Being that unit is individually physically present, it is also possible to two or more unit are integrated in a unit.
If described function is using the form realization of SFU software functional unit and as independent production marketing or use, permissible
It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is the most in other words
The part contributing prior art or the part of this technical scheme can embody with the form of software product, this meter
Calculation machine software product is stored in a storage medium, including some instructions with so that a computer equipment (can be individual
People's computer, remote control terminal, or the network equipment etc.) perform completely or partially walking of method described in each embodiment of the present invention
Suddenly.And aforesaid storage medium includes: USB flash disk, portable hard drive, read only memory (ROM, Read-Only Memory), deposit at random
The various media that can store program code such as access to memory (RAM, Random Access Memory), magnetic disc or CD.
It should also be noted that similar label and letter represent similar terms, therefore, the most a certain Xiang Yi in following accompanying drawing
Individual accompanying drawing is defined, then need not it be defined further and explains in accompanying drawing subsequently, additionally, term " the
One ", " second ", " the 3rd " etc. are only used for distinguishing and describe, and it is not intended that instruction or hint relative importance.
It is last it is noted that the detailed description of the invention of embodiment described above, the only present invention, in order to the present invention to be described
Technical scheme, be not intended to limit, protection scope of the present invention is not limited thereto, although with reference to previous embodiment to this
Bright it is described in detail, it will be understood by those within the art that: any those familiar with the art
In the technical scope that the invention discloses, the technical scheme described in previous embodiment still can be modified or can be light by it
It is readily conceivable that change, or wherein portion of techniques feature is carried out equivalent;And these are revised, change or replace, do not make
The essence of appropriate technical solution departs from the spirit and scope of embodiment of the present invention technical scheme.All should contain the protection in the present invention
Within the scope of.Therefore, protection scope of the present invention should be as the criterion with described scope of the claims.
Claims (10)
1. a visual pattern processing equipment, it is characterised in that including: multidimensional image harvester and front-end image process dress
Put;
Described multidimensional image harvester, dynamic continuous print view data in being used for obtaining its visual range, by all of image
Data are all preset frame rate with first and are sent to front-end image processing means;
Described front-end image processing means, is used for receiving described dynamic continuous print view data, to described dynamic continuous print image
Data carry out three-dimensional modeling process, obtain threedimensional model, and obtain the sky that described view data is corresponding from described threedimensional model
Between positional information.
Visual pattern processing equipment the most according to claim 1, it is characterised in that also include high accuracy assistant images collection
Device;
Described high accuracy assistant images harvester, for gathering the high accuracy vedio data in described visual range, will
Described high accuracy vedio data is preset frame rate with second and is sent to described front-end image processing means;
Described front-end image processing means is additionally operable to, and receives described high accuracy vedio data, according to described high accuracy video
View data carries out calibration process to described threedimensional model, the threedimensional model after being calibrated, and the three-dimensional after described calibration
Model obtains the spatial positional information that described view data is corresponding.
Visual pattern processing equipment the most according to claim 2, it is characterised in that described multidimensional image harvester includes
Monocular camera lens;
Described monocular camera lens, is used for gathering in its visual range dynamically continuous print view data, by all of view data all with
First presets frame rate sends to front-end image processing means.
Visual pattern processing equipment the most according to claim 2, it is characterised in that described multidimensional image harvester includes
Binocular head;Described binocular head includes: first group gathers camera lens and second group of collection camera lens;
Described first group of collection camera lens and described second group of collection camera lens are used to, dynamic continuous print in gathering respective visual range
View data, all presets frame rate with first by all of view data and sends to front-end image processing means.
5. according to the visual pattern processing equipment described in claim 3 or 4, it is characterised in that described front-end image processing means
Including: control device and special visual processing apparatus;
Described control device, for the algorithm controlling in described special visual processing apparatus processing procedure, and with described algorithm
Corresponding result;
Described special visual processing apparatus, under the control of described control device, receives described dynamic continuous print picture number
According to, described dynamic continuous print view data is carried out three-dimensional modeling process, obtains threedimensional model, and obtain from described threedimensional model
Take the spatial positional information that described view data is corresponding;And/or, receive described high accuracy vedio data, according to described height
Precision vedio data carries out calibration process to described threedimensional model, the threedimensional model after being calibrated, and from described calibration
After threedimensional model in obtain the spatial positional information that described view data is corresponding.
Visual pattern processing equipment the most according to claim 5, it is characterised in that described front-end image processing means is also wrapped
Include memorizer;
Described control device is additionally operable to, and controls the data stream of described memorizer storage and corresponding data flow circuit;
Described memorizer, under the control of described control device, stores the dynamic of described multidimensional image harvester transmission
Continuous print view data, and/or, the high accuracy vedio data, described that described high accuracy assistant images harvester sends
Threedimensional model, and/or, threedimensional model after described calibration and spatial positional information corresponding to described view data.
Visual pattern processing equipment the most according to claim 6, it is characterised in that described special visual processing apparatus bag
Include: supersonic detector and use processing device;
Described supersonic detector, for detecting the range information of described barrier, by information described in described distance information transmission
Fusion treatment device;
Described use processing device, for determining described obstacle information according to described video image and described range information,
And export described obstacle information.
Visual pattern processing equipment the most according to claim 7, it is characterised in that described first group gathers camera lens and described
Second group gathers camera lens and all includes a monocular camera lens or multiple monocular camera lens;Described high accuracy assistant images harvester includes
Photographic head.
Visual pattern processing equipment the most according to claim 8, it is characterised in that described front-end image processing means is also wrapped
Include: speech recognition synthesizer and path planning subsystem;
Described speech recognition synthesizer, for receiving the voice messaging that user sends, is identified place to described voice messaging
Reason, obtains the destination address of correspondence;And, according to described destination address and described obstacle information, synthesis and described destination
The suggestion voice that location is corresponding, exports described suggestion voice to point out;
Described path planning subsystem, for being adjusted original guidance path according to described obstacle information or again giving birth to
Become guidance path.
10. a visual pattern processing system, it is characterised in that including: the vision described in any one of the claims 1~9
Image processing equipment;Also include: intelligent machine and remote control terminal;
Described visual pattern processing equipment embeds in described intelligent machine, for the obstacle in the described intelligent machine front of detection in real time
Thing information, and described obstacle information is sent to described remote control terminal;
Described remote control terminal, is used for receiving described obstacle information, monitors described intelligence in real time according to described obstacle information
The walking states of machine, and under the control of staff, the control that the walking states of described intelligent machine is mated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610581601.5A CN106197452A (en) | 2016-07-21 | 2016-07-21 | A kind of visual pattern processing equipment and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610581601.5A CN106197452A (en) | 2016-07-21 | 2016-07-21 | A kind of visual pattern processing equipment and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106197452A true CN106197452A (en) | 2016-12-07 |
Family
ID=57492725
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610581601.5A Pending CN106197452A (en) | 2016-07-21 | 2016-07-21 | A kind of visual pattern processing equipment and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106197452A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107123158A (en) * | 2017-04-06 | 2017-09-01 | 北京臻迪科技股份有限公司 | A kind of imaging system of unmanned boat |
CN108095987A (en) * | 2017-12-06 | 2018-06-01 | 英业达科技有限公司 | Visually impaired navigation system and its method |
CN108839061A (en) * | 2018-05-31 | 2018-11-20 | 芜湖星途机器人科技有限公司 | Auto-navigation robot |
CN109074490A (en) * | 2018-07-06 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | Path detection method, related device and computer readable storage medium |
CN109084700A (en) * | 2018-06-29 | 2018-12-25 | 上海摩软通讯技术有限公司 | The three dimensional local information acquisition methods and system of article |
CN109493581A (en) * | 2017-09-13 | 2019-03-19 | 富士施乐株式会社 | Information processing unit and the computer-readable medium for storing program |
CN109770463A (en) * | 2019-03-19 | 2019-05-21 | 江苏皓之睿数字科技有限公司 | A kind of apparel size automatic measurement system and method based on machine vision |
CN110232731A (en) * | 2019-04-16 | 2019-09-13 | 广东康云科技有限公司 | A kind of smart city system and its implementation |
CN112506182A (en) * | 2020-10-29 | 2021-03-16 | 久瓴(江苏)数字智能科技有限公司 | Floor sweeping robot positioning method and device, computer equipment and storage medium |
CN113103228A (en) * | 2021-03-29 | 2021-07-13 | 航天时代电子技术股份有限公司 | Teleoperation robot |
CN113188563A (en) * | 2021-04-19 | 2021-07-30 | 上海博泰悦臻网络技术服务有限公司 | Navigation method and system |
CN114598695A (en) * | 2022-03-10 | 2022-06-07 | 苏州蓝甲虫机器人科技有限公司 | All-round machine vision identification system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101701828A (en) * | 2009-11-23 | 2010-05-05 | 常州达奇信息科技有限公司 | Blind autonomous navigation method based on stereoscopic vision and information fusion |
CN102435188A (en) * | 2011-09-15 | 2012-05-02 | 南京航空航天大学 | Monocular vision/inertia autonomous navigation method for indoor environment |
US20130321395A1 (en) * | 2012-06-05 | 2013-12-05 | Billy P. Chen | Method, system and apparatus for providing visual feedback of a map view change |
CN103955920A (en) * | 2014-04-14 | 2014-07-30 | 桂林电子科技大学 | Binocular vision obstacle detection method based on three-dimensional point cloud segmentation |
CN104574386A (en) * | 2014-12-26 | 2015-04-29 | 速感科技(北京)有限公司 | Indoor positioning method based on three-dimensional environment model matching |
-
2016
- 2016-07-21 CN CN201610581601.5A patent/CN106197452A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101701828A (en) * | 2009-11-23 | 2010-05-05 | 常州达奇信息科技有限公司 | Blind autonomous navigation method based on stereoscopic vision and information fusion |
CN102435188A (en) * | 2011-09-15 | 2012-05-02 | 南京航空航天大学 | Monocular vision/inertia autonomous navigation method for indoor environment |
US20130321395A1 (en) * | 2012-06-05 | 2013-12-05 | Billy P. Chen | Method, system and apparatus for providing visual feedback of a map view change |
CN103955920A (en) * | 2014-04-14 | 2014-07-30 | 桂林电子科技大学 | Binocular vision obstacle detection method based on three-dimensional point cloud segmentation |
CN104574386A (en) * | 2014-12-26 | 2015-04-29 | 速感科技(北京)有限公司 | Indoor positioning method based on three-dimensional environment model matching |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107123158A (en) * | 2017-04-06 | 2017-09-01 | 北京臻迪科技股份有限公司 | A kind of imaging system of unmanned boat |
CN107123158B (en) * | 2017-04-06 | 2020-12-29 | 北京臻迪科技股份有限公司 | Imaging system of unmanned ship |
CN109493581A (en) * | 2017-09-13 | 2019-03-19 | 富士施乐株式会社 | Information processing unit and the computer-readable medium for storing program |
US10819902B2 (en) | 2017-09-13 | 2020-10-27 | Fuji Xerox Co., Ltd. | Information processing apparatus and non-transitory computer readable medium |
CN108095987A (en) * | 2017-12-06 | 2018-06-01 | 英业达科技有限公司 | Visually impaired navigation system and its method |
CN108839061A (en) * | 2018-05-31 | 2018-11-20 | 芜湖星途机器人科技有限公司 | Auto-navigation robot |
CN109084700A (en) * | 2018-06-29 | 2018-12-25 | 上海摩软通讯技术有限公司 | The three dimensional local information acquisition methods and system of article |
WO2020006764A1 (en) * | 2018-07-06 | 2020-01-09 | 深圳前海达闼云端智能科技有限公司 | Path detection method, related device, and computer readable storage medium |
CN109074490A (en) * | 2018-07-06 | 2018-12-21 | 深圳前海达闼云端智能科技有限公司 | Path detection method, related device and computer readable storage medium |
CN109770463A (en) * | 2019-03-19 | 2019-05-21 | 江苏皓之睿数字科技有限公司 | A kind of apparel size automatic measurement system and method based on machine vision |
CN110232731A (en) * | 2019-04-16 | 2019-09-13 | 广东康云科技有限公司 | A kind of smart city system and its implementation |
CN112506182A (en) * | 2020-10-29 | 2021-03-16 | 久瓴(江苏)数字智能科技有限公司 | Floor sweeping robot positioning method and device, computer equipment and storage medium |
CN113103228A (en) * | 2021-03-29 | 2021-07-13 | 航天时代电子技术股份有限公司 | Teleoperation robot |
CN113103228B (en) * | 2021-03-29 | 2023-08-15 | 航天时代电子技术股份有限公司 | Teleoperation robot |
CN113188563A (en) * | 2021-04-19 | 2021-07-30 | 上海博泰悦臻网络技术服务有限公司 | Navigation method and system |
CN114598695A (en) * | 2022-03-10 | 2022-06-07 | 苏州蓝甲虫机器人科技有限公司 | All-round machine vision identification system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106197452A (en) | A kind of visual pattern processing equipment and system | |
CN111897332B (en) | Semantic intelligent substation robot humanoid inspection operation method and system | |
CN106162144A (en) | A kind of visual pattern processing equipment, system and intelligent machine for overnight sight | |
CN106197429A (en) | A kind of Multi-information acquisition location equipment and system | |
CN100369487C (en) | Object detection device, object detection server, and object detection method | |
CN111958592B (en) | Image semantic analysis system and method for transformer substation inspection robot | |
Krotkov | Active computer vision by cooperative focus and stereo | |
José et al. | The SmartVision local navigation aid for blind and visually impaired persons | |
CN103680291B (en) | The method synchronizing location and mapping based on ceiling vision | |
CN104036488B (en) | Binocular vision-based human body posture and action research method | |
CN112025729B (en) | Multifunctional intelligent medical service robot system based on ROS | |
CN106981082A (en) | Vehicle-mounted camera scaling method, device and mobile unit | |
CN108073167A (en) | A kind of positioning and air navigation aid based on depth camera and laser radar | |
CN109547769B (en) | Highway traffic dynamic three-dimensional digital scene acquisition and construction system and working method thereof | |
CN110751123B (en) | Monocular vision inertial odometer system and method | |
CN109242003A (en) | Method is determined based on the vehicle-mounted vision system displacement of depth convolutional neural networks | |
US20230063939A1 (en) | Electro-hydraulic varifocal lens-based method for tracking three-dimensional trajectory of object by using mobile robot | |
CN110334701A (en) | Collecting method based on deep learning and multi-vision visual under the twin environment of number | |
CN104079916A (en) | Panoramic three-dimensional visual sensor and using method | |
CN113848931B (en) | Agricultural machinery automatic driving obstacle recognition method, system, equipment and storage medium | |
CN106175780A (en) | Facial muscle motion-captured analysis system and the method for analysis thereof | |
CN111968048A (en) | Method and system for enhancing image data of few samples in power inspection | |
CN110533719A (en) | Augmented reality localization method and device based on environmental visual Feature point recognition technology | |
CN107972027A (en) | The localization method and device of robot, robot | |
CN109299656A (en) | A kind of deeply determining method of vehicle-mounted vision system scene visual |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161207 |