CN108230373A - Mechanical cleaning devices run trace corrects platform - Google Patents
Mechanical cleaning devices run trace corrects platform Download PDFInfo
- Publication number
- CN108230373A CN108230373A CN201810116958.5A CN201810116958A CN108230373A CN 108230373 A CN108230373 A CN 108230373A CN 201810116958 A CN201810116958 A CN 201810116958A CN 108230373 A CN108230373 A CN 108230373A
- Authority
- CN
- China
- Prior art keywords
- image
- glass
- equipment
- cleaning devices
- mechanical cleaning
- 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.)
- Withdrawn
Links
- 238000004140 cleaning Methods 0.000 title claims abstract description 83
- 239000000428 dust Substances 0.000 claims abstract description 25
- 230000009977 dual effect Effects 0.000 claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 239000011521 glass Substances 0.000 claims description 72
- 230000000877 morphologic effect Effects 0.000 claims description 28
- 239000013598 vector Substances 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 13
- 239000000203 mixture Substances 0.000 claims description 8
- 238000012986 modification Methods 0.000 claims description 8
- 230000004048 modification Effects 0.000 claims description 8
- 238000000034 method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 3
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 4
- CDBYLPFSWZWCQE-UHFFFAOYSA-L Sodium Carbonate Chemical compound [Na+].[Na+].[O-]C([O-])=O CDBYLPFSWZWCQE-UHFFFAOYSA-L 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 239000000377 silicon dioxide Substances 0.000 description 2
- 235000019738 Limestone Nutrition 0.000 description 1
- KKCBUQHMOMHUOY-UHFFFAOYSA-N Na2O Inorganic materials [O-2].[Na+].[Na+] KKCBUQHMOMHUOY-UHFFFAOYSA-N 0.000 description 1
- BPQQTUXANYXVAA-UHFFFAOYSA-N Orthosilicate Chemical group [O-][Si]([O-])([O-])[O-] BPQQTUXANYXVAA-UHFFFAOYSA-N 0.000 description 1
- 239000006004 Quartz sand Substances 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- AYJRCSIUFZENHW-DEQYMQKBSA-L barium(2+);oxomethanediolate Chemical compound [Ba+2].[O-][14C]([O-])=O AYJRCSIUFZENHW-DEQYMQKBSA-L 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910021538 borax Inorganic materials 0.000 description 1
- KGBXLFKZBHKPEV-UHFFFAOYSA-N boric acid Chemical compound OB(O)O KGBXLFKZBHKPEV-UHFFFAOYSA-N 0.000 description 1
- 239000004327 boric acid Substances 0.000 description 1
- 229910052681 coesite Inorganic materials 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 229910052906 cristobalite Inorganic materials 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000010433 feldspar Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 239000006028 limestone Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000007769 metal material Substances 0.000 description 1
- 150000002739 metals Chemical class 0.000 description 1
- 150000004702 methyl esters Chemical class 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 229910000029 sodium carbonate Inorganic materials 0.000 description 1
- 235000017550 sodium carbonate Nutrition 0.000 description 1
- 229910052911 sodium silicate Inorganic materials 0.000 description 1
- 239000004328 sodium tetraborate Substances 0.000 description 1
- 235000010339 sodium tetraborate Nutrition 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
- 239000005315 stained glass Substances 0.000 description 1
- 229910052682 stishovite Inorganic materials 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000005341 toughened glass Substances 0.000 description 1
- 229910052905 tridymite Inorganic materials 0.000 description 1
- 229910052882 wollastonite Inorganic materials 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/292—Multi-camera tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20228—Disparity calculation for image-based rendering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Studio Devices (AREA)
Abstract
The present invention relates to a kind of mechanical cleaning devices run trace to correct platform, including:Dust concentration detection device, for detecting the dust concentration of neighbouring environment, to be exported as real-time dust concentration;Mechanical cleaning devices are connect with the dust concentration detection device, for receiving the real-time dust concentration, and determine corresponding cleaning dynamics based on the real-time dust concentration;Track output equipment is connect with the mechanical cleaning devices, for the cleaning determined run trace to be sent to the mechanical cleaning devices, in order to which the mechanical cleaning devices carry out clean operation according to the cleaning run trace;Dual camera component is arranged on the front end of the mechanical cleaning devices, including horizontally disposed two cameras;The dual camera component is for shooting front scenery, to obtain left side scene image and right side scene image respectively.Front glassware is evaded by means of the invention it is possible to realize and effectively realize.
Description
Technical field
The present invention relates to clean robot fields more particularly to a kind of mechanical cleaning devices run trace to correct platform.
Background technology
With the development of China's urbanization, skyscraper is more and more, and the cleaning of the skyscraper window towards household,
It will be as a huge market.Current window clean robot is mostly negative-pressure adsorption, vacuum suction mostly using suction type
It is adsorbed on window with magnetic absorption mode, is by true wherein for the window clean robot using vacuum suction mode
Empty sucker suction realizes the placement of robot on window.But there is vacuum suctions for the robot of existing vacuum suction mode
The problem of attached easy leakage.
Invention content
To solve the above-mentioned problems, the present invention provides a kind of mechanical cleaning devices run trace to correct platform, Neng Gouji
The glassware in front is effectively identified in the imaging characteristics of glass, the image shot from mechanical cleaning devices, and adaptive
The travel track of mechanical cleaning devices is changed on ground, so as to which the accident for avoiding mechanical cleaning devices collision front glassware occurs.
Based on technical scheme of the present invention, the present invention has following key inventive point:
(1) high-accuracy glass image identification on the basis of, based on glass image entirely acquisition image relative position,
The travelling route of automatic modification mechanical cleaning devices, it is unnecessary so as to avoid causing glass equipment and mechanical cleaning devices
Damage;
(2) the glassy zone recognition mechanism that first image is just known, confirmed in image is established, ensure that the essence of glassy zone identification
Degree, more valuable reference data is provided for follow-up respective handling;
(3) the histogram analysis mode of average staturation image is introduced, and glassy zone is utilized in image confirmation
The physical characteristic to differ greatly of the saturation degree of both sides image and glassy zone, so as to provide reliable recognition mode;
(4) it is glass left-side images, glass image and glass using the saturation degree average mode of 5 pixel, 5 pixel window
The acquisition of the respective average staturation image of image right provides reliable scheme;
(5) pass through scene image on the left of being obtained respectively to horizontally disposed two cameras and the parallax of right side scene image
Analysis determines distance of the main target apart from camera in the scenery of front, accordingly to adjust the focal length of two cameras, and by two
The image of a camera shooting is combined, to obtain the big field-of-view image of high-definition.
According to an aspect of the present invention, it provides a kind of mechanical cleaning devices run trace and corrects platform, the platform packet
It includes:
Dust concentration detection device, for detecting the dust concentration of neighbouring environment, to be exported as real-time dust concentration;
Mechanical cleaning devices are connect with the dust concentration detection device, for receiving the real-time dust concentration, and base
Corresponding cleaning dynamics is determined in the real-time dust concentration;
Track output equipment is connect with the mechanical cleaning devices, for the cleaning determined run trace to be sent to institute
Mechanical cleaning devices are stated, in order to which the mechanical cleaning devices carry out clean operation according to the cleaning run trace;
Dual camera component is arranged on the front end of the mechanical cleaning devices, including horizontally disposed two cameras;Institute
Dual camera component is stated for being shot to front scenery, to obtain left side scene image and right side scene image respectively;
Disparity Analysis equipment is connect with two cameras of the dual camera component, respectively for receiving the left side
Scene image and the right side scene image, and the left side scene image is divided into multiple cut zone, and based on each
A cut zone finds the similar area of matching content in the right side scene image, each in the scene image of left side is divided
The coordinate shift of region and its similar area in the scene image of right side is as zone shift amount, based on the left side scene image
Each region offset determine parallax between the left side scene image and the right side scene image;
Focus adjustment equipment is connect respectively with the dual camera component and the Disparity Analysis equipment, for being based on
Main target that parallax determines to shoot in the left side scene image or the right side scene image is stated apart from the dual camera
The distance of component, and focus adjustment is carried out to described two cameras based on the distance;
Image combining apparatus is connect with the focus adjustment equipment and the dual camera component, in the focal length
After adjustment equipment completes focus adjustment, described two cameras are obtained into left side scene image respectively and right side scene image carries out
Splice to obtain and export real-time stitching image;
Morphological scale-space equipment is connect with described image unit equipment, for receiving the real-time stitching image, and to institute
It states real-time stitching image and performs Morphological scale-space processing, to obtain and export Morphological scale-space image;
Equipment is just known in region, is connect with the Morphological scale-space equipment, for receiving the Morphological scale-space image, for
Whether the brightness value of each pixel in the Morphological scale-space image judges it in default glass upper limit brightness value and pre-
If in the range of luminance values of glass lower limit brightness value composition, if in the range of luminance values, judge that the pixel is
Initial pixel, and all initial pixels composition in the Morphological scale-space image is just known into pixel region.
Description of the drawings
Embodiment of the present invention is described below with reference to attached drawing, wherein:
Fig. 1 is the appearance profile of the mechanical cleaning devices run trace amendment platform according to embodiment of the present invention
Figure.
Fig. 2 is the structure box of the mechanical cleaning devices run trace amendment platform according to embodiment of the present invention
Figure.
Specific embodiment
The embodiment for correcting platform to the mechanical cleaning devices run trace of the present invention below with reference to accompanying drawings carries out detailed
It describes in detail bright.
Glass is amorphous inorganic non-metallic material, and usually with a variety of inorganic minerals, (such as quartz sand, borax, boric acid, weight are brilliant
Stone, barium carbonate, lime stone, feldspar, soda ash etc.) it is primary raw material, it additionally incorporates made of a small amount of auxiliary material.It it is main into
It is divided into silica and other oxides.The chemical composition of simple glass is Na2SiO3、CaSiO3、SiO2Or Na2O·CaO·
6SiO2Deng main component is silicate double salt, is a kind of non-crystalline solids of random structure.It is widely used in building, uses
, every wind light transmission, to belong to mixture.The another coloured glass for having the oxide for being mixed into certain metals or salt and showing color
Glass and pass through tempered glass etc. made from the method for physics or chemistry.Sometimes some transparent plastics (such as polymethyls
Sour methyl esters) it is also referred to as organic glass.
Glassware is the common items of house, workshop and intra-office, widely used in mechanical cleaning devices
Today the glassware in forward path can not effectively be identified and be hidden, be the difficulty that mechanical cleaning devices are difficult to overcome
One of topic.
In order to overcome above-mentioned deficiency, the present invention has built a kind of mechanical cleaning devices run trace and has corrected platform, for solving
Certainly above-mentioned technical problem.
Fig. 1 is the appearance profile of the mechanical cleaning devices run trace amendment platform according to embodiment of the present invention
Figure.
As can be seen that the platform includes from the profile outline:Dual camera component 1, mechanical cleaning devices 2,
Dust concentration detection device 3 and work light set 4.
Wherein, work light set 4 is made of three work lights, for representing the difference of the platform respectively
State.
Fig. 2 is the structure box of the mechanical cleaning devices run trace amendment platform according to embodiment of the present invention
Figure, the platform include:
Dust concentration detection device, for detecting the dust concentration of neighbouring environment, to be exported as real-time dust concentration;
Mechanical cleaning devices are connect with the dust concentration detection device, for receiving the real-time dust concentration, and base
Corresponding cleaning dynamics is determined in the real-time dust concentration;
Track output equipment is connect with the mechanical cleaning devices, for the cleaning determined run trace to be sent to institute
Mechanical cleaning devices are stated, in order to which the mechanical cleaning devices carry out clean operation according to the cleaning run trace.
Then, the concrete structure for continuing to correct the mechanical cleaning devices run trace of the present invention platform carries out further
Explanation.
The mechanical cleaning devices run trace is corrected can also include in platform:
Dual camera component is arranged on the front end of the mechanical cleaning devices, including horizontally disposed two cameras;
Wherein, the dual camera component is for shooting front scenery, with obtain respectively left side scene image and
Right side scene image.
The mechanical cleaning devices run trace is corrected can also include in platform:
Disparity Analysis equipment is connect with two cameras of the dual camera component, respectively for receiving the left side
Scene image and the right side scene image, and the left side scene image is divided into multiple cut zone, and based on each
A cut zone finds the similar area of matching content in the right side scene image, each in the scene image of left side is divided
The coordinate shift of region and its similar area in the scene image of right side is as zone shift amount, based on the left side scene image
Each region offset determine parallax between the left side scene image and the right side scene image.
The mechanical cleaning devices run trace is corrected can also include in platform:
Focus adjustment equipment is connect respectively with the dual camera component and the Disparity Analysis equipment, for being based on
Main target that parallax determines to shoot in the left side scene image or the right side scene image is stated apart from the dual camera
The distance of component, and focus adjustment is carried out to described two cameras based on the distance;
Image combining apparatus is connect with the focus adjustment equipment and the dual camera component, in the focal length
After adjustment equipment completes focus adjustment, described two cameras are obtained into left side scene image respectively and right side scene image carries out
Splice to obtain and export real-time stitching image.
The mechanical cleaning devices run trace is corrected can also include in platform:
Morphological scale-space equipment is connect with described image unit equipment, for receiving the real-time stitching image, and to institute
It states real-time stitching image and performs Morphological scale-space processing, to obtain and export Morphological scale-space image;
Equipment is just known in region, is connect with the Morphological scale-space equipment, for receiving the Morphological scale-space image, for
Whether the brightness value of each pixel in the Morphological scale-space image judges it in default glass upper limit brightness value and pre-
If in the range of luminance values of glass lower limit brightness value composition, if in the range of luminance values, judge that the pixel is
Initial pixel, and all initial pixels composition in the Morphological scale-space image is just known into pixel region;
Process of fitting treatment equipment is just known equipment with the region and is connect, for receiving the just knowledge pixel region, and by described in
Just know pixel region fitting and just know image to obtain;
Image divides equipment, and just knowing equipment with the process of fitting treatment equipment and the region respectively connect, for being based on
It states and just knows position of the image in the Morphological scale-space image, the Morphological scale-space image is divided into glass left hand view
Picture, glass image and glass image right;
Saturation analysis equipment divides equipment with described image and connect, for receiving the glass left-side images, the glass
Glass image and the glass image right, for each pixel in the glass left-side images, calculate using it in
The heart, around in 5 pixel, 5 pixel region the saturation degree of each pixel average value using as its average staturation, based on institute
The average staturation for stating each pixel in glass left-side images obtains the corresponding average staturation of the glass left-side images
Image based on the same treatment to the glass left-side images, obtains the corresponding average staturation figure of the glass image right
Picture and the corresponding average staturation image of the glass image;
Histogram treatment equipment is connect with the saturation analysis equipment, for receiving glass left-side images, described
Glass image and the corresponding average staturation image of the glass image right, and the glass left-side images are put down
Equal saturation degree image performs statistics with histogram, obtain the histogram vectors of the corresponding saturation degree of the glass left-side images using as
First histogram vectors perform statistics with histogram to the average staturation image of the glass image right, obtain the glass
The histogram vectors of the corresponding saturation degree of image right are using as the second histogram vectors, to the average saturation of the glass image
It spends image and performs statistics with histogram, obtain the histogram vectors of the corresponding saturation degree of the glass image using as third histogram
Vector;
Region determines equipment, is connect with the histogram treatment equipment, in the first histogram vectors and third Nogata
The mould for scheming the difference of vector is more than or equal to default mould threshold value, and in the difference of the second histogram vectors and third histogram vectors
When mould is more than or equal to default mould threshold value, the just knowledge image is determined as glass image and is exported, otherwise, just know image by described
It is determined as non-glass image and exports;
Wherein, the Disparity Analysis equipment determines the left side based on each region offset of the left side scene image
Parallax between scene image and the right side scene image includes:By the highest region of the frequency of occurrences in the offset of each region
Offset is as the parallax between the left side scene image and the right side scene image;
Wherein, the track output equipment also determines that equipment is connect with the region, for true in the just knowledge image
When being set to glass image, based on the determining cleaning of the relative position modification for just knowing image in the Morphological scale-space image
Run trace, and modified cleaning run trace is sent to the mechanical cleaning devices.
In the mechanical cleaning devices run trace corrects platform:
The track output equipment be additionally operable to it is described just know image and be confirmed as non-glass image when, keep determining clear
Clean run trace is constant, so that the mechanical cleaning devices walk on by determining cleaning run trace.
It can also include in platform in addition, the mechanical cleaning devices run trace is corrected:GPS positioning device, for connecing
The navigation data that GPS navigation satellite is sent is received, to determine the navigation position of the mechanical cleaning devices.
Initial GPS plans to be born under the leader of American Association Plan Bureau, and 24 satellites are placed on mutually by the program
Into on 120 degree of three tracks.There are 8 satellites on each track, any point can observe 6 to 9 satellites on the earth.This
Sample, for thick code precision up to 100m, smart code precision is 10m.Since budget is compressed, GPS plans have to reduce satellite launch quantity,
It is changed to by 18 satellite distributions on 60 degree of 6 tracks are mutually, however this scheme causes satellite reliability that cannot ensure.
Last modification is carried out again within 1988:21 work stars and 3 spare stars are operated on 6 tracks for being mutually 60 degree.This
It is also working method used in GPS satellite.
GPS navigation system be based on global 24 positioning satellites, to all parts of the world it is round-the-clock three-dimensional is provided
A kind of radio-navigation positioning system of the information such as position, three-dimensional velocity.It is made of three parts, when ground control segment,
It is made of master station, ground-plane antenna, monitoring station and communication auxiliary system.Second is that space segment, is made of 24 satellites, is distributed in
6 orbit planes.Third, user apparatus part, is made of GPS receiver and satellite antenna.Civilian positioning accuracy is up to 10 meters
It is interior.
Mechanical cleaning devices run trace using the present invention corrects platform, holds for mechanical cleaning devices in the prior art
The technical issues of easily colliding front glassware is imaged focal length first with 3-D view adjust automatically, recycles glassware
The clear image that is obtained after focusing of imaging characteristics in be accurately partitioned into glass image, finally, existed based on the glass image
The determining cleaning run trace of relative position modification in the Morphological scale-space image, and by modified cleaning run trace
The mechanical cleaning devices are sent to, so as to avoid the collision with front glassware.
It is understood that although the present invention has been disclosed in the preferred embodiments as above, above-described embodiment not to
Limit the present invention.For any those skilled in the art, without departing from the scope of the technical proposal of the invention,
Many possible changes and modifications are all made to technical solution of the present invention using the technology contents of the disclosure above or are revised as
With the equivalent embodiment of variation.Therefore, every content without departing from technical solution of the present invention, technical spirit pair according to the present invention
Any simple modifications, equivalents, and modifications made for any of the above embodiments still fall within the range of technical solution of the present invention protection
It is interior.
Claims (6)
1. a kind of mechanical cleaning devices run trace corrects platform, the platform includes:
Dust concentration detection device, for detecting the dust concentration of neighbouring environment, to be exported as real-time dust concentration;
Mechanical cleaning devices are connect with the dust concentration detection device, for receiving the real-time dust concentration, and based on institute
It states real-time dust concentration and determines corresponding cleaning dynamics;
Track output equipment is connect with the mechanical cleaning devices, for the cleaning determined run trace to be sent to the machine
Tool cleaning equipment, in order to which the mechanical cleaning devices carry out clean operation according to the cleaning run trace.
2. mechanical cleaning devices run trace as described in claim 1 corrects platform, which is characterized in that the platform also wraps
It includes:
Dual camera component is arranged on the front end of the mechanical cleaning devices, including horizontally disposed two cameras;
Wherein, the dual camera component is for shooting front scenery, to obtain left side scene image and right side respectively
Scene image.
3. mechanical cleaning devices run trace as claimed in claim 2 corrects platform, which is characterized in that the platform also wraps
It includes:
Disparity Analysis equipment is connect respectively with two cameras of the dual camera component, for receiving the left side scenery
Image and the right side scene image, and the left side scene image is divided into multiple cut zone, and based on each point
The similar area that matching content is found in region in the right side scene image is cut, by each cut zone in the scene image of left side
Coordinate shift with its similar area in the scene image of right side is as zone shift amount, based on each of the left side scene image
A zone shift amount determines the parallax between the left side scene image and the right side scene image.
4. mechanical cleaning devices run trace as claimed in claim 3 corrects platform, which is characterized in that the platform also wraps
It includes:
Focus adjustment equipment is connect respectively with the dual camera component and the Disparity Analysis equipment, for being based on described regard
The main target that difference determines to shoot in the left side scene image or the right side scene image is apart from the dual camera component
Distance, and based on the distance to described two cameras carry out focus adjustment;
Image combining apparatus is connect with the focus adjustment equipment and the dual camera component, in the focus adjustment
After equipment completes focus adjustment, described two cameras are obtained into left side scene image respectively and right side scene image splices
To obtain and export real-time stitching image.
5. mechanical cleaning devices run trace as claimed in claim 4 corrects platform, which is characterized in that the platform also wraps
It includes:
Morphological scale-space equipment is connect with described image unit equipment, for receiving the real-time stitching image, and to the reality
When stitching image perform Morphological scale-space processing, to obtain and export Morphological scale-space image;
Equipment is just known in region, is connect with the Morphological scale-space equipment, for receiving the Morphological scale-space image, for described
Whether the brightness value of each pixel in Morphological scale-space image judges it in default glass upper limit brightness value and default glass
In the range of luminance values of glass lower limit brightness value composition, if in the range of luminance values, it is initial to judge the pixel
Pixel, and all initial pixels composition in the Morphological scale-space image is just known into pixel region;
Process of fitting treatment equipment is just known equipment with the region and is connect, and for receiving the just knowledge pixel region, and just knows described
Pixel region fitting just knows image to obtain;
Image divides equipment, and just knowing equipment with the process of fitting treatment equipment and the region respectively connect, described first for being based on
Know position of the image in the Morphological scale-space image, the Morphological scale-space image is divided into glass left-side images, glass
Glass image and glass image right;
Saturation analysis equipment divides equipment with described image and connect, for receiving the glass left-side images, the glass figure
As and the glass image right, for each pixel in the glass left-side images, calculate it is centered on it,
Around in 5 pixel, 5 pixel region the saturation degree of each pixel average value using as its average staturation, based on the glass
The average staturation of each pixel in left-side images obtains the corresponding average staturation image of the glass left-side images, base
In the same treatment to the glass left-side images, the corresponding average staturation image of the glass image right and institute are obtained
State the corresponding average staturation image of glass image;
Histogram treatment equipment is connect with the saturation analysis equipment, for receiving the glass left-side images, the glass
Image and the corresponding average staturation image of the glass image right, and to the average full of the glass left-side images
Statistics with histogram is performed with degree image, obtains the histogram vectors of the corresponding saturation degree of the glass left-side images using as first
Histogram vectors perform statistics with histogram to the average staturation image of the glass image right, obtain on the right side of the glass
The histogram vectors of the corresponding saturation degree of image are using as the second histogram vectors, to the average staturation figure of the glass image
As performing statistics with histogram, obtain the histogram vectors of the corresponding saturation degree of the glass image using as third histogram to
Amount;
Region determines equipment, is connect with the histogram treatment equipment, for the first histogram vectors and third histogram to
The mould of the difference of amount is more than or equal to default mould threshold value, and big in the mould of the second histogram vectors and the difference of third histogram vectors
When equal to default mould threshold value, the just knowledge image is determined as glass image and is exported, otherwise, the just knowledge image is determined
For non-glass image and export;
Wherein, the Disparity Analysis equipment determines the left side scenery based on each region offset of the left side scene image
Parallax between image and the right side scene image includes:By the highest region offset of the frequency of occurrences in the offset of each region
Amount is as the parallax between the left side scene image and the right side scene image;
Wherein, the track output equipment also determines that equipment is connect with the region, for being confirmed as in the just knowledge image
During glass image, walked based on the determining cleaning of the relative position modification for just knowing image in the Morphological scale-space image
Track, and modified cleaning run trace is sent to the mechanical cleaning devices.
6. mechanical cleaning devices run trace as claimed in claim 5 corrects platform, it is characterised in that:
The track output equipment is additionally operable to, when the just knowledge image is confirmed as non-glass image, keep determining cleaning row
Walk that track is constant, so that the mechanical cleaning devices walk on by determining cleaning run trace.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810116958.5A CN108230373A (en) | 2018-02-06 | 2018-02-06 | Mechanical cleaning devices run trace corrects platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810116958.5A CN108230373A (en) | 2018-02-06 | 2018-02-06 | Mechanical cleaning devices run trace corrects platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108230373A true CN108230373A (en) | 2018-06-29 |
Family
ID=62670334
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810116958.5A Withdrawn CN108230373A (en) | 2018-02-06 | 2018-02-06 | Mechanical cleaning devices run trace corrects platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108230373A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117274227A (en) * | 2023-10-23 | 2023-12-22 | 宁波市宇星水表有限公司 | Water meter surface state management system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1470368A (en) * | 2002-07-26 | 2004-01-28 | ������������ʽ���� | Robot cleaning device and robot cleaning system and control method thereof |
CN1891129A (en) * | 2005-06-28 | 2007-01-10 | 松下电器产业株式会社 | Dust detection device and electric dust collector mounted with the same |
CN101577005A (en) * | 2009-06-12 | 2009-11-11 | 北京中星微电子有限公司 | Target tracking method and device |
CN102721647A (en) * | 2012-06-29 | 2012-10-10 | 深圳市银星智能科技股份有限公司 | Garbage concentration detection device and garbage concentration identification method for dust absorption product |
CN103076345A (en) * | 2013-01-16 | 2013-05-01 | 东莞市三姆森光电科技有限公司 | Detection method and full-automatic optical detection system for ITO conductive glass |
CN104021388A (en) * | 2014-05-14 | 2014-09-03 | 西安理工大学 | Reversing obstacle automatic detection and early warning method based on binocular vision |
CN104574389A (en) * | 2014-12-26 | 2015-04-29 | 康奋威科技(杭州)有限公司 | Battery piece chromatism selection control method based on color machine vision |
CN105259898A (en) * | 2015-10-13 | 2016-01-20 | 江苏拓新天机器人科技有限公司 | Floor sweeping robot controlled by smart phone |
-
2018
- 2018-02-06 CN CN201810116958.5A patent/CN108230373A/en not_active Withdrawn
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1470368A (en) * | 2002-07-26 | 2004-01-28 | ������������ʽ���� | Robot cleaning device and robot cleaning system and control method thereof |
CN1891129A (en) * | 2005-06-28 | 2007-01-10 | 松下电器产业株式会社 | Dust detection device and electric dust collector mounted with the same |
CN101577005A (en) * | 2009-06-12 | 2009-11-11 | 北京中星微电子有限公司 | Target tracking method and device |
CN102721647A (en) * | 2012-06-29 | 2012-10-10 | 深圳市银星智能科技股份有限公司 | Garbage concentration detection device and garbage concentration identification method for dust absorption product |
CN103076345A (en) * | 2013-01-16 | 2013-05-01 | 东莞市三姆森光电科技有限公司 | Detection method and full-automatic optical detection system for ITO conductive glass |
CN104021388A (en) * | 2014-05-14 | 2014-09-03 | 西安理工大学 | Reversing obstacle automatic detection and early warning method based on binocular vision |
CN104574389A (en) * | 2014-12-26 | 2015-04-29 | 康奋威科技(杭州)有限公司 | Battery piece chromatism selection control method based on color machine vision |
CN105259898A (en) * | 2015-10-13 | 2016-01-20 | 江苏拓新天机器人科技有限公司 | Floor sweeping robot controlled by smart phone |
Non-Patent Citations (2)
Title |
---|
张少平 等: "航拍图像中玻璃绝缘子自爆缺陷的检测及定位", 《太赫兹科学与电子信息学部》 * |
谭本忠 等: "《看图学修汽车音响(彩色版)》", 31 January 2013, 机械工业出版社 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117274227A (en) * | 2023-10-23 | 2023-12-22 | 宁波市宇星水表有限公司 | Water meter surface state management system |
CN117274227B (en) * | 2023-10-23 | 2024-06-07 | 宁波埃美柯水表有限公司 | Water meter surface state management system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112505065B (en) | Method for detecting surface defects of large part by indoor unmanned aerial vehicle | |
CN107421506B (en) | Visual tracking and positioning system and method based on indoor visible light communication | |
CN109509230A (en) | A kind of SLAM method applied to more camera lens combined type panorama cameras | |
CN111024066A (en) | Unmanned aerial vehicle vision-inertia fusion indoor positioning method | |
CN105953771B (en) | A kind of active theodolite system and measuring method | |
CN110347160A (en) | A kind of automatic guide vehicle and its air navigation aid based on dual camera barcode scanning | |
CN110570453B (en) | Binocular vision-based visual odometer method based on closed-loop tracking characteristics | |
CN110887486B (en) | Unmanned aerial vehicle visual navigation positioning method based on laser line assistance | |
CN106054878A (en) | Inertial guidance vehicle navigation method based on two-dimensional code positioning, and inertial guidance vehicle | |
CN110230983A (en) | Antivibration formula optical 3-dimensional localization method and device | |
CN107703951A (en) | A kind of unmanned plane barrier-avoiding method and system based on binocular vision | |
CN107453811B (en) | A method of the unmanned plane based on photopic vision communication cooperates with SLAM | |
CN109387194A (en) | A kind of method for positioning mobile robot and positioning system | |
CN113537046A (en) | Map lane marking method and system based on vehicle track big data detection | |
CN109116865A (en) | Large scale equipment unmanned plane cruising inspection system and its method based on machine vision | |
CN106733686B (en) | A kind of assembly line object positioning method of view-based access control model and code-disc data fusion | |
CN108230373A (en) | Mechanical cleaning devices run trace corrects platform | |
CN108645408A (en) | Unmanned aerial vehicle autonomous recovery target prediction method based on navigation information | |
CN114966789A (en) | Mapping method and system fusing GNSS and multi-view vision | |
CN109118524A (en) | Mechanical cleaning devices run trace modification method | |
CN107909543A (en) | A kind of flake binocular vision Stereo matching space-location method | |
CN112050814A (en) | Unmanned aerial vehicle visual navigation system and method for indoor transformer substation | |
CN106444774B (en) | Vision navigation method of mobile robot based on indoor illumination | |
CN206074001U (en) | A kind of robot indoor locating system based on 3D video cameras | |
Wang et al. | Direct sparse stereo visual-inertial global odometry |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180629 |