CN105389795B - A kind of rubbish material level detection method, device and feeding trigger - Google Patents
A kind of rubbish material level detection method, device and feeding trigger Download PDFInfo
- Publication number
- CN105389795B CN105389795B CN201510669760.6A CN201510669760A CN105389795B CN 105389795 B CN105389795 B CN 105389795B CN 201510669760 A CN201510669760 A CN 201510669760A CN 105389795 B CN105389795 B CN 105389795B
- Authority
- CN
- China
- Prior art keywords
- rubbish
- image
- cheated
- material hole
- coordinate system
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of rubbish material level detection methods, device and feeding trigger, in the present case, rubbish image can be cheated by the material cheated to collected material carry out image procossing, corresponding material in the rubbish image of identification discharging hole cheats region, and profile processing can be carried out by cheating region to the material, obtain the garbage areas profile diagram for cheating each rubbish boundary in region for characterizing the material, and then it can be according to the garbage areas profile diagram and the material pit foundation directrix of setting, determine picture altitude of the rubbish in material is cheated in material hole, and actual height of the rubbish in material is cheated in material hole is obtained according to determining picture altitude, to realize the automatic detection of rubbish position, for existing manual detection mode, accuracy higher, it is more efficient.
Description
Technical field
The present invention relates to rubbish material position detection technique field more particularly to a kind of rubbish material level detection method, device and on
Flitch machine.
Background technology
During the binder of garbage compression station, rubbish topple over uneven and rubbish it is complex in composition etc. due to,
It is stuck compared with the rubbish putty easily caused in material hole when rubbish feeds intake excessive, cause rubbish that can not fall to compressor, is formed and " overflow and struggle against
Pneumatics " phenomenon, therefore, it is necessary to periodically be detected in real time or to the material position of rubbish, to solve the above problems.
Specifically, it since the composition of rubbish is extremely complex, such as may include polybag, bottle, trees and paper scrap, make
It is usually non-rigid curved surface to obtain it and be formed by curved surface, thus, the existing ultrasound suitable for rigid body curved surface can not be used
The detection that material position is carried out away from detection methods such as, laser rangings is only capable of by way of manually monitoring corresponding to judge by rule of thumb
Rubbish material position.
Specifically, when carrying out the detection of rubbish material position using artificial monitor mode, the monitoring in hole is mainly expected by watching
Video is realized.But because there are the disturbing factors such as deformation, visual angle change and ambient noise in transmission process in video,
Real image with material hole there are larger difference, thus, easily cause artificial observation to video image be inaccurate, cause
There are larger errors for final material-level measure result, reduce the accuracy of material-level measure result.In addition, since rubbish is non-rigid
Body material, material position boundary exist in the form of curve is non-directional, therefore, material-level measure are being carried out using artificial monitor mode
When, it is also necessary to the artificial conversion of march strands position to straight line material position, to further reduced the accurate of material-level measure result
Property, so that material-level measure result reliability it is relatively low.Further more, when carrying out material-level measure using artificial monitor mode, due to big
Part operation is required for manually completing, thus can also there is a problem of that the degree of automation is low so that the effect of rubbish material-level measure
Rate is not high.
That is, existing rubbish material position detection mode has that accuracy is relatively low and less efficient etc., because
This, it is urgent to provide a kind of new rubbish material position detection modes to solve the above problems.
Invention content
It is existing to solve an embodiment of the present invention provides a kind of rubbish material level detection method, device and feeding trigger
Relatively low and less efficient etc. the problem of accuracy present in rubbish material position detection mode.
An embodiment of the present invention provides a kind of rubbish material level detection methods, including:
The material in rubbish material-level detecting device acquisition material hole cheats rubbish image, and the image processing techniques based on setting is determined
Corresponding material in the rubbish image of the material hole cheats region;
Profile processing is carried out to material hole region, obtains the rubbish for cheating each rubbish boundary in region for characterizing the material
Region contour figure;
According to the garbage areas profile diagram and the material pit foundation directrix of setting, determine the rubbish in material hole in material is cheated
Picture altitude, and according to determining picture altitude, determine actual height of the rubbish in material is cheated in material hole.
Correspondingly, the embodiment of the present invention additionally provides a kind of rubbish material-level detecting device, including:
Image acquisition units, the material hole rubbish image for acquiring material hole;
Material hole area determination unit is determined for the image processing techniques based on setting in the rubbish image of the material hole
Corresponding material hole region;
Profile processing unit obtains cheating region for characterizing the material for carrying out profile processing to material hole region
Each rubbish boundary garbage areas profile diagram;
Rubbish material position determination unit is determined for the material pit foundation directrix according to the garbage areas profile diagram and setting
Picture altitude of the rubbish in material is cheated in material hole, and according to determining picture altitude, determine the rubbish in material hole in material is cheated
Actual height.
Further, the embodiment of the present invention additionally provides a kind of feeding trigger, and the feeding trigger includes that the present invention is implemented
Rubbish material-level detecting device described in example.
The present invention has the beneficial effect that:
An embodiment of the present invention provides a kind of rubbish material level detection method, device and feeding triggers, in the embodiment of the present invention
In the technical solution, rubbish image can be cheated by the material cheated to collected material and carries out image procossing, identification discharging hole rubbish
Corresponding material in image cheats region, and can carry out profile processing by cheating region to the material, obtains for characterizing the areas Liao Keng
The garbage areas profile diagram on each rubbish boundary in domain, and then can be accurate according to the garbage areas profile diagram and the material pit foundation of setting
Line determines picture altitude of the rubbish in material is cheated in material hole, and obtains the rubbish in material hole according to determining picture altitude and exist
Actual height in material hole, to realize the automatic detection of rubbish position, for existing manual detection mode, essence
It is exactness higher, more efficient.
Description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill in field, without creative efforts, other are can also be obtained according to these attached drawings
Attached drawing.
Fig. 1 show the flow diagram of rubbish material level detection method described in the embodiment of the present invention;
Fig. 2 show a kind of possible position of image capture device described in the embodiment of the present invention and light filling lighting apparatus
Structural schematic diagram;
Fig. 3 (a) show the hole of the material described in embodiment of the present invention rubbish image schematic diagram;
Fig. 3 (b) show the rubbish connected region figure described in the embodiment of the present invention;
Fig. 3 (c) show the garbage areas profile diagram described in the embodiment of the present invention;
Fig. 4 show the determination schematic diagram of the rubbish boundary straight line described in the embodiment of the present invention;
Fig. 5 show the structural schematic diagram of rubbish material-level detecting device described in the embodiment of the present invention.
Specific implementation mode
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, it is clear that described embodiments are only a part of the embodiments of the present invention, rather than whole implementation
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
All other embodiment, shall fall within the protection scope of the present invention.
Embodiment one:
The embodiment of the present invention one provides a kind of rubbish material level detection method, as shown in Figure 1, it is the embodiment of the present invention one
Described in rubbish material level detection method flow diagram, the rubbish material level detection method may include following steps:
Step 101:The material in acquisition material hole cheats rubbish image;
Step 102:Image processing techniques based on setting determines the material hole region in the rubbish image of the material hole;
Step 103:Profile processing is carried out to material hole region, obtains each rubbish side for cheating region for characterizing the material
The garbage areas profile diagram on boundary;
Step 104:According to the garbage areas profile diagram and the material pit foundation directrix of setting, determine that the rubbish in material hole exists
Picture altitude in material hole, and according to determining picture altitude, determine actual height of the rubbish in material is cheated in material hole.
That is, in the technical solution described in the embodiment of the present invention one, rubbish can be cheated by the material cheated to collected material
Rubbish image carries out image procossing, and the corresponding material in the rubbish image of identification discharging hole cheats region, and can be by cheating region to the material
Profile processing is carried out, obtains the garbage areas profile diagram for cheating each rubbish boundary in region for characterizing the material, and then can be according to this
Garbage areas profile diagram and the material pit foundation directrix of setting, the determining picture altitude for expecting the rubbish in hole in material is cheated, and according to
Determining picture altitude obtains actual height of the rubbish in material is cheated in material hole, to realize the automatic inspection of rubbish position
It surveys, it is accuracy higher, more efficient for existing manual detection mode.
In the following, by each step in the embodiment of the present invention is described in detail:
Optionally, the material in the acquisition material hole described in step 101 cheats rubbish image, can be embodied as:
Image capture device (such as video camera or camera) by the way that the side on material is cheated is arranged is acquired is being expected by being arranged
The material in the material hole of light filling lighting apparatus (such as incandescent lamp, LED light) adequate illumination of side cheats rubbish image on hole.
Wherein, (Fig. 2 is that a kind of possible positional structure of image capture device and light filling lighting apparatus is shown as shown in Figure 2
It is intended to), described image collecting device can cheat the first setting height (H with horizontal plane at setting angle (θ) and apart from the materialc),
The light filling lighting apparatus can cheat the second setting height apart from the material.And in order to avoid image capture device blocks light,
When described image collecting device and the light filling lighting apparatus are located at the same upper side in material hole, first setting height one
As can be more than second setting height;And in order to enable image capture device can collect the complete and comprehensive of material hole
Material hole rubbish image, the setting angle can generally be more than 0 degree and be less than 90 degree, as long as can ensure that image capture device can be adopted
Collect the complete and comprehensive material hole rubbish image in material hole.
In addition, it is necessary to explanation, described image collecting device can not also be located at material hole with the light filling lighting apparatus
Same upper side, e.g., a upper left side for being located at material hole, a upper right side etc. for being located at material hole;At this point, described first sets
Fixed height may be less than or equal to second setting height other than it can be more than second setting height, and the present invention is real
Example is applied not repeat this.
More preferably, as shown in Fig. 2, in order to save equipment installation resource, described image collecting device is illuminated with the light filling
Equipment is generally placed at the top of the side for being not provided with the feeding trigger for carrying out feeding garbage in material hole, and the present invention is real
Example is applied also not repeat this.
Further, it should be noted that when the material in acquisition material hole cheats rubbish image, in order to more accurately realize rubbish
The detection of material position can acquire the material hole rubbish image in material hole in real time.Certainly, it should be noted that meeting corresponding accuracy
On the basis of it is required that, in order to save Image Acquisition resource, also periodically (such as every 1 minute or 3 minutes) acquisition the material cheated can be expected
Rubbish image is cheated, the embodiment of the present invention does not also repeat this.
Further, after collecting the material hole rubbish image in material hole, you can carry out phase to material hole rubbish image
The image procossing answered executes step 102 to identify that the corresponding material in the rubbish image of the material hole cheats region.
Optionally, the image processing techniques based on setting described in step 102 is determined in the rubbish image of the material hole
Material hole region, can be embodied as:
Based on image masks technology, the mask product processing that non-material cheats region is carried out to material hole rubbish image, with true
Make the corresponding material hole region in the rubbish image of the material hole.
That is, since the non-material hole region in material hole is largely changeless, rubbish can be cheated to the material
Image carries out the mask product processing in non-material hole region, to go unless expecting to cheat noise region.
Specifically, rubbish image can be cheated to the material by following formula and carries out the mask product processing that non-material cheats region:
G (x, y)=f (x, y) * m (x, y);
Wherein, f (x, y) is the original material hole rubbish image indicated in the form of two-dimensional function, and m (x, y) is image masks letter
Number, g (x, y) be the mask product that is indicated in the form of two-dimensional function treated material hole rubbish image, wherein (x, y) is to expect hole
The value of the air coordinates of respective point in rubbish image, f (x, y) is that intensity or gray scale of the image at point (x, y) (generally take
It is [0,255] to be worth section), whether the value of m (x, y) is cheated region in material by point (x, y) and is determined, is then in material hole region
1, it is then 0 in non-material hole region.
Further, since image capture device the image collected may generally be colored, and rubbish material-level measure is general
It only needs the profile of processing rubbish, be not necessarily to colour information, therefore, executing the image procossing skill based on setting described in step 102
Before art determines the material hole region in the rubbish image of the material hole, the method may also include:
If it is determined that material hole rubbish image is coloured image, then gray processing processing is carried out to material hole rubbish image,
Material hole rubbish gray level image is obtained, to accelerate subsequent image processing procedure.
Optionally, gray processing processing is carried out to material hole rubbish image, it may include:
If it is determined that each pixel of material hole rubbish image is color made of R (red), G (green), B (indigo plant) sub-pixel combinations
Color image pixel is then directed to each pixel of material hole rubbish image, the pixel can be converted to ash by following formula
Spend image pixel:
Gray=R*0.299+G*0.587+B*0.114;
Wherein, Gray indicates that the pixel of material hole rubbish gray level image, R, G, B indicate the corresponding colour of material hole rubbish image
Each sub-pixel point of pixel.
Correspondingly, the image processing techniques based on setting described in step 102 is determined in the rubbish image of the material hole
Material hole region, may also be embodied for:
Based on image masks technology, the areas Fei Liaokeng are carried out to the corresponding material hole rubbish gray level image of material hole rubbish image
The mask product in domain is handled, to determine that the corresponding material in the rubbish image of the material hole cheats region.
Wherein, similar with the mask product processing procedure of the foregoing description, rubbish gray scale can be cheated to material by following formula
Image carries out the mask product processing in non-material hole region:
G1 (x, y)=f1 (x, y) * m (x, y);
Wherein, g1 (x, y) is the mask product that is indicated in the form of two-dimensional function treated material hole rubbish gray level image, f1
(x, y) is the original material hole rubbish gray level image indicated in the form of two-dimensional function, and m (x, y) is image masks function, wherein (x,
Y) it is the air coordinates for expecting the respective point in the rubbish gray level image of hole, the value of f (x, y) is intensity of the image at point (x, y)
Or whether gray scale (general interval is [0,255]), the value of m (x, y) are cheated region in material by point (x, y) and are determined, locate
It is then 1 in material hole region, is then 0 in non-material hole region.
Further, after determining the corresponding material hole region in discharging hole rubbish image, you can execute step 103 institute
The profile processing operation stated.
Optionally, profile processing is carried out (i.e. to after the processing of mask product to material hole region described in step 103
Material hole rubbish image carry out profile processing), obtain the garbage areas wheel for cheating each rubbish boundary in region for characterizing the material
Exterior feature figure, can be embodied as:
Edge detecting technology (such as Canny edge detections technology) based on setting carries out edge to material hole region
Detection forms rubbish edge image;
Following operation is executed to the rubbish edge image, forms rubbish connected region figure (specifically, it is assumed that institute before
The material hole rubbish image of formation can be as shown in Fig. 3 (a), then being formed by rubbish connected region figure at this time can be such as Fig. 3 (b) institute
Show):
All marginal points in the rubbish edge image are counted, and the marginal point counted on is added in set S0;From
A marginal point is chosen in the central area of the rubbish edge image, connection edge point set S1 is added, and update set S0=
S0-S1;It selects a point pi being connected to from S1, and is set being less than with the pixel distance between the point pi that selects in S0
(setpoint distance can be flexibly arranged set a distance according to actual conditions, such as the marginal point qj that may be configured as 2) is connected, and will own
Set S1 is added in the marginal point qj for meeting condition (being less than setpoint distance with the pixel distance between the point pi that selects), updates
Set S0=S0-S1;It repeats the above-mentioned selected element pi from S1 and set S1 is added in the qj for the condition that meets and updates set S0
Operation, until determining that set S0 is empty;
On the rubbish connected region figure, each row on scan image successively from left to right, and connect from left to right
First on direction and the last one marginal point, form the right boundary of rubbish;Meanwhile scan image successively from top to bottom
On each row, and using first marginal point on direction from top to bottom as the coboundary of rubbish;According to the left and right of rubbish
Boundary and coboundary form garbage areas profile diagram (specifically, it is assumed that being formed by rubbish connected region figure before can be such as
Shown in Fig. 3 (b), then being formed by garbage areas profile diagram at this time can be as shown in Fig. 3 (c)).
Further, after obtaining garbage areas profile diagram, you can execute step 104 described according to the rubbish area
Domain profile diagram and the material pit foundation directrix of setting determine picture altitude of the rubbish in material is cheated in material hole, and according to determining
Picture altitude determines the operation of actual height of the rubbish in material is cheated in material hole.
Optionally, described in step 104 according to the garbage areas profile diagram and the material pit foundation directrix of setting, determine material
Picture altitude of the rubbish in material is cheated in hole, and according to determining picture altitude, determine the rubbish in material hole in material is cheated
Actual height can be embodied as:
According to the garbage areas profile diagram and the material pit foundation directrix of setting, (the material pit foundation directrix can cheat region according to material
The boundary line in region is cheated with non-material and is determined), each boundary of rubbish is counted along X direction (i.e. the u axis directions of image coordinate)
Point, and record the longitudinal axis value (i.e. the v axis value of image coordinate) corresponding to each boundary point counted on;
(rubbish is formed by along the boundary point that X direction counts on to the longitudinal axis value corresponding to each boundary point for counting on
The longitudinal axis value of each point in rubbish contour curve) carry out mean operation (taking mean value), and using obtained longitudinal axis value average value as
Picture altitude of the rubbish in material is cheated in material hole;(optionally, at this point, can also be formed shown in Fig. 4 according to the longitudinal axis value average value
Rubbish boundary straight line, details are not described herein again);
It (is used according to image coordinate system (coordinate system of the image projection for indicating real world) and Image Acquisition coordinate system
In indicating the coordinate system at visual angle of image capture device) between transformational relation and Image Acquisition coordinate system and world's coordinate
It is the transformational relation between (coordinate system for indicating real world), picture altitude of the rubbish during material is cheated in material is cheated turns
It changes world coordinates into, obtains true altitude of the rubbish in material is cheated.
Wherein, according to the transformational relation and Image Acquisition coordinate system between image coordinate system and Image Acquisition coordinate system
Transformational relation between world coordinate system, picture altitude of the rubbish in material is cheated during material is cheated are converted into world coordinates, obtain
True altitude of the rubbish in material is cheated in being cheated to material, it may include:
According to the transformational relation between following image coordinate system and Image Acquisition coordinate system:
U=f × Xc/Zc
V=f × Yc/Zc;
Picture altitude v of the rubbish in material is cheated during material is cheated is converted into the corresponding height Y in Image Acquisition coordinate systemc;
And
According to the transformational relation between following Image Acquisition coordinate system and world coordinate system:
By the corresponding height Y in Image Acquisition coordinate systemcBe converted to the corresponding height Y in world coordinate systemw, obtain material hole
In rubbish material cheat in true altitude;
Wherein, u indicates that the pixel abscissa of image, v indicate that the pixel ordinate of image, f are the coke of image capture device
Away from;Xc、Yc、ZcX-axis in respectively Image Acquisition coordinate system OcXcYcZc, y-axis, the coordinate value of z-axis;Xw、Yw、ZwRespectively generation
X-axis in boundary coordinate system OwXwYwZw, y-axis, the coordinate value of z-axis;Setting folders of the θ between image capture device and horizontal plane
Angle, HcFor the vertical range between image capture device and material hole, i.e. first setting height in image capture device distance material hole;
And when the relative position between image capture device and material hole is fixed, ZwValue be fixed value, such as generally can be along θ
Direction, the distance between image capture device and material hole.
For example, it is assumed that picture altitude of the rubbish in identified material hole in material is cheated is v, then it can in the following manner really
True altitude of the rubbish in material is cheated in fixed material hole:
First according to formula (1) v=f × Y in the transformational relation between image coordinate system and Image Acquisition coordinate systemc/
Zc, determine Y corresponding with the vcValue, obtains formula (2) Yc=Zcv/f;Meanwhile it can be according to Image Acquisition coordinate system and the world
Transformational relation between coordinate system obtains formula (3):Yc=(Yw+Hc)cosθ+ZwSin θ and formula (4):Zc=(Yw+Hc)
(-sinθ)+Zwcosθ;In turn, formula (4) can be obtained according to formula (1), formula (2) and formula (3):Finally, according to formula (4), you can obtain the corresponding Y of the vw, that is, in material hole
True altitude of the rubbish in material is cheated.
That is, can be according to the transformational relation and Image Acquisition between Image Acquisition coordinate system and image coordinate system
Transformational relation between coordinate system and world coordinate system obtains the transformational relation between image coordinate system and world coordinate system, most
Whole realization indicates the effect of the distance in world coordinate system with image coordinate.
Further, while the rubbish in determining discharging hole is in the actual height during material is cheated or later, the method
It may also include:
The material is cheated into rubbish image and its corresponding rubbish actual height is shown, so that user checks.
The embodiment of the present invention one provides a kind of rubbish material level detection method, can cheat rubbish by the material cheated to collected material
Rubbish image carries out image procossing, and the corresponding material in the rubbish image of identification discharging hole cheats region, and can be by cheating region to the material
Profile processing is carried out, obtains the garbage areas profile diagram for cheating each rubbish boundary in region for characterizing the material, and then can be according to this
Garbage areas profile diagram and the material pit foundation directrix of setting, the determining picture altitude for expecting the rubbish in hole in material is cheated, and according to
Determining picture altitude obtains actual height of the rubbish in material is cheated in material hole, to realize the automatic inspection of rubbish position
It surveys, it is accuracy higher, more efficient for existing manual detection mode.
Embodiment two:
Based on inventive concept identical with embodiment one, the embodiment of the present application two provides a kind of rubbish material-level measure dress
It sets, the specific implementation of the rubbish material-level detecting device can be found in the associated description in above method embodiment one, repeat place not
It repeats again, as shown in figure 5, the rubbish material-level detecting device mainly may include:
Image acquisition units 51 can be used for acquiring the material hole rubbish image in material hole;
Material hole area determination unit 52 can be used for the image processing techniques based on setting and determine material hole rubbish image
In material cheat region;
Profile processing unit 53 can be used for carrying out profile processing to material hole region, obtain for characterizing the material hole
The garbage areas profile diagram on each rubbish boundary in region;
Rubbish material position determination unit 54 can be used for the material pit foundation directrix according to the garbage areas profile diagram and setting,
It determines picture altitude of the rubbish in material is cheated in material hole, and according to determining picture altitude, determines that the rubbish in material hole is being expected
Actual height in hole.
Optionally, described image collecting unit 51 may include being arranged the Image Acquisition subelement and benefit that upper side is cheated in material
Optical illumination subelement;Wherein, described image acquisition subelement is set with horizontal plane at setting angle and apart from material hole first
Highly, the light filling illumination subelement cheats the second setting height apart from the material, and the setting angle is more than 0 degree and is less than 90
Degree;And when described image acquisition subelement is located at the same upper side in material hole with light filling illumination subelement, described first
Setting height is more than second setting height;
The light filling illuminates subelement, can be used for cheating progress light filling illumination to material;
Described image acquires subelement, can be used for acquiring the material hole in the material hole that subelement adequate illumination is illuminated by the light filling
Rubbish image.
Further, the rubbish material-level detecting device may also include gray processing processing unit 55:
The gray processing processing unit 55 can be used for determining that the material cheats rubbish in the image processing techniques based on setting
Before material hole region in image, however, it is determined that material hole rubbish image is coloured image, then to the material cheat rubbish image into
The processing of row gray processing obtains material hole rubbish gray level image.
Further, material hole area determination unit 52 is particularly used in based on image masks technology, is cheated to the material
Rubbish image carries out the mask product processing in non-material hole region, to determine the corresponding areas Liao Keng in the rubbish image of the material hole
Domain.
Optionally, material hole area determination unit 52 is particularly used in based on image masks technology, and rubbish is cheated to the material
The corresponding material hole rubbish gray level image of rubbish image carries out the mask product processing in non-material hole region, to determine that the material cheats rubbish
Corresponding material in image cheats region.
Further, the profile processing unit 53 is particularly used in the edge detecting technology based on setting, to the material
It cheats region and carries out edge detection, form rubbish edge image;And following operation is executed to the rubbish edge image, form rubbish
Expect connected region figure:All marginal points in the rubbish edge image are counted, and set S0 is added in the marginal point counted on
In;A marginal point is chosen from the central area of the rubbish edge image, connection edge point set S1 is added, and update set
S0=S0-S1;It selects a point pi being connected to from S1, and the pixel distance in S0 between the point pi that selects is less than
The marginal point qj of setpoint distance is connected, and set S1, update set S0=S0- is added in all marginal point qj for meeting condition
S1;It repeats the above-mentioned selected element pi from S1 and set S1 is added in the qj for the condition that meets and updates the operation of set S0, until
Determine that set S0 is sky;And
On the rubbish connected region figure, each row on scan image successively from left to right, and connect from left to right
First on direction and the last one marginal point, form the right boundary of rubbish;Meanwhile scan image successively from top to bottom
On each row, and using first marginal point on direction from top to bottom as the coboundary of rubbish;And according to a left side for rubbish
Right margin and coboundary form garbage areas profile diagram.
Further, the rubbish material position determination unit 54 is particularly used according to the garbage areas profile diagram and sets
Fixed material pit foundation directrix counts each boundary point of rubbish along X direction, and records corresponding to each boundary point counted on
Longitudinal axis value, and, mean operation is carried out to the longitudinal axis value corresponding to each boundary point, and using obtained longitudinal axis value average value as material
Picture altitude of the rubbish in material is cheated in hole;According to the transformational relation between image coordinate system and Image Acquisition coordinate system, with
And the transformational relation between Image Acquisition coordinate system and world coordinate system, picture altitude of the rubbish in material is cheated during material is cheated turn
It changes world coordinates into, obtains true altitude of the rubbish in material is cheated in material hole.
Wherein, the rubbish material position determination unit is specifically used for according to following image coordinate system and Image Acquisition coordinate system
Between transformational relation:
U=f × Xc/Zc
V=f × Yc/Zc;
Picture altitude v of the rubbish in material is cheated during material is cheated is converted into the corresponding height Y in Image Acquisition coordinate systemc;
And
According to the transformational relation between following Image Acquisition coordinate system and world coordinate system:
By the corresponding height Y in Image Acquisition coordinate systemcBe converted to the corresponding height Y in world coordinate systemw, obtain material hole
In rubbish material cheat in true altitude;
Wherein, u indicates that the pixel abscissa of image, v indicate that the pixel ordinate of image, f are the coke of image capture device
Away from;Xc、Yc、ZcX-axis in respectively Image Acquisition coordinate system OcXcYcZc, y-axis, the coordinate value of z-axis;Xw、Yw、ZwRespectively generation
X-axis in boundary coordinate system OwXwYwZw, y-axis, the coordinate value of z-axis, and, ZwSpecific value be along the directions θ, image capture device
The distance between material hole;Setting angles of the θ between image capture device and horizontal plane, HcIt is cheated for image capture device and material
Between vertical range, i.e., image capture device distance material hole the first setting height.
Further, the rubbish material-level detecting device may also include information display unit 56:
Described information display unit 56, can be used for determine material hole in rubbish material cheat in actual height while or
Later, the material is cheated into rubbish image and its corresponding rubbish actual height is shown.
Further, the embodiment of the present invention additionally provides a kind of feeding trigger, and the feeding trigger includes that the present invention is implemented
Rubbish material-level detecting device described in example, details are not described herein again.
It will be understood by those skilled in the art that the embodiment of the present invention can be provided as method, apparatus (equipment) or computer journey
Sequence product.Therefore, complete hardware embodiment, complete software embodiment or combining software and hardware aspects can be used in the present invention
The form of embodiment.Moreover, the present invention can be used in one or more wherein include computer usable program code calculating
The computer program implemented in machine usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow chart of device (equipment) and computer program product
And/or block diagram describes.It should be understood that each flow in flowchart and/or the block diagram can be realized by computer program instructions
And/or the combination of the flow and/or box in box and flowchart and/or the block diagram.These computer programs can be provided to refer to
Enable the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to generate
One machine so that by the instruction that computer or the processor of other programmable data processing devices execute generate for realizing
The device for the function of being specified in one flow of flow chart or multiple flows and/or one box of block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
God and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (13)
1. a kind of rubbish material level detection method, which is characterized in that including:
The material in acquisition material hole cheats rubbish image, and the image processing techniques based on setting is determined in the rubbish image of the material hole
Material hole region;
Edge detecting technology based on setting carries out edge detection to material hole region, forms rubbish edge image;
Following operation is executed to the rubbish edge image, forms rubbish connected region figure:
All marginal points in the rubbish edge image are counted, and the marginal point counted on is added in set S0;From described
A marginal point is chosen in the central area of rubbish edge image, connection edge point set S1 is added, and update set S0=S0-
S1;Select a point pi being connected to from S1, and by the pixel distance in S0 between the point pi that selects be less than setting away from
From marginal point qj be connected, and set S1 are added in all marginal point qj for meeting condition, update set S0=S0-S1;It repeats
The above-mentioned selected element pi from S1 and set S1 is added in the qj of the condition that meets and updates the operation of set S0, until determination is gathered
S0 is sky;
On the rubbish connected region figure, each row on scan image successively from left to right, and connect direction from left to right
On first and the last one marginal point, form the right boundary of rubbish;Meanwhile from top to bottom successively on scan image
Each row, and using first marginal point on direction from top to bottom as the coboundary of rubbish;According to the right boundary of rubbish
And coboundary, form garbage areas profile diagram;
According to the garbage areas profile diagram and the material pit foundation directrix of setting, image of the rubbish in material is cheated in material hole is determined
Highly, and according to determining picture altitude, actual height of the rubbish in material is cheated in material hole is determined.
2. the method as described in claim 1, which is characterized in that the material in acquisition material hole cheats rubbish image, including:
It cheats the image capture device acquisition of upper side by being arranged in material and is cheated the light filling lighting apparatus of upper side in material by being arranged and filled
The material in the material hole of illumination is divided to cheat rubbish image.
3. the method as described in claim 1, which is characterized in that determine the material hole in the image processing techniques based on setting
Before material hole region in rubbish image, the method further includes:
If it is determined that material hole rubbish image is coloured image, then gray processing processing is carried out to material hole rubbish image, obtained
Material hole rubbish gray level image.
4. the method as described in claim 1, which is characterized in that the image processing techniques based on setting determines the material
It cheats the material in rubbish image and cheats region, including:
Based on image masks technology, the mask product processing that non-material cheats region is carried out to material hole rubbish image, to determine
Corresponding material in the rubbish image of the material hole cheats region.
5. the method as described in claim 1, which is characterized in that according to the garbage areas profile diagram and the material pit foundation of setting
Directrix determines picture altitude of the rubbish in material is cheated in material hole, and according to determining picture altitude, determines the rubbish in material hole
Actual height in material is cheated, including:
According to the garbage areas profile diagram and the material pit foundation directrix of setting, each boundary of rubbish is counted along X direction
Point, and record the longitudinal axis value corresponding to each boundary point counted on;
Mean operation is carried out to the longitudinal axis value corresponding to each boundary point, and using obtained longitudinal axis value average value as the rubbish in material hole
Picture altitude of the rubbish in material is cheated;
According to the transformational relation and Image Acquisition coordinate system and world's coordinate between image coordinate system and Image Acquisition coordinate system
Transformational relation between system, picture altitude of the rubbish in material is cheated during material is cheated are converted into world coordinates, obtain in material hole
True altitude of the rubbish in material is cheated.
6. method as claimed in claim 5, which is characterized in that according to turning between image coordinate system and Image Acquisition coordinate system
The transformational relation between relationship and Image Acquisition coordinate system and world coordinate system is changed, the rubbish during material is cheated is in material is cheated
Picture altitude is converted into world coordinates, obtains true altitude of the rubbish in material is cheated in material hole, including:
According to the transformational relation between following image coordinate system and Image Acquisition coordinate system:
U=f × Xc/Zc
V=f × Yc/Zc;
Picture altitude v of the rubbish in material is cheated during material is cheated is converted into the corresponding height Y in Image Acquisition coordinate systemc;And
According to the transformational relation between following Image Acquisition coordinate system and world coordinate system:
By the corresponding height Y in Image Acquisition coordinate systemcBe converted to the corresponding height Y in world coordinate systemw, obtain in material hole
True altitude of the rubbish in material is cheated;
Wherein, u indicates that the pixel abscissa of image, v indicate that the pixel ordinate of image, f are the focal length of image capture device;Xc、
Yc、ZcX-axis in respectively Image Acquisition coordinate system OcXcYcZc, y-axis, the coordinate value of z-axis;Xw、Yw、ZwRespectively world's coordinate
It is the x-axis in OwXwYwZw, y-axis, the coordinate value of z-axis, and, ZwSpecific value be along the directions θ, image capture device is cheated with material
The distance between;Setting angles of the θ between image capture device and horizontal plane, HcBetween image capture device and material hole
Vertical range.
7. a kind of rubbish material-level detecting device, which is characterized in that including:
Image acquisition units, the material hole rubbish image for acquiring material hole;
Material hole area determination unit determines the material hole in the rubbish image of the material hole for the image processing techniques based on setting
Region;
Profile processing unit is specifically used for the edge detecting technology based on setting, and edge detection, shape are carried out to material hole region
At rubbish edge image;And following operation is executed to the rubbish edge image, form rubbish connected region figure:Described in statistics
All marginal points in rubbish edge image, and the marginal point counted on is added in set S0;From the rubbish edge image
Central area choose a marginal point, connection edge point set S1 is added, and updates set S0=S0-S1;It is selected from S1
The marginal point qj phases for going out a point pi being connected to, and setpoint distance being less than in S0 with the pixel distance between the point pi that selects
Even, and by all marginal point qj for meeting condition set S1, update set S0=S0-S1 is added;Repetition is above-mentioned to be selected from S1
Point pi and set S1 is added in the qj of the condition that meets and updates the operation of set S0, until determining that set S0 is empty;And
On the rubbish connected region figure, each row on scan image successively from left to right, and connect on direction from left to right the
One and the last one marginal point, form the right boundary of rubbish;Meanwhile each row on scan image successively from top to bottom,
And using first marginal point on direction from top to bottom as the coboundary of rubbish;And according to the right boundary of rubbish with
And coboundary, form garbage areas profile diagram;
Rubbish material position determination unit determines material hole for the material pit foundation directrix according to the garbage areas profile diagram and setting
In picture altitude of the rubbish in material is cheated, and according to determining picture altitude, determine reality of the rubbish in material is cheated in material hole
Border height.
8. rubbish material-level detecting device as claimed in claim 7, which is characterized in that described image collecting unit includes that setting exists
The Image Acquisition subelement and light filling of the upper side in material hole illuminate subelement;
The light filling illuminates subelement, and light filling illumination is carried out for being cheated to material;
Described image acquires subelement, and the material for acquiring the material hole for illuminating subelement adequate illumination by the light filling cheats rubbish figure
Picture.
9. rubbish material-level detecting device as claimed in claim 7, which is characterized in that the rubbish material-level detecting device further includes
Gray processing processing unit:
The gray processing processing unit, used in determining material hole rubbish image in the image processing techniques based on setting
Before the region of material hole, however, it is determined that material hole rubbish image is coloured image, then carries out gray processing to material hole rubbish image
Processing obtains material hole rubbish gray level image.
10. rubbish material-level detecting device as claimed in claim 7, which is characterized in that
The material cheats area determination unit, is specifically used for being based on image masks technology, and non-material is carried out to material hole rubbish image
The mask product processing for cheating region, to determine that the corresponding material in the rubbish image of the material hole cheats region.
11. rubbish material-level detecting device as claimed in claim 7, which is characterized in that
The rubbish material position determination unit is specifically used for the material pit foundation directrix according to the garbage areas profile diagram and setting,
Each boundary point of rubbish is counted along X direction, and records the longitudinal axis value corresponding to each boundary point counted on, and, to each
Longitudinal axis value corresponding to boundary point carries out mean operation, and is cheated in material using obtained longitudinal axis value average value as the rubbish in material hole
In picture altitude;According to the transformational relation and Image Acquisition coordinate system between image coordinate system and Image Acquisition coordinate system
Transformational relation between world coordinate system, picture altitude of the rubbish in material is cheated during material is cheated are converted into world coordinates, obtain
True altitude of the rubbish in material is cheated in being cheated to material.
12. rubbish material-level detecting device as claimed in claim 11, which is characterized in that the rubbish material position determination unit, tool
Body is used for according to the transformational relation between following image coordinate system and Image Acquisition coordinate system:
U=f × Xc/Zc
V=f × Yc/Zc;
Picture altitude v of the rubbish in material is cheated during material is cheated is converted into the corresponding height Y in Image Acquisition coordinate systemc;And
According to the transformational relation between following Image Acquisition coordinate system and world coordinate system:
By the corresponding height Y in Image Acquisition coordinate systemcBe converted to the corresponding height Y in world coordinate systemw, obtain in material hole
True altitude of the rubbish in material is cheated;
Wherein, u indicates that the pixel abscissa of image, v indicate that the pixel ordinate of image, f are the focal length of image capture device;Xc、
Yc、ZcX-axis in respectively Image Acquisition coordinate system OcXcYcZc, y-axis, the coordinate value of z-axis;Xw、Yw、ZwRespectively world's coordinate
It is the x-axis in OwXwYwZw, y-axis, the coordinate value of z-axis, and, ZwSpecific value be along the directions θ, image capture device is cheated with material
The distance between;Setting angles of the θ between image capture device and horizontal plane, HcBetween image capture device and material hole
Vertical range.
13. a kind of feeding trigger, which is characterized in that the feeding trigger includes any rubbish of claim 7~12
Level detecting apparatus.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510669760.6A CN105389795B (en) | 2015-10-13 | 2015-10-13 | A kind of rubbish material level detection method, device and feeding trigger |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510669760.6A CN105389795B (en) | 2015-10-13 | 2015-10-13 | A kind of rubbish material level detection method, device and feeding trigger |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105389795A CN105389795A (en) | 2016-03-09 |
CN105389795B true CN105389795B (en) | 2018-09-28 |
Family
ID=55422045
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510669760.6A Active CN105389795B (en) | 2015-10-13 | 2015-10-13 | A kind of rubbish material level detection method, device and feeding trigger |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105389795B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6554148B2 (en) * | 2017-07-31 | 2019-07-31 | 荏原環境プラント株式会社 | Apparatus, system, program, method, and data structure for estimating waste quality |
CN115293661B (en) * | 2022-10-08 | 2022-12-09 | 湖南仁和环保科技有限公司 | Garbage transportation scheduling system and scheduling method based on image processing |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6234351B1 (en) * | 1998-01-28 | 2001-05-22 | A. R. Arena Products, Inc. | Apparatus and method for enhancing evacuation of bulk material shipper bags |
CN101270981A (en) * | 2007-03-23 | 2008-09-24 | 高幼年 | Material position measuring method and device based on machine vision |
CN102072720A (en) * | 2010-12-21 | 2011-05-25 | 西安交通大学 | High accurately measuring method for in-tube liquid level elevation of photoelectric and tubular settlement meter |
CN102116659A (en) * | 2010-10-19 | 2011-07-06 | 中国矿业大学(北京) | Interval convergence based stock bin level detection method |
CN102116661A (en) * | 2010-10-19 | 2011-07-06 | 中国矿业大学(北京) | Method for detecting dynamic stock level in stock bin limit position based on machine vision |
CN102680496A (en) * | 2011-04-15 | 2012-09-19 | 京东方科技集团股份有限公司 | Foreign body detection device and method |
CN102997973A (en) * | 2011-09-14 | 2013-03-27 | 阿尔斯通技术有限公司 | Level detector for measuring foam and aerated slurry level in a wet flue gas desulfurization absorber tower |
CN103834758A (en) * | 2014-03-14 | 2014-06-04 | 中南大学 | Blast furnace materiel level real-time detection method with continuous high precision |
CN107010335A (en) * | 2017-05-31 | 2017-08-04 | 国电科学技术研究院 | It is a kind of to be convenient for the feed bin that material position is continuously measured |
-
2015
- 2015-10-13 CN CN201510669760.6A patent/CN105389795B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6234351B1 (en) * | 1998-01-28 | 2001-05-22 | A. R. Arena Products, Inc. | Apparatus and method for enhancing evacuation of bulk material shipper bags |
CN101270981A (en) * | 2007-03-23 | 2008-09-24 | 高幼年 | Material position measuring method and device based on machine vision |
CN102116659A (en) * | 2010-10-19 | 2011-07-06 | 中国矿业大学(北京) | Interval convergence based stock bin level detection method |
CN102116661A (en) * | 2010-10-19 | 2011-07-06 | 中国矿业大学(北京) | Method for detecting dynamic stock level in stock bin limit position based on machine vision |
CN102072720A (en) * | 2010-12-21 | 2011-05-25 | 西安交通大学 | High accurately measuring method for in-tube liquid level elevation of photoelectric and tubular settlement meter |
CN102680496A (en) * | 2011-04-15 | 2012-09-19 | 京东方科技集团股份有限公司 | Foreign body detection device and method |
CN102997973A (en) * | 2011-09-14 | 2013-03-27 | 阿尔斯通技术有限公司 | Level detector for measuring foam and aerated slurry level in a wet flue gas desulfurization absorber tower |
CN103834758A (en) * | 2014-03-14 | 2014-06-04 | 中南大学 | Blast furnace materiel level real-time detection method with continuous high precision |
CN107010335A (en) * | 2017-05-31 | 2017-08-04 | 国电科学技术研究院 | It is a kind of to be convenient for the feed bin that material position is continuously measured |
Also Published As
Publication number | Publication date |
---|---|
CN105389795A (en) | 2016-03-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101498592B (en) | Reading method and apparatus for pointer instrument | |
CN110261410A (en) | A kind of detection device and method of glass lens defect | |
CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
CN102988052B (en) | Method and system for measuring foot length | |
CN105217198B (en) | A kind of feeding garbage control method, device and feeding trigger | |
CN105866129A (en) | Product surface quality online detection method based on digital projection | |
CN104394385B (en) | A kind of ceramic tile quality on-line detecting device and its detection method | |
CN104335030A (en) | Method for inspecting for foreign substance on substrate | |
CN107869954B (en) | Binocular vision volume weight measurement system and implementation method thereof | |
CN101886942A (en) | Water gauge marking method and water level detection method | |
CN103185549A (en) | Board inspection apparatus and method | |
CN105784710A (en) | Concrete bridge crack detection device based on digital image processing | |
CN103954334B (en) | Fully automatic image pickup type water meter verification system and operating method thereof | |
CN111323434B (en) | Application of phase deflection technology in glass defect detection | |
CN106127205A (en) | A kind of recognition methods of the digital instrument image being applicable to indoor track machine people | |
CN107271445B (en) | Defect detection method and device | |
CN206223683U (en) | A kind of tabular workpiece with hole surface defect detection apparatus | |
CN104541303B (en) | For the method for carrying out nondestructive test to blade pre-form | |
CN114577805A (en) | MiniLED backlight panel defect detection method and device | |
CN104766310B (en) | light source detection system and detection method | |
CN204405556U (en) | A kind of glue into concrete beam cracks pick-up unit based on Digital Image Processing | |
CN108445010A (en) | Automatic optical detection method and device | |
CN105389795B (en) | A kind of rubbish material level detection method, device and feeding trigger | |
CN107436304A (en) | A kind of surface of concrete structure detection means | |
CN111982933B (en) | Coating defect detection system and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20170622 Address after: 410000 Hunan province Changsha hi tech Development Zone, Lin Yulu No. 288 Applicant after: Changsha ZOOMLION Environmental Industry Co., Ltd. Address before: 410013 Yuelu District, Hunan, silver basin Road, No. 361, No. Applicant before: Zoomlion Heavy Industry Science & Technology Development Co., Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |