CN105550683A - Vision-based pointer instrument automatic reading system and method - Google Patents
Vision-based pointer instrument automatic reading system and method Download PDFInfo
- Publication number
- CN105550683A CN105550683A CN201510894410.XA CN201510894410A CN105550683A CN 105550683 A CN105550683 A CN 105550683A CN 201510894410 A CN201510894410 A CN 201510894410A CN 105550683 A CN105550683 A CN 105550683A
- Authority
- CN
- China
- Prior art keywords
- pointer
- pointer instrument
- value
- circle
- instrument
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a vision-based pointer instrument automatic reading system and method. The system comprises: a circle center acquiring module used for acquiring image data of a pointer instrument and searching for the center of a circle of the pointer instrument in the image data; a pointer acquiring module used for extracting pointers of the pointer instrument through a Houghline function of Hough transform; a dial acquiring module used for extraction of a dial of the pointer instrument, extraction of the dial is determined according to image color information, and an optimal threshold value of color is determined by use of values of RGB, thereby extracting the dial of the pointer instrument; and a scale reading module used for calculating and reading an indicated number through the acquired pointers of the pointer instrument and the dial of the pointer instrument. Readings are directly obtained according to processing of an algorithm and are transmitted to a command center, and the command center can observe whether the instrument works normally according to the data, which is convenient and rapid.
Description
Technical field
The present invention relates to instrument automatic detecting image processing field, particularly relate to a kind of pointer instrument automatic Car Plate Reading System and method of view-based access control model.
Background technology
Current most domestic high-risk areas adopts manual type to make an inspection tour equipment, but be subject to the restriction of tour personnel to the familiarity of equipment, professional skill, working experience, attitude, the factors such as sense of responsibility and the state of mind, the work of patrolling and examining is a very difficult job, especially to the high-risk areas of remote districts, manpower and the time of at substantial is needed; Secondly, because high-risk areas mostly is high pressure, SF6 equipment, manual inspection has very large danger; Simultaneously for the high-risk areas of unmanned or few man on duty, the emergency command scheduling difficulty when high-risk areas fault is also very large.Therefore necessary research replaces the crusing robot of staff to carry out automatic detecting to high-risk areas to a certain extent becomes the development trend of patrolling and examining high-risk areas.
Along with the development of technology of Internet of things, instrument onboard data sending module newly developed, is sent to control center by meter reading automatically, but this technology must built-in corresponding module, and cost is higher, can not be used for present stage to have installed in fixed instrumentation.Therefore be necessary that exploitation is a kind of and accurately can represent the system of number by readout meter, existing instrument is not reequiped, replace the various instrument of coherent detection personnel to high-risk areas to read, and reduce the error of reading.Had intelligent inspection robot, not only checkout equipment is accurate, and can record tour data, greatly alleviates staff's working strength, and ensures the safety problem of patrol officer when detecting.
Still a large amount of in the large industrial enterprise of China at present exist the pointer instrument of simulating, and its reading and test problems still need manpower, and the level of detection and reading robotization is lower.High-risk areas crusing robot does not occur extensive universal at present, and reason is that high-risk areas crusing robot system all has much room for improvement in reliability and accuracy.Also be also need continue research and break through on some technology point in fact.High-risk areas crusing robot system is the predetermined point that robot needs to be arrived by navigational system regulation in advance from master mode, executes the task.These tasks comprise automatic identifier table and reading, and this task needs to be applied to the reading that machine vision technique has come identification to instrument and pointer.This just needs those skilled in the art badly and solves corresponding technical matters, carries out accurate reading to pointer instrument.
Summary of the invention
The present invention is intended at least solve the technical matters existed in prior art, especially innovatively proposes a kind of pointer instrument automatic Car Plate Reading System and method of view-based access control model.
In order to realize above-mentioned purpose of the present invention, the invention provides a kind of pointer instrument automatic Car Plate Reading System of view-based access control model, it comprises:
Obtaining center of circle module, for obtaining image of gauge with pointer data, finding the center of circle of view data middle finger pin type instrument;
Obtain pointer module, for being extracted the pointer of pointer instrument by the Houghline function of Hough transform;
Obtain index dial module, the extraction for the index dial of pointer instrument is determined according to image color information, utilizes the optimal threshold of the value determination color of RGB, thus extracts the index dial of pointer instrument;
Read calibration block, for the pointer of pointer instrument by obtaining and the index dial of pointer instrument, calculating is carried out to indicated number and read.
The present invention also discloses a kind of automatic read method of pointer instrument of view-based access control model, and it comprises the steps:
S1, obtains image of gauge with pointer data, finds the center of circle of view data middle finger pin type instrument;
S2, extracts the pointer of pointer instrument by the Houghline function of Hough transform;
S3, the extraction of the index dial of pointer instrument is determined according to image color information, utilizes the optimal threshold of the value determination color of RGB, thus extracts the index dial of pointer instrument;
S4, by obtain the pointer of pointer instrument and the index dial of pointer instrument to indicated number carry out calculatings reading.
The automatic read method of pointer instrument of described view-based access control model, preferably, described S1 comprises:
S1-1, carry out pre-processing image data, the local binarization of self-adaption binaryzation is used to process, entire image is divided into N number of window according to certain rule by described local binarization, by the pixel in this window, two parts are divided into according to a unified threshold value T again to each window in this N number of window, carry out binary conversion treatment, get the mean value of this window;
S1-2, carries out local auto-adaptive binarization method; Local auto-adaptive binaryzation, the method is exactly on the basis of local binarization, and setting threshold value is by the mean value E to this window pixel, the difference square P between pixel, the various local features such as the root-mean-square value Q between pixel, set the calculating that a parametric equation carries out threshold value;
S1-3, by the parameter of setting input, uses MATLAB function to find the round dial of pointer instrument; Owing to only having described round dial to be circular in view data, therefore use imfindcircles function, obtained the circle in region by setting least radius and maximum radius, and mark its center of circle and radius;
Its principle utilizes hough to detect transform circle, obtained by parameter such as setting least radius and maximum radius etc.
To the center of circle and the radius of the circle detected; This function appears at ImageProcessingToolbox8.0, is all imfindcircles function by this function package in the version after MATLAB2012 version; Hough detection efficiency is low, code redundancy, and can not the circle detecting target area of entirely accurate, does not therefore use hough to detect here, and uses imfindcircles function, accurately detected by the fenestra in region bad for picture quality;
S1-4, intercepts the circle of target area in view data, is set to black by extra-regional part; Utilize the center of circle that S1-3 obtains, retain circle inner, circle external pixels is set to 0.
The automatic read method of pointer instrument of described view-based access control model, preferably, described S2 comprises: processed view data by gray scale morphology
The corrosion of gray level image and expansion process are directly calculated from the gray level function of view data and structural element; Certain in image 1 f (x, y) gray scale morphology erosion operation is defined as
(f Θ g) (x, y)=min{f (x-i, y-j)-g (-i ,-j) } gray scale morphology dilation operation is defined as
Grayscale morphologic expand namely with structural element g (i, j) for template, search the gray scale of image in structural motif magnitude range and maximum value; Erosion operation process is then with structural element g (i, j) for template, searches the minimal value of the gray scale difference of image in structural motif magnitude range; The morphological dilation of gray scale and the expression formula of morphological erosion computing and the convolution integral of image procossing closely similar, take advantage of to replace connecting with, difference, replace asking summation with minimum, maximum computing;
Gray scale morphology closed operation is defined as
Gray scale morphology opening operation is defined as
Opening operation adopts identical structural elements first to do the interative computation corroding and do and expand, and closed operation adopts identical structural elements first to do the interative computation expanding and do and corrode; The basic role of opening operation and closed operation is to the smoothing process of image: opening operation can be filled some duck eyes and the target of two vicinities be coupled together.
The automatic read method of pointer instrument of described view-based access control model, preferably, described S2 comprises:
S2-1, carry out cumulative statistics by parameter space, adopt straight line polar equation, transformation equation is as follows:
ρ＝xcosθ+ysinθ，
A sinusoidal curve in the corresponding new argument space of point in raw image data, i.e. point-sinusoidal curve antithesis; The detailed process of detection of straight lines is exactly the value allowing θ get time, then calculates the value of ρ, then adds up to cumulative array according to the value of θ and ρ, thus obtain the number of collinear point;
For the determination of θ and ρ span, if detected straight line is at first quartile, upper right corner coordinate is (m, n);
S2-2, when straight line is from when being rotated counterclockwise with x-axis overlapping position, the value of θ starts by 0 ° of increase, until 180 °, so the span of θ is 0 ° ~ 180 °; By straight line polar equation:
wherein
so during and if only if φ=± 90 ° (adjusting the value of θ according to φ),
I.e. ρ span
The size of totalizer just can be determined by the span of θ, ρ and resolution, thus detection of straight lines.
The automatic read method of pointer instrument of described view-based access control model, preferably, described S3 comprises: left side start line and the right terminated line all have certain angle with horizontal line, are set to alpha2 and alpha3 respectively; Suppose that alpha1 is the angle between pointer and the horizontal line of its direction, theta is the angle of left side start line to pointer direction; Positive and negative according to alpha1, is divided into following four kinds by the situation calculating theta:
The first situation: suppose that alpha1 is negative, then theta=alpha2 – alpha1;
The second situation: suppose that alpha1 is just, then theta=alpha2+180 °-alpha1;
The third situation: suppose that alpha1 is just, then theta=alpha2 – alpha1;
4th kind of situation: suppose that alpha1 is negative, then theta=alpha2+180 °-alpha1.
The automatic read method of pointer instrument of described view-based access control model, preferably, described S4 comprises:
S4-1, carries out gray-scale edges process to raw image data, prepares, remove interfere information for next step detects ellipse;
S4-2, detects oval and marks.
The automatic read method of pointer instrument of described view-based access control model, preferably, described S4-2 comprises:
S4-2-1, in two dimensional surface coordinate system, ellipse represents by two kinds of forms, and a kind of is utilize the quantic of equation of conic section to represent, as follows:
Ax
2+ Bxy+Cy
2+ Dx+Ey+F=0, wherein A, B, C, D, E, F are coefficient (constant)
Represent with the geometric parameter of plane coordinate system in addition, i.e. ellipse center location (x
0, y
0), major axis and minor axis (a, b), the rotational angle theta of major axis, these 5 parameters of any ellipse in two dimensional surface are uniquely determined,
S4-2-2, passes through formula
Wherein a is major axis, and b is minor axis;
For ellipse fitting, when stochastic error is normal distribution by least square method, the optimal estimation techniques released by maximum likelihood method, makes the quadratic sum of measuring error minimum, is obtaining one of the most reliable method of one group of unknown quantity from one group of measured value; Least square technology mainly finds parameter sets, thus the distance metric between minimise data point and ellipse, distance metric here common are geometric distance and algebraic distance; Geometric distance represents the distance of certain point to curve closest approach, certain point (x in plane
0, y
0) to the algebraic distance of curve representated by Equation f (x, y)=0 be exactly f (x
0, y
0)=0 is below introduce least square method using algebraic distance as distance metric;
S4-2-3, if elliptic equation is such as formula Ax
2+ Bxy+Cy
2shown in+Dx+Ey+F=0, in order to avoid null solution, and any integral multiple separated all is considered as the statement to same ellipse, do some restrictions to parameter, constraint condition is set to A+C=1; Obviously, the discrete point directly after the above-mentioned equation edge detection of application carries out least square process, just can obtain each coefficient in equation, namely ask objective function
Minimum value determine each coefficient, make f (A, B, C, D, E, F) value be minimum, according to Eular-Lagrange equations, must have
obtain a system of linear equations thus, then application solves the algorithm of system of linear equations, such as Gaussian elimination, in conjunction with constraint condition, just can in the hope of equation coefficient A, and the value of B, C, D, E, F; Its essence is according to Eular-Lagrange equations reverse coefficient A, B, C, D, E, F.
In sum, owing to have employed technique scheme, the invention has the beneficial effects as follows:
Design a kind of identifiable design and calculate the system of the accurate registration of the various instrument in high-risk areas, according to the corresponding algorithm of dissimilar design of instrument, achievement in research is implanted chip to use in sensor loading intelligent robot, intelligent robot obtains algorithm to be processed view data to the instrument of specified point by camera or thermal imaging along the map magnetic track set, then directly obtain registration according to the process of algorithm and pass to command centre, whether command centre can observe instrument according to data and normally work, liberate labour to a great extent, also improve work efficiency.
The advantage of Hough transform method is under there is noise effect on pointer border or discontinuous situation occurs for the pointer image that has other targets to hide and cause, still has good fault-tolerance and robustness.Solution uses thinning algorithm to go to reduce operation time exactly, to reach the object detected fast.
Additional aspect of the present invention and advantage will part provide in the following description, and part will become obvious from the following description, or be recognized by practice of the present invention.
Accompanying drawing explanation
Above-mentioned and/or additional aspect of the present invention and advantage will become obvious and easy understand from accompanying drawing below combining to the description of embodiment, wherein:
Fig. 1 is overview flow chart of the present invention;
Fig. 2 is angle schematic diagram of the present invention;
Fig. 3 is identification schematic diagram of the present invention;
Fig. 4 is identification schematic diagram of the present invention;
Fig. 5 is identification schematic diagram of the present invention;
Fig. 6 is identification schematic diagram of the present invention;
Fig. 7-10 is embodiment of the present invention schematic diagram.
Embodiment
Be described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has element that is identical or similar functions from start to finish.Being exemplary below by the embodiment be described with reference to the drawings, only for explaining the present invention, and can not limitation of the present invention being interpreted as.
In describing the invention, it will be appreciated that, term " longitudinal direction ", " transverse direction ", " on ", D score, "front", "rear", "left", "right", " vertically ", " level ", " top ", " end " " interior ", the orientation of the instruction such as " outward " or position relationship be based on orientation shown in the drawings or position relationship, only the present invention for convenience of description and simplified characterization, instead of indicate or imply that the device of indication or element must have specific orientation, with specific azimuth configuration and operation, therefore can not be interpreted as limitation of the present invention.
In describing the invention, unless otherwise prescribed and limit, it should be noted that, term " installation ", " being connected ", " connection " should be interpreted broadly, such as, can be mechanical connection or electrical connection, also can be the connection of two element internals, can be directly be connected, also indirectly can be connected by intermediary, for the ordinary skill in the art, the concrete meaning of above-mentioned term can be understood as the case may be.
Pass through algorithm steps:
The first step: picture pre-service, uses self-adaption binaryzation.
Here the graythresh not adopting MATLAB to carry and rim detection, and use self-adaption binaryzation.
Because graythresh effect is bad, moreover inherently comprises binaryzation, belong to overall binaryzation, there is very large defect in overall binaryzation in performance image detail.
And self-adaption binaryzation belongs to local binarization, compensate for the defect of overall binaryzation.Entire image is divided into N number of window according to certain rule by local binarization, according to a unified threshold value T, the pixel in this window is divided into two parts again, carries out binary conversion treatment to each window in this N number of window.Local binarization also has a defect, and this defect is present in the selected of uniform threshold.This threshold value does not get through rational computing, is generally the mean value getting this window, which results in the defect still occurring overall binaryzation at each window, in order to address this problem, occurred local auto-adaptive binarization method.Local auto-adaptive binaryzation, the method is exactly on the basis of local binarization, the setting of threshold value is more rationalized.The threshold value of the method is by the mean value E to this window pixel, and the difference square P between pixel, the various local features such as the root-mean-square value Q between pixel, set the calculating that a parametric equation carries out threshold value.The binary image drawn so just more can show the details in binary image.
Second step: by the parameter of setting input, the function using MATLAB to carry finds round dial.
Owing to only having dial plate to be circular in Instrument image, therefore use imfindcircles function, obtained the circle in region by setting least radius and maximum radius, and mark its center of circle and radius.
3rd step: intercept target area circle on the basis of previous step, extra-regional part is set to black.
Utilize the center of circle obtained in the previous step and radius, retain circle inner, circle external pixels is set to 0.
4th step: detect pointer.Go out the longest straight line by hough straight-line detection and be pointer.
The extraction of pointer can obtain according to the houghline function in hough conversion, and the basic thought of Hough transform is the duality of dotted line.On the one hand, the corresponding line intersected in parameter space of the point of conllinear in image space; On the other hand, all straight lines intersecting at same point in parameter space have the point of conllinear corresponding with it in image space.Therefore hough conversion is the test problems of straight-line detection question variation in image space to parameter space mid point, completes Detection task by the statistics that simply adds up in parameter space.
If use straight-line equation in parameter space, when image space straight slope is infinitely great, totalizer size can be made and become very large, thus make computation complexity excessive.For addressing this problem, adopt straight line polar equation, transformation equation is as follows:
Carry out cumulative statistics by parameter space, adopt straight line polar equation, transformation equation is as follows:
ρ＝xcosθ+ysinθ，
A sinusoidal curve in the corresponding new argument space of point in raw image data, i.e. point-sinusoidal curve antithesis; The detailed process of detection of straight lines is exactly the value allowing θ get time, then calculates the value of ρ, then adds up to cumulative array according to the value of θ and ρ, thus obtain the number of collinear point;
For the determination of θ and ρ span, if detected straight line is at first quartile, upper right corner coordinate is (m, n); According to this equation, a sinusoidal curve in the corresponding new argument space of the point in original image space, i.e. point-sinusoidal curve antithesis.The detailed process of detection of straight lines allows θ get all over possible values exactly, then calculates the value of ρ, then adds up to cumulative array according to the value of θ and ρ, thus obtain the number of collinear point.Then the situation of first quartile cathetus is as shown in Figure 2,
As seen in figures 3-6, left side start line and the right terminated line all have certain angle with horizontal line, are set to alpha2 and alpha3 respectively; Suppose that alpha1 is the angle between pointer and the horizontal line of its direction, theta is the angle of left side start line to pointer direction; Positive and negative according to alpha1, is divided into following four kinds by the situation calculating theta:
The first situation: suppose that alpha1 is negative, then theta=alpha2 – alpha1;
The second situation: suppose that alpha1 is just, then theta=alpha2+180 °-alpha1;
The third situation: suppose that alpha1 is just, then theta=alpha2 – alpha1;
4th kind of situation: suppose that alpha1 is negative, then theta=alpha2+180 °-alpha1.
The embodiment schematic diagram in practical operation is carried out as is seen in figs 7-10 for the present invention.
As shown in Figure 1, the present invention also discloses a kind of automatic read method of pointer instrument of view-based access control model, and it comprises the steps:
S1, obtains image of gauge with pointer data, finds the center of circle of view data middle finger pin type instrument;
S2, extracts the pointer of pointer instrument by the Houghline function of Hough transform;
S3, the extraction of the index dial of pointer instrument is determined according to image color information, utilizes the optimal threshold of the value determination color of RGB, thus extracts the index dial of pointer instrument;
S4, by obtain the pointer of pointer instrument and the index dial of pointer instrument to indicated number carry out calculatings reading.
The automatic read method of pointer instrument of described view-based access control model, preferably, described S1 comprises:
S1-1, carry out pre-processing image data, the local binarization of self-adaption binaryzation is used to process, entire image is divided into N number of window according to certain rule by described local binarization, by the pixel in this window, two parts are divided into according to a unified threshold value T again to each window in this N number of window, carry out binary conversion treatment, get the mean value of this window;
S1-2, carries out local auto-adaptive binarization method; Local auto-adaptive binaryzation, the method is exactly on the basis of local binarization, and setting threshold value is by the mean value E to this window pixel, the difference square P between pixel, the various local features such as the root-mean-square value Q between pixel, set the calculating that a parametric equation carries out threshold value;
S1-3, by the parameter of setting input, uses MATLAB function to find the round dial of pointer instrument; Owing to only having described round dial to be circular in view data, therefore use imfindcircles function, obtained the circle in region by setting least radius and maximum radius, and mark its center of circle and radius;
Its principle utilizes hough to detect transform circle, obtained by parameter such as setting least radius and maximum radius etc.
To the center of circle and the radius of the circle detected; This function appears at ImageProcessingToolbox8.0, is all imfindcircles function by this function package in the version after MATLAB2012 version; Hough detection efficiency is low, code redundancy, and can not the circle detecting target area of entirely accurate, does not therefore use hough to detect here, and uses imfindcircles function, accurately detected by the fenestra in region bad for picture quality;
S1-4, intercepts the circle of target area in view data, is set to black by extra-regional part; Utilize the center of circle that S1-3 obtains, retain circle inner, circle external pixels is set to 0.
The automatic read method of pointer instrument of described view-based access control model, preferably, described S2 comprises: processed view data by gray scale morphology
The corrosion of gray level image and expansion process are directly calculated from the gray level function of view data and structural element; Certain in image 1 f (x, y) gray scale morphology erosion operation is defined as
(f Θ g) (x, y)=min{f (x-i, y-j)-g (-i ,-j) } gray scale morphology dilation operation is defined as
Grayscale morphologic expand namely with structural element g (i, j) for template, search the gray scale of image in structural motif magnitude range and maximum value; Erosion operation process is then with structural element g (i, j) for template, searches the minimal value of the gray scale difference of image in structural motif magnitude range; The morphological dilation of gray scale and the expression formula of morphological erosion computing and the convolution integral of image procossing closely similar, take advantage of to replace connecting with, difference, replace asking summation with minimum, maximum computing;
Gray scale morphology closed operation is defined as
Gray scale morphology opening operation is defined as
Opening operation adopts identical structural elements first to do the interative computation corroding and do and expand, and closed operation adopts identical structural elements first to do the interative computation expanding and do and corrode; The basic role of opening operation and closed operation is to the smoothing process of image: opening operation can be filled some duck eyes and the target of two vicinities be coupled together.
The automatic read method of pointer instrument of described view-based access control model, preferably, described S2 comprises:
S2-1, carry out cumulative statistics by parameter space, adopt straight line polar equation, transformation equation is as follows:
ρ＝xcosθ+ysinθ，
A sinusoidal curve in the corresponding new argument space of point in raw image data, i.e. point-sinusoidal curve antithesis; The detailed process of detection of straight lines is exactly the value allowing θ get time, then calculates the value of ρ, then adds up to cumulative array according to the value of θ and ρ, thus obtain the number of collinear point;
For the determination of θ and ρ span, if detected straight line is at first quartile, upper right corner coordinate is (m, n);
S2-2, when straight line is from when being rotated counterclockwise with x-axis overlapping position, the value of θ starts by 0 ° of increase, until 180 °, so the span of θ is 0 ° ~ 180 °; By straight line polar equation:
wherein
so during and if only if φ=± 90 ° (adjusting the value of θ according to φ),
I.e. ρ span
The size of totalizer just can be determined by the span of θ, ρ and resolution, thus detection of straight lines.
The automatic read method of pointer instrument of described view-based access control model, preferably, described S4 comprises:
S4-1, carries out gray-scale edges process to raw image data, prepares, remove interfere information for next step detects ellipse;
S4-2, detects oval and marks.
The automatic read method of pointer instrument of described view-based access control model, preferably, described S4-2 comprises:
S4-2-1, in two dimensional surface coordinate system, ellipse represents by two kinds of forms, and a kind of is utilize the quantic of equation of conic section to represent, as follows:
Ax
2+ Bxy+Cy
2+ Dx+Ey+F=0, wherein A, B, C, D, E, F are coefficient (constant)
Represent with the geometric parameter of plane coordinate system in addition, i.e. ellipse center location (x
0, y
0), major axis and minor axis (a, b), the rotational angle theta of major axis, these 5 parameters of any ellipse in two dimensional surface are uniquely determined,
S4-2-2, passes through formula
Wherein a is major axis, and b is minor axis;
For ellipse fitting, when stochastic error is normal distribution by least square method, the optimal estimation techniques released by maximum likelihood method, makes the quadratic sum of measuring error minimum, is obtaining one of the most reliable method of one group of unknown quantity from one group of measured value; Least square technology mainly finds parameter sets, thus the distance metric between minimise data point and ellipse, distance metric here common are geometric distance and algebraic distance; Geometric distance represents the distance of certain point to curve closest approach, certain point (x in plane
0, y
0) to the algebraic distance of curve representated by Equation f (x, y)=0 be exactly f (x
0, y
0)=0 is below introduce least square method using algebraic distance as distance metric;
S4-2-3, if elliptic equation is such as formula Ax
2+ Bxy+Cy
2shown in+Dx+Ey+F=0, in order to avoid null solution, and any integral multiple separated all is considered as the statement to same ellipse, do some restrictions to parameter, constraint condition is set to A+C=1; Obviously, the discrete point directly after the above-mentioned equation edge detection of application carries out least square process, just can obtain each coefficient in equation, namely ask objective function
Minimum value determine each coefficient, make f (A, B, C, D, E, F) value be minimum, according to Eular-Lagrange equations, must have
obtain a system of linear equations thus, then application solves the algorithm of system of linear equations, such as Gaussian elimination, in conjunction with constraint condition, just can in the hope of equation coefficient A, and the value of B, C, D, E, F; Its essence is according to Eular-Lagrange equations reverse coefficient A, B, C, D, E, F.
The invention provides a kind of pointer instrument automatic Car Plate Reading System of view-based access control model, it comprises:
Obtaining center of circle module, for obtaining image of gauge with pointer data, finding the center of circle of view data middle finger pin type instrument;
Obtain pointer module, for being extracted the pointer of pointer instrument by the Houghline function of Hough transform;
Obtain index dial module, the extraction for the index dial of pointer instrument is determined according to image color information, utilizes the optimal threshold of the value determination color of RGB, thus extracts the index dial of pointer instrument;
Read calibration block, for the pointer of pointer instrument by obtaining and the index dial of pointer instrument, calculating is carried out to indicated number and read.
Action in above-mentioned module is identical with the automatic read method of the pointer instrument of view-based access control model.
In sum, owing to have employed technique scheme, the invention has the beneficial effects as follows:
Design a kind of identifiable design and calculate the system of the accurate registration of the various instrument in high-risk areas, according to the corresponding algorithm of dissimilar design of instrument, achievement in research is implanted chip to use in sensor loading intelligent robot, intelligent robot obtains algorithm to be processed view data to the instrument of specified point by camera or thermal imaging along the map magnetic track set, then directly obtain registration according to the process of algorithm and pass to command centre, whether command centre can observe instrument according to data and normally work, liberate labour to a great extent, also improve work efficiency.
The advantage of Hough transform method is under there is noise effect on pointer border or discontinuous situation occurs for the pointer image that has other targets to hide and cause, still has good fault-tolerance and robustness.Solution uses thinning algorithm to go to reduce operation time exactly, to reach the object detected fast.
In the description of this instructions, specific features, structure, material or feature that the description of reference term " embodiment ", " some embodiments ", " example ", " concrete example " or " some examples " etc. means to describe in conjunction with this embodiment or example are contained at least one embodiment of the present invention or example.In this manual, identical embodiment or example are not necessarily referred to the schematic representation of above-mentioned term.And the specific features of description, structure, material or feature can combine in an appropriate manner in any one or more embodiment or example.
Although illustrate and describe embodiments of the invention, those having ordinary skill in the art will appreciate that: can carry out multiple change, amendment, replacement and modification to these embodiments when not departing from principle of the present invention and aim, scope of the present invention is by claim and equivalents thereof.
Claims (8)
1. a pointer instrument automatic Car Plate Reading System for view-based access control model, is characterized in that, comprising:
Obtaining center of circle module, for obtaining image of gauge with pointer data, finding the center of circle of view data middle finger pin type instrument;
Obtain pointer module, for being extracted the pointer of pointer instrument by the Houghline function of Hough transform;
Obtain index dial module, the extraction for the index dial of pointer instrument is determined according to image color information, utilizes the optimal threshold of the value determination color of RGB, thus extracts the index dial of pointer instrument;
Read calibration block, for the pointer of pointer instrument by obtaining and the index dial of pointer instrument, calculating is carried out to indicated number and read.
2. the automatic read method of the pointer instrument of view-based access control model, is characterized in that, comprise the steps:
S1, obtains image of gauge with pointer data, finds the center of circle of view data middle finger pin type instrument;
S2, extracts the pointer of pointer instrument by the Houghline function of Hough transform;
S3, the extraction of the index dial of pointer instrument is determined according to image color information, utilizes the optimal threshold of the value determination color of RGB, thus extracts the index dial of pointer instrument;
S4, by obtain the pointer of pointer instrument and the index dial of pointer instrument to indicated number carry out calculatings reading.
3. the automatic read method of the pointer instrument of view-based access control model according to claim 2, is characterized in that, described S1 comprises:
S1-1, carry out pre-processing image data, the local binarization of self-adaption binaryzation is used to process, entire image is divided into N number of window according to certain rule by described local binarization, by the pixel in this window, two parts are divided into according to a unified threshold value T again to each window in this N number of window, carry out binary conversion treatment, get the mean value of this window;
S1-2, carries out local auto-adaptive binarization method; Local auto-adaptive binaryzation, the method is exactly on the basis of local binarization, and setting threshold value is by the mean value E to this window pixel, the difference square P between pixel, the various local features such as the root-mean-square value Q between pixel, set the calculating that a parametric equation carries out threshold value;
S1-3, by the parameter of setting input, uses MATLAB function to find the round dial of pointer instrument; Owing to only having described round dial to be circular in view data, therefore use imfindcircles function, obtained the circle in region by setting least radius and maximum radius, and mark its center of circle and radius;
Its principle utilizes hough to detect transform circle, obtained by parameter such as setting least radius and maximum radius etc.
To the center of circle and the radius of the circle detected; This function appears at ImageProcessingToolbox8.0, is all imfindcircles function by this function package in the version after MATLAB2012 version; Hough detection efficiency is low, code redundancy, and can not the circle detecting target area of entirely accurate, does not therefore use hough to detect here, and uses imfindcircles function, accurately detected by the fenestra in region bad for picture quality;
S1-4, intercepts the circle of target area in view data, is set to black by extra-regional part; Utilize the center of circle that S1-3 obtains, retain circle inner, circle external pixels is set to 0.
4. the automatic read method of the pointer instrument of view-based access control model according to claim 2, is characterized in that, described S2 comprises: processed view data by gray scale morphology
The corrosion of gray level image and expansion process are directly calculated from the gray level function of view data and structural element; Certain in image 1 f (x, y) gray scale morphology erosion operation is defined as
(f Θ g) (x, y)=min{f (x-i, y-j)-g (-i ,-j) } gray scale morphology dilation operation is defined as
Grayscale morphologic expand namely with structural element g (i, j) for template, search the gray scale of image in structural motif magnitude range and maximum value; Erosion operation process is then with structural element g (i, j) for template, searches the minimal value of the gray scale difference of image in structural motif magnitude range; The morphological dilation of gray scale and the expression formula of morphological erosion computing and the convolution integral of image procossing closely similar, take advantage of to replace connecting with, difference, replace asking summation with minimum, maximum computing;
Gray scale morphology closed operation is defined as
Gray scale morphology opening operation is defined as
Opening operation adopts identical structural elements first to do the interative computation corroding and do and expand, and closed operation adopts identical structural elements first to do the interative computation expanding and do and corrode; The basic role of opening operation and closed operation is to the smoothing process of image: opening operation can be filled some duck eyes and the target of two vicinities be coupled together.
5. the automatic read method of the pointer instrument of view-based access control model according to claim 2, is characterized in that, described S2 comprises:
S2-1, carry out cumulative statistics by parameter space, adopt straight line polar equation, transformation equation is as follows:
ρ＝xcosθ+ysinθ，
A sinusoidal curve in the corresponding new argument space of point in raw image data, i.e. point-sinusoidal curve antithesis; The detailed process of detection of straight lines is exactly the value allowing θ get time, then calculates the value of ρ, then adds up to cumulative array according to the value of θ and ρ, thus obtain the number of collinear point;
For the determination of θ and ρ span, if detected straight line is at first quartile, upper right corner coordinate is (m, n);
S2-2, when straight line is from when being rotated counterclockwise with x-axis overlapping position, the value of θ starts by 0 ° of increase, until 180 °, so the span of θ is 0 ° ~ 180 °; By straight line polar equation:
wherein
so during and if only if φ=± 90 ° (adjusting the value of θ according to φ),
I.e. ρ span
the size of totalizer just can be determined by the span of θ, ρ and resolution, thus detection of straight lines.
6. the automatic read method of the pointer instrument of view-based access control model according to claim 2, is characterized in that, described S3 comprises:
Left side start line and the right terminated line all have certain angle with horizontal line, are set to alpha2 and alpha3 respectively; Suppose that alpha1 is the angle between pointer and the horizontal line of its direction, theta is the angle of left side start line to pointer direction; Positive and negative according to alpha1, is divided into following four kinds by the situation calculating theta:
The first situation: suppose that alpha1 is negative, then theta=alpha2 – alpha1;
The second situation: suppose that alpha1 is just, then theta=alpha2+180 °-alpha1;
The third situation: suppose that alpha1 is just, then theta=alpha2 – alpha1;
4th kind of situation: suppose that alpha1 is negative, then theta=alpha2+180 °-alpha1.
7. the automatic read method of the pointer instrument of view-based access control model according to claim 2, is characterized in that, described S4 comprises:
S4-1, carries out gray-scale edges process to raw image data, prepares, remove interfere information for next step detects ellipse;
S4-2, detects oval and marks.
8. the automatic read method of the pointer instrument of view-based access control model according to claim 7, is characterized in that, described S4-2 comprises:
S4-2-1, in two dimensional surface coordinate system, ellipse represents by two kinds of forms, and a kind of is utilize the quantic of equation of conic section to represent, as follows:
Ax
2+ Bxy+Cy
2+ Dx+Ey+F=0, wherein A, B, C, D, E, F are coefficient (constant)
Represent with the geometric parameter of plane coordinate system in addition, i.e. ellipse center location (x
0, y
0), major axis and minor axis (a, b), the rotational angle theta of major axis, these 5 parameters of any ellipse in two dimensional surface are uniquely determined,
S4-2-2, passes through formula
Wherein a is major axis, and b is minor axis;
For ellipse fitting, when stochastic error is normal distribution by least square method, the optimal estimation techniques released by maximum likelihood method, makes the quadratic sum of measuring error minimum, is obtaining one of the most reliable method of one group of unknown quantity from one group of measured value; Least square technology mainly finds parameter sets, thus the distance metric between minimise data point and ellipse, distance metric here common are geometric distance and algebraic distance; Geometric distance represents the distance of certain point to curve closest approach, certain point (x in plane
0, y
0) to the algebraic distance of curve representated by Equation f (x, y)=0 be exactly f (x
0, y
0)=0 is below introduce least square method using algebraic distance as distance metric;
S4-2-3, if elliptic equation is such as formula Ax
2+ Bxy+Cy
2shown in+Dx+Ey+F=0, in order to avoid null solution, and any integral multiple separated all is considered as the statement to same ellipse, do some restrictions to parameter, constraint condition is set to A+C=1; Obviously, the discrete point directly after the above-mentioned equation edge detection of application carries out least square process, just can obtain each coefficient in equation, namely ask objective function
Minimum value determine each coefficient, make f (A, B, C, D, E, F) value be minimum, according to Eular-Lagrange equations, must have
obtain a system of linear equations thus, then application solves the algorithm of system of linear equations, and such as Gaussian elimination, in conjunction with constraint condition, tries to achieve equation coefficient A, the value of B, C, D, E, F.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510894410.XA CN105550683A (en) | 2015-12-07 | 2015-12-07 | Vision-based pointer instrument automatic reading system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510894410.XA CN105550683A (en) | 2015-12-07 | 2015-12-07 | Vision-based pointer instrument automatic reading system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105550683A true CN105550683A (en) | 2016-05-04 |
Family
ID=55829866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510894410.XA Pending CN105550683A (en) | 2015-12-07 | 2015-12-07 | Vision-based pointer instrument automatic reading system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105550683A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740856A (en) * | 2016-01-28 | 2016-07-06 | 宁波理工监测科技股份有限公司 | Method for reading readings of pointer instrument based on machine vision |
| CN106295658A (en) * | 2016-08-13 | 2017-01-04 | 国网福建省电力有限公司 | A kind of transformer station readings of pointer type meters automatic recognition system |
| CN106295665A (en) * | 2016-08-13 | 2017-01-04 | 国网福建省电力有限公司 | A kind of transformer station readings of pointer type meters automatic identifying method |
| CN107038447A (en) * | 2017-04-26 | 2017-08-11 | 大连理工大学 | A kind of pointer instrument recognition methods based on machine vision |
| CN107292310A (en) * | 2017-06-19 | 2017-10-24 | 电子科技大学 | A kind of circular pointer dial plate vision positioning and automatic reading method |
| CN107301412A (en) * | 2017-05-08 | 2017-10-27 | 浙江工业大学 | A kind of readings of pointer type meters method based on image procossing |
| CN107729896A (en) * | 2017-10-24 | 2018-02-23 | 武汉科技大学 | A kind of automatic identifying method suitable for the wide tuning drive gear formula instrument of transformer station |
| CN108256524A (en) * | 2018-01-24 | 2018-07-06 | 国家电网公司 | A kind of automatic reading method of multilist index formula instrument |
| CN108337472A (en) * | 2017-01-19 | 2018-07-27 | 由田新技股份有限公司 | Device, system and method for image analysis instrument information |
| CN108550177A (en) * | 2018-03-27 | 2018-09-18 | 重庆大学 | A kind of software for marking picture and result being marked to be used for deep learning training |
| CN108764253A (en) * | 2018-05-15 | 2018-11-06 | 杭州电子科技大学 | Pointer instrument digitizing solution |
| CN109359637A (en) * | 2018-12-14 | 2019-02-19 | 福建工程学院 | Pointer instrument readings method based on machine vision |
| CN109558871A (en) * | 2018-10-26 | 2019-04-02 | 中国科学院长春光学精密机械与物理研究所 | A kind of readings of pointer type meters recognition methods and device |
| CN109598713A (en) * | 2018-11-30 | 2019-04-09 | 北京宇航系统工程研究所 | A kind of method for detecting abnormality based on image recognition |
| CN109934221A (en) * | 2019-02-22 | 2019-06-25 | 山东大学 | Power equipment based on attention mechanism automatically analyzes identification monitoring method and system |
| CN110097062A (en) * | 2019-04-26 | 2019-08-06 | 亿嘉和科技股份有限公司 | A kind of pointer recognition methods using pointer central point |
| CN110414521A (en) * | 2019-07-03 | 2019-11-05 | 安徽继远软件有限公司 | Oil level gauge for transformer registration recognition methods in a kind of substation |
| CN110987292A (en) * | 2019-12-10 | 2020-04-10 | 上海精密计量测试研究所 | Automatic calibrating device and method for torque wrench |
| CN111598109A (en) * | 2020-05-07 | 2020-08-28 | 国网四川省电力公司电力科学研究院 | Intelligent identification method for reading of pointer instrument of transformer substation |
| CN112488928A (en) * | 2020-10-12 | 2021-03-12 | 国网河南省电力公司济源供电公司 | Transformer oil conservator oil level online monitoring device and method based on image recognition technology |
| CN112639901A (en) * | 2018-08-30 | 2021-04-09 | 欧吉斯信息技术有限公司 | Meter reading apparatus, meter reading method, and computer program |
| CN112989963A (en) * | 2021-02-24 | 2021-06-18 | 唐山不锈钢有限责任公司 | Rockwell hardness test process supervision and judgment method based on graph recognition |
| CN113780142A (en) * | 2021-09-03 | 2021-12-10 | 华南师范大学 | Machine vision-based method and device for reading arc-shaped oil temperature gauge of transformer |
| CN116071736A (en) * | 2023-03-07 | 2023-05-05 | 北京全路通信信号研究设计院集团有限公司 | Meter reading method and device, electronic equipment and storage medium |
| CN116619392A (en) * | 2023-07-24 | 2023-08-22 | 常熟理工学院 | Calibration plate, calibration method and calibration system for cross-medium vision of robot |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101660932A (en) * | 2009-06-15 | 2010-03-03 | 浙江大学 | Automatic calibration method of pointer type automobile meter |
| US20120287162A1 (en) * | 2011-05-09 | 2012-11-15 | Aminian Mehdi | Method for displaying location related information |
| CN102799867A (en) * | 2012-07-09 | 2012-11-28 | 哈尔滨工业大学 | Meter pointer angle identification method based on image processing |
| CN103207987A (en) * | 2013-02-28 | 2013-07-17 | 华北电力大学 | Indicating value identification method of dial instrument |
-
2015
- 2015-12-07 CN CN201510894410.XA patent/CN105550683A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101660932A (en) * | 2009-06-15 | 2010-03-03 | 浙江大学 | Automatic calibration method of pointer type automobile meter |
| US20120287162A1 (en) * | 2011-05-09 | 2012-11-15 | Aminian Mehdi | Method for displaying location related information |
| CN102799867A (en) * | 2012-07-09 | 2012-11-28 | 哈尔滨工业大学 | Meter pointer angle identification method based on image processing |
| CN103207987A (en) * | 2013-02-28 | 2013-07-17 | 华北电力大学 | Indicating value identification method of dial instrument |
Non-Patent Citations (3)
| Title |
|---|
| 苏亭 等: "《清华大学附中学生获奖小论文选》", 31 August 1998 * |
| 袁磊: ""基于机器视觉的指针式仪表示值识别研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 马小菊: ""指针式仪表自动判读研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740856B (en) * | 2016-01-28 | 2019-01-18 | 宁波理工监测科技股份有限公司 | A kind of pointer instrument registration read method based on machine vision |
| CN105740856A (en) * | 2016-01-28 | 2016-07-06 | 宁波理工监测科技股份有限公司 | Method for reading readings of pointer instrument based on machine vision |
| CN106295658A (en) * | 2016-08-13 | 2017-01-04 | 国网福建省电力有限公司 | A kind of transformer station readings of pointer type meters automatic recognition system |
| CN106295665A (en) * | 2016-08-13 | 2017-01-04 | 国网福建省电力有限公司 | A kind of transformer station readings of pointer type meters automatic identifying method |
| CN106295665B (en) * | 2016-08-13 | 2019-10-01 | 国网福建省电力有限公司 | A kind of substation's readings of pointer type meters automatic identifying method |
| CN106295658B (en) * | 2016-08-13 | 2019-10-01 | 国网福建省电力有限公司 | A kind of substation's readings of pointer type meters automatic recognition system |
| CN108337472A (en) * | 2017-01-19 | 2018-07-27 | 由田新技股份有限公司 | Device, system and method for image analysis instrument information |
| CN107038447A (en) * | 2017-04-26 | 2017-08-11 | 大连理工大学 | A kind of pointer instrument recognition methods based on machine vision |
| CN107301412A (en) * | 2017-05-08 | 2017-10-27 | 浙江工业大学 | A kind of readings of pointer type meters method based on image procossing |
| CN107301412B (en) * | 2017-05-08 | 2019-12-17 | 浙江工业大学 | Pointer instrument reading method based on image processing |
| CN107292310A (en) * | 2017-06-19 | 2017-10-24 | 电子科技大学 | A kind of circular pointer dial plate vision positioning and automatic reading method |
| CN107729896A (en) * | 2017-10-24 | 2018-02-23 | 武汉科技大学 | A kind of automatic identifying method suitable for the wide tuning drive gear formula instrument of transformer station |
| CN108256524A (en) * | 2018-01-24 | 2018-07-06 | 国家电网公司 | A kind of automatic reading method of multilist index formula instrument |
| CN108256524B (en) * | 2018-01-24 | 2021-12-17 | 国家电网公司 | Automatic reading method of multi-dial pointer instrument |
| CN108550177A (en) * | 2018-03-27 | 2018-09-18 | 重庆大学 | A kind of software for marking picture and result being marked to be used for deep learning training |
| CN108764253A (en) * | 2018-05-15 | 2018-11-06 | 杭州电子科技大学 | Pointer instrument digitizing solution |
| CN112639901B (en) * | 2018-08-30 | 2023-06-27 | 欧吉斯信息技术有限公司 | Meter reading device, meter reading method, and storage medium |
| CN112639901A (en) * | 2018-08-30 | 2021-04-09 | 欧吉斯信息技术有限公司 | Meter reading apparatus, meter reading method, and computer program |
| CN109558871A (en) * | 2018-10-26 | 2019-04-02 | 中国科学院长春光学精密机械与物理研究所 | A kind of readings of pointer type meters recognition methods and device |
| CN109558871B (en) * | 2018-10-26 | 2021-09-17 | 中国科学院长春光学精密机械与物理研究所 | Pointer instrument reading identification method and device |
| CN109598713A (en) * | 2018-11-30 | 2019-04-09 | 北京宇航系统工程研究所 | A kind of method for detecting abnormality based on image recognition |
| CN109359637A (en) * | 2018-12-14 | 2019-02-19 | 福建工程学院 | Pointer instrument readings method based on machine vision |
| CN109359637B (en) * | 2018-12-14 | 2022-04-05 | 福建工程学院 | Pointer instrument value reading method based on machine vision |
| CN109934221A (en) * | 2019-02-22 | 2019-06-25 | 山东大学 | Power equipment based on attention mechanism automatically analyzes identification monitoring method and system |
| CN110097062A (en) * | 2019-04-26 | 2019-08-06 | 亿嘉和科技股份有限公司 | A kind of pointer recognition methods using pointer central point |
| CN110414521A (en) * | 2019-07-03 | 2019-11-05 | 安徽继远软件有限公司 | Oil level gauge for transformer registration recognition methods in a kind of substation |
| CN110987292A (en) * | 2019-12-10 | 2020-04-10 | 上海精密计量测试研究所 | Automatic calibrating device and method for torque wrench |
| CN111598109B (en) * | 2020-05-07 | 2022-07-22 | 国网四川省电力公司电力科学研究院 | Intelligent identification method for reading of transformer substation pointer instrument |
| CN111598109A (en) * | 2020-05-07 | 2020-08-28 | 国网四川省电力公司电力科学研究院 | Intelligent identification method for reading of pointer instrument of transformer substation |
| CN112488928A (en) * | 2020-10-12 | 2021-03-12 | 国网河南省电力公司济源供电公司 | Transformer oil conservator oil level online monitoring device and method based on image recognition technology |
| CN112989963A (en) * | 2021-02-24 | 2021-06-18 | 唐山不锈钢有限责任公司 | Rockwell hardness test process supervision and judgment method based on graph recognition |
| CN113780142A (en) * | 2021-09-03 | 2021-12-10 | 华南师范大学 | Machine vision-based method and device for reading arc-shaped oil temperature gauge of transformer |
| CN113780142B (en) * | 2021-09-03 | 2023-06-09 | 华南师范大学 | Transformer arc oil temperature gauge reading method and device based on machine vision |
| CN116071736A (en) * | 2023-03-07 | 2023-05-05 | 北京全路通信信号研究设计院集团有限公司 | Meter reading method and device, electronic equipment and storage medium |
| CN116619392A (en) * | 2023-07-24 | 2023-08-22 | 常熟理工学院 | Calibration plate, calibration method and calibration system for cross-medium vision of robot |
| CN116619392B (en) * | 2023-07-24 | 2023-11-07 | 常熟理工学院 | Calibration plate, calibration method and calibration system for cross-medium vision of robot |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105550683A (en) | Vision-based pointer instrument automatic reading system and method | |
| CN112906694B (en) | Reading correction system and method for transformer substation inclined pointer instrument image | |
| CN103759758B (en) | A kind of method for detecting position of the automobile meter pointer based on mechanical angle and scale identification | |
| CN107145890B (en) | A kind of pointer dashboard automatic reading method under remote multi-angle of view environment | |
| CN107341802B (en) | Corner sub-pixel positioning method based on curvature and gray scale compounding | |
| CN103207987B (en) | A kind of registration recognition methods of pointer instrument | |
| CN103824080B (en) | Robot SLAM object state detection method in dynamic sparse environment | |
| CN111814740B (en) | Pointer instrument reading identification method, device, computer equipment and storage medium | |
| CN103727930A (en) | Edge-matching-based relative pose calibration method of laser range finder and camera | |
| CN105303168A (en) | Multi-view pointer type instrument identification method and device | |
| CN113379712B (en) | Steel bridge bolt disease detection method and system based on computer vision | |
| CN103033253A (en) | Non-contact vibration detecting method of tower crane structure | |
| CN102589435A (en) | Efficient and accurate detection method of laser beam center under noise environment | |
| CN103971081A (en) | Multi-lane detection method and system | |
| CN103425988A (en) | Real-time positioning and matching method with arc geometric primitives | |
| CN115176274A (en) | Heterogeneous image registration method and system | |
| CN104048648A (en) | Relative pose measurement method for large size non-cooperative target | |
| CN103994786A (en) | Image detecting method for arc ruler lines of pointer instrument scale | |
| CN103499337A (en) | Vehicle-mounted monocular camera distance and height measuring device based on vertical target | |
| CN105608703A (en) | Current transformer oil level detection method of intelligent substation inspection robot | |
| CN103593849A (en) | Method for quickly recognizing and tracking image sequence oval artificial target points | |
| CN112036409A (en) | Reading identification method and device of liquid level meter | |
| CN105139384A (en) | Defective capsule detection method and apparatus | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN114359573A (en) | Pointer meter reading identification method and device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160504 |
|
| RJ01 | Rejection of invention patent application after publication |