CN111814740B - Pointer instrument reading identification method, device, computer equipment and storage medium - Google Patents
Pointer instrument reading identification method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN111814740B CN111814740B CN202010737551.1A CN202010737551A CN111814740B CN 111814740 B CN111814740 B CN 111814740B CN 202010737551 A CN202010737551 A CN 202010737551A CN 111814740 B CN111814740 B CN 111814740B
- Authority
- CN
- China
- Prior art keywords
- pointer
- image
- pointer instrument
- detected
- determining
- 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
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 60
- 230000001133 acceleration Effects 0.000 claims abstract description 29
- 238000001514 detection method Methods 0.000 claims abstract description 23
- 238000004590 computer program Methods 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000010276 construction Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 abstract description 12
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000006185 dispersion Substances 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000007796 conventional method Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/02—Recognising information on displays, dials, clocks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a pointer instrument reading identification method, a pointer instrument reading identification device, computer equipment and a storage medium. The method comprises the steps of obtaining an image of a pointer instrument to be detected, and determining the image of the pointer instrument to be detected according to a target detection algorithm. Judging whether the pointer instrument image to be detected is matched with a preset template image or not based on an acceleration robust feature algorithm, and if so, determining key points of the pointer instrument image to be detected according to preset key points of the preset template image. And constructing a scale curve of the pointer instrument to be measured according to the key points. And determining suspected pointer points according to the gray values of the coordinate points on the scale curves. And determining the pointer position of the pointer instrument to be measured according to the gray value between the circle center point of the scale and the suspected pointer point. According to the pointer position, the reading of the pointer instrument to be measured is determined, and the identification method of the pointer instrument reading provided by the application has higher inspection efficiency and accuracy for various pointer instruments.
Description
Technical Field
The application relates to the technical field of intelligent power equipment, in particular to a pointer instrument reading identification method, a pointer instrument reading identification device, computer equipment and a storage medium.
Background
With the development of power systems, the requirements on the service quality and the safe operation level of the power grid are continuously improved. Important components of the power grid are various substations, and the power equipment needs to be periodically inspected to strictly ensure the stable and reliable operation of the power equipment. The inspection of the transformer substation refers to the daily work that the transformer substation periodically inspects and checks the transformer equipment in the jurisdiction and ensures the normal and reliable operation of the power equipment. The transformer substation is provided with a plurality of devices, and is provided with various pointer instruments, thus being very important for the inspection of various pointer instruments.
In the traditional technology, the inspection of various pointer instruments is mainly performed manually, workers carry paper standard inspection work books, closely observe the readings of pointers, and fill in inspection results. However, such a patrol approach is inefficient and prone to error.
Disclosure of Invention
Based on the foregoing, it is necessary to provide a method, an apparatus, a computer device and a storage medium for identifying a pointer meter reading.
In one aspect, an embodiment of the present application provides a method for identifying a pointer meter reading, including:
acquiring an image to be detected, wherein the image to be detected comprises an image of a pointer instrument to be detected;
Determining the type of the pointer instrument to be detected and the position of the pointer instrument to be detected in the image to be detected according to a target detection algorithm to obtain an image of the pointer instrument to be detected;
judging whether the pointer instrument image to be detected is matched with a preset template image or not based on an acceleration robust feature algorithm;
if the pointer instrument image to be measured is matched with the preset template image, determining key points of the pointer instrument image to be measured according to preset key points of the preset template image, wherein the key points comprise a scale starting point, a scale midpoint, a scale end point and a scale circle center point of the pointer instrument to be measured;
according to the key points, constructing a scale curve of the pointer instrument to be measured on the pointer instrument image to be measured;
determining suspected pointer points according to the gray values of coordinate points on the scale curves;
determining the pointer position of the pointer instrument to be measured according to the gray value between the scale circle center point and the suspected pointer point;
and determining the reading of the pointer instrument to be measured according to the pointer position.
In one embodiment, the determining whether the pointer instrument image to be measured and the preset template image are matched based on the acceleration robust feature algorithm includes:
Acquiring characteristic points of the pointer instrument image to be detected based on the acceleration robust characteristic algorithm to obtain characteristic points to be detected, and acquiring characteristic points of the preset template image to obtain preset characteristic points;
and judging whether the pointer instrument image to be detected is matched with the preset template image according to the feature points to be detected and the preset feature points.
In one embodiment, the determining, according to the feature point to be detected and the preset feature point, whether the pointer instrument image to be detected and the preset template image are matched includes:
calculating Euclidean distance between the feature points to be detected and the preset feature points;
if the Euclidean distance is in the preset distance range, determining that the pointer instrument image to be detected is matched with the preset template image;
and if the Euclidean distance is not in the preset distance range, returning to execute the acceleration-based robust feature algorithm, and judging whether the pointer instrument image to be detected is matched with a preset template image.
In one embodiment, the determining the key point of the pointer instrument to be measured according to the preset key point of the preset template image includes:
determining a homography matrix according to the feature points to be detected and the preset feature points;
And determining the key points of the pointer instrument to be tested according to the homography matrix and the preset key points in the preset template image.
In one embodiment, the determining the suspected pointer point according to the gray value of the coordinate point on the scale curve includes:
determining a gray value to be measured according to the gray value of the coordinate point on the scale curve based on a gradient projection method;
and if the gray value to be detected is in the preset gray value range, determining a coordinate point corresponding to the gray value to be detected as the suspected pointer point.
In one embodiment, the determining the pointer position of the pointer instrument to be measured according to the gray value between the circle center point of the scale and the suspected pointer point includes:
calculating the variance of gray values between the circle center points of the scales and the suspected pointer points;
and determining the pointer position of the pointer instrument to be measured according to the variance.
In one embodiment, the target detection algorithm is a master RCNN algorithm.
In another aspect, an embodiment of the present application further provides an identification device for reading a pointer instrument, including:
the acquisition module is used for acquiring an image to be detected, wherein the image to be detected comprises an image of a pointer instrument to be detected;
The determining module is used for determining the type of the pointer instrument to be detected and the position of the pointer instrument to be detected in the image to be detected according to a target detection algorithm to obtain an image of the pointer instrument to be detected;
the judging module is used for judging whether the pointer instrument image to be detected is matched with a preset template image or not based on an acceleration robust feature algorithm;
the determining module is further configured to determine a key point of the to-be-measured pointer instrument image according to a preset key point of the preset template image if the to-be-measured pointer instrument image is matched with the preset template image, where the key point includes a scale starting point, a scale midpoint, a scale end point and a scale center point of the to-be-measured pointer instrument;
the construction module is used for constructing a scale curve of the pointer instrument to be tested on the pointer instrument image to be tested according to the key points;
the determining module is also used for determining suspected pointer points according to the gray values of the coordinate points on the scale curves;
the determining module is also used for determining the pointer position of the pointer instrument to be measured according to the gray value between the scale circle center point and the suspected pointer point;
and the determining module is also used for determining the reading of the pointer instrument to be tested according to the pointer position.
The present application also provides a computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when the processor executes the computer program.
The present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method described above.
The embodiment of the application provides a pointer instrument reading identification method, a pointer instrument reading identification device, computer equipment and a storage medium. According to the method, the image to be detected including the image of the pointer instrument to be detected is obtained, the image of the pointer instrument to be detected is determined according to a target detection algorithm, the image is processed, and the image is matched with a preset template image. And determining the key points of the pointer instrument image to be detected according to the preset key points of the preset template image. And determining the pointer position of the pointer instrument to be measured according to the key points through a related algorithm, so that the reading of the pointer instrument to be measured can be determined. The automatic pointer instrument identification reading does not need on-site inspection of staff, can improve the efficiency and accuracy of inspection of various pointer instruments, and can reduce the waste of human resources.
Drawings
In order to more clearly illustrate the technical solutions of embodiments or conventional techniques of the present application, the drawings that are required to be used in the description of the embodiments or conventional techniques will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for different persons skilled in the art.
FIG. 1 is a flow chart illustrating steps of a method for identifying a pointer meter reading according to one embodiment of the present application;
FIG. 2 is a flow chart illustrating steps of a method for identifying a pointer meter reading according to one embodiment of the present application;
FIG. 3 is a flow chart illustrating steps of a method for identifying a pointer meter reading according to one embodiment of the present application;
FIG. 4 is a flowchart illustrating steps of a method for identifying a pointer meter reading according to one embodiment of the present application;
FIG. 5 is a flow chart illustrating steps of a method for identifying a pointer meter reading according to one embodiment of the present application;
FIG. 6 is a flow chart illustrating steps of a method for identifying a pointer meter reading according to one embodiment of the present application;
FIG. 7 is a schematic diagram of a pointer meter reading identification device according to one embodiment of the present application;
Fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the above objects, features and advantages of the present application more comprehensible, embodiments accompanied with figures are described in detail below. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is, however, susceptible of embodiment in many other forms than those described herein and similar modifications can be made by those skilled in the art without departing from the spirit of the application, and therefore the application is not to be limited to the specific embodiments disclosed below.
The following describes the technical solution of the present application and how the technical solution of the present application solves the technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
The method for identifying the readings of the pointer instrument can be applied to any occasion needing to read the pointer instrument, and can identify the readings of various pointer instruments, for example: barometer, thermometer, oil temperature gauge, oil pressure gauge, etc. The method of pointer meter reading may be implemented by computer devices including, but not limited to, personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The image to be measured can be acquired in real time or can be stored in the memory of the computer equipment in advance. The identification method of the pointer instrument reading can be realized through Python, can also be applied to other software, and can realize voltage regulation through other programming languages.
Referring to fig. 1, an embodiment of the present application provides a method for identifying a pointer meter reading, where in this embodiment, a computer device is used as an execution body to describe a method for identifying a pointer meter reading of a substation, and the method includes the steps of:
s100, obtaining an image to be detected, wherein the image to be detected comprises an image of a pointer instrument to be detected.
The image to be measured can be an image of the pointer instrument to be read in the photographed transformer substation, and the image comprises the image of the pointer instrument to be measured and a background image. In the transformer substation, the image to be detected can be shot through a camera on the inspection robot, and the image to be detected can also be shot through a camera on the unmanned aerial vehicle. After the images to be detected are shot by the inspection robot or the unmanned aerial vehicle, the images to be detected can be directly sent to the computer equipment and stored in a memory of the computer equipment. When the computer equipment needs to identify the pointer instrument reading, the image to be detected is directly obtained from the memory. The present embodiment does not impose any limitation on the method of acquiring the image to be measured.
S200, determining the type of the pointer instrument to be detected and the position of the pointer instrument to be detected in the image to be detected according to a target detection algorithm, and obtaining the image of the pointer instrument to be detected.
The target detection algorithm may be a deep neural network based detection algorithm, such as: convolutional neural network (R-CNN), overTeat, fastCNN, SSD, and YOLO, etc. The present embodiment does not impose any limitation on the target detection algorithm employed as long as the function thereof can be realized. The type of the pointer instrument to be measured in the image to be measured and the position of the pointer instrument to be measured in the image to be measured can be determined through a target detection algorithm. For example: the pointer instrument to be measured in the image to be measured can be determined to be a thermometer through the target detection algorithm, and coordinate points of the thermometer in the image to be measured can be obtained. The image of the pointer instrument to be measured can be an image obtained by intercepting the pointer instrument to be measured, or an image of marking the position of the pointer instrument to be measured in the image to be measured.
S300, judging whether the pointer instrument image to be detected is matched with a preset template image or not based on an acceleration robust feature algorithm.
The accelerated robust feature algorithm (Speeded Up Robust Features, SURF) is a robust image recognition and description algorithm. The SURF algorithm uses determinant values of the Heisen matrix as feature points for detection and uses an integral graph for accelerating operation, so that the pointer instrument image to be detected and the preset template image can be better identified, and whether the pointer instrument image to be detected and the preset template image are matched can be better judged. The preset template image is an image of various pointer meters photographed in various directions by a worker in advance, and is stored in a memory of the computer device. After determining the type of the pointer instrument to be detected, the computer equipment directly searches a preset template image with the same type as the pointer instrument to be detected in a memory for matching when the computer equipment needs to match with the image of the pointer instrument to be detected.
S400, if the pointer instrument image to be measured is matched with the preset template image, determining key points of the pointer instrument image to be measured according to preset key points of the preset template image, wherein the key points comprise a scale starting point, a scale middle point, a scale end point and a scale center point of the pointer instrument to be measured.
When a worker makes a preset template image, preset key points are directly marked on the preset template image, and the preset key points comprise preset scale starting points, scale middle points, scale end points and scale circle center points of a pointer instrument on the preset template image. If the pointer instrument is circular, the scale starting point and the scale end point are overlapped. If the pointer instrument image to be measured is matched with the preset template image, the preset key points and the key points of the pointer instrument to be measured on the pointer instrument image to be measured can be in one-to-one correspondence, and the key points of the pointer instrument image to be measured can be determined according to the preset key points. The method for determining the key points of the pointer instrument image to be detected according to the preset key points of the preset template image is not limited in any way.
S500, according to the key points, constructing scale curves of the pointer instrument to be measured on the pointer instrument image to be measured.
And constructing a scale curve of the pointer instrument to be measured on the pointer instrument image to be measured according to the scale starting point, the scale midpoint and the scale end point in the key points. If the pointer instrument to be measured is circular, the obtained scale curve is a circular curve; if the pointer instrument to be measured is fan-shaped, the obtained scale curve is an arc-shaped curve.
S600, determining suspected pointer points according to gray values of coordinate points on the scale curves.
The coordinate points on the scale curve comprise the scale points of the pointer instrument to be measured and points where the pointer intersects with the scale curve. The gray value refers to the color depth of the scale point of the pointer instrument to be measured on the scale curve and the point where the pointer intersects the scale curve, and the gray value generally ranges from 0 to 255, white is 255, and black is 0. The suspected pointer points refer to points, possibly intersecting the scale curve, of the coordinate points on the scale curve, and the number of the suspected pointer points can be a plurality of the suspected pointer points. The gray values corresponding to different coordinate points on the scale curve may be different or the same. And determining suspected pointer points in the coordinate points on the scale curve according to the gray values of the coordinate points on the scale curve.
S700, determining the pointer position of the pointer instrument to be measured according to the gray value between the circle center point of the scale and the suspected pointer point.
Gray values between the scale center point and the suspected pointer point, namely gray values on a straight line formed between the scale center point and the suspected pointer point. If one number of suspected pointer points exists and gray values between the scale circle center points and the suspected pointer points are the same, a straight line formed by the scale circle center points and the suspected pointer points can be determined to be the pointer of the pointer instrument to be measured, and then the pointer position is determined. If the number of the suspected pointer points is multiple, the pointer of the pointer instrument to be measured can be determined according to the gray value on each straight line obtained by statistics through counting the gray value on the straight line formed by the circle center point of the scale and each suspected pointer point, and then the pointer position is determined.
S800, determining the reading of the pointer instrument to be measured according to the pointer position.
After the pointer position is determined, the reading of the pointer instrument to be measured can be determined according to the intersection point of the pointer and the scale curve and the scale of the pointer instrument to be measured of the type. In a specific embodiment, the reading of the pointer instrument to be measured can be determined according to the scale of the pointer instrument to be measured by calculating the included angle between the pointer and the straight line formed between the circle center point of the scale and the starting point of the scale and the percentage of the included angle to the whole angle of the pointer instrument. For example: the pointer instrument to be measured is a thermometer with a round dial plate, the scale of the thermometer is 0-10 ℃, the included angle of a straight line formed between the pointer and the circle center point of the scale and the starting point of the scale is calculated to be 50% of the angle of the whole pointer instrument, and then the reading of the thermometer is 5 ℃.
According to the pointer instrument reading identification method provided by the embodiment, the image to be detected containing the image of the pointer instrument to be detected is obtained, the image of the pointer instrument to be detected is determined according to the target detection algorithm, the image is processed, and the image is matched with the preset template image. And determining the key points of the pointer instrument image to be detected according to the preset key points of the preset template image. And determining the pointer position of the pointer instrument to be measured according to the key points through a related algorithm, so that the reading of the pointer instrument to be measured can be determined. The automatic pointer instrument identification reading does not need on-site inspection of staff, can improve the efficiency and accuracy of inspection of various pointer instruments of the transformer substation, and can reduce the waste of human resources. In addition, the method provided by the embodiment can directly store the reading of the pointer instrument without recording by staff, and can avoid omission or errors.
Referring to fig. 2, in one embodiment, step S300, based on the acceleration robust feature algorithm, determines whether the pointer instrument image to be measured and the preset template image match, including:
s310, acquiring characteristic points of an image of the pointer instrument to be detected based on an acceleration robust characteristic algorithm, acquiring the characteristic points to be detected, acquiring the characteristic points of a preset template image, and acquiring the preset characteristic points.
The acceleration robust feature algorithm adopts a square filter to process an image of the pointer instrument to be detected, and a hessian matrix can be used for detecting feature points of the image of the pointer instrument to be detected to obtain feature points to be detected. And similarly, processing the preset template image based on the acceleration robust feature algorithm to obtain preset feature points. The number of the feature points to be detected and the number of the preset feature points are multiple, and the feature points to be detected and the preset feature points are in one-to-one correspondence.
S320, judging whether the pointer instrument image to be detected is matched with the preset template image according to the feature points to be detected and the preset feature points.
The method for judging whether the pointer instrument image to be detected is matched with the preset template image according to the feature points to be detected and the preset feature points is not limited, so long as the functions of the method can be realized. In the embodiment, the speed of acquiring the feature points to be detected and the preset feature points by using the acceleration robust feature algorithm is high, so that the recognition speed of the readings of the pointer instrument to be detected can be improved.
Referring to fig. 3, in one embodiment, step S320 of determining whether the pointer instrument image to be measured and the preset template image are matched according to the feature points to be measured and the preset feature points includes:
s321, calculating Euclidean distance between the feature points to be detected and the preset feature points.
Euclidean distance, also known as Euclidean metric, is a commonly used distance definition. The Euclidean distance between the feature point to be measured and the preset feature point refers to the real distance between the feature point to be measured and the preset feature point in the Euclidean space, wherein the Euclidean space refers to the two-dimensional space where the feature point to be measured and the preset feature point are located, and the Euclidean distance between the feature point to be measured and the preset feature point is calculated by calculating the Euclidean distance between each feature point to be measured and the corresponding preset feature point.
S322, judging whether the Euclidean distance is in a preset range.
And S323, if the Euclidean distance is within the preset distance range, determining that the pointer instrument image to be detected is matched with the preset template image.
Judging whether the Euclidean distance between each feature point to be detected and the corresponding preset feature point is within the preset distance range or not through computer equipment, if the Euclidean distance between each feature point to be detected and the corresponding preset feature point is within the preset distance range, indicating that the feature point to be detected is matched with the preset feature point, namely, the feature point to be detected can be projected onto the preset feature point, then the pointer instrument image to be detected can be determined to be matched with the preset template image, in other words, the pointer instrument to be detected in the pointer instrument image to be detected can be projected onto the preset pointer instrument in the preset template image.
And if the Euclidean distance is not in the preset distance range, returning to execute the acceleration-based robust feature algorithm, and judging whether the pointer instrument image to be detected is matched with a preset template image.
If the Euclidean distance between each feature point to be detected and the corresponding preset feature point is not in the preset distance range, the fact that the feature point to be detected is not matched with the preset feature point is indicated, namely, the feature point to be detected cannot be projected onto the preset feature point, the pointer instrument image to be detected is not matched with the preset template image, the step S300 is executed, and the template image which can be matched with the pointer instrument image to be detected is searched in the preset template image again.
In this embodiment, by calculating the euclidean distance between the feature point to be measured and the preset feature point, whether the feature point to be measured is matched with the preset feature point can be determined more clearly, so that whether the pointer instrument image to be measured is matched with the preset template image can be determined more clearly. When the pointer instrument is not matched, the re-matching can be returned in time, and the accuracy of the subsequent identification of the pointer instrument reading to be detected can be improved.
Referring to fig. 4, in one embodiment, step S400 determines key points of the pointer instrument to be measured according to preset key points of the preset template image, including:
S410, determining a homography matrix according to the feature points to be detected and the preset feature points.
S420, determining key points of the pointer instrument to be tested according to the homography matrix and key points in the preset template image.
After the fact that the pointer instrument image to be detected is matched with the preset template image is determined, the feature points to be detected are matched with the preset feature points, namely, the feature points to be detected can be projected onto the corresponding preset feature points. According to the homography matrix determined by the feature points to be detected and the preset feature points, the mapping relation between the feature points to be detected and the preset feature points can be represented, and the mapping relation between the pointer instrument image to be detected and the preset template image can also be represented. According to the homography matrix, a preset scale starting point, a scale midpoint, a scale end point and a scale center point in key points in a preset template image can be mapped to a pointer instrument to be measured in the pointer instrument image to be measured, and then the scale starting point, the scale midpoint, the scale end point and the scale center point in the key points of the pointer instrument to be measured can be obtained.
In this embodiment, the homography matrix is obtained through the mapping relationship between the feature points to be detected and the preset feature points. According to the homography matrix, the preset key points in the preset template image can be accurately mapped to the pointer instrument to be measured in the pointer instrument image to be measured, and the key points of the pointer instrument to be measured can be determined. According to the feature points to be detected and the preset feature points, whether the pointer instrument image to be detected is matched with the preset template image or not can be judged, key points of the pointer instrument to be detected can be determined, and the practicability of the identification method of the pointer instrument reading can be improved.
Referring to fig. 5, in one embodiment, step S600 includes determining a suspected pointer point according to a gray value of a coordinate point on a scale curve:
s610, determining a gray value to be measured according to the gray value of the coordinate point on the scale curve based on the gradient projection method.
S620, if the gray value to be measured is within the preset gray value range, determining the coordinate point corresponding to the gray value to be measured as a suspected pointer point.
The basic idea of gradient projection is: when the iteration point is in the feasible region, taking the negative gradient direction at the point as a feasible descending method; when an iteration point is on a feasible region boundary, taking the projection of the negative gradient direction at the point on the feasible region boundary produces a feasible descent direction. And (3) adopting a gradient projection method to the gray values of all coordinate points on the scale curve to obtain an optimal solution in the gray values of all coordinate points, and taking the optimal solution as the gray value to be measured. Judging whether the gray value to be detected is in a preset gray value range or not through computer equipment, and if the gray value to be detected is in the preset gray value range, determining a coordinate point corresponding to the gray value to be detected as a suspected pointer point; if the gray value to be measured is not in the preset gray value range, the coordinate point corresponding to the gray value to be measured is not a suspected pointer point.
In this embodiment, the suspected pointer points existing on the scale curve are preliminarily determined by using the gradient projection method, so that the calculation amount can be reduced for accurately determining the pointer position of the pointer instrument to be measured subsequently, and the calculation efficiency can be improved.
Referring to fig. 6, in one embodiment, S700 determines a pointer position of a pointer instrument to be measured according to a gray value between a circle center point of a scale and a suspected pointer point, including:
s710, calculating the variance of gray values between the circle center point of the scale and the suspected pointer point.
S720, determining the pointer position of the pointer instrument to be measured according to the variance.
There may be one or more suspected pointer points obtained by the computer device. If one suspected pointer point exists, counting the gray value of each point on the straight line formed by the circle center point of the scale and the suspected pointer point, and calculating the variance of the gray values of all points. The variance of the gray values of all points may describe the degree of dispersion of the gray values of all points. If the variance of the gray values of all the points is smaller than the preset variance, the fact that the degree of dispersion of the gray values of all the points is smaller is indicated that a straight line formed by the circle center point of the scale and the suspected pointer point actually exists, and the straight line between the suspected pointer point and the circle center point of the scale is the pointer of the pointer instrument to be measured, so that the pointer position of the pointer instrument to be measured can be determined. If the variance of the gray values of all the points is greater than or equal to the preset variance, it indicates that the degree of dispersion of the gray values of all the points is greater, that is, the straight line directly formed by the center of the degree and the suspected pointer point is not present, and the suspected pointer point is not the actual pointer point, and the step S300 is executed. If the number of the suspected pointer points is multiple, counting the gray value of each point on the straight line formed by the scale center point and each suspected pointer point, and determining the straight line between one suspected pointer point and the scale center point as the pointer of the pointer instrument to be measured according to the same method.
In this embodiment, by calculating the gray value between the circle center point of the scale and the suspected pointer point, it may be further determined whether the suspected pointer point is an actual pointer point, so that the accuracy of the subsequent readings of the pointer instrument to be measured may be improved.
In one embodiment, the target detection algorithm is a master RCNN algorithm. The four basic steps of the target detection algorithm include: candidate region generation, feature point extraction, classification and position refinement. The master RCNN algorithm can unify the four basic steps of the target detection algorithm into a deep network frame, all the calculation cannot be repeated, and the running speed can be increased, so that the speed of identifying the readings of the pointer instrument to be detected can be increased.
In a specific embodiment, after determining the type of the pointer instrument to be measured and the position of the pointer instrument to be measured in the image to be measured according to the target detection algorithm in step S200 and obtaining the image of the pointer instrument to be measured, step S300 further includes preprocessing the image of the pointer instrument to be measured before determining whether the image of the pointer instrument to be measured and the image of the preset template are matched based on the acceleration robust feature algorithm. Specifically, histogram equalization processing can be performed on the pointer instrument image to be detected. During histogram equalization processing, the gray scale distribution of the pointer instrument image to be measured is adjusted, so that the distribution of the pointer instrument image to be measured on 0-255 gray scales is more uniform, the contrast of the pointer instrument image to be measured can be improved, and the matching of the pointer instrument image to be measured and a preset template image is facilitated. And the problem of reflection of the image to be measured due to illumination when the image to be measured is shot can be solved. The method can also be used for denoising the pointer instrument image to be measured, and can solve the noise pollution caused in the transmission process of the pointer instrument image to be measured. The method can also cut the image of the pointer instrument to be measured, so that the separation of the foreground and the background is realized, in other words, the separation of the image of the pointer instrument to be measured in the image to be measured and other images is realized, and the matching of the image of the pointer instrument to be measured and the preset template image is facilitated. The method can also correct the image of the pointer instrument to be measured, and avoid the influence of the inclination of the image of the pointer instrument to be measured on the subsequent matching.
It should be understood that, although the steps in the flowcharts in the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the figures may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of other steps or other steps.
Referring to fig. 7, an identification device 10 for indicating a meter reading according to an embodiment of the present application includes an acquisition module 100, a determination module 200, a determination module 300, and a construction module 400. Wherein,
the obtaining module 100 is configured to obtain an image to be measured, where the image to be measured includes an image of a pointer instrument to be measured.
The determining module 200 is configured to determine, according to a target detection algorithm, a type of the pointer instrument to be detected and a position of the pointer instrument to be detected in the image to be detected, so as to obtain an image of the pointer instrument to be detected.
The judging module 300 is configured to judge whether the pointer instrument image to be detected and the preset template image are matched based on an acceleration robust feature algorithm.
The determining module 200 is further configured to determine, if the to-be-measured pointer instrument image is matched with the preset template image, a key point of the to-be-measured pointer instrument image according to a preset key point of the preset template image, where the key point includes a scale start point, a scale midpoint, a scale end point and a scale center point of the to-be-measured pointer instrument.
The construction module 400 is configured to construct a scale curve of the pointer instrument to be measured on the image of the pointer instrument to be measured according to the key points.
The determining module 200 is further configured to determine a suspected pointer point according to the gray value of the coordinate point on the scale curve.
The determining module 200 is further configured to determine a pointer position of the pointer instrument to be measured according to the gray value between the scale center point and the suspected pointer point.
The determining module 200 is further configured to determine a reading of the pointer instrument to be measured according to the pointer position.
In one embodiment, the judging module 300 is further configured to obtain a feature point of the pointer instrument image to be detected based on the acceleration robust feature algorithm, obtain a feature point to be detected, and obtain a feature point of the preset template image, so as to obtain a preset feature point; and judging whether the pointer instrument image to be detected is matched with the preset template image according to the feature points to be detected and the preset feature points.
In one embodiment, the judging module 300 is further configured to calculate a euclidean distance between the feature point to be measured and the preset feature point; if the Euclidean distance is in the preset distance range, determining that the pointer instrument image to be detected is matched with the preset template image; and if the Euclidean distance is not in the preset distance range, returning to execute the acceleration-based robust feature algorithm, and judging whether the pointer instrument image to be detected is matched with a preset template image.
In one embodiment, the determining module 200 is further configured to determine a homography matrix according to the feature points to be detected and the preset feature points; and determining the key points of the pointer instrument to be tested according to the homography matrix and the preset key points in the preset template image.
In one embodiment, the determining module 200 is further configured to determine a gray value to be measured according to the gray value of the coordinate point on the scale curve based on the gradient projection method; and if the gray value to be detected is in the preset gray value range, determining a coordinate point corresponding to the gray value to be detected as the suspected pointer point.
In one embodiment, the determining module 200 is further configured to calculate a variance of gray values between the scale center point and the suspected pointer point; and determining the pointer position of the pointer instrument to be measured according to the variance.
For specific limitations on the identification device 10 for pointer meter readings, reference may be made to the above limitation on the identification method for pointer meter readings, and the details are not repeated here. The various modules in the identification appliance 10 of the pointer meter reading may be implemented in whole or in part by software, hardware, and combinations thereof. The above devices, modules or units may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above devices or modules.
Referring to fig. 8, in one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 8. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium, an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing preset template images, images to be detected and the like. The network interface of the computer device is used for communicating with an external terminal through network connection. The computer device, when executed by the processor, implements a method of identifying a pointer meter reading.
It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor, when executing the computer program, performing the steps of:
acquiring an image to be detected, wherein the image to be detected comprises an image of a pointer instrument to be detected;
determining the type of the pointer instrument to be detected and the position of the pointer instrument to be detected in the image to be detected according to a target detection algorithm to obtain an image of the pointer instrument to be detected;
judging whether the pointer instrument image to be detected is matched with a preset template image or not based on an acceleration robust feature algorithm;
if the pointer instrument image to be measured is matched with the preset template image, determining key points of the pointer instrument image to be measured according to preset key points of the preset template image, wherein the key points comprise a scale starting point, a scale midpoint, a scale end point and a scale circle center point of the pointer instrument to be measured;
According to the key points, constructing a scale curve of the pointer instrument to be measured on the pointer instrument image to be measured;
determining suspected pointer points according to the gray values of coordinate points on the scale curves;
determining the pointer position of the pointer instrument to be measured according to the gray value between the scale circle center point and the suspected pointer point;
and determining the reading of the pointer instrument to be measured according to the pointer position.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring characteristic points of the pointer instrument image to be detected based on the acceleration robust characteristic algorithm to obtain characteristic points to be detected, and acquiring characteristic points of the preset template image to obtain preset characteristic points; and judging whether the pointer instrument image to be detected is matched with the preset template image according to the feature points to be detected and the preset feature points.
In one embodiment, the processor when executing the computer program further performs the steps of: calculating Euclidean distance between the feature points to be detected and the preset feature points; if the Euclidean distance is in the preset distance range, determining that the pointer instrument image to be detected is matched with the preset template image; and if the Euclidean distance is not in the preset distance range, returning to execute the acceleration-based robust feature algorithm, and judging whether the pointer instrument image to be detected is matched with a preset template image.
In one embodiment, the processor when executing the computer program further performs the steps of: determining a homography matrix according to the feature points to be detected and the preset feature points; and determining the key points of the pointer instrument to be tested according to the homography matrix and the preset key points in the preset template image.
In one embodiment, the processor when executing the computer program further performs the steps of: determining a gray value to be measured according to the gray value of the coordinate point on the scale curve based on a gradient projection method; and if the gray value to be detected is in the preset gray value range, determining a coordinate point corresponding to the gray value to be detected as the suspected pointer point.
In one embodiment, the processor when executing the computer program further performs the steps of: calculating the variance of gray values between the circle center points of the scales and the suspected pointer points; and determining the pointer position of the pointer instrument to be measured according to the variance.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring an image to be detected, wherein the image to be detected comprises an image of a pointer instrument to be detected;
Determining the type of the pointer instrument to be detected and the position of the pointer instrument to be detected in the image to be detected according to a target detection algorithm to obtain an image of the pointer instrument to be detected;
judging whether the pointer instrument image to be detected is matched with a preset template image or not based on an acceleration robust feature algorithm;
if the pointer instrument image to be measured is matched with the preset template image, determining key points of the pointer instrument image to be measured according to preset key points of the preset template image, wherein the key points comprise a scale starting point, a scale midpoint, a scale end point and a scale circle center point of the pointer instrument to be measured;
according to the key points, constructing a scale curve of the pointer instrument to be measured on the pointer instrument image to be measured;
determining suspected pointer points according to the gray values of coordinate points on the scale curves;
determining the pointer position of the pointer instrument to be measured according to the gray value between the scale circle center point and the suspected pointer point;
and determining the reading of the pointer instrument to be measured according to the pointer position.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring characteristic points of the pointer instrument image to be detected based on the acceleration robust characteristic algorithm to obtain characteristic points to be detected, and acquiring characteristic points of the preset template image to obtain preset characteristic points; and judging whether the pointer instrument image to be detected is matched with the preset template image according to the feature points to be detected and the preset feature points.
In one embodiment, the computer program when executed by the processor further performs the steps of: calculating Euclidean distance between the feature points to be detected and the preset feature points; if the Euclidean distance is in the preset distance range, determining that the pointer instrument image to be detected is matched with the preset template image; and if the Euclidean distance is not in the preset distance range, returning to execute the acceleration-based robust feature algorithm, and judging whether the pointer instrument image to be detected is matched with a preset template image.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining a homography matrix according to the feature points to be detected and the preset feature points; and determining the key points of the pointer instrument to be tested according to the homography matrix and the preset key points in the preset template image.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining a gray value to be measured according to the gray value of the coordinate point on the scale curve based on a gradient projection method; and if the gray value to be detected is in the preset gray value range, determining a coordinate point corresponding to the gray value to be detected as the suspected pointer point.
In one embodiment, the computer program when executed by the processor further performs the steps of: calculating the variance of gray values between the circle center points of the scales and the suspected pointer points; and determining the pointer position of the pointer instrument to be measured according to the variance.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.
Claims (10)
1. A method of identifying a pointer meter reading, comprising:
acquiring an image to be detected, wherein the image to be detected comprises an image of a pointer instrument to be detected;
determining the type of the pointer instrument to be detected and the position of the pointer instrument to be detected in the image to be detected according to a target detection algorithm to obtain an image of the pointer instrument to be detected;
Judging whether the pointer instrument image to be detected is matched with a preset template image or not based on an acceleration robust feature algorithm;
if the pointer instrument image to be measured is matched with the preset template image, determining key points of the pointer instrument image to be measured according to preset key points of the preset template image, wherein the key points comprise a scale starting point, a scale midpoint, a scale end point and a scale circle center point of the pointer instrument to be measured;
according to the key points, constructing a scale curve of the pointer instrument to be measured on the pointer instrument image to be measured;
determining suspected pointer points according to the gray values of coordinate points on the scale curves;
determining the pointer position of the pointer instrument to be measured according to the gray value between the scale circle center point and the suspected pointer point;
determining the reading of the pointer instrument to be measured according to the pointer position;
the determining the pointer position of the pointer instrument to be measured according to the gray value between the scale circle center point and the suspected pointer point comprises the following steps:
calculating the variance of gray values between the circle center points of the scales and the suspected pointer points;
and determining the pointer position of the pointer instrument to be measured according to the variance.
2. The method of claim 1, wherein the determining whether the pointer instrument image to be measured and the preset template image match based on the acceleration robust feature algorithm comprises:
acquiring characteristic points of the pointer instrument image to be detected based on the acceleration robust characteristic algorithm to obtain characteristic points to be detected, and acquiring characteristic points of the preset template image to obtain preset characteristic points;
and judging whether the pointer instrument image to be detected is matched with the preset template image according to the feature points to be detected and the preset feature points.
3. The method according to claim 2, wherein the determining whether the pointer instrument image to be measured and the preset template image are matched according to the feature points to be measured and the preset feature points includes:
calculating Euclidean distance between the feature points to be detected and the preset feature points;
if the Euclidean distance is in the preset distance range, determining that the pointer instrument image to be detected is matched with the preset template image;
and if the Euclidean distance is not in the preset distance range, returning to execute the acceleration-based robust feature algorithm, and judging whether the pointer instrument image to be detected is matched with a preset template image.
4. The method according to claim 2, wherein determining the key point of the pointer instrument to be measured according to the preset key point of the preset template image comprises:
determining a homography matrix according to the feature points to be detected and the preset feature points;
and determining the key points of the pointer instrument to be tested according to the homography matrix and the preset key points in the preset template image.
5. The method of claim 1, wherein determining a suspected pointer point based on the gray values of the coordinate points on the scale curve comprises:
determining a gray value to be measured according to the gray value of the coordinate point on the scale curve based on a gradient projection method;
and if the gray value to be detected is in the preset gray value range, determining a coordinate point corresponding to the gray value to be detected as the suspected pointer point.
6. The method of claim 1, wherein the target detection algorithm is a master RCNN algorithm.
7. The method of claim 1, wherein prior to the determining whether the pointer instrument image under test and a preset template image match based on the acceleration robust feature algorithm, the method further comprises:
And carrying out histogram equalization processing on the pointer instrument image to be detected.
8. An identification device for pointer meter readings, comprising:
the acquisition module is used for acquiring an image to be detected, wherein the image to be detected comprises an image of a pointer instrument to be detected;
the determining module is used for determining the type of the pointer instrument to be detected and the position of the pointer instrument to be detected in the image to be detected according to a target detection algorithm to obtain an image of the pointer instrument to be detected;
the judging module is used for judging whether the pointer instrument image to be detected is matched with a preset template image or not based on an acceleration robust feature algorithm;
the determining module is further configured to determine a key point of the to-be-measured pointer instrument image according to a preset key point of the preset template image if the to-be-measured pointer instrument image is matched with the preset template image, where the key point includes a scale starting point, a scale midpoint, a scale end point and a scale center point of the to-be-measured pointer instrument;
the construction module is used for constructing a scale curve of the pointer instrument to be tested on the pointer instrument image to be tested according to the key points;
the determining module is also used for determining suspected pointer points according to the gray values of the coordinate points on the scale curves;
The determining module is also used for determining the pointer position of the pointer instrument to be measured according to the gray value between the scale circle center point and the suspected pointer point;
the determining module is also used for determining the reading of the pointer instrument to be detected according to the pointer position;
the determining module is also used for calculating the variance of the gray value between the scale circle center point and the suspected pointer point; and determining the pointer position of the pointer instrument to be measured according to the variance.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010737551.1A CN111814740B (en) | 2020-07-28 | 2020-07-28 | Pointer instrument reading identification method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010737551.1A CN111814740B (en) | 2020-07-28 | 2020-07-28 | Pointer instrument reading identification method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111814740A CN111814740A (en) | 2020-10-23 |
| CN111814740B true CN111814740B (en) | 2024-03-26 |
Family
ID=72863213
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010737551.1A Active CN111814740B (en) | 2020-07-28 | 2020-07-28 | Pointer instrument reading identification method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111814740B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112861867A (en) * | 2021-02-01 | 2021-05-28 | 北京大学 | Pointer type instrument panel identification method, system and storage medium |
| CN112699876B (en) * | 2021-03-24 | 2021-07-09 | 中海油能源发展股份有限公司采油服务分公司 | Automatic reading method for various meters of gas collecting station |
| CN113313122A (en) * | 2021-06-11 | 2021-08-27 | 曲阜师范大学 | Pointer type instrument automatic reading identification method based on computer vision |
| CN115496807B (en) * | 2022-11-18 | 2023-01-20 | 南方电网数字电网研究院有限公司 | Meter pointer positioning method and device, computer equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002188939A (en) * | 2000-12-21 | 2002-07-05 | Nec Corp | Pointer-type meter measuring system by image recognition and pointer-type meter measuring method |
| JP2004325155A (en) * | 2003-04-23 | 2004-11-18 | Calsonic Kansei Corp | Method, apparatus, and program for inspecting vehicle instrument |
| CN103759758A (en) * | 2014-01-26 | 2014-04-30 | 哈尔滨工业大学 | Method for detecting position of automobile meter needle based on mechanical angle and scale identification |
| WO2016101643A1 (en) * | 2014-12-26 | 2016-06-30 | 国网重庆市电力公司电力科学研究院 | Meter data read method and system |
| CN106228161A (en) * | 2016-07-18 | 2016-12-14 | 电子科技大学 | A kind of pointer-type dial plate automatic reading method |
| CN108009535A (en) * | 2017-11-21 | 2018-05-08 | 武汉中元华电科技股份有限公司 | A kind of simple pointer meter reading method based on machine vision |
| CN108960226A (en) * | 2018-07-12 | 2018-12-07 | 广东电网有限责任公司 | A kind of pointer instrument class expression value number reading method and device |
| CN109117720A (en) * | 2018-07-06 | 2019-01-01 | 华中科技大学 | A kind of readings of pointer type meters recognition methods based on machine vision |
| CN109948469A (en) * | 2019-03-01 | 2019-06-28 | 吉林大学 | The automatic detection recognition method of crusing robot instrument based on deep learning |
| JP2020024741A (en) * | 2018-04-27 | 2020-02-13 | 株式会社東芝 | Reading system, reading method, program, and recording medium |
-
2020
- 2020-07-28 CN CN202010737551.1A patent/CN111814740B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002188939A (en) * | 2000-12-21 | 2002-07-05 | Nec Corp | Pointer-type meter measuring system by image recognition and pointer-type meter measuring method |
| JP2004325155A (en) * | 2003-04-23 | 2004-11-18 | Calsonic Kansei Corp | Method, apparatus, and program for inspecting vehicle instrument |
| CN103759758A (en) * | 2014-01-26 | 2014-04-30 | 哈尔滨工业大学 | Method for detecting position of automobile meter needle based on mechanical angle and scale identification |
| WO2016101643A1 (en) * | 2014-12-26 | 2016-06-30 | 国网重庆市电力公司电力科学研究院 | Meter data read method and system |
| CN106228161A (en) * | 2016-07-18 | 2016-12-14 | 电子科技大学 | A kind of pointer-type dial plate automatic reading method |
| CN108009535A (en) * | 2017-11-21 | 2018-05-08 | 武汉中元华电科技股份有限公司 | A kind of simple pointer meter reading method based on machine vision |
| JP2020024741A (en) * | 2018-04-27 | 2020-02-13 | 株式会社東芝 | Reading system, reading method, program, and recording medium |
| CN109117720A (en) * | 2018-07-06 | 2019-01-01 | 华中科技大学 | A kind of readings of pointer type meters recognition methods based on machine vision |
| CN108960226A (en) * | 2018-07-12 | 2018-12-07 | 广东电网有限责任公司 | A kind of pointer instrument class expression value number reading method and device |
| CN109948469A (en) * | 2019-03-01 | 2019-06-28 | 吉林大学 | The automatic detection recognition method of crusing robot instrument based on deep learning |
Non-Patent Citations (3)
| Title |
|---|
| Substation pointer instrument reading based on image processing;Shi Wei 等;《Electronic Science and Technology》;第29卷(第01期);118-20, 127 * |
| 变电站巡检机器人中的指针式仪表读数识别系统设计与实现;王东灿;《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》(第06期);C042-594 * |
| 巡检机器人中的指针式仪表读数识别系统;许丽 等;《仪器仪表学报》(第07期);224-232 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111814740A (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111814740B (en) | Pointer instrument reading identification method, device, computer equipment and storage medium | |
| CN111414934A (en) | Pointer type meter reading automatic identification method based on fast R-CNN and U-Net | |
| CN111476827A (en) | Target tracking method, system, electronic device and storage medium | |
| CN109508709B (en) | Single pointer instrument reading method based on machine vision | |
| CN110796082A (en) | Nameplate text detection method and device, computer equipment and storage medium | |
| CN111950396A (en) | Instrument reading neural network identification method | |
| CN111372042B (en) | Fault detection method and device, computer equipment and storage medium | |
| Mai et al. | An automatic meter reading method based on one-dimensional measuring curve mapping | |
| CN111259903A (en) | Identification table counting method and device, readable storage medium and computer equipment | |
| CN111767192A (en) | Service data detection method, device, equipment and medium based on artificial intelligence | |
| Sowah et al. | An intelligent instrument reader: using computer vision and machine learning to automate meter reading | |
| CN116486146A (en) | Fault detection method, system, device and medium for rotary mechanical equipment | |
| CN116051809A (en) | Sulfur hexafluoride instrument reading identification method and equipment based on deep learning | |
| EP4050560B1 (en) | Wafer testing method and apparatus, and device and storage medium | |
| CN113989632A (en) | Bridge detection method and device for remote sensing image, electronic equipment and storage medium | |
| CN115311447A (en) | Pointer instrument indicating number identification method based on deep convolutional neural network | |
| CN114155380A (en) | Instrument panel image identification method and device, computer equipment and storage medium | |
| CN112417975A (en) | Method and device for obtaining reading of pointer instrument | |
| CN112950568A (en) | Scale length calculation method and device, computer equipment and storage medium | |
| Sowah et al. | Intelligent instrument reader using computer vision and machine learning | |
| US11989908B2 (en) | Visual positioning method, mobile machine using the same, and computer readable storage medium | |
| CN116740385B (en) | Equipment quality inspection method, device and system | |
| CN111553418B (en) | Method and device for detecting neuron reconstruction errors and computer equipment | |
| CN113469162B (en) | Pointer instrument identification method, device, equipment and medium based on double-scale segmentation | |
| CN115565164B (en) | Instrument panel numerical value identification method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: Room 86, room 406, No.1, Yichuang street, Zhongxin Guangzhou Knowledge City, Huangpu District, Guangzhou City, Guangdong Province Applicant after: Southern Power Grid Digital Grid Research Institute Co.,Ltd. Address before: 511458 Room 1301, Chengtou Building, 106 Fengze East Road, Nansha District, Guangzhou City, Guangdong Province (self-compiled 1301-12159) Applicant before: Southern Power Grid Digital Grid Research Institute Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |