CN112528740A - Pressing plate state identification method - Google Patents
Pressing plate state identification method Download PDFInfo
- Publication number
- CN112528740A CN112528740A CN202011227929.XA CN202011227929A CN112528740A CN 112528740 A CN112528740 A CN 112528740A CN 202011227929 A CN202011227929 A CN 202011227929A CN 112528740 A CN112528740 A CN 112528740A
- Authority
- CN
- China
- Prior art keywords
- image
- pressing plate
- state
- straight line
- template library
- 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
Images
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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
Abstract
The invention relates to a method for identifying the state of a pressing plate, which comprises the following steps: s1: collecting state images of the pressing plate, and constructing a template library; s2: shooting an image of a pressing plate to be detected, and carrying out image segmentation on the image of the pressing plate to be detected to obtain a pressing plate segmentation image; s3: traversing a template library, and performing template matching on the pressure plate segmentation image; s4: and outputting the corresponding state of the pressure plate image which is most matched with the pressure plate segmentation image in the template library, namely the corresponding state of the pressure plate to be detected. The invention does not need to extract the image characteristics of the relay protection and the pressing plate of the automatic device, has high recognition speed and solves the problem of low recognition rate caused by recognizing the state of the pressing plate through the edge in the prior scheme. The invention can identify the state of the pressing plates with different specifications, realizes the coping with the pressing plates with different shapes, improves the identification precision by improving the number of the template samples, and has simple calculation and higher speed.
Description
Technical Field
The invention relates to the field of power protection devices, in particular to a method for identifying a pressing plate state.
Background
At present, there are several ways for relay protection and automatic device pressure plate state identification: (1) the shape of the pressing plate is subjected to edge feature extraction, for example, for a rectangular pressing plate, a straight line is extracted by identifying the outline feature of an image, then the pressing plate is subjected to rectangle identification, the interference treatment is carried out on the wool and the spurs at the edge of the straight line, the minimum rectangle of the pressing plate is finally obtained, and the inclination angle of the minimum rectangle is calculated, so that the state of the rectangular pressing plate is obtained. The method only aims at the rectangular pressing plate, and has limitation in identifying the state of the square or triangular pressing plate, so that different image processing needs to be carried out according to different shapes to obtain the state of the pressing plate. (2) A neural network model is constructed through a large number of pressing plate pictures, and the pressing plate state in the pressing plate image can be decided and identified through the trained neural network model. The method needs more workload, needs to collect a plurality of sample pictures, and takes long time to train the network model. (3) The method comprises the steps of identifying through an SVM decision classifier, establishing the SVM decision classifier by extracting feature information of images, then training a pressing plate state, and classifying pictures of the pressing plate state to be judged so as to obtain the pressing plate state. The method needs to extract the characteristics of the sample image, and through binary tree classification, when a certain node is wrongly classified, a chain reaction is easily caused, and the mistake is inherited to a terminal leaf. (4) The special color of the pressing plate is matched with the template, so that the method is strong in pertinence, is suitable for the pressing plate with larger color difference with the background color, but is not suitable for the condition that the color of the pressing plate is similar to the background color.
Chinese patent CN109191419A published in 2019, 1, 11, provides a real-time platen detection and state recognition system and method based on machine learning, and loads a platen detection and state judgment model file for training; preprocessing the collected real-time detection image of the pressing plate; training the detection of a pressing plate by utilizing a deep convolutional neural network, judging whether the pressing plate exists in the collected detection image, if so, identifying the state of the pressing plate, otherwise, continuously receiving the detection image, and classifying and outputting the detection result; extracting the contour characteristic and the color characteristic of the pressing plate, establishing a characteristic classifier by using a support vector mechanism, and identifying the on-off state of a switch of the pressing plate by using the classified characteristic vector and the color mark. However, the patent mainly identifies the state of the pressing plate through technical means such as edge identification, and the identification efficiency is relatively low, and a space for further improvement is provided.
Disclosure of Invention
The invention provides a pressing plate state identification method for overcoming the defect of low pressing plate state identification efficiency in the prior art.
The method comprises the following steps:
s1: collecting state images of the pressing plate, and constructing a template library;
s2: shooting an image of a pressing plate to be detected, and carrying out image segmentation on the image of the pressing plate to be detected to obtain a pressing plate segmentation image;
s3: traversing a template library, and performing template matching on the pressure plate segmentation image;
s4: and outputting the corresponding state of the pressure plate image which is most matched with the pressure plate segmentation image in the template library, namely the corresponding state of the pressure plate to be detected.
Preferably, S1 includes the steps of:
s1.1: collecting the existing pressing plate image, and then carrying out graying and filtering on the collected image to obtain a processed image;
s1.2: setting a corresponding pressing plate state according to the processed image; matching the sample image in the template library with the state of the pressing plate;
s1.3: and storing the processed image and the pressing plate state into a database to complete the establishment of the template library.
Preferably, the graying of S1.1 is performed by a weighted average method.
Preferably, the weighted average formula is:
f(i，j)＝0.30R(i，j)+0.59G(i，j)+0.11B(i，j)
where f (i, j) is the gray value of the image at (i, j), R (i, j) is the red component of the image at (i, j), G (i, j) is the green component of the image at (i, j), B (i, j) is the blue component of the image at (i, j), and (i, j) is the coordinates of the pixel point.
Preferably, the filtering of the collected image in S1.1 is gaussian filtering.
Preferably, S2 includes the steps of:
s2.1: shooting images of the pressing plate to be tested through the camera equipment;
s2.2: carrying out gray level processing and filtering on the image of the pressing plate to be detected; then, judging straight lines to obtain a straight line set; the gray scale processing method and the filtering method are the same as the method adopted in S1.1.
S2.3: and calculating out the inner frame of the cabinet through a straight line set, and calculating to obtain an image of a single pressing plate according to the inner frame and the number of the pressing plates, namely, a pressing plate segmentation image.
Preferably, the straight line judgment in S2.2 is specifically: performing edge detection on the pressure plate image to be detected after gray processing and filtering by using a Canny operator to obtain a contour set; from the contour set, a straight line set is obtained using a hough transform.
Preferably, the inner frame of the cabinet calculated in S2.3 is specifically:
obtaining any straight line in the straight line set according to the straight line set, defining the direction vector of the straight line set as L, and satisfying | L | > | LminOf L, wherein LminAnd l is the minimum length of the straight line, the straight line finds an intersected straight line along the straight line direction, and then finds the next intersected straight line along the intersected straight line direction until a rectangle is formed by the intersection. And acquiring a rectangle with the largest area, correcting the rectangle through perspective transformation, and acquiring an image of the inner border of the cabinet.
Preferably, in S2.3, the image of a single platen is obtained by calculation according to the inner frame and the number of platens, and the calculation method includes:
and (3) according to the transverse number N and the longitudinal number M of the pressing plates in the box, dividing the image into N x M areas in an equal area manner to obtain a pressing plate division image.
Preferably, S3 is specifically: traversing the images of the template library, calculating the images of the template library and the pressure plate segmentation images, respectively binarizing the images of the template library and the pressure plate segmentation images, calculating the K value, determining the corresponding state of the images of the template library at the moment when the K value is minimum and the matching degree is high, and determining the state of the pressure plate segmentation images according to the state of the images of the template library so as to determine the state of the pressure plate to be detected.
Preferably, the K value is calculated as follows:
dividing the image of the template library into 3 × 3 regions, respectively labeled as k1、k2、k3、k4、k5、k6、k7、k8、k9；
The binarized platen segmented image was divided into 9 regions of 3 x 3, and each region was labeled as k'1、k'2、k'3、k'4、k'5、k'6、k'7、k'8、k'9；
Wherein k is1To k is9Are respectively k'1To k'9One-to-one correspondence is realized;
the K value is calculated according to the following formula:
compared with the prior art, the technical scheme of the invention has the beneficial effects that: the method does not need to extract the image features of the pressing plate, has high recognition speed, and solves the problem of low recognition rate caused by edge recognition in the prior art.
The invention can identify the state of the pressing plates with different specifications, realizes the coping with the pressing plates with different shapes, improves the identification precision by improving the number of the template samples, and has uncomplicated calculation and higher speed.
Drawings
Fig. 1 is a flowchart of a platen state identification method according to embodiment 1.
FIG. 2 is a flow chart of the construction of the template library.
FIG. 3 is a platen image segmentation flow chart.
Fig. 4 is a flow of template matching.
FIG. 5 is a flow chart of a K value calculation method.
Fig. 6 is a schematic diagram of image division.
Fig. 7 is a flowchart of a binarization calculation method.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
Example 1:
the embodiment provides a platen state identification method, which is used for identifying a platen state and is realized by an image identification technology, so that the effect of identifying various platen states is achieved.
As shown in fig. 1, the method comprises the steps of:
s1: and collecting the state image of the pressing plate and constructing a template library.
The construction process of the template library is shown in FIG. 2. Collecting the state image of a certain type of pressing plate, and then carrying out graying and filtering on the image to obtain a processed image. And setting the state of the pressing plate according to the processed image, so that the sample image in the template library is matched with the state of the pressing plate. And storing the processed image and the pressing plate state into a database to complete the establishment of the template library.
The method comprises the following steps of carrying out graying on a pressure plate image, forming a grayscale image with relatively good effect by adopting a weighted average method for graying, and displaying the state of the pressure plate more clearly, wherein the formula is as follows: f (i, j) ═ 0.30R (i, j) +0.59G (i, j) +0.11B (i, j).
In the present embodiment, the weighted average method is used for the graying, but the method is not limited to the weighted average method, and for example, the component method, the maximum value method, the average value method, and other methods capable of graying are all within the scope of the present invention.
In this embodiment, the platen image is filtered by using a gaussian filtering method, and the formula is as follows:
it should be noted that, the filtering in this embodiment uses gaussian filtering, but is not limited to gaussian filtering, and for example, mean filtering, block filtering, median filtering, and the like, which can implement the filtering described in the present invention, should be within the scope of the present invention.
In this embodiment, the pressing plate state is set by manually determining the actual state of the relay protection and the pressing plate image of the automatic device.
In this embodiment, each row of data in the database includes image data and platen status, which correspond to each other.
S2: shooting an image of a pressing plate to be detected, and carrying out image segmentation on the image of the pressing plate to be detected to obtain a pressing plate segmentation image;
as shown in fig. 3, the platen image segmentation process specifically includes: since the entire platen image is taken, it is necessary to divide the image to determine the state of one of the platens. Shooting a pressing plate image through the camera equipment, carrying out gray processing and filtering on the pressing plate image, then carrying out straight line judgment to obtain a straight line set, then calculating out a frame in the cabinet through the straight line set, and then calculating out an image of a single pressing plate according to the inner frame and the number of the pressing plates.
Wherein, the straight line judgment specifically comprises: and according to the generated filtered image, performing edge detection on the filtered image by using a Canny operator to obtain a contour set. From the contour set, a straight line set is obtained using a hough transform.
It should be noted that, in the present embodiment, the Canny operator is used for edge detection, but the present invention is not limited to Canny operators, and for example, Sobel operators, Scharr operators, laplacian operators, and other operators capable of implementing edge detection according to the present invention should fall within the scope of the present invention.
In this example. The method for calculating the inner frame of the cabinet comprises the following steps:
obtaining any straight line in the straight line set according to the calculated straight line set, defining the direction vector of the straight line set as L, and satisfying | L | > | LminOf L, wherein LminAnd l is the minimum length of the straight line, the straight line finds an intersected straight line along the straight line direction, and then finds the next intersected straight line along the intersected straight line direction until a rectangle is formed by the intersection. Obtaining the rectangle with the largest area, correcting the rectangle through perspective transformation, and obtaining the inner edge frame diagram of the cabinetLike this.
In this embodiment, an image of a single pressing plate is obtained by calculation according to the number of frames and pressing plates, and the calculation method includes: and (3) according to the transverse number N and the longitudinal number M of the pressing plates in the box, dividing the image into N x M areas in an equal area manner to obtain a pressing plate division image.
S3: traversing a template library, and performing template matching on the pressure plate segmentation image;
the template matching process is shown in figure 4, the image of the template library is traversed, the calculation is carried out on the image and the pressing plate segmentation image, the K value is calculated after the images are respectively binarized, the K value is the minimum, the matching degree is high, the image corresponding state of the template library at the moment is returned, and the state of the pressing plate segmentation image is determined according to the state of the template library.
In this embodiment, the calculation flow chart of the K value is shown in FIG. 5, first, the image is divided into K of Sudoku1To k is9In the local area (as shown in FIG. 6), the K value is calculated as follows, the image has been processed by binarization, and the K value is now1To k is9Is the number of values, k ', of which the platen divided image is 1'1To k'9Respectively calculating the value of each area for the number of the values of 1 in the template library image, accumulating the values, and calculating the K value:
K＝(k1-k'1)+(k2-k'2)+(k3-k'3)+(k4-k'4)+(k5-k'5)+(k6-k'6)+(k7-k'7)+(k8-k'8)+(k9-k'9)
as shown in fig. 7, the binarization calculation method is to calculate the mean value of the grayscale images as a threshold value T, and the grayscale less than T is set to 1, otherwise to 0.
For the binarization method, a double-edge threshold may be used.
S4: and outputting the corresponding state of the pressure plate image which is most matched with the pressure plate segmentation image in the template library, namely the corresponding state of the pressure plate to be detected.
The method of the embodiment can be applied to a rectangular pressing plate to realize state identification of the pressing plate. The method can be applied to square pressing plates to realize state recognition. The device can be applied to a knife-shaped pressing plate to realize state identification. The method can be applied to the pressing plate with an irregular shape to realize the state recognition.
In summary, the platen state identification method of the present embodiment can identify states of multiple platens with different specifications, so as to implement handling of platens with different shapes, and can improve identification accuracy by increasing the number of template samples, and the calculation is not complex and the speed is fast.
In the embodiment, the operator of the Sudoku template is used, and the state recognition of pressing plates of different types such as rectangles, squares and knife shapes is realized on the premise of not changing the algorithm. The method for identifying the state of the pressing plate by calculating the offset angle of the pressing plate in the embodiment can not be generally applied and has low identification efficiency.
The terms describing positional relationships in the drawings are for illustrative purposes only and are not to be construed as limiting the patent;
it should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. A platen state identification method, comprising the steps of:
s1: collecting state images of the pressing plate, and constructing a template library;
s2: shooting an image of a pressing plate to be detected, and carrying out image segmentation on the image of the pressing plate to be detected to obtain a pressing plate segmentation image;
s3: traversing a template library, and performing template matching on the pressure plate segmentation image;
s4: and outputting the corresponding state of the pressure plate image which is most matched with the pressure plate segmentation image in the template library, namely the corresponding state of the pressure plate to be detected.
2. The platen state recognition method according to claim 1, wherein S1 includes the steps of:
s1.1: collecting the existing pressing plate image, and then carrying out graying and filtering on the collected image to obtain a processed image;
s1.2: setting a corresponding pressing plate state according to the processed image;
s1.3: and storing the processed image and the pressing plate state into a database to complete the establishment of the template library.
3. The platen state recognition method according to claim 2, wherein the graying of S1.1 is performed by a weighted average method.
4. The platen state recognition method according to claim 2 or 3, wherein the collected image is filtered by Gaussian filtering in S1.1.
5. The platen state recognition method according to claim 4, wherein S2 includes the steps of:
s2.1: shooting images of the pressing plate to be tested through the camera equipment;
s2.2: carrying out gray level processing and filtering on the image of the pressing plate to be detected; then, judging straight lines to obtain a straight line set;
s2.3: and calculating out the inner frame of the cabinet through a straight line set, and calculating to obtain an image of a single pressing plate according to the inner frame and the number of the pressing plates, namely, a pressing plate segmentation image.
6. The platen state recognition method of claim 5, wherein the straight line determination in S2.2 is specifically: performing edge detection on the pressure plate image to be detected after gray processing and filtering by using a Canny operator to obtain a contour set; from the contour set, a straight line set is obtained using a hough transform.
7. The platen state recognition method according to claim 5 or 6, wherein the step of calculating the inner frame of the cabinet in S2.3 is specifically as follows:
according to the straight line set, obtaining any straight line in the straight line set, defining the direction vector of the straight line set as L, and regarding the condition that | L! count is satisfied>|LminOf L, wherein LminAnd l is the minimum length of the straight line, the straight line finds an intersected straight line along the straight line direction, and then finds the next intersected straight line along the intersected straight line direction until a rectangle is formed by the intersection. And acquiring a rectangle with the largest area, correcting the rectangle through perspective transformation, and acquiring an image of the inner border of the cabinet.
8. The platen state recognition method of claim 7, wherein in S2.3, the image of a single platen is obtained by calculation according to the inner frame and the number of platens, and the calculation method is as follows:
and (3) according to the transverse number N and the longitudinal number M of the pressing plates in the box, dividing the image into N x M areas in an equal area manner to obtain a pressing plate division image.
9. The platen state recognition method according to claim 1 or 8, wherein S3 specifically is: traversing the images of the template library, calculating the images of the template library and the pressure plate segmentation images, respectively binarizing the images of the template library and the pressure plate segmentation images, calculating the K value, determining the corresponding state of the images of the template library at the moment when the K value is minimum and the matching degree is high, and determining the state of the pressure plate segmentation images according to the state of the images of the template library so as to determine the state of the pressure plate to be detected.
10. The platen state recognition method according to claim 9, wherein the K value is calculated as follows:
dividing the image of the template library into 3 × 3 regions, respectively labeled as k1、k2、k3、k4、k5、k6、k7、k8、k9；
After binarization is carried outIs divided into 9 regions of 3 x 3, which are respectively marked as k'1、k′2、k′3、k′4、k′5、k′6、k′7、k′8、k′9；
Wherein k is1To k is9Are respectively k'1To k'9One-to-one correspondence is realized;
the K value is calculated according to the following formula:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011227929.XA CN112528740A (en) | 2020-11-06 | 2020-11-06 | Pressing plate state identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011227929.XA CN112528740A (en) | 2020-11-06 | 2020-11-06 | Pressing plate state identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112528740A true CN112528740A (en) | 2021-03-19 |
Family
ID=74979772
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011227929.XA Pending CN112528740A (en) | 2020-11-06 | 2020-11-06 | Pressing plate state identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112528740A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113191356A (en) * | 2021-05-19 | 2021-07-30 | 南方电网电力科技股份有限公司 | State identification method and related device for switch cabinet pressing plate equipment |
| CN113673405A (en) * | 2021-08-14 | 2021-11-19 | 深圳市快易典教育科技有限公司 | Exercise correction method and system based on question recognition and intelligent home teaching and learning machine |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446869A (en) * | 2016-10-20 | 2017-02-22 | 国家电网公司 | Automatic detection method for state of isolating switch based on image intelligent recognition algorithm |
| CN106971182A (en) * | 2017-02-06 | 2017-07-21 | 王兴照 | Embedded electric power relay pressing plate is thrown and moves back state Intelligent Identify device and implementation method |
| CN107527344A (en) * | 2017-09-18 | 2017-12-29 | 广东电网有限责任公司珠海供电局 | A kind of relay-protection pressing plate condition detecting system and detection method |
| CN108010026A (en) * | 2017-12-26 | 2018-05-08 | 深圳供电局有限公司 | One kind protection pressing plate state identification method and device |
| CN108121996A (en) * | 2017-11-21 | 2018-06-05 | 武汉中元华电软件有限公司 | A kind of hard pressing plate state identification method of power screen cabinet based on machine vision |
| CN109687382A (en) * | 2018-12-13 | 2019-04-26 | 广东电网有限责任公司 | It is a kind of based on color stencil matching relay-protection pressing plate throwing move back state identification method |
| CN110674808A (en) * | 2019-08-28 | 2020-01-10 | 国网天津市电力公司电力科学研究院 | Transformer substation pressure plate state intelligent identification method and device |
-
2020
- 2020-11-06 CN CN202011227929.XA patent/CN112528740A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446869A (en) * | 2016-10-20 | 2017-02-22 | 国家电网公司 | Automatic detection method for state of isolating switch based on image intelligent recognition algorithm |
| CN106971182A (en) * | 2017-02-06 | 2017-07-21 | 王兴照 | Embedded electric power relay pressing plate is thrown and moves back state Intelligent Identify device and implementation method |
| CN107527344A (en) * | 2017-09-18 | 2017-12-29 | 广东电网有限责任公司珠海供电局 | A kind of relay-protection pressing plate condition detecting system and detection method |
| CN108121996A (en) * | 2017-11-21 | 2018-06-05 | 武汉中元华电软件有限公司 | A kind of hard pressing plate state identification method of power screen cabinet based on machine vision |
| CN108010026A (en) * | 2017-12-26 | 2018-05-08 | 深圳供电局有限公司 | One kind protection pressing plate state identification method and device |
| CN109687382A (en) * | 2018-12-13 | 2019-04-26 | 广东电网有限责任公司 | It is a kind of based on color stencil matching relay-protection pressing plate throwing move back state identification method |
| CN110674808A (en) * | 2019-08-28 | 2020-01-10 | 国网天津市电力公司电力科学研究院 | Transformer substation pressure plate state intelligent identification method and device |
Non-Patent Citations (1)
| Title |
|---|
| 肖立军;莫玲;: "基于模式识别的继电保护压板状态检定系统", 新技术新工艺, no. 11 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113191356A (en) * | 2021-05-19 | 2021-07-30 | 南方电网电力科技股份有限公司 | State identification method and related device for switch cabinet pressing plate equipment |
| CN113673405A (en) * | 2021-08-14 | 2021-11-19 | 深圳市快易典教育科技有限公司 | Exercise correction method and system based on question recognition and intelligent home teaching and learning machine |
| CN113673405B (en) * | 2021-08-14 | 2024-03-29 | 深圳市快易典教育科技有限公司 | Problem correction method and system based on problem recognition and intelligent home education learning machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107545239B (en) | Fake plate detection method based on license plate recognition and vehicle characteristic matching | |
| CN110334706B (en) | Image target identification method and device | |
| CN104951784B (en) | A kind of vehicle is unlicensed and license plate shading real-time detection method | |
| Zheng et al. | An algorithm for accuracy enhancement of license plate recognition | |
| KR101403876B1 (en) | Method and Apparatus for Vehicle License Plate Recognition | |
| CN109409355B (en) | Novel transformer nameplate identification method and device | |
| CN109636824A (en) | A kind of multiple target method of counting based on image recognition technology | |
| CN106203539B (en) | Method and device for identifying container number | |
| CN104156704A (en) | Novel license plate identification method and system | |
| CN109918971B (en) | Method and device for detecting number of people in monitoring video | |
| CN101122952A (en) | Picture words detecting method | |
| CN104198497A (en) | Surface defect detection method based on visual saliency map and support vector machine | |
| CN108171098B (en) | Bar code detection method and equipment | |
| CN112883881B (en) | Unordered sorting method and unordered sorting device for strip-shaped agricultural products | |
| Yang et al. | Real-time traffic sign detection via color probability model and integral channel features | |
| CN107464245B (en) | Image structure edge positioning method and device | |
| Abedin et al. | Traffic sign recognition using surf: Speeded up robust feature descriptor and artificial neural network classifier | |
| CN112528740A (en) | Pressing plate state identification method | |
| CN103679187A (en) | Image identifying method and system | |
| CN112132153A (en) | Tomato fruit identification method and system based on clustering and morphological processing | |
| CN115620075A (en) | Method, system and equipment for generating data set for leukocyte classification model | |
| CN115512134A (en) | Express item stacking abnormity early warning method, device, equipment and storage medium | |
| CN115731493A (en) | Rainfall micro physical characteristic parameter extraction and analysis method based on video image recognition | |
| CN111401364A (en) | License plate positioning algorithm based on combination of color features and template matching | |
| CN108520252B (en) | Road sign identification method based on generalized Hough transform and wavelet transform |
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 |