CN111931785A - Edge detection method for infrared image target of power equipment - Google Patents
Edge detection method for infrared image target of power equipment Download PDFInfo
- Publication number
- CN111931785A CN111931785A CN202010566923.9A CN202010566923A CN111931785A CN 111931785 A CN111931785 A CN 111931785A CN 202010566923 A CN202010566923 A CN 202010566923A CN 111931785 A CN111931785 A CN 111931785A
- Authority
- CN
- China
- Prior art keywords
- gradient
- edge
- infrared image
- temperature
- maximum
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/457—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by analysing connectivity, e.g. edge linking, connected component analysis or slices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention discloses an edge detection method of an infrared image target of power equipment, belonging to the technical field of edge detection methods of infrared image targets; the technical problem to be solved is as follows: the improvement of the edge detection method of the infrared image target of the power equipment is provided; the technical scheme for solving the technical problem is as follows: extracting temperature matrix data corresponding to the infrared image, wherein the temperature data is directly derived through infrared imager control software or calculated through infrared radiation original data stored in the infrared image; calculating gradient values and directions of the temperature matrix; comparing gradient values before and after the pixel points along the gradient direction, reserving the pixel points with the maximum local gradient, and thinning the image edge by a non-maximum inhibition method; selecting a maximum temperature threshold and a minimum temperature threshold of the gradient amplitude, and performing edge connection to form an edge detection graph of the infrared image; the method is applied to the edge detection of the infrared image target of the power equipment.
Description
Technical Field
The invention discloses an edge detection method for an infrared image target of power equipment, and belongs to the technical field of edge detection methods for infrared image targets.
Background
The infrared temperature measurement of the power equipment is a non-contact live detection method, has the advantages of no disassembly, no contact, no sampling, no power outage and the like, is easy to operate, can quickly and accurately acquire the temperature field distribution of the power equipment through infrared images, thereby finding latent defects in the power equipment and taking corresponding repair measures, and has important significance for ensuring the safe and stable operation of a power grid, so the infrared temperature measurement is widely applied to the operation and maintenance detection of the power grid equipment.
However, with the continuous expansion of the power grid scale and the increasing number of substations, the defects and shortcomings of operation and maintenance personnel in the aspect of analysis and diagnosis of infrared images are increasingly highlighted, and mainly reflected as:
firstly, the defect diagnosis of the existing electric power equipment depends on manual analysis seriously, the requirements on professional knowledge and experience of analysts are high, the artificial subjective influence is large, and misjudgment is easy to occur;
with the rapid increase of the number of power equipment, the manual analysis efficiency is low, the labor intensity is high, and the manual analysis capability is difficult to cope with the rapidly increasing atlas analysis requirement;
the existing equipment fault analysis method based on the infrared atlas is required to be established on the basis of accurately distinguishing target equipment from a background environment, and because an infrared imager performs radiation imaging through the surface temperature of an object, the infrared imager receives the infrared radiation of a detection target and simultaneously receives the interference of a large amount of radiation information of a non-detection object, compared with a visible light image, the infrared image has the advantages of large background noise, weak signal, low contrast, less fuzzy details of the edge of the target equipment and interweaving of different equipment; in the traditional infrared image target identification, a pixel matrix of an image RGB channel is generally used as a characteristic vector, a color moment, a color histogram, a color set and the like are used as characteristics of target equipment, and edge detection is performed through the processes of filtering, enhancing, thresholding and the like; however, the infrared image has quite rich color space and difficult extraction of target equipment features, so that the identified image target is not ideal, the detection error is large, and the automatic diagnosis analysis result is wrong.
Therefore, a method capable of replacing manual infrared atlas target edge detection is urgently needed, and rapid and efficient identification of target equipment in an infrared image is achieved, so that a foundation is laid for next defect analysis and diagnosis.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to solve the technical problems that: an improvement of an edge detection method of an infrared image target of power equipment is provided.
In order to solve the technical problems, the invention adopts the technical scheme that: an edge detection method for an infrared image target of power equipment comprises the following steps:
the method comprises the following steps: extracting temperature matrix data corresponding to the infrared image, wherein the temperature data is directly derived through infrared imager control software or calculated through infrared radiation original data stored in the infrared image;
step two: calculating gradient values and directions of the temperature matrix;
step three: comparing gradient values before and after the pixel points along the gradient direction, reserving the pixel points with the maximum local gradient, and thinning the image edge by a non-maximum inhibition method;
step four: and selecting a maximum temperature threshold and a minimum temperature threshold of the gradient amplitude, and performing edge connection to form an edge detection graph of the infrared image.
And in the second step, the gradient value and the direction of the temperature matrix are calculated by a first-order finite difference method to obtain the gradient value and the direction of the temperature matrix, and the specific calculation formula is as follows:
the above formula is the calculation formula of the gradient value in the x direction, wherein
The value is a gradient value in the x direction, and T (i, j) is the temperature corresponding to the infrared image pixel point (i, j);
the above formula is a y-direction gradient value calculation formula, wherein
The y-direction gradient value is obtained, and T (i, j) is the temperature corresponding to the infrared image pixel point (i, j);
the above formula is the gradient amplitude corresponding to the pixel point (i, j)
The calculation formula of (2);
the above formula is the gradient direction
The calculation formula of (2).
And in the third step, the local gradient maximum value pixel is retained, and the image edge is refined by a non-maximum value inhibition method, and the specific steps are as follows:
step 3.1: defining g1-g8 as eight field pixels of the pixel C, selecting the g1-g8 in a clockwise arrangement mode, and enabling the pixel C to be located in the center of the eight field pixels;
step 3.2: according to the formula
Calculating the gradient direction of the pixel point C, and expressing the gradient direction by a line L1;
step 3.3: defining the intersection points of the line L1 and the field pixel points as temp1 and temp2, extracting the temperature values of temp1 and temp2 through the first step when the temp1 and the temp2 are positive pixel points, and calculating the temperature values corresponding to the temp1 and the temp2 through interpolation when the temp1 and the temp2 are sub-pixel points;
step 3.4: judging the temperature values of the pixel point C, temp1 and the temp2, when the temperature value of the pixel point C is the maximum, keeping the pixel point C, and when the temperature value of the pixel point C is not the maximum, discarding the pixel point C;
step 3.5: and judging all pixel points on the infrared image according to the method from the step 3.1 to the step 3.4.
The specific judgment step for selecting the maximum temperature threshold and the minimum temperature threshold of the gradient amplitude in the fourth step is as follows:
step 4.1: setting the maximum temperature threshold as maxVal and the minimum temperature threshold as minVal;
step 4.2: judging the sizes of the pixel point gradient and the maxVal and the minVal, reserving the edge with the gradient larger than the maxVal as a true edge, and discarding the edge with the gradient smaller than the minVal as a false edge;
step 4.3: the gradient is located at the edge between the maxVal and the minVal, whether the gradient is an edge or a non-edge is judged through the connectivity of the gradient, a part which is connected to a reliable edge larger than the maxVal and is judged to be the edge is reserved, and a part which is not connected to the reliable edge larger than the maxVal and is judged to be not the edge is discarded.
Compared with the prior art, the invention has the beneficial effects that: the edge detection method provided by the invention directly extracts the temperature information corresponding to the infrared image as the characteristic vector to carry out the edge detection of the target equipment, does not need the image preprocessing process of filtering and enhancing, and has small calculation amount and quicker calculation; based on the obvious difference between the equipment temperature and the environmental temperature, the edge detection is carried out by utilizing the temperature gradient, so that the target equipment and the background environment are effectively separated; the method of non-maximum value inhibition is applied, and the edge of the target equipment is efficiently refined; by setting the maximum temperature threshold and the minimum temperature threshold, background filtering and edge connection are realized, the recognition rate of the target equipment is improved, and the recognition is fast and accurate.
Drawings
The invention will be further described with reference to the accompanying drawings in which:
FIG. 1 is a flowchart illustrating the steps of the edge detection method according to the present invention;
FIG. 2 is a schematic diagram of an embodiment of an image edge refinement method using non-maxima suppression;
FIG. 3 is a diagram illustrating edge determination according to an embodiment of the present invention.
Detailed Description
As shown in fig. 1 to 3, the method for detecting the edge of the infrared image target of the power device directly uses the temperature information of the infrared image as the feature vector to identify the target based on the information that the temperature of the target device in the infrared image is obviously different from the background, overcomes the difficulty that the target and the background are difficult to be effectively separated in the traditional RGB image-based color space identification method, and realizes the rapid and accurate identification of the target device in the infrared image.
The step flow chart of the method for detecting the edge of the infrared image target of the power equipment is shown in fig. 1, the first step is to extract temperature data corresponding to the infrared image, the temperature data is directly exported through infrared imager control software or is calculated through infrared radiation original data stored in the infrared image, and the temperature data is arranged into temperature matrix data required by calculation.
And step two, calculating the gradient value and the direction of the temperature matrix, wherein the edge of the equipment is the place with the largest temperature change, the edge of the equipment is identified through the temperature gradient amplitude, and each pixel point of the infrared image corresponds to one temperature value, so that the temperature data are discrete, the gradient value and the direction of the temperature can be calculated through a first-order finite difference method, and the specific calculation formula is as follows:
the above formula (1) is a formula for calculating the gradient value in the x direction, wherein
Is x-direction gradient value, T (i, j) is temperature corresponding to infrared image pixel point (i, j), and the above formula (2) is y-direction gradient value calculation formula
For the y-direction gradient value, the above formula (3) is the gradient amplitude corresponding to the pixel point (i, j)
The above formula (4) is the gradient direction
The calculation formula of (2).
Step three, comparing gradient values before and after pixel points along the gradient direction through the gradient values calculated in the step two, and reserving the pixel points with the local gradient maximum values; thinning the edge of the equipment by a non-maximum suppression method, as shown in fig. 2, defining g1-g8 as eight field pixels of a current pixel C, g1-g8 in clockwise arrangement and selection to form a square, wherein the pixel C is located at the center position of the eight field pixels, and a line L1 is the gradient direction of the pixel C, as shown in fig. 2, the intersection of the connecting lines of L1 and g2g3 is temp1, the intersection of the connecting lines of L1 and g6g7 is temp2, temp1 and temp2 are not necessarily located on a positive pixel, when temp1 and temp2 are positive pixels, the temperature values of temp1 and temp2 are extracted through a first step, and when the temp1 and the temp2 are sub-pixels, the temperature values corresponding to the temp 35 1 and temp2 are calculated through interpolation; comparing the temperature of C, temp1 and the temperature of temp2, when the temperature value of C is maximum, retaining C, when the temperature value of C is not maximum, discarding C; and judging whether the pixel points are reserved or discarded according to the method for all the pixel points on the infrared image.
Selecting a maximum temperature threshold and a minimum temperature threshold of the gradient amplitude, and performing edge connection to form an edge detection graph of the infrared image; judging which edges are real edges and which edges are not real edges through the fourth step, so that two thresholds, namely a maximum temperature threshold maxVal and a minimum temperature threshold minVal, are required to be set, judging the sizes of the gradient of the pixel point, the maxVal and the minVal, keeping the edges with the gradient larger than the maxVal as real edges, and discarding the edges with the gradient smaller than the minVal as false edges; the gradient is positioned at the edge between the maxVal and the minVal, whether the edge is the non-edge or the edge is judged through the connectivity of the gradient, a part which is connected to the reliable edge which is larger than the maxVal and is judged to be the edge is reserved, and a part which is not connected to the reliable edge which is larger than the maxVal and is judged to be not the edge is discarded; as shown in fig. 3, the pixel point a is located above the maximum temperature threshold maxVal and belongs to the true edge, the pixel point B and the pixel point D are located between the maximum temperature threshold maxVal and the minimum temperature threshold minVal, it needs to be determined whether the pixel point is the true edge, the pixel point D is connected to the pixel point a at the true edge, the pixel point D is determined to be a part of the edge to be reserved, the pixel point B is not connected to the pixel point a at the true edge, and the pixel point B is determined not to be a part of the edge to be discarded.
The edge detection of the target equipment in the infrared image can be realized through the steps from one step to four, the background information in the image is completely filtered, the edge of the target equipment is clear, and the accurate extraction of the target equipment is realized. Because the purpose of the infrared image shooting reaction is to obtain the temperature field distribution condition of the target equipment, compared with the RGB information of the extracted image, the edge detection method directly extracts the temperature data corresponding to the image and can reflect the essential information of the image; the traditional image RGB matrix-based method needs preprocessing processes such as filtering and enhancing, the calculated amount is large, the steps are omitted, and the calculation is faster; because the background in the infrared image of the power equipment is complex and the color space is rich, but the temperature difference between the target equipment and the background of the environment is obvious, compared with the traditional technical means, the scheme is easier to extract the target equipment from the background and is hardly interfered by the background environment; compared with the current method for identifying the target based on deep learning, the method can complete the identification task on a common PC without a large number of training samples and ultra-strong computing power.
The method for realizing the edge detection adopts a set of corresponding infrared image detection system, which comprises an infrared imager, a console and a display, wherein the console is internally provided with a control panel, the control panel is provided with a microcontroller, an analog-to-digital converter and a memory, the microcontroller is connected with the analog-to-digital converter, the memory, the infrared imager and the display through leads, and only one set of infrared imager control software is arranged in the console.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (4)
1. An edge detection method for an infrared image target of electrical equipment is characterized by comprising the following steps: the method comprises the following steps:
the method comprises the following steps: extracting temperature matrix data corresponding to the infrared image, wherein the temperature data is directly derived through infrared imager control software or calculated through infrared radiation original data stored in the infrared image;
step two: calculating gradient values and directions of the temperature matrix;
step three: comparing gradient values before and after the pixel points along the gradient direction, reserving the pixel points with the maximum local gradient, and thinning the image edge by a non-maximum inhibition method;
step four: and selecting a maximum temperature threshold and a minimum temperature threshold of the gradient amplitude, and performing edge connection to form an edge detection graph of the infrared image.
2. The method for detecting the edge of the infrared image target of the electric power equipment as claimed in claim 1, wherein the method comprises the following steps: and in the second step, the gradient value and the direction of the temperature matrix are calculated by a first-order finite difference method to obtain the gradient value and the direction of the temperature matrix, and the specific calculation formula is as follows:
the above formula is the calculation formula of the gradient value in the x direction, wherein
The value is a gradient value in the x direction, and T (i, j) is the temperature corresponding to the infrared image pixel point (i, j);
the above formula is a y-direction gradient value calculation formula, wherein
The y-direction gradient value is obtained, and T (i, j) is the temperature corresponding to the infrared image pixel point (i, j);
the above formula is the gradient amplitude corresponding to the pixel point (i, j)
The calculation formula of (2);
the above formula is the gradient direction
The calculation formula of (2).
3. The method for detecting the edge of the infrared image target of the electric power equipment as claimed in claim 2, wherein the method comprises the following steps: and in the third step, the local gradient maximum value pixel is retained, and the image edge is refined by a non-maximum value inhibition method, and the specific steps are as follows:
step 3.1: defining g1-g8 as eight field pixels of the pixel C, selecting the g1-g8 in a clockwise arrangement mode, and enabling the pixel C to be located in the center of the eight field pixels;
step 3.2: according to the formula
Calculating the gradient direction of the pixel point C, and expressing the gradient direction by a line L1;
step 3.3: defining the intersection points of the line L1 and the field pixel points as temp1 and temp2, extracting the temperature values of temp1 and temp2 through the first step when the temp1 and the temp2 are positive pixel points, and calculating the temperature values corresponding to the temp1 and the temp2 through interpolation when the temp1 and the temp2 are sub-pixel points;
step 3.4: judging the temperature values of the pixel point C, temp1 and the temp2, when the temperature value of the pixel point C is the maximum, keeping the pixel point C, and when the temperature value of the pixel point C is not the maximum, discarding the pixel point C;
step 3.5: and judging all pixel points on the infrared image according to the method from the step 3.1 to the step 3.4.
4. The method for detecting the edge of the infrared image target of the electric power equipment as claimed in claim 3, wherein the method comprises the following steps: the specific judgment step for selecting the maximum temperature threshold and the minimum temperature threshold of the gradient amplitude in the fourth step is as follows:
step 4.1: setting the maximum temperature threshold as maxVal and the minimum temperature threshold as minVal;
step 4.2: judging the sizes of the pixel point gradient and the maxVal and the minVal, reserving the edge with the gradient larger than the maxVal as a true edge, and discarding the edge with the gradient smaller than the minVal as a false edge;
step 4.3: the gradient is located at the edge between the maxVal and the minVal, whether the gradient is an edge or a non-edge is judged through the connectivity of the gradient, a part which is connected to a reliable edge larger than the maxVal and is judged to be the edge is reserved, and a part which is not connected to the reliable edge larger than the maxVal and is judged to be not the edge is discarded.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010566923.9A CN111931785A (en) | 2020-06-19 | 2020-06-19 | Edge detection method for infrared image target of power equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010566923.9A CN111931785A (en) | 2020-06-19 | 2020-06-19 | Edge detection method for infrared image target of power equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111931785A true CN111931785A (en) | 2020-11-13 |
Family
ID=73317332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010566923.9A Pending CN111931785A (en) | 2020-06-19 | 2020-06-19 | Edge detection method for infrared image target of power equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111931785A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112489066A (en) * | 2020-11-30 | 2021-03-12 | 国网山西省电力公司晋城供电公司 | Method for extracting infrared thermal imaging image edge of power distribution equipment |
| CN114757907A (en) * | 2022-04-06 | 2022-07-15 | 上海擎测机电工程技术有限公司 | Data processing method of infrared sensor |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015079282A1 (en) * | 2013-11-28 | 2015-06-04 | Intel Corporation | Method for determining local differentiating color for image feature detectors |
| CN105427286A (en) * | 2015-11-06 | 2016-03-23 | 中国电子科技集团公司第二十八研究所 | Gray scale and gradient segmentation-based infrared target detection method |
| US20160267675A1 (en) * | 2014-06-23 | 2016-09-15 | Boe Technology Group Co., Ltd. | Image edge detection method and apparatus thereof, image target identification method and apparatus thereof |
| WO2017177717A1 (en) * | 2016-04-14 | 2017-10-19 | 广州视源电子科技股份有限公司 | Element positioning method and system based on color and gradient |
| CN107314819A (en) * | 2017-07-03 | 2017-11-03 | 南京绿谷信息科技有限公司 | A kind of detection of photovoltaic plant hot spot and localization method based on infrared image |
| CN109360217A (en) * | 2018-09-29 | 2019-02-19 | 国电南瑞科技股份有限公司 | Power transmission and transforming equipment method for detecting image edge, apparatus and system |
| CN109377469A (en) * | 2018-11-07 | 2019-02-22 | 永州市诺方舟电子科技有限公司 | A kind of processing method, system and the storage medium of thermal imaging fusion visible images |
| CN109816651A (en) * | 2019-01-24 | 2019-05-28 | 电子科技大学 | Thermal image defect characteristic extracting method based on change rate and temperature difference |
| CN110348500A (en) * | 2019-06-30 | 2019-10-18 | 浙江大学 | Sleep disturbance aided diagnosis method based on deep learning and infrared thermal imagery |
-
2020
- 2020-06-19 CN CN202010566923.9A patent/CN111931785A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015079282A1 (en) * | 2013-11-28 | 2015-06-04 | Intel Corporation | Method for determining local differentiating color for image feature detectors |
| US20160267675A1 (en) * | 2014-06-23 | 2016-09-15 | Boe Technology Group Co., Ltd. | Image edge detection method and apparatus thereof, image target identification method and apparatus thereof |
| CN105427286A (en) * | 2015-11-06 | 2016-03-23 | 中国电子科技集团公司第二十八研究所 | Gray scale and gradient segmentation-based infrared target detection method |
| WO2017177717A1 (en) * | 2016-04-14 | 2017-10-19 | 广州视源电子科技股份有限公司 | Element positioning method and system based on color and gradient |
| CN107314819A (en) * | 2017-07-03 | 2017-11-03 | 南京绿谷信息科技有限公司 | A kind of detection of photovoltaic plant hot spot and localization method based on infrared image |
| CN109360217A (en) * | 2018-09-29 | 2019-02-19 | 国电南瑞科技股份有限公司 | Power transmission and transforming equipment method for detecting image edge, apparatus and system |
| CN109377469A (en) * | 2018-11-07 | 2019-02-22 | 永州市诺方舟电子科技有限公司 | A kind of processing method, system and the storage medium of thermal imaging fusion visible images |
| CN109816651A (en) * | 2019-01-24 | 2019-05-28 | 电子科技大学 | Thermal image defect characteristic extracting method based on change rate and temperature difference |
| CN110348500A (en) * | 2019-06-30 | 2019-10-18 | 浙江大学 | Sleep disturbance aided diagnosis method based on deep learning and infrared thermal imagery |
Non-Patent Citations (4)
| Title |
|---|
| 牛奕;甘玲童;马云;: "基于红外无损检测的非金属材料粘贴缺陷识别", 红外技术, no. 04, pages 1 * |
| 王嘉俊;段先华;: "改进Canny算子在水面目标边缘检测中的研究", 计算机时代, no. 01, pages 1 - 3 * |
| 许宏科，秦严严，陈会茹: "一种基于改进 Canny 的边缘检测算法", 红外技术, vol. 36, no. 3, pages 1 - 3 * |
| 贺敏: "基于交流电磁场和涡流激励热成像的复合检测技术研究", 中国优秀博士学位论文全文数据库信息辑, no. 2, pages 5 - 7 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112489066A (en) * | 2020-11-30 | 2021-03-12 | 国网山西省电力公司晋城供电公司 | Method for extracting infrared thermal imaging image edge of power distribution equipment |
| CN112489066B (en) * | 2020-11-30 | 2023-07-04 | 国网山西省电力公司晋城供电公司 | Extraction method for infrared thermal imaging image edge of power distribution equipment |
| CN114757907A (en) * | 2022-04-06 | 2022-07-15 | 上海擎测机电工程技术有限公司 | Data processing method of infrared sensor |
| CN114757907B (en) * | 2022-04-06 | 2023-03-10 | 上海擎测机电工程技术有限公司 | Data processing method of infrared sensor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112199993B (en) | Method for identifying transformer substation insulator infrared image detection model in any direction based on artificial intelligence | |
| Chen et al. | Accurate and robust crack detection using steerable evidence filtering in electroluminescence images of solar cells | |
| CN103487729B (en) | Based on the power equipments defect detection method that ultraviolet video and infrared video merge | |
| CN108121991B (en) | Deep learning ship target detection method based on edge candidate region extraction | |
| CN103136531A (en) | Automatic identification method of insulator chain infrared image | |
| CN110321933B (en) | Fault identification method and device based on deep learning | |
| CN107492094A (en) | A kind of unmanned plane visible detection method of high voltage line insulator | |
| CN111598889B (en) | Identification method and device for inclination fault of equalizing ring and computer equipment | |
| US5923776A (en) | Object extraction in images | |
| CN111539330B (en) | Transformer substation digital display instrument identification method based on double-SVM multi-classifier | |
| CN116721107B (en) | Intelligent monitoring system for cable production quality | |
| CN105678760A (en) | Method for recognizing insulator image on the basis of Canny edge detection algorithm | |
| CN111931785A (en) | Edge detection method for infrared image target of power equipment | |
| CN110726725A (en) | Transmission line hardware corrosion detection method and device | |
| CN112669287B (en) | Electrical equipment temperature monitoring method based on image recognition | |
| CN111126253A (en) | Knife switch state detection method based on image recognition | |
| CN111915509B (en) | Protection pressing plate state identification method based on shadow removal optimization of image processing | |
| CN106951863B (en) | Method for detecting change of infrared image of substation equipment based on random forest | |
| CN109345586A (en) | Electrical equipment discharge characteristic extracting method based on ultraviolet imagery technology | |
| CN109447062A (en) | Pointer-type gauges recognition methods based on crusing robot | |
| CN109389165A (en) | Oil level gauge for transformer recognition methods based on crusing robot | |
| CN104573713A (en) | Mutual inductor infrared image recognition method based on image textual features | |
| CN107274382B (en) | State identification method and device of hard pressing plate and electronic equipment | |
| KR101779040B1 (en) | Method and apparatus for extracting panel area from thermal infrared images of photovoltaic array | |
| CN111047598A (en) | Deep learning-based ultraviolet discharge light spot segmentation method and device for power transmission and transformation equipment |
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 |