CN112734637B - Thermal infrared image processing method and system for monitoring temperature of lead - Google Patents
Thermal infrared image processing method and system for monitoring temperature of lead Download PDFInfo
- Publication number
- CN112734637B CN112734637B CN202011503810.0A CN202011503810A CN112734637B CN 112734637 B CN112734637 B CN 112734637B CN 202011503810 A CN202011503810 A CN 202011503810A CN 112734637 B CN112734637 B CN 112734637B
- Authority
- CN
- China
- Prior art keywords
- image
- temperature
- images
- wire
- lead
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 28
- 238000003672 processing method Methods 0.000 title claims abstract description 9
- 238000009826 distribution Methods 0.000 claims abstract description 43
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000010801 machine learning Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 32
- 238000012806 monitoring device Methods 0.000 claims description 16
- 230000004927 fusion Effects 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000003709 image segmentation Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012800 visualization Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 abstract description 5
- 238000001514 detection method Methods 0.000 description 7
- 238000012423 maintenance Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003064 k means clustering Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007667 floating Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4007—Interpolation-based scaling, e.g. bilinear interpolation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
-
- 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
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Abstract
A thermal infrared image processing method and system for monitoring the temperature of a lead comprises the following steps: 1) collecting infrared thermal image images of a plurality of different wires of the power distribution cabinet at fixed points, and storing and preprocessing the images; 2) performing image processing on the infrared thermal image by adopting a machine learning algorithm, and then identifying a lead area and the temperature of the lead area in each image; 3) and repeating the steps 1) and 2), splicing the plurality of identified images to obtain all the wires of the power distribution cabinet and the corresponding temperature maps thereof. The invention realizes real-time updating and storing of temperature data of each wire, improves the accuracy of temperature monitoring, and effectively avoids the phenomenon of abnormal heat of the wires due to the rise of the temperature.
Description
Technical Field
The invention relates to the field of power distribution cabinets, in particular to a thermal infrared image processing method and system for monitoring the temperature of a lead.
Background
The electric power resource is a necessary energy resource for activities such as production and life in various fields of China society, and is closely related to the production and life of people. With the continuous progress of society and the vigorous development of science and technology brought by the progress, the application technical field of the power distribution cabinet participation also becomes wider. The power distribution cabinet is used as an important carrier to participate in the expression process of system functions in various fields such as national defense, aerospace, industrial production and the like.
The power distribution cabinet is divided into a power distribution cabinet, a lighting distribution cabinet and a metering cabinet, and is the final-stage equipment of a power distribution system. The distribution cabinet functions to distribute power to each load location through distribution control and to perform blackout maintenance when short circuits, overloads, and leaks occur in the circuit. The most common types of power distribution cabinets are fixed panel cabinets, protective cabinets, drawer cabinets and power distribution cabinets for electrical lighting. The distribution line is used as the most core component in a power supply system and a power transmission network, and can guarantee the production and living needs of users.
The safe and normal operation of the power distribution cabinet equipment is related to whether the production system can effectively produce on time or not, and is also related to the safety of production personnel and even the whole industry. The main reasons for safety accidents of the power distribution cabinet are current overload, short circuit, line aging and the like. Almost all reasons finally cause the rise of wire temperature to cause the heat abnormal phenomenon, in addition it usually needs long-time operation in the enclosed environment, thus this causes the whole easy temperature anomaly of its switch board thereby causes incident such as power failure or conflagration. The electric accidents do not happen instantly in most cases, a temperature change process exists, if the monitoring system gives an alarm when the monitoring system is abnormal, and workers can overhaul and solve problems in advance when no serious disaster is caused.
Therefore, in order to ensure the service life of the operation of the power distribution cabinet and the reliability and high efficiency of the operation, the operation temperature of the power distribution cabinet needs to be monitored in real time during the operation of the power distribution cabinet. The traditional manual temperature measuring mode is low in efficiency and safety guarantee mode, time and labor cost are high, and steps are mechanical. Therefore, the design of the on-line monitoring system capable of monitoring the temperature of the lead in real time in the operation of the production system has important practical significance.
Disclosure of Invention
The invention mainly aims to overcome the defect that power transmission wires in the conventional power distribution cabinet run in a closed environment for a long time and accidents such as power failure or fire disasters are easily caused by abnormal temperature, and provides a thermal infrared image processing method and a thermal infrared image processing system for monitoring the temperature of the wires, so that operation and maintenance personnel can accurately obtain the temperature information of the wires in the power distribution cabinet, the waste of time and physical strength caused by manual detection of the temperature of the wires by the operation and maintenance personnel is effectively avoided, the normal running of the power distribution cabinet is ensured, and various potential safety hazards caused by the temperature rise of the wires are effectively eliminated.
The invention adopts the following technical scheme:
a thermal infrared image processing method for monitoring the temperature of a lead is characterized by comprising the following steps:
1) collecting infrared thermal image images of a plurality of different wires of the power distribution cabinet at fixed points, and storing and preprocessing the images;
2) performing image processing on the infrared thermal image by adopting a machine learning algorithm, and then identifying a lead area and the temperature of the lead area in each image;
3) and repeating the steps 1) and 2), splicing the plurality of identified images to obtain all the wires of the power distribution cabinet and the corresponding temperature maps thereof.
Preferably, the preprocessing includes interpolation processing, gray enhancement, and pseudo-colorization encoding processing.
Preferably, the pseudo-colorization coding processing is to perform numerical value normalization processing on the image, and then map the image to corresponding color pixel points, specifically: mapping an original value x of the data sequence D to an interval [0,1 ] by Min-max normalization]Value x of*The formula is as follows:
wherein D isminAnd DmaxRespectively, the minimum and maximum values of the data sequence D.
Preferably, the image processing includes the following: and (3) carrying out image segmentation by adopting a K-means unsupervised clustering algorithm, marking the binary image obtained by segmentation by using a 4-neighborhood region growing method, and extracting the area and coordinate attributes of a connected domain to obtain a wire region and coordinates thereof.
Preferably, the temperature of the identification wire region is specifically: and after the connected domain is marked, extracting the maximum value in each connected domain image array, namely the highest temperature of each lead, marking the maximum value in the red rectangular frame of each lead, and finally marking the maximum temperature in all leads by using a cross cursor to serve as the index of the highest temperature value.
Preferably, the infrared thermal image is collected at a movable fixed point, the overlapping proportion of the images is controlled to be 30% -60% during collection, the obtained multiple images are processed in the steps 1) -2), and then image splicing of the overlapping parts of the adjacent images is carried out, so that all wires of the power distribution cabinet and corresponding temperature maps of the wires are obtained.
Preferably, the stitching includes image registration and image fusion reconstruction.
Preferably, the image fusion reconstruction is performed by overlapping and adding pixel values of the image in an overlapping region according to a linear weight to obtain a spliced pixel value, and the image fusion reconstruction is completed according to the following formula:
wherein I1(x, y) and I2(x, y) are the pixel values of the first and second images, R1Representing non-overlapping regions, R, in the first image2Representing the overlapping area of two images, R3Representing the non-overlapping area in the second image, and d (x) is a weight coefficient.
A wire temperature monitoring system, comprising:
the system comprises a plurality of movable monitoring devices, a plurality of sensors and a plurality of sensors, wherein the movable monitoring devices are used for collecting infrared thermal image images of a plurality of different wires of the power distribution cabinet at fixed points;
and the host module is communicated with the mobile monitoring device, stores and preprocesses the infrared thermal image, processes the image by adopting a machine learning algorithm, identifies the wire area and the temperature of each image, and splices a plurality of identified images to obtain all wires of the power distribution cabinet and corresponding temperature images thereof.
Preferably, the mobile monitoring device comprises a main body, a thermal infrared imager, a two-degree-of-freedom cloud platform and a control module, the two-degree-of-freedom cloud platform is connected with and drives the thermal infrared imager to rotate left and right or move up and down, the control module is installed on a base of the main body and is connected with and controls the two-degree-of-freedom cloud platform, and the host module is communicated with the control module and the thermal infrared imager.
Preferably, the host module comprises a lead temperature identification module, a lead temperature alarm module, a lead temperature visualization module and a database; the wire temperature identification module is used for processing images, identifying a wire area and the temperature thereof in each image and splicing a plurality of identified images; the wire temperature alarm module is used for giving an alarm when the highest temperature of the wire exceeds the normal operation allowable temperature, and the wire temperature visualization module is used for displaying the final global wire and temperature identification map; the database is used for storing infrared thermal image images and temperature information.
As can be seen from the above description of the present invention, compared with the prior art, the present invention has the following advantages:
the method and the device provided by the invention are based on the fusion of infrared thermal imagery and image processing and image splicing technologies, realize the identification of all wires in the power distribution cabinet and the temperature identification corresponding to each wire, realize the real-time updating and storage of the temperature data of each wire, improve the accuracy of temperature monitoring, and effectively avoid the phenomenon of thermal abnormity of the wires due to the rise of the temperature.
The invention is beneficial to reflecting the safety state of the power distribution cabinet for a long time through long-term monitoring, and the staff can overhaul and solve the problem in advance when no major disaster is caused, thereby providing a good foundation for the safe and healthy online monitoring, dynamic prediction and control of the wires in the power distribution cabinet.
The mobile fixed-point detection device of the infrared thermography technology has the advantages of simple structure, low cost and capability of obtaining the temperature information of the lead in a short distance, and improves the accuracy of temperature identification of the lead compared with remote measurement.
According to the invention, the global wire identification method in the power distribution cabinet is spliced with the wire temperature image, so that the method has great significance for real-time monitoring of the experimental power distribution cabinet and dynamic prediction in the later period, the accuracy of local wire temperature identification to the accuracy of global wire temperature identification is realized, and the good operation of the whole online monitoring system is ensured.
By implementing the method, operation and maintenance personnel can accurately obtain the temperature information of the wires in the power distribution cabinet, the good operation of the power distribution cabinet is improved and ensured, various potential safety hazards caused by the temperature rise of the wires are effectively eliminated, and the waste of time and physical force caused by the manual detection of the temperature of the wires by the operation and maintenance personnel is effectively avoided.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a block diagram of the system of the present invention;
FIG. 3 is a block diagram of a mobile monitoring device according to the present invention;
the invention is described in further detail below with reference to the figures and specific examples.
Detailed Description
The invention is further described below by means of specific embodiments.
As used herein, the terms "first," "second," "third," and the like are used solely to distinguish similar objects from one another, and are not necessarily used to describe a particular order or sequence, nor are they to be construed as indicating or implying relative importance. In the description, the directions or positional relationships indicated by "up", "down", "left", "right", "front" and "rear" are used based on the directions or positional relationships shown in the drawings, and are only for convenience of describing the present invention, and do not indicate or imply that the device referred to must have a specific direction, be constructed and operated in a specific direction, and thus, should not be construed as limiting the scope of the present invention. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
In addition, in the description of the present application, "a plurality" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
Referring to fig. 1, a thermal infrared image processing method for monitoring wire temperature includes the following steps:
1) and collecting infrared thermal image images of a plurality of different wires of the power distribution cabinet at fixed points, and storing and preprocessing the images. In this step, the preprocessing includes interpolation processing, gradation enhancement, and pseudo-colorization encoding processing.
Wherein, three common interpolation methods are selected for interpolation, which are respectively: nearest neighbor interpolation, bilinear interpolation, bicubic interpolation. Preferably, the original 32 × 24 pixel image is subjected to bilinear interpolation processing to obtain an interpolation map of 512 × 384 pixels, but the interpolation is not limited to bilinear interpolation.
And (3) carrying out pseudo-color coding processing to obtain a pseudo-color infrared digital image, normalizing the temperature, corresponding to a 0-255 interval, and corresponding the gray value of 0-255 to other colors according to a certain rule to present a color image. The obtained Colormap can be used for realizing the pseudo colorization of the image by utilizing the Colormaps embedded in the matplotlib module of the Python.
The numerical normalization is specifically as follows:
mapping an original value x of the image array sequence D into an interval [0,1 ] through Min-max standardization]Value x of*The formula is as follows:
wherein D isminAnd DmaxThe minimum value and the maximum value of the image array sequence D are respectively.
Meanwhile, nonlinear gray scale enhancement adopting a logarithmic formula is carried out on the image obtained after bilinear interpolation, and aiming at the problem of wire region detection, a gray scale enhancement algorithm is utilized on the image after interpolation to enhance the regional characteristics and the spatial structure characteristics of the wire, so that the region where the wire is located is more independent compared with other regions, and a technical basis is provided for subsequent detection of the wire profile. This step uses a separate output picture as the lead region extraction.
The nonlinear gray scale enhancement algorithm adopting the logarithmic formula is mainly used for expanding the low gray scale value part of the image and compressing the high gray scale value part of the image so as to achieve the purpose of emphasizing the low gray scale part of the image. The method specifically comprises the following steps:
s＝c*logv+1(1+v*r)r∈[0,1]
wherein s is an output image, r is an input image after gray level normalization, c and v are constants, and the larger v is, the more obvious the gray level improvement is.
The image colorization specifically comprises the following steps:
respectively obtaining integer type and floating point type jet maps, storing the integer type and floating point type jet maps in a txt file for later use, calling a gray2color function, and carrying out color mapping on the arrays in the interval of 0-255 according to rules to obtain a lead color mapping chart.
2) And (4) performing image processing on the infrared thermal image by adopting a machine learning algorithm, and then identifying the wire area and the temperature of each image. The method comprises the steps of image segmentation, image corrosion, connected domain marking, attribute analysis, temperature identification and the like.
Common image segmentation methods include a threshold-based segmentation method, an edge-based segmentation method, a deep learning-based segmentation method and a machine learning-based segmentation method, and the threshold-based segmentation method and the edge-based segmentation method ignore the spatial structure information of an object in an image, so that the recognition effect is inferior to that of other algorithms under the same enhancement effect. The segmentation method based on deep learning needs a large number of data sets, the generalization and the robustness of the segmentation method are limited by the data sets, the cost is high, the efficiency is uncertain, and the practicability is low. Therefore, the segmentation of the conductor region is realized by adopting a clustering algorithm in machine learning, and common clustering algorithms comprise hierarchical clustering, fuzzy clustering, K-means clustering and the like.
Preferably, the image segmentation is performed by K-means clustering, but not limited to this method, wherein K-means clustering image segmentation specifically comprises: converting the image subjected to logarithmic enhancement in the last step into a gray sequence G, and randomly selecting 2 objects as initial clustering centers mu of the gray sequence G1、μ2For each sample x in the gray sequence GiCalculate it to the cluster center μ1、μ2The euclidean distance of (a) is expressed as:
classifying the samples by the calculated distance to obtain an initial sample classification set G1、G2. For the samples in each classification set, the centroid of the samples is recalculated, and the formula is as follows:
after that, the above two steps are iterated continuously, when the centroid mu isjIs less than a certain threshold, classification is considered complete. Taking the gray classification sequence G at this time1、G2. Sequence G1All points in the sequence G with a gray value of 02And carrying out gray level image reconstruction on the gray level sequence by using all the points in the image to form a binary image by using the gray level value of 255.
For a binary image, if two pixel points are adjacent and have the same value, the two pixel points are in the same interconnected region. Visually, the points that are connected to each other form a region, and the set of all the connected points in the region is called a connected region. In an image, each pixel, when centered on itself, typically has 8 neighboring pixels around it. 4 connectivity considers only 4 adjacent pixels, i.e. up, down, left, and right; 8 connected then considers a total of 8 contiguous pixels, additionally including points at diagonal locations.
Preferably, the connected domain extraction marking and the attribute analysis adopt a 4-neighborhood region growing method, which specifically comprises the following steps: and marking the corroded binary image by using a 4-neighborhood region growing method, and extracting the area and coordinate attributes of the connected domain. And setting a minimum value of 200 for the area, removing the interference area, and obtaining the correct area and the coordinates of the lead. After the wire coordinates are obtained, they are visually marked, with each wire marked with a red rectangular box.
The temperature identification specifically comprises the following steps: and after the connected domain is marked, extracting the maximum value in each connected domain image array, namely the maximum temperature of each lead, marking the maximum value in the red rectangular frame of each lead, and finally marking the maximum temperature in all leads by using a cross cursor to serve as the maximum temperature value index.
3) And repeating the steps 1) and 2), splicing the plurality of identified images to obtain all the wires of the power distribution cabinet and the corresponding temperature maps thereof.
The method utilizes the movable fixed-point acquisition of the infrared thermal image, the overlapping proportion of the images is controlled to be 30-60% during acquisition, the obtained multiple images are processed in the steps 1) -2), and then image splicing of the overlapping parts of the adjacent images is carried out, so that all wires of the power distribution cabinet and corresponding temperature maps thereof are obtained. And the splicing comprises image registration and image fusion reconstruction.
Image registration using feature point-based image registration includes: feature point detection, feature point description, feature point search and matching. The invention uses SIFT feature detection algorithm based on feature points.
Detecting characteristic points: and detecting SIFT key feature points of the images to be spliced, calculating the feature points, matching all the feature points of the images to be spliced, and returning a matching result.
Description of characteristic points: and extracting the gradient or gray related information in the neighborhood of the detected feature points to generate a multi-dimensional feature descriptor.
Searching and matching feature points: the distance between feature points detected and described based on the SIFT algorithm is measured by the Euclidean distance. In the feature matching stage, a BBF (best Bin first) algorithm is adopted to search a feature space, namely, a matching feature point with the nearest distance is found.
And the image fusion realizes the fusion of the overlapped parts of the registered multiple images, and the pixel values of the images in the overlapped area are overlapped and added according to linear weight to be used as the spliced pixel values, so that the image fusion reconstruction is completed.
The formula is as follows:
wherein I1(x, y) and I2(x, y) are the pixel values of the first and second images, R1Representing non-overlapping regions, R, in the first image2Representing the overlapping area of two images, R3Representing the non-overlapping area in the second image, d (x) is a weight coefficient representing the proportion of the pixel value of the first image to the total pixel value, and the value range is [0, 1%]Suppose the edge position of the first image in the overlapping region is X0If the width of the overlap region is w, the weight coefficient is:
finally, the global wire and temperature identification graph is displayed on a data display, the temperature data of each wire is updated and stored in real time, and the health state of each wire in the power distribution cabinet is judged by taking long-term monitoring; when the highest temperature in the global image exceeds the allowable temperature for normal operation of the wire, the system immediately alarms to remind monitoring personnel, after the staff carries out timely rush repair, operation and maintenance, the program returns to data acquisition after the temperature of the wire is monitored to be recovered to be normal, and the next cycle operation is continued.
The invention also provides a wire temperature monitoring system, which comprises a plurality of movable monitoring devices and a host module, wherein the host module is communicated with the movable monitoring devices.
Referring to fig. 3, the plurality of mobile monitoring devices are used for collecting infrared thermal image images of a plurality of different wires of the power distribution cabinet at fixed points. Each movable monitoring device comprises a thermal infrared imager 1, a two-degree-of-freedom cloud platform 2, a control module 3, a main body 4, a WIFI module 7 and the like, the two-degree-of-freedom cloud platform 2 is connected with and drives the thermal infrared imager 1 to rotate left and right or move up and down, and the control module 3 is installed on the main body 4 and is connected with and controls the two-degree-of-freedom cloud platform 2 to act.
In the invention, the main body 4 is provided with a travelling mechanism and a power supply module, and the control module 3 can also control the travelling mechanism to move and turn, so that the main body 4 is driven to travel and the driving is stopped at a proper position. The power module is used for providing power for the mobile monitoring device. The thermal infrared imager 1 employs MLX 90640. The control module can select an ESP32 single-chip microcomputer, collects image information of the thermal infrared imager through an I2C data bus, and sends the image information to the host module through the WIFI module 7.
Furthermore, the two-degree-of-freedom cloud platform 2 is fixedly installed on the main body 4 through a support frame, the moving monitoring device controls the moving, steering and stopping driving of the traveling mechanism through the control module 3, and is matched with the thermal infrared imager to collect image information at fixed points of wires at different positions in the switch cabinet in a short distance, so that array source infrared digital images of 32 x 24 pixels are obtained, and the obtained array information is transmitted to the host module.
The host module can select STM, PIC, ARM and other series of processor chips, and its main functions include WIFI communication, parameter configuration, data storage, wire temperature identification, wire temperature warning, realization of image concatenation etc. through storing and the preliminary treatment to thermal infrared imagery image, adopt machine learning algorithm to carry out image processing, wire region and its temperature in every picture is discerned again, and with many image concatenations after the discernment, obtain all wires of switch board and corresponding temperature map.
Specifically, the host module can comprise a wire temperature identification module, a wire temperature alarm module, a wire temperature visualization module, a database and other functional modules; the wire temperature identification module can be used for image processing, identifying the wire area and the temperature thereof in each image and splicing a plurality of identified images; the wire temperature alarm module is used for giving an alarm when the highest temperature of the wire exceeds the normal operation allowable temperature, and the wire temperature visualization module is used for displaying the final global wire and temperature identification map; the database is used for storing infrared thermal image images and temperature information.
In the invention, the mobile monitoring device can also be provided with a data display 5 and a temperature alarm 6 which are both connected with the control module 3. The control module 3 receives the wire temperature value, alarm information and the like after image processing and graph splicing analysis processing from the host module, displays the wire temperature value, the alarm information and the like through the data display 5, and performs sound-light alarm on abnormal temperature through temperature alarm. The data display 5 may be arranged on top of the mobile monitoring device, placed in an inclined manner for the operation and maintenance personnel to check the records.
The above description is only an embodiment of the present invention, but the design concept of the present invention is not limited thereto, and any insubstantial modifications made by using the design concept should fall within the scope of infringing the present invention.
Claims (8)
1. A thermal infrared image processing method for monitoring the temperature of a lead is characterized by comprising the following steps:
1) collecting infrared thermal image images of a plurality of different wires of a power distribution cabinet at fixed points, collecting the infrared thermal image images at the movable fixed points, controlling the overlapping proportion between the images to be 30-60% during collection, and storing and preprocessing the obtained plurality of images;
2) performing image processing on the infrared thermal image by adopting a machine learning algorithm, and identifying a wire area and the temperature of the wire area in each image;
3) repeating the steps 1) and 2), and carrying out image splicing of the overlapped parts of the adjacent images on the plurality of identified images to obtain all the wires of the power distribution cabinet and corresponding temperature maps thereof; the splicing comprises image registration and image fusion reconstruction, the image fusion reconstruction is to overlap and add pixel values of the images in an overlapping area according to linear weights to form spliced pixel values, and the image fusion reconstruction is completed according to the formula:
wherein I1(x, y) and I2(x, y) are first web and second web, respectivelyPixel values, R, of two images1Representing non-overlapping regions, R, in the first image2Representing the overlapping area of two images, R3Representing the non-overlapping area in the second image, d (x) is a weight coefficient representing the proportion of the pixel value of the first image to the total pixel value, and the value range is [0, 1%]Suppose the edge position of the first image in the overlapping region is X0And if the width of the overlapping area is w, the weight coefficient is:
2. the method as claimed in claim 1, wherein the preprocessing includes interpolation, gray enhancement and pseudo-color coding.
3. The method for processing the thermal infrared image for monitoring the temperature of the conducting wire according to claim 2, wherein the pseudo-colorization coding processing is to perform numerical value normalization processing on the image and then map the image to corresponding color pixels, and specifically comprises the following steps: mapping an original value x of the data sequence D to an interval [0,1 ] by Min-max normalization]Value x of*The formula is as follows:
wherein D isminAnd DmaxRespectively, the minimum and maximum values of the data sequence D.
4. The method as claimed in claim 1, wherein the image processing comprises the following steps: and (3) carrying out image segmentation by adopting a K-means unsupervised clustering algorithm, marking the binary image obtained by segmentation by using a 4-neighborhood region growing method, and extracting the area and coordinate attributes of a connected domain to obtain a wire region and coordinates thereof.
5. The method for processing the thermal infrared image for monitoring the temperature of the conducting wire according to claim 1, wherein the temperature of the conducting wire area is identified by: and after the connected domain is marked, extracting the maximum value in each connected domain image array, namely the highest temperature of each lead, marking the maximum value in the red rectangular frame of each lead, and finally marking the maximum temperature in all leads by using a cross cursor to serve as the index of the highest temperature value.
6. A wire temperature monitoring system, wherein a thermal infrared image processing method for wire temperature monitoring according to any one of claims 1 to 5 is adopted, and the method comprises:
the plurality of mobile monitoring devices are used for collecting infrared thermal image images of a plurality of different wires of the power distribution cabinet at fixed points;
and the host module is communicated with the mobile monitoring device, stores and preprocesses the infrared thermal image, processes the image by adopting a machine learning algorithm, identifies the wire area and the temperature of each image, and splices a plurality of identified images to obtain all wires of the power distribution cabinet and corresponding temperature images thereof.
7. The system for monitoring the temperature of the conducting wire according to claim 6, wherein the mobile monitoring device comprises a main body, a thermal infrared imager, a two-degree-of-freedom cloud platform and a control module, the two-degree-of-freedom cloud platform is connected to drive the thermal infrared imager to rotate left and right or move up and down, the control module is installed on a base of the main body and is connected to control the two-degree-of-freedom cloud platform, and the main body module is communicated with the control module and the thermal infrared imager.
8. The lead temperature monitoring system of claim 6, wherein the host module comprises a lead temperature identification module, a lead temperature alarm module, a lead temperature visualization module, and a database; the wire temperature identification module is used for processing images, identifying a wire area and the temperature thereof in each image and splicing a plurality of identified images; the wire temperature alarm module is used for giving an alarm when the highest temperature of the wire exceeds the normal operation allowable temperature, and the wire temperature visualization module is used for displaying the final global wire and temperature identification map; the database is used for storing infrared thermal image images and temperature information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011503810.0A CN112734637B (en) | 2020-12-18 | 2020-12-18 | Thermal infrared image processing method and system for monitoring temperature of lead |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011503810.0A CN112734637B (en) | 2020-12-18 | 2020-12-18 | Thermal infrared image processing method and system for monitoring temperature of lead |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112734637A CN112734637A (en) | 2021-04-30 |
| CN112734637B true CN112734637B (en) | 2022-06-21 |
Family
ID=75603082
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011503810.0A Active CN112734637B (en) | 2020-12-18 | 2020-12-18 | Thermal infrared image processing method and system for monitoring temperature of lead |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112734637B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114782300B (en) * | 2022-04-29 | 2023-04-07 | 苏州华兴源创科技股份有限公司 | Product image reconstruction method, product reconstruction model training method and device |
| CN116503633B (en) * | 2023-07-03 | 2023-09-05 | 山东艾迈科思电气有限公司 | Intelligent detection control method for switch cabinet state based on image recognition |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567983A (en) * | 2010-12-26 | 2012-07-11 | 浙江大立科技股份有限公司 | Determining method for positions of monitored targets in instant infrared chart and application |
| GB201507124D0 (en) * | 2015-04-27 | 2015-06-10 | Thermoteknix Systems Ltd | Conveyer belt monitoring system and method |
| CN112001327A (en) * | 2020-08-25 | 2020-11-27 | 全球能源互联网研究院有限公司 | Valve hall equipment fault identification method and system |
| CN112013966A (en) * | 2020-08-24 | 2020-12-01 | 电子科技大学 | Power equipment infrared image processing method based on measured temperature |
-
2020
- 2020-12-18 CN CN202011503810.0A patent/CN112734637B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567983A (en) * | 2010-12-26 | 2012-07-11 | 浙江大立科技股份有限公司 | Determining method for positions of monitored targets in instant infrared chart and application |
| GB201507124D0 (en) * | 2015-04-27 | 2015-06-10 | Thermoteknix Systems Ltd | Conveyer belt monitoring system and method |
| CN112013966A (en) * | 2020-08-24 | 2020-12-01 | 电子科技大学 | Power equipment infrared image processing method based on measured temperature |
| CN112001327A (en) * | 2020-08-25 | 2020-11-27 | 全球能源互联网研究院有限公司 | Valve hall equipment fault identification method and system |
Non-Patent Citations (1)
| Title |
|---|
| 基于紫外联合红外热像的三通道便携式变电站监测装置;褚磊等;《电子技术与软件工程》;20190130(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112734637A (en) | 2021-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108037133B (en) | Intelligent electric power equipment defect identification method and system based on unmanned aerial vehicle inspection image | |
| CN110598736B (en) | Power equipment infrared image fault positioning, identifying and predicting method | |
| CN112734692B (en) | Defect identification method and device for power transformation equipment | |
| CN103247039B (en) | A kind of high voltage cable live detection method based on composite vision | |
| CN108537154A (en) | Transmission line of electricity Bird's Nest recognition methods based on HOG features and machine learning | |
| CN112734637B (en) | Thermal infrared image processing method and system for monitoring temperature of lead | |
| CN116824517B (en) | Substation operation and maintenance safety control system based on visualization | |
| CN116168351B (en) | Inspection method and device for power equipment | |
| CN117274722B (en) | Intelligent detection method for distribution box based on infrared image | |
| CN113920097A (en) | Power equipment state detection method and system based on multi-source image | |
| CN115346083A (en) | Temperature anomaly detection model training method, device, equipment and medium | |
| CN115965578A (en) | Binocular stereo matching detection method and device based on channel attention mechanism | |
| Nassu et al. | A computer vision system for monitoring disconnect switches in distribution substations | |
| CN112419243B (en) | Power distribution room equipment fault identification method based on infrared image analysis | |
| CN116958841B (en) | Unmanned aerial vehicle inspection system for power distribution line based on image recognition | |
| CN113031110B (en) | Cloud layer monitoring method and device, photovoltaic power prediction method and device | |
| Wang et al. | Substation Equipment Defect Detection based on Temporal-spatial Similarity Calculation | |
| CN113780224B (en) | Unmanned inspection method and system for transformer substation | |
| Murthy et al. | Distribution system insulator monitoring using video surveillance and support vector machines for complex background images | |
| CN113239731B (en) | Image digital feature extraction method of thermal fault infrared thermal image spectrum of circuit breaker | |
| Gao | Fault detection method of electrical wiring based on computer vision | |
| Jiafeng et al. | State Diagnosis Method of Distribution Network and Tower Multi-Circuit Line Live Operation Based on Image Recognition | |
| Murthy et al. | Video surveillance-based insulator condition monitoring analysis for substation monitoring system (SMS) | |
| CN117664351A (en) | Binocular imager-based power equipment temperature monitoring method and system | |
| CN116822692A (en) | Line abnormity prediction method and device and electronic 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |