CN114821035A - Distance parameter identification method for infrared temperature measurement equipment of power equipment - Google Patents
Distance parameter identification method for infrared temperature measurement equipment of power equipment Download PDFInfo
- Publication number
- CN114821035A CN114821035A CN202210369206.6A CN202210369206A CN114821035A CN 114821035 A CN114821035 A CN 114821035A CN 202210369206 A CN202210369206 A CN 202210369206A CN 114821035 A CN114821035 A CN 114821035A
- Authority
- CN
- China
- Prior art keywords
- equipment
- image
- target
- distance
- power equipment
- 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
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- 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
- G06V10/273—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 removing elements interfering with the pattern to be recognised
-
- 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
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- 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
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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
- G06T2207/20076—Probabilistic image processing
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a distance parameter identification method for an infrared temperature measurement device of an electric power device, which can accurately identify the shooting distance between a handheld thermal infrared imager and the electric power device during infrared temperature measurement. The technical method can automatically identify the distance of the power equipment by utilizing the pixel width of the power equipment in the infrared image, and solves the problem of difficult distance identification of the infrared image of the power equipment due to the change of the shooting angle and incomplete shooting of the equipment.
Description
Technical Field
The invention relates to the technical field of infrared distance measurement, in particular to a distance parameter identification method for infrared temperature measurement equipment of power equipment.
Background
The substation power equipment inevitably fails in long-term operation, and the most obvious characteristic when it fails is temperature anomaly. The thermal infrared imager can detect the running temperature of the equipment without power failure and contact with the equipment, monitors the running state of the equipment and is suitable for real-time monitoring of the temperature of a high-voltage charged body. In recent years, thermal infrared imagers have been used in a wide range of applications for monitoring the condition of power equipment.
However, despite the increasing use of thermal imaging in power equipment monitoring, the potential drawbacks and limitations of thermal imaging have been relatively less studied. Factors influencing infrared imaging are multiple, wherein the shooting distance is one of main factors influencing the infrared imaging effect, and accurate measurement of the shooting distance is one of main methods for improving the fault accuracy of infrared imaging detection equipment.
The invention mainly relates to a distance parameter identification method for infrared temperature measurement equipment of power equipment, aiming at the problems of infrared live detection at present. Aiming at the problem that the shooting distance setting of a thermal imager product suitable for electrical detection is inaccurate when the thermal imager is used at present, and infrared image temperature measurement data are abnormal, the improved algorithm for monocular distance measurement of the electrical equipment based on target pixel width identification is provided, the automatic identification of the equipment distance by utilizing the pixel width of the electrical equipment in an infrared image is realized, the problem that the distance identification difficulty is large due to shooting angle transformation and incomplete equipment shooting of the electrical equipment infrared imaging is solved, and the result shows that the improved algorithm can meet the monocular distance measurement requirement of the electrical equipment infrared image.
The invention mainly utilizes the fact that the pixel width of the target equipment is not influenced by the shooting angle when the infrared image is shot, and accordingly improves the monocular distance measurement algorithm. Because the camera has an angle with the horizontal vertical direction during shooting, the imaging coordinate system and the pixel coordinate system are not in parallel relation, so that the target plane is approximately perpendicular to the optical axis to combine with the relation between the imaging coordinate system and the world coordinate system, and the distance of the equipment is solved by adopting the pixel width.
Disclosure of Invention
The present invention is directed to solving the above problems of the prior art. A distance parameter identification method for infrared temperature measurement equipment of power equipment is provided. The technical scheme of the invention is as follows:
a distance parameter identification method for infrared temperature measurement equipment of power equipment comprises the following steps:
inputting an infrared image of the power equipment, and carrying out preprocessing of removing redundant information and enhancing a data set on the infrared image of the power equipment;
marking the power equipment area in the infrared image by using labelme software;
performing target detection based on an SSD (single-shot multi-box detector) algorithm to obtain automatic identification of the device type;
obtaining a minimum adjacent rectangular frame of the power equipment through an image processing algorithm in OpenCV, outputting vertex coordinates of the minimum adjacent rectangular frame, and calculating the pixel width of the identification target equipment;
the automatic identification of the equipment distance in the image is realized based on an improved monocular distance measurement algorithm, the object plane is approximately perpendicular to the optical axis, and only the relative position change on the Z axis exists between the world coordinate system and the camera coordinate system, so that the distance of the equipment is solved by utilizing the relation between the imaging coordinate system and the world coordinate system.
Further, the preprocessing of removing redundant information and enhancing a data set on the infrared image of the power device specifically includes:
redundant information including characters and symbols of the original thermal image is removed by compiling a batch processing program through an OS module in Python, the data set is enhanced by readjusting the imaging temperature range setting, the pretreatment of the sample image is completed,
further, the marking of the power equipment region in the infrared image by the labelme software specifically includes:
and labeling the equipment type corresponding to the image by Labelme software, analyzing the image characteristics of different equipment, evaluating the designed deep learning model through the equipment classification problem, and training and testing the target recognition model through labeling the equipment position. The deep learning model is a convolutional neural network for image recognition and consists of a plurality of convolutional layers, an activation layer, a pooling layer and a full-link layer. The convolutional layer is used for dimension reduction processing and feature extraction, the active layer is used for simulating any function and enhancing the characterization capability of the network, the pooling layer is used for reducing the calculated amount and improving the generalization capability, and the full-connection layer is used for feature classification and improving the output quality.
Further, the automatic identification of the type of the target detection and acquisition device by using the SSD algorithm specifically includes:
the SSD target test model structure is divided into two parts: the first part is a target basic feature extraction network; the second part is a multi-scale feature detection network and is used for carrying out multi-scale feature extraction on the feature layer extracted by the first part; the SSD target detection algorithm flow consists of two steps: one is target positioning, namely, the position of a target object in a picture is given; one is classification detection, which gives the probability that each candidate belongs to a particular class.
Further, the target test model specifically includes:
after the pictures are input, through forward network transmission, all the area candidate frames generate a category probability predicted value and a position offset predicted value, and according to a set threshold, frames with the probability predicted values lower than the threshold are deleted, namely the frames are considered to have no target. And then removing the redundant frames by using the category as a unit through non-maximum suppression to obtain the detection frames matched with the target to be detected.
Further, the obtaining a minimum adjacent rectangular frame of the power device through an image processing algorithm in OpenCV, outputting vertex coordinates of the minimum adjacent rectangular frame, and calculating a pixel width of the recognition target device specifically includes:
firstly, obtaining an SSD target detection frame, reading the vertex coordinates of an equipment box and removing images except the box, then extracting an equipment area part in the image based on a mask technology, removing noise interference including wired electricity around the equipment by performing open operation of corrosion expansion on the image, finally performing contour fitting on the image to identify the minimum adjacent rectangle of the equipment, and outputting the coordinates of 4 vertexes of the rectangle; the pixel width is equal to the minimum adjacent rectangle box short side length, so that the distance of the device can be calculated.
Further, the extracting of the device region part in the image based on the mask technology specifically includes: firstly, carrying out binarization processing on an image to enable the image to only contain black and white colors, then carrying out filtering and denoising on the image to obtain a clearer device outline, finally segmenting the image by using an image segmentation method to obtain an image mask region, and extracting a device region part in the image.
The pixel width is equal to the length of the short side of the minimum adjacent rectangular frame, so that the distance of the equipment can be calculated, and the target pixel width calculation formula is as follows:
wherein dx and dy are parameters obtained by camera calibration, and u 0 、v、v 0 Are parameters identified in the infrared image.
Further, the automatic identification of the device distance in the image based on the improved monocular distance measuring algorithm specifically includes: based on the principle of similar triangles in the geometric ranging algorithm, the distance between the camera and the target is finally calculated as follows:
wherein D is the actual width of the device, w is the width of the target pixel, f, dx and dy are parameters obtained by calibrating the camera, and u 0 、v、v 0 Are identified parameters in the infrared image.
The invention has the following advantages and beneficial effects:
the innovation of the invention is mainly realized by steps 5 to 7 of the claims, and the automatic identification of the device distance in the image is realized by using the relation among the world coordinate system, the imaging coordinate system and the pixel coordinate system by adopting the improved monocular distance measuring algorithm. And step 1 to step 4 are used for laying a cushion for the subsequent steps, mainly for outputting the vertex coordinates of the minimum adjacent rectangular box and providing data support for the realization of the subsequent improved monocular distance measuring algorithm. Because the thermal imager product suitable for electrical detection needs oneself input the shooting distance when using at present, and the testing personnel can only set up the average distance through the mode of eye observation usually, lead to infrared image data inaccurate, propose the improvement algorithm of monocular distance measurement in view of the above, realize the automatic identification of distance.
Drawings
FIG. 1 is a schematic diagram of an infrared image pre-processing process according to a preferred embodiment of the present invention;
FIG. 2 is a diagram of an SSD model architecture;
FIG. 3 is a pixel width flow of an identification device;
FIG. 4 is a correspondence of actual width to pixel width;
fig. 5 is a flow chart of a preferred embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described in detail and clearly with reference to the accompanying drawings. The described embodiments are only some of the embodiments of the present invention.
The technical scheme for solving the technical problems is as follows:
as shown in fig. 5, a method for identifying distance parameters of an infrared temperature measurement device of an electrical device can accurately identify a shooting distance between a handheld thermal infrared imager and the electrical device during infrared temperature measurement, and includes preprocessing an infrared image, marking an electrical device area in the infrared image, automatically identifying a device type based on an SSD algorithm, obtaining a minimum adjacent rectangular frame of the device based on image processing, identifying a pixel width of a target device, and automatically identifying a device distance in the image based on an improved monocular distance measurement algorithm.
1. SSD algorithm-based power equipment target detection and type identification
According to the invention, the infrared image data set is preprocessed on the basis of constructing the infrared image data set of the power equipment. Redundant information such as characters and symbols of the original thermal image is removed by writing a batch processing program, the temperature range setting of the imaging is readjusted, the data set is enhanced, the preprocessing of the sample image is completed, and the processing process is shown in fig. 1. After the preprocessing of the infrared image is completed, the labelme software is used for marking the power equipment area in the infrared image. And labeling the equipment type corresponding to the image by Labelme software, analyzing the image characteristics of different equipment, evaluating the designed deep learning model through the equipment classification problem, and training and testing the target recognition model through labeling the equipment position.
A single-stage target detection model represented by an SSD (single-shot multi-frame detector) algorithm better realizes compromise among calculation precision, calculation speed and calculation complexity. The SSD target test model structure is divided into two parts: the first part is a target basic feature extraction network; the second part is a multi-scale feature detection network, and multi-scale feature extraction can be carried out on the feature layer extracted from the previous part. The SSD target detection algorithm flow consists of two steps: one is target positioning, namely, the position of a target object in a picture is given; one is classification detection, which gives the probability that each candidate belongs to a particular class, and the architecture diagram of which is shown in fig. 2.
2. Target device pixel width identification based on image processing algorithm
For infrared images, the pixel width of the target device is identified through an image processing algorithm in OpenCV. Firstly, obtaining an SSD target detection frame, reading the coordinates of an equipment box and removing images except the box, then extracting an equipment area part in the image based on a mask technology, removing noise interference such as wired electricity and the like around the equipment by carrying out open operation of corrosion expansion on the image, finally carrying out contour fitting on the image to identify the minimum adjacent rectangle of the equipment, and outputting the coordinates of 4 vertexes of the rectangle. It can be found that the pixel width is equal to the minimum contiguous rectangle box short side length, so that the distance of the device can be calculated. The specific implementation steps are shown in fig. 3.
3. Automatic device distance identification based on improved monocular distance measurement algorithm
Aiming at the problem that the optical axis is not parallel to the ground due to the fact that an angle exists between a lens and a horizontal plane when an existing infrared image is shot, the invention provides the method which can enable a target plane to be approximately perpendicular to the optical axis, and only the relative position change on the Z axis exists between a world coordinate system and a camera coordinate system. Aiming at the problem that the pixel width of a target detection frame is not the pixel width corresponding to the actual width of the equipment due to the inclination of the shooting angle of the equipment, the transformation between an imaging coordinate system and a pixel coordinate system is solved through the target pixel width. It can be found that even if the angle of the device is inclined, the maximum width of the device does not change no matter which angle the power device is shot from because the whole appearance of the power device is cylindrical; even if the device does not shoot fully, its width can still be reflected. The correspondence between the actual width of the device and the pixel width in the present invention is shown in fig. 4.
Based on the principle of similar triangles in the geometric ranging algorithm, the distance between the camera and the target is finally calculated as follows:
wherein D is the actual width of the device, w is the width of the target pixel, f, dx and dy are parameters obtained by calibrating the camera, and u 0 、v、v 0 Are identified parameters in the infrared image.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above examples are to be construed as merely illustrative and not limitative of the remainder of the disclosure. After reading the description of the invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.
Claims (8)
1. A distance parameter identification method for infrared temperature measurement equipment of power equipment is characterized by comprising the following steps:
inputting an infrared image of the power equipment, and carrying out preprocessing of removing redundant information and enhancing a data set on the infrared image of the power equipment;
marking the power equipment area in the infrared image by using labelme software;
performing target detection based on an SSD single-shot multi-frame detector algorithm to obtain automatic identification of the equipment type;
obtaining a minimum adjacent rectangular frame of the power equipment through an image processing algorithm in OpenCV, outputting vertex coordinates of the minimum adjacent rectangular frame, and calculating the pixel width of the identification target equipment;
the automatic identification of the equipment distance in the image is realized based on an improved monocular distance measurement algorithm, the object plane is approximately perpendicular to the optical axis, and only the relative position change on the Z axis exists between the world coordinate system and the camera coordinate system, so that the distance of the equipment is solved by utilizing the relation between the imaging coordinate system and the world coordinate system.
2. The method for identifying the distance parameter of the infrared temperature measuring equipment of the electric power equipment according to claim 1, wherein the preprocessing for removing redundant information and enhancing a data set on the infrared image of the electric power equipment specifically comprises:
and compiling a batch processing program through an OS module in Python to remove redundant information including characters and symbols of the original thermal image, and enhancing the data set by readjusting the imaging temperature range setting to finish the pretreatment of the sample image.
3. The method for identifying the distance parameter of the infrared temperature measuring equipment of the electric power equipment according to claim 1, wherein the step of marking the area of the electric power equipment in the infrared image by using labelme software specifically comprises the following steps:
the Labelme software labels the equipment type that the image corresponds, be used for analyzing the image characteristic of different equipment, and through the deep learning model of equipment classification problem evaluation design, be used for training and test target identification model through labeling equipment position, the deep learning model is the convolutional neural network who is used for image recognition, by a plurality of convolution layer, activation layer, pooling layer and full tie-layer constitute, wherein convolution layer is used for reducing dimension and handles and extract the characteristic, activation layer is used for simulating arbitrary function, the characterization ability of reinforcing network, pooling layer is used for reducing the calculated amount, improve the generalization ability, full tie-layer is used for the characteristic classification, improve output quality.
4. The method for identifying the distance parameter of the infrared temperature measuring equipment of the electric power equipment according to claim 1, wherein the automatic identification of the type of the target detection obtaining equipment by using the SSD algorithm specifically comprises:
the SSD target test model structure is divided into two parts: the first part is a target basic feature extraction network; the second part is a multi-scale feature detection network and is used for carrying out multi-scale feature extraction on the feature layer extracted by the first part; the SSD target detection algorithm flow consists of two steps: one is target positioning, namely, the position of a target object in a picture is given; one is classification detection, which gives the probability that each candidate belongs to a particular class.
5. The method for identifying the distance parameter of the infrared temperature measuring equipment of the electric power equipment as claimed in claim 4, wherein the target test model specifically comprises:
after the pictures are input, through forward network transmission, all the area candidate frames generate a category probability predicted value and a position offset predicted value, and according to a set threshold, frames with the probability predicted values lower than the threshold are deleted, namely the frames are considered to have no target. And then removing the redundant frames by using the category as a unit through non-maximum suppression to obtain the detection frames matched with the target to be detected.
6. The method for identifying the distance parameter of the infrared temperature measuring equipment of the electric power equipment according to claim 5, wherein the step of obtaining a minimum adjacent rectangular frame of the electric power equipment through an image processing algorithm in OpenCV, outputting vertex coordinates of the minimum adjacent rectangular frame, and calculating the pixel width of the identification target equipment specifically comprises the steps of:
firstly, obtaining an SSD target detection frame, reading the vertex coordinates of an equipment box and removing images except the box, then extracting an equipment area part in the image based on a mask technology, removing noise interference including wired electricity around the equipment by performing open operation of corrosion expansion on the image, finally performing contour fitting on the image to identify the minimum adjacent rectangle of the equipment, and outputting the coordinates of 4 vertexes of the rectangle; the pixel width is equal to the minimum adjacent rectangle box short side length, so that the distance of the device can be calculated.
7. The method for identifying the distance parameter of the infrared temperature measuring equipment of the electric power equipment as claimed in claim 6, wherein the extracting the equipment area part in the image based on the mask technology specifically comprises:
firstly, carrying out binarization processing on an image to enable the image to only contain black and white colors, then carrying out filtering and denoising on the image to obtain a clearer device outline, finally segmenting the image by using an image segmentation method to obtain an image mask region, and extracting a device region part in the image;
the pixel width is equal to the length of the short side of the minimum adjacent rectangular frame, so that the distance of the equipment can be calculated, and the target pixel width calculation formula is as follows:
wherein dx and dy are parameters obtained by camera calibration, and u 0 、v、v 0 Are identified parameters in the infrared image.
8. The method for identifying the distance parameter of the electrical equipment infrared temperature measurement equipment according to claim 7, wherein the automatic identification of the equipment distance in the image is realized based on an improved monocular distance measurement algorithm, and specifically comprises: based on the principle of similar triangles in the geometric ranging algorithm, the distance between the camera and the target is finally calculated as follows:
wherein D is the actual width of the device, w is the width of the target pixel, f, dx and dy are parameters obtained by calibrating the camera, and u 0 、v、v 0 Are identified parameters in the infrared image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210369206.6A CN114821035A (en) | 2022-04-08 | 2022-04-08 | Distance parameter identification method for infrared temperature measurement equipment of power equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210369206.6A CN114821035A (en) | 2022-04-08 | 2022-04-08 | Distance parameter identification method for infrared temperature measurement equipment of power equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114821035A true CN114821035A (en) | 2022-07-29 |
Family
ID=82534779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210369206.6A Pending CN114821035A (en) | 2022-04-08 | 2022-04-08 | Distance parameter identification method for infrared temperature measurement equipment of power equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114821035A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116110071A (en) * | 2023-04-07 | 2023-05-12 | 济南大学 | Image format pipeline and instrument diagram pipeline identification method based on deep learning |
-
2022
- 2022-04-08 CN CN202210369206.6A patent/CN114821035A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116110071A (en) * | 2023-04-07 | 2023-05-12 | 济南大学 | Image format pipeline and instrument diagram pipeline identification method based on deep learning |
| CN116110071B (en) * | 2023-04-07 | 2023-09-12 | 济南大学 | Image format pipeline and instrument diagram pipeline identification method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109615611B (en) | Inspection image-based insulator self-explosion defect detection method | |
| US20200364849A1 (en) | Method and device for automatically drawing structural cracks and precisely measuring widths thereof | |
| JP6305171B2 (en) | How to detect objects in a scene | |
| CN111415339B (en) | Image defect detection method for complex texture industrial product | |
| CN112862757A (en) | Weight evaluation system based on computer vision technology and implementation method | |
| CN107016348A (en) | With reference to the method for detecting human face of depth information, detection means and electronic installation | |
| CN110675447A (en) | People counting method based on combination of visible light camera and thermal imager | |
| CN114897816A (en) | Mask R-CNN mineral particle identification and particle size detection method based on improved Mask | |
| CN109544535B (en) | Peeping camera detection method and system based on optical filtering characteristics of infrared cut-off filter | |
| CN112017243B (en) | Medium visibility recognition method | |
| CN116228780B (en) | Silicon wafer defect detection method and system based on computer vision | |
| CN113034474A (en) | Test method for wafer map of OLED display | |
| CN113688817A (en) | Instrument identification method and system for automatic inspection | |
| Kurmi et al. | Pose error reduction for focus enhancement in thermal synthetic aperture visualization | |
| CN115375991A (en) | Strong/weak illumination and fog environment self-adaptive target detection method | |
| CN114821035A (en) | Distance parameter identification method for infrared temperature measurement equipment of power equipment | |
| CN113008380B (en) | Intelligent AI body temperature early warning method, system and storage medium | |
| CN112016558B (en) | Medium visibility recognition method based on image quality | |
| CN112613568B (en) | Target identification method and device based on visible light and infrared multispectral image sequence | |
| CN112541478A (en) | Insulator string stain detection method and system based on binocular camera | |
| CN117314986A (en) | Unmanned aerial vehicle cross-mode power distribution equipment inspection image registration method based on semantic segmentation | |
| CN112924037A (en) | Infrared body temperature detection system and detection method based on image registration | |
| CN116758425A (en) | Automatic acceptance checking method and device for large-base photovoltaic power station | |
| CN115909401A (en) | Cattle face identification method and device integrating deep learning, electronic equipment and medium | |
| CN113409334A (en) | Centroid-based structured light angle point detection method |
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 |