CN109636797B - Method for detecting deformation of non-contact flexible direct current converter valve module - Google Patents
Method for detecting deformation of non-contact flexible direct current converter valve module Download PDFInfo
- Publication number
- CN109636797B CN109636797B CN201811575244.7A CN201811575244A CN109636797B CN 109636797 B CN109636797 B CN 109636797B CN 201811575244 A CN201811575244 A CN 201811575244A CN 109636797 B CN109636797 B CN 109636797B
- Authority
- CN
- China
- Prior art keywords
- image
- visible light
- converter valve
- direct current
- valve module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims description 12
- 238000009499 grossing Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 9
- 238000003491 array Methods 0.000 claims description 5
- 239000003086 colorant Substances 0.000 claims description 3
- 230000008447 perception Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
-
- G06T5/73—
-
- G06T5/92—
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
Abstract
The invention relates to a deformation detection method for a non-contact flexible direct current converter valve module, which comprises the steps of providing a thermal infrared imager, outputting 16-bit infrared image data and a visible light image by the thermal infrared imager, and converting the 16-bit infrared image data into 8-bit gray level image data; smoothing the two images by adopting histogram equalization and a Gaussian filter to realize image noise reduction; then extracting the data characteristics of the two images through a Surf algorithm, and respectively positioning the direct current converter valve modules in the two images according to a characteristic point matching algorithm; meanwhile, the improved perceptual hash algorithm is utilized to obtain the fingerprints of the two images; finally, judging whether the direct current converter valve module is deformed or not according to the fingerprints of the two images and by utilizing the improved Hamming distance; and if the two images are judged to be deformed, the direct current converter valve module is deformed. The invention can automatically analyze and judge whether the direct current converter valve module is deformed or not; improve work efficiency, reduce the human cost.
Description
Technical Field
The invention relates to the technical field of a power grid power transmission and transformation equipment state monitoring system, in particular to a method for detecting deformation of a non-contact flexible direct current converter valve module.
Background
At present, an operation and maintenance person holds a thermal imager with naked eyes to manually inspect and judge whether a flexible direct current converter valve module is deformed or not, and the method has great limitation. In a common online infrared monitoring system, an infrared thermal imager is generally mounted on a holder device, and a background control system controls the infrared thermal imager to scan the whole monitored area in a cruising manner through the holder device. In the cruising scanning process of the thermal infrared imager, the highest temperature of the full screen or the highest temperature of a certain area is taken to realize the surface temperature detection of the equipment, and the visible light camera is only used for visual assistance and does not effectively monitor the deformation of the flexible direct current converter valve module. When the equipment of the converter valve module in the valve hall is patrolled, because the equipment number is huge and the picture number is large, the judgment and the inspection only depend on the video picture observed by people, the time consumption is huge, and important potential hidden dangers or abnormalities of the equipment can be omitted; at present, an infrared video system regularly inspects and collects a large amount of equipment temperature distribution data and appearance photos every day, and the data effectively used by the system is only a temperature alarm data source.
Disclosure of Invention
In view of the above, the present invention provides a method for detecting deformation of a non-contact flexible dc converter valve module, which can automatically analyze and determine whether the dc converter valve module deforms; improve work efficiency, reduce the human cost.
The invention is realized by adopting the following scheme: a method for detecting deformation of a non-contact flexible direct current converter valve module provides a thermal infrared imager, and comprises the following steps:
s1, outputting the monitored 16-bit infrared image and visible light image by the thermal infrared imager, and converting the 16-bit infrared image into an 8-bit gray level image by a window-shifting algorithm;
step S2, histogram equalization is carried out on the visible light image and the 8-bit gray level image in the step S1, and smoothing processing is carried out on the image through a Gaussian filter (GaussianFilter) to realize image noise reduction;
step S3, extracting the data characteristics of the visible light image and the 8-bit gray level image through a Surf algorithm, and respectively generating characteristic descriptors;
s4, respectively positioning the direct current converter valve modules in the visible light image and the 8-bit gray scale image data according to a BruteForceMatcher feature point matching algorithm;
step S5, respectively processing the image overlapping areas of the visible light image and the 8-bit gray scale image data matched in the step S4 by utilizing an improved perception hash algorithm to respectively obtain the fingerprints of the visible light image and the 8-bit gray scale image data;
step S6, judging whether the direct current converter valve module is deformed or not by utilizing the improved Hamming distance according to the visible light image obtained in the step S5 and the fingerprint of the 8-bit gray scale image data;
and step S7, judging the deformation of the direct current converter valve module when both the judgment result of the visible light image and the judgment result of the infrared image judge that the direct current converter valve module is deformed.
Further, the processing of the picture overlapping area by using the improved perceptual hashing algorithm in step S5 specifically includes the following steps:
step S51: reducing the size of the picture: respectively reducing the visible light image and the 8-bit grayscale image to a size of 16x16 for a total of 256 pixels; step S52: simplifying the picture colors: respectively converting the visible light image and the reduced image of the 8-bit gray scale image into gray scale images; step S53: calculating the average gray level values of 256 pixels in the visible light image and the reduced 8-bit gray level image in step S51;
step S54: comparing the gray levels of each of the 256 pixels in the visible light image and the reduced 8-bit gray level image in step S53 with the average gray level values thereof, respectively; the compared image is the fingerprint of the visible light image and the 8-bit gray level image; if the comparison result is larger than or equal to the average value, the fingerprint is marked as 1; if the comparison result is smaller than the average value, the fingerprint is marked as 0;
step S55: the two comparison results of step S54 are stored in 16 × 16 integer type arrays to form two 256-bit integer two-dimensional arrays. (the normal hash value is a one-dimensional array without coordinate information, and is improved into a two-dimensional array).
Further, the step S6 of determining whether the dc converter valve module has deformation or not by using the improved hamming distance (the improved hamming distance is weighted) according to the obtained visible light image and the 8-bit grayscale fingerprint specifically includes the following steps:
step S61: comparing the obtained fingerprints of the visible light image and the 8-bit gray level image with the preset standard fingerprints of the visible light image and the 8-bit gray level image respectively, and recording the number of different points and coordinate information respectively;
step S62: respectively calculating the maximum number and the weight of the connected different points according to the number and the coordinate information of the two groups of different points recorded in the step S61; (the more the different point coordinate distribution is gathered, the larger the weight is, the smaller the different point coordinate distribution is about discrete weight, when the closest distance between two different points is more than 16, the weight is 1, when the closest distance between two different points is 1, the weight is 16, and so on).
Step S63: and if the sum of the weights of all the different points of the two groups calculated in the step S62 is greater than 32, determining that the direct current converter valve module is deformed.
Compared with the prior art, the invention has the following beneficial effects: the invention can fully and effectively utilize the data acquired by the infrared video system to automatically analyze and judge whether the direct current converter valve module is deformed; improve work efficiency, reduce the human cost.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
As shown in fig. 1, the present embodiment provides a method for detecting deformation of a non-contact flexible dc converter valve module, and provides a thermal infrared imager, including the following steps:
s1, outputting the monitored 16-bit infrared image and visible light image by the thermal infrared imager, and converting the 16-bit infrared image into an 8-bit gray level image by a window-shifting algorithm;
step S2, histogram equalization is carried out on the visible light image and the 8-bit gray level image in the step S1, and smoothing processing is carried out on the image through a Gaussian filter (GaussianFilter) to realize image noise reduction;
step S3, extracting the data characteristics of the visible light image and the 8-bit gray level image through a Surf algorithm, and respectively generating characteristic descriptors;
s4, respectively positioning the direct current converter valve modules in the visible light image and the 8-bit gray scale image data according to a BruteForceMatcher feature point matching algorithm;
step S5, respectively processing the image overlapping areas of the visible light image and the 8-bit gray scale image data matched in the step S4 by utilizing an improved perception hash algorithm to respectively obtain the fingerprints of the visible light image and the 8-bit gray scale image data;
step S6, judging whether the direct current converter valve module is deformed or not by utilizing the improved Hamming distance according to the visible light image obtained in the step S5 and the fingerprint of the 8-bit gray scale image data;
and step S7, judging the deformation of the direct current converter valve module when the judgment result of the visible light image and the judgment result of the infrared image both judge that the direct current converter valve module is deformed.
In this embodiment, the processing the picture overlapping area by using the modified perceptual hashing algorithm in step S5 specifically includes the following steps:
step S51: reducing the size of the picture: respectively reducing the visible light image and the 8-bit grayscale image to a size of 16x16 for a total of 256 pixels; step S52: simplifying the picture colors: respectively converting the visible light image and the reduced image of the 8-bit gray scale image into gray scale images; step S53: calculating the average gray level values of 256 pixels in the visible light image and the reduced 8-bit gray level image in step S51;
step S54: comparing the gray levels of each of the 256 pixels in the visible light image and the reduced 8-bit gray level image in step S53 with the average gray level values thereof, respectively; the compared image is the fingerprint of the visible light image and the 8-bit gray level image; if the comparison result is larger than or equal to the average value, the fingerprint is marked as 1; if the comparison result is smaller than the average value, the fingerprint is marked as 0;
step S55: the two comparison results of step S54 are stored in 16 × 16 integer type arrays to form two 256-bit integer two-dimensional arrays. (the normal hash value is a one-dimensional array without coordinate information, and is improved into a two-dimensional array).
In this embodiment, the step S6 of determining whether the dc converter valve module has deformation or not by using the improved hamming distance (the improved hamming distance is weighted) according to the obtained visible light image and the 8-bit grayscale fingerprint specifically includes the following steps:
step S61: comparing the obtained fingerprints of the visible light image and the 8-bit gray level image with the preset standard fingerprints of the visible light image and the 8-bit gray level image respectively, and recording the number of different points and coordinate information respectively;
step S62: respectively calculating the maximum number and the weight of the connected different points according to the number and the coordinate information of the two groups of different points recorded in the step S61; (the more the different point coordinate distribution is gathered, the larger the weight is, the smaller the different point coordinate distribution is about discrete weight, when the closest distance between two different points is more than 16, the weight is 1, when the closest distance between two different points is 1, the weight is 16, and so on).
Step S63: and if the sum of the weights of all the different points of the two groups calculated in the step S62 is greater than 32, determining that the direct current converter valve module is deformed.
The above description is only a preferred embodiment of the present invention, and all equivalent changes and modifications made in accordance with the claims of the present invention should be covered by the present invention.
Claims (2)
1. A method for detecting deformation of a non-contact flexible direct current converter valve module provides a thermal infrared imager, and is characterized in that: the method comprises the following steps:
s1, outputting the monitored 16-bit infrared image and visible light image by the thermal infrared imager, and converting the 16-bit infrared image into an 8-bit gray image by a window adjusting algorithm;
step S2, histogram equalization is carried out on the visible light image and the 8-bit gray level image in the step S1, and smoothing processing is carried out on the image through a Gaussian filter to realize image noise reduction;
step S3, extracting the data characteristics of the visible light image and the 8-bit gray level image through a Surf algorithm, and respectively generating characteristic descriptors;
step S4, respectively positioning the direct current converter valve module in the visible light image and the 8-bit gray scale image data according to a BruteForceMatcher feature point matching algorithm;
step S5, respectively processing the image overlapping areas of the visible light image and the 8-bit gray scale image data matched in the step S4 by utilizing an improved perception hash algorithm to respectively obtain the fingerprints of the visible light image and the 8-bit gray scale image data; specifically, a fingerprint is a two-dimensional array with coordinate information;
step S6, judging whether the direct current converter valve module is deformed or not by utilizing the improved Hamming distance according to the visible light image obtained in the step S5 and the fingerprint of the 8-bit gray scale image data;
step S7, judging the deformation of the direct current converter valve module when the judgment result of the visible light image and the judgment result of the infrared image both judge that the direct current converter valve module is deformed;
in the step S6, according to the obtained visible light image and the 8-bit grayscale fingerprint, determining whether the dc converter valve module has a distortion by using the improved hamming distance specifically includes the following steps:
step S61: comparing the obtained fingerprints of the visible light image and the 8-bit gray level image with the preset standard fingerprints of the visible light image and the 8-bit gray level image respectively, and recording the number of different points and coordinate information respectively;
step S62: respectively calculating the maximum number and the weight of the connected different points according to the number and the coordinate information of the two groups of different points recorded in the step S61; the more gathered the coordinate distribution of different points, the more discrete the coordinate distribution of different points, the smaller the coordinate distribution of different points, when the closest distance between the two different points is greater than 16, the weight is 1, when the closest distance between the two different points is 1, the weight is 16, and so on;
step S63: and if the sum of the weights of all the different points of the two groups calculated in the step S62 is greater than 32, determining that the direct current converter valve module is deformed.
2. The method for detecting the deformation of the non-contact flexible direct current converter valve module according to claim 1, wherein the method comprises the following steps: step S5, the processing of the picture overlap region by using the modified perceptual hashing algorithm specifically includes the following steps:
step S51: reducing the size of the picture: respectively reducing the visible light image and the 8-bit grayscale image to a size of 16x16 for a total of 256 pixels; step S52: simplifying the picture colors: respectively converting the visible light image and the reduced image of the 8-bit gray scale image into gray scale images; step S53: calculating the average gray level values of 256 pixels in the visible light image and the reduced 8-bit gray level image in step S51;
step S54: comparing the gray levels of each of the 256 pixels in the visible light image and the reduced 8-bit gray level image in step S53 with the average gray level values thereof, respectively; the compared image is the fingerprint of the visible light image and the 8-bit gray level image; if the comparison result is larger than or equal to the average value, the fingerprint is marked as 1; if the comparison result is smaller than the average value, the fingerprint is marked as 0;
step S55: the two comparison results of step S54 are stored in a 16 × 16 integer type array, forming two sets of 256-bit integer two-dimensional arrays.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811575244.7A CN109636797B (en) | 2018-12-21 | 2018-12-21 | Method for detecting deformation of non-contact flexible direct current converter valve module |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811575244.7A CN109636797B (en) | 2018-12-21 | 2018-12-21 | Method for detecting deformation of non-contact flexible direct current converter valve module |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109636797A CN109636797A (en) | 2019-04-16 |
| CN109636797B true CN109636797B (en) | 2022-08-05 |
Family
ID=66076525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811575244.7A Active CN109636797B (en) | 2018-12-21 | 2018-12-21 | Method for detecting deformation of non-contact flexible direct current converter valve module |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109636797B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112556593B (en) * | 2020-11-05 | 2022-07-29 | 西安西电电力系统有限公司 | Non-contact flexible direct current converter valve module deformation detection equipment and method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1148333A1 (en) * | 2000-02-05 | 2001-10-24 | YXLON International X-Ray GmbH | Automatic casting defects recognition in specimens |
| CN105160654A (en) * | 2015-07-09 | 2015-12-16 | 浙江工商大学 | Towel label defect detecting method based on feature point extraction |
| CN105200938A (en) * | 2015-08-27 | 2015-12-30 | 广西交通科学研究院 | Vision-based anti-collision system for gate rail |
| CN107203990A (en) * | 2017-04-02 | 2017-09-26 | 南京汇川图像视觉技术有限公司 | A kind of labeling damage testing method based on template matches and image quality measure |
| CN107478340A (en) * | 2017-07-25 | 2017-12-15 | 许继集团有限公司 | A kind of converter valve monitoring method and system |
| CN107784659A (en) * | 2017-10-16 | 2018-03-09 | 华南理工大学 | A kind of method for searching for the similar visible images of electrical equipment infrared image |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013185129A2 (en) * | 2012-06-08 | 2013-12-12 | Correlated Solutions, Inc. | Optical non-contacting apparatus for shape and deformation measurement of vibrating objects using image analysis methodology |
-
2018
- 2018-12-21 CN CN201811575244.7A patent/CN109636797B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1148333A1 (en) * | 2000-02-05 | 2001-10-24 | YXLON International X-Ray GmbH | Automatic casting defects recognition in specimens |
| CN105160654A (en) * | 2015-07-09 | 2015-12-16 | 浙江工商大学 | Towel label defect detecting method based on feature point extraction |
| CN105200938A (en) * | 2015-08-27 | 2015-12-30 | 广西交通科学研究院 | Vision-based anti-collision system for gate rail |
| CN107203990A (en) * | 2017-04-02 | 2017-09-26 | 南京汇川图像视觉技术有限公司 | A kind of labeling damage testing method based on template matches and image quality measure |
| CN107478340A (en) * | 2017-07-25 | 2017-12-15 | 许继集团有限公司 | A kind of converter valve monitoring method and system |
| CN107784659A (en) * | 2017-10-16 | 2018-03-09 | 华南理工大学 | A kind of method for searching for the similar visible images of electrical equipment infrared image |
Non-Patent Citations (6)
| Title |
|---|
| 一种新颖的红外与可见光图像自动配准算法;舒丽霞等;《华中科技大学学报(自然科学版)》;20030630(第06期);全文 * |
| 基于内容的SIFT+LSH管道缺陷检索算法研究;李静等;《计算机测量与控制》;20180425(第04期);全文 * |
| 基于图像处理的苹果表面缺陷检测系统的设计;代秋芳等;《科技创新导报》;20160803(第09期);全文 * |
| 基于感知哈希算法的目标跟踪研究;张宇;《电子世界》;20180223(第04期);全文 * |
| 基于改进结构相似度的标签缺陷检测系统研究与实现;高吉;《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》;20181015(第10期);I138-542 * |
| 柔性直流换流站阀厅智能辅助综合监控系统设计;陈晓捷等;《电工技术》;20161110(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109636797A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106548182B (en) | Pavement crack detection method and device based on deep learning and main cause analysis | |
| CN106650665B (en) | Face tracking method and device | |
| KR20100072772A (en) | Method and apparatus for real-time face detection using stereo vision | |
| CN106934377B (en) | Improved human face detection system | |
| CN110287787B (en) | Image recognition method, image recognition device and computer-readable storage medium | |
| CN108665468B (en) | Device and method for extracting tangent tower insulator string | |
| CN109636797B (en) | Method for detecting deformation of non-contact flexible direct current converter valve module | |
| CN116797977A (en) | Method and device for identifying dynamic target of inspection robot and measuring temperature and storage medium | |
| CN110595397A (en) | Grate cooler working condition monitoring method based on image recognition | |
| CN108664886A (en) | A kind of fast face recognition method adapting to substation's disengaging monitoring demand | |
| CN117274722B (en) | Intelligent detection method for distribution box based on infrared image | |
| CN107977959B (en) | Respirator state identification method suitable for electric power robot | |
| CN1492379A (en) | Method for covering face of news interviewee using quick face detection | |
| CN110320523A (en) | Follow the target locating set and method of robot | |
| US20180253582A1 (en) | Method and circuit for fingerprint detection | |
| Tribak et al. | Remote solar panels identification based on patterns localization | |
| US20140327796A1 (en) | Method for estimating camera response function | |
| CN104615985B (en) | A kind of recognition methods of human face similarity degree | |
| CN107798282B (en) | Method and device for detecting human face of living body | |
| CN114677667A (en) | Transformer substation electrical equipment infrared fault identification method based on deep learning | |
| CN112418085B (en) | Facial expression recognition method under partial shielding working condition | |
| CN110010228B (en) | Face skin perspective algorithm based on image analysis | |
| CN113643352A (en) | Natural icing on-line monitoring running wire image icing degree evaluation method | |
| CN112241707A (en) | Wind-powered electricity generation field intelligence video identification device | |
| CN108491852B (en) | Blind pixel detection method for area array infrared focal plane |
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 |