CN104008544A - Transformer substation casing pipe infrared image locating method based on BRISK - Google Patents
Transformer substation casing pipe infrared image locating method based on BRISK Download PDFInfo
- Publication number
- CN104008544A CN104008544A CN201410213444.3A CN201410213444A CN104008544A CN 104008544 A CN104008544 A CN 104008544A CN 201410213444 A CN201410213444 A CN 201410213444A CN 104008544 A CN104008544 A CN 104008544A
- Authority
- CN
- China
- Prior art keywords
- sleeve pipe
- transformer station
- infrared image
- brisk
- pipe infrared
- 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
Landscapes
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a transformer substation casing pipe infrared image locating method based on BRISK. The method includes the steps that pretreatment is conducted on a transformer substation casing pipe infrared image to be measured; based on a pretreatment result of the transformer substation casing pipe infrared image to be measured, matching treatment is conducted; based on the matching treatment result of the transformer substation casing pipe infrared image to be measured, a casing pipe region is located. According to the transformer substation casing pipe infrared image locating method based on the BRISK, the defects that the calculation amount is large, the number of occupied resources is large and diagnosis efficiency is low in the prior art are overcome, and the method has the advantages of being small in calculation amount and the number of occupied resources and high in diagnosis efficiency.
Description
Technical field
The present invention relates to power transmission and transforming equipment running status service technique field, particularly, relate to a kind of transformer station's sleeve pipe infrared image localization method based on BRISK.
Background technology
Transformer station is the power hub of undertaking voltage transformation, delivery of electrical energy and terminal distribution in electric system.And sleeve pipe is the vitals of transformer station's major equipment, if the defect of existence or fault will directly jeopardize safe operation and the power supply reliability thereof of transformer station.Therefore the sleeve pipe state of transformer station is monitored, it is very important reducing and stopping sleeve pipe accident.Effectively the IR thermal imaging inspection technology of detecting devices thermal information has been widely used in electric system at present, and sleeve pipe failure cause is mostly relevant with long-term fever, so for its fault of quantitative Diagnosis, must identify sleeve pipe on thermal-induced imagery, and to its location.At present to the research of the infrared image location technology of transformer station's sleeve pipe in the starting stage, and often under laboratory environment, realize.Therefore, adopt the localization method from site infrare image studies transformer station sleeve pipe to there is important engineering practical value.
Image position method based on local invariant feature is study hotspot at present.A kind of local invariant feature-BRISK of novelty (Binary Robust Invariant Scalable Keypoints, the constant yardstick key point of scale-of-two robust) algorithm has the advantages such as yardstick unchangeability and rotational invariance, with other local invariant feature algorithm, as: SIFT (Scale Invariant Feature Transform, yardstick unchangeability Feature Conversion), SURF (Speeded-Up Robust Features, accelerate robust features) etc. compare, its arithmetic speed and internal memory occupancy volume have had obvious improvement, so for real-time application scenario, target in continuous videos image is identified and is positioned with better effect, need to adopt BRISK algorithm to position transformer station's sleeve pipe infrared image.
Existing transformer station sleeve pipe infrared positioning method mostly rests on the starting stage, and algorithm operation quantity used is huge, take computational resource more, be difficult to meet the requirement of field engineering to real-time, in order to improve the efficiency of transformer station's sleeve pipe fault diagnosis, need to provide a kind of method that meets transformer station's sleeve pipe infrared image location of engineering actual demand.
In realizing process of the present invention, inventor find at least to exist in prior art operand large, take the defects such as the many and diagnosis efficiency of resource is low.
Summary of the invention
The object of the invention is to, for the problems referred to above, propose a kind of transformer station's sleeve pipe infrared image localization method based on BRISK, with realize operand little, take the advantage that resource is few and diagnosis efficiency is high.
For achieving the above object, the technical solution used in the present invention is: a kind of transformer station's sleeve pipe infrared image localization method based on BRISK, comprising:
A, transformer station to be measured sleeve pipe infrared image is carried out to pre-service;
B, the pre-service result based on transformer station to be measured sleeve pipe infrared image, carry out matching treatment;
C, the matching treatment result based on transformer station to be measured sleeve pipe infrared image, carry out sleeve area localization process.
Further, after step c, also comprise:
D, based on sleeve area localization process result, carry out sleeve area Graphics Processing.
Further, described steps d, specifically comprises:
In the locating area of surveillance map picture, transformer station's sleeve pipe is indicated with rectangle frame in surveillance map picture, complete the automatic identification of transformer station's sleeve pipe infrared image.
Further, described step a, specifically comprises:
Transformer station sleeve pipe infrared monitoring image and transformer station sleeve pipe infrared template image carried out to gray processing, then utilize morphologic opening operation respectively surveillance map picture and template image first to be corroded to the denoising of having expanded again first respectively.
Further, described step b, specifically comprises:
B1, the pre-service result based on transformer station to be measured sleeve pipe infrared image, carry out the processing of BRISK characteristic matching;
B2, the BRISK characteristic matching result based on transformer station to be measured sleeve pipe infrared image, reject erroneous matching and process.
Further, described step b1, specifically comprises:
Utilize BRISK algorithm, respectively transformer station's sleeve pipe infrared monitoring image and the infrared template image of transformer station's sleeve pipe are carried out to AGAST corner detection algorithm and detect Local Extremum and remove noise and edge obtains unique point realization character and extracts;
Adopt Hamming distance to calculate matching degree, be about to the first step-by-step XOR of feature XOR, 1 number in statistics: if it is less, show that matching degree is higher.
Further, described step b2, specifically comprises:
Utilize RANSAC to detected unique point to carrying out eliminating error matching treatment, the point that obtains correct coupling is right.
Further, described step c, specifically comprises:
Consider between transformer station's sleeve pipe infrared image template and transformer station's sleeve pipe infrared monitoring image and have translation, convergent-divergent and rotation relationship, (if x, y), (x', y') be respectively the right coordinate of corresponding point in template and surveillance map picture, its affine Transform Model be expressed as:
In above formula, have 6 parameters [a11, a12, a21, a22, b1, b2], it has determined the affine relation between the coordinate of two width images, therefore at least need 3 pairs of points to determining this 6 parameters;
To transformer station's sleeve pipe infrared image template image, utilize above-mentioned affine Transform Model to obtain the position of template image in surveillance map picture, determine locating area.
Transformer station's sleeve pipe infrared image localization method based on BRISK of various embodiments of the present invention, owing to comprising: transformer station to be measured sleeve pipe infrared image is carried out to pre-service; Pre-service result based on transformer station to be measured sleeve pipe infrared image, carries out matching treatment; Matching treatment result based on transformer station to be measured sleeve pipe infrared image, carries out sleeve area localization process; Can accurately locate the transformer station's sleeve pipe in infrared monitoring image, be the fault diagnosis of the transformer station's sleeve pipe in power transmission and transformation link and the maintenance support that provides the necessary technical; Thereby can overcome in prior art operand large, take the many and low defect of diagnosis efficiency of resource, with realize operand little, take the advantage that resource is few and diagnosis efficiency is high.
Other features and advantages of the present invention will be set forth in the following description, and, partly from instructions, become apparent, or understand by implementing the present invention.
Below by drawings and Examples, technical scheme of the present invention is described in further detail.
Accompanying drawing explanation
Accompanying drawing is used to provide a further understanding of the present invention, and forms a part for instructions, for explaining the present invention, is not construed as limiting the invention together with embodiments of the present invention.In the accompanying drawings:
Fig. 1 is the schematic flow sheet that the present invention is based on transformer station's sleeve pipe infrared image localization method of BRISK;
Fig. 2 carries out the experimental result of location automatically by the inventive method to transformer station's sleeve pipe infrared image, wherein: (a) transformer station's sleeve pipe infrared monitoring image, (b) the infrared template image of transformer station's sleeve pipe, (c) BRISK matching result figure, (d) RANSAC rejects mistake matching result figure, (e) transformer station's sleeve area positioning result figure.
Embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described, should be appreciated that preferred embodiment described herein, only for description and interpretation the present invention, is not intended to limit the present invention.
According to the embodiment of the present invention, as depicted in figs. 1 and 2, provide a kind of transformer station's sleeve pipe infrared image localization method based on BRISK.
Transformer station's sleeve pipe infrared image localization method based on BRISK of the present embodiment, specifically comprises the following steps:
(1) pre-service
Pre-service mainly comprises: first respectively transformer station's sleeve pipe infrared monitoring image and the infrared template image of transformer station's sleeve pipe are carried out to gray processing, then utilize morphologic opening operation respectively surveillance map picture and template image first to be corroded to the denoising of having expanded again.
(2) BRISK characteristic matching
1. utilizing BRISK algorithm respectively transformer station's sleeve pipe infrared monitoring image and the infrared template image of transformer station's sleeve pipe to be carried out to AGAST (Adaptive and Generic Accelerated Segment Test) corner detection algorithm detects Local Extremum and removes noise and edge obtains unique point realization character and extracts; Different from SIFT, SURF scheduling algorithm, BRISK utilizes random point pair, but uses equally distributed sampled point on several concentric Bresenham circles (amounting to 60), and traversal forms sampled point pair between two.By the long distance sample under Euclidean distance meaning, to estimating unique point direction, rotation sample area, resamples, and then utilizes short distance sampled point to generating scale-of-two descriptor.
2. the description of unique point, adopts binary string to describe each unique point, and its advantage is to adopt Hamming distance to calculate matching degree, is about to the first step-by-step XOR (XOR) of feature, and then 1 number in statistics, if it is less, shows that matching degree is higher.This algorithm has a clear superiority in than general Euclidean distance algorithm in arithmetic speed.
(3) reject Mismatching point
Utilize RANSAC (RANdom SAmple Consensus, random sampling consistency algorithm) to detected unique point to carrying out eliminating error matching treatment, the point that obtains correct coupling is right.
(4) sleeve area location
Because there is translation, convergent-divergent and rotation relationship between template and surveillance map picture, therefore establish (x, y), (x', y') is respectively the right coordinate of corresponding point in template and surveillance map picture, and its affine Transform Model can be expressed as:
In above formula, have 6 parameters [a11, a12, a21, a22, b1, b2], it has determined the affine relation between the coordinate of two width images, therefore at least need 3 pairs of points to determining this 6 parameters.
To template image, utilize above-mentioned affine Transform Model to obtain the position of template image in surveillance map picture, thereby determine locating area.
(5) sleeve area shows
In the locating area of surveillance map picture, transformer station's sleeve pipe is indicated with rectangle frame in surveillance map picture, so just completed the automatic identification of transformer station's sleeve pipe infrared image.
Compared with the conventional method, transformer station's sleeve pipe infrared image localization method based on BRISK of above-described embodiment, the beneficial effect that can reach is: can accurately locate the transformer station's sleeve pipe in infrared monitoring image, for the fault diagnosis of the transformer station's sleeve pipe in power transmission and transformation link and the maintenance support that provides the necessary technical, there is significant economic benefit and higher engineering using value.
Transformer station's whole flow process of sleeve pipe infrared image automatic positioning method can represent with Fig. 1.Below by concrete application example, technical scheme of the present invention is further described.
By technical scheme of the present invention, on-the-spot transformer station's sleeve pipe infrared monitoring image is positioned to processing.Fig. 2 (a) is transformer station's sleeve pipe infrared monitoring image; Fig. 2 (b) is the infrared template image of transformer station's sleeve pipe; Fig. 2 (c) is BRISK characteristic matching result figure, and what in Fig. 2 (c), with line, represent utilizes the Hamming distance point that the match is successful right; Fig. 2 (d) rejects mistake matching result figure: owing to there being erroneous matching, so utilize RANSAC to reject Mismatching point pair, leave correct matching double points, and represent with line; Fig. 2 (e) is the sleeve pipe positioning result figure of transformer station: utilize the boundary coordinate of the correct match point of surveillance map picture, orient therein the identified region of transformer station's sleeve pipe, with rectangle rectangle frame, position sign.
From experimental result, can find out that technical scheme of the present invention can identify transformer station's sleeve pipe exactly from on-the-spot infrared monitoring image, for the Infrared Fault Diagnosis of the transformer station's sleeve pipe in power transmission and transformation link is laid a good foundation.
Finally it should be noted that: the foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, although the present invention is had been described in detail with reference to previous embodiment, for a person skilled in the art, its technical scheme that still can record aforementioned each embodiment is modified, or part technical characterictic is wherein equal to replacement.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (8)
1. the transformer station's sleeve pipe infrared image localization method based on BRISK, is characterized in that, comprising:
A, transformer station to be measured sleeve pipe infrared image is carried out to pre-service;
B, the pre-service result based on transformer station to be measured sleeve pipe infrared image, carry out matching treatment;
C, the matching treatment result based on transformer station to be measured sleeve pipe infrared image, carry out sleeve area localization process.
2. the transformer station's sleeve pipe infrared image localization method based on BRISK according to claim 1, is characterized in that, after step c, also comprises:
D, based on sleeve area localization process result, carry out sleeve area Graphics Processing.
3. the transformer station's sleeve pipe infrared image localization method based on BRISK according to claim 2, is characterized in that, described steps d, specifically comprises:
In the locating area of surveillance map picture, transformer station's sleeve pipe is indicated with rectangle frame in surveillance map picture, complete the automatic identification of transformer station's sleeve pipe infrared image.
4. according to the transformer station's sleeve pipe infrared image localization method based on BRISK described in any one in claim 1-3, it is characterized in that, described step a, specifically comprises:
Transformer station sleeve pipe infrared monitoring image and transformer station sleeve pipe infrared template image carried out to gray processing, then utilize morphologic opening operation respectively surveillance map picture and template image first to be corroded to the denoising of having expanded again first respectively.
5. according to the transformer station's sleeve pipe infrared image localization method based on BRISK described in any one in claim 1-3, it is characterized in that, described step b, specifically comprises:
B1, the pre-service result based on transformer station to be measured sleeve pipe infrared image, carry out the processing of BRISK characteristic matching;
B2, the BRISK characteristic matching result based on transformer station to be measured sleeve pipe infrared image, reject erroneous matching and process.
6. the transformer station's sleeve pipe infrared image localization method based on BRISK according to claim 5, is characterized in that, described step b1, specifically comprises:
Utilize BRISK algorithm, respectively transformer station's sleeve pipe infrared monitoring image and the infrared template image of transformer station's sleeve pipe are carried out to AGAST corner detection algorithm and detect Local Extremum and remove noise and edge obtains unique point realization character and extracts;
Adopt Hamming distance to calculate matching degree, be about to the first step-by-step XOR of feature XOR, 1 number in statistics: if it is less, show that matching degree is higher.
7. the transformer station's sleeve pipe infrared image localization method based on BRISK according to claim 5, is characterized in that, described step b2, specifically comprises:
Utilize RANSAC to detected unique point to carrying out eliminating error matching treatment, the point that obtains correct coupling is right.
8. according to the transformer station's sleeve pipe infrared image localization method based on BRISK described in any one in claim 1-3, it is characterized in that, described step c, specifically comprises:
Consider between transformer station's sleeve pipe infrared image template and transformer station's sleeve pipe infrared monitoring image and have translation, convergent-divergent and rotation relationship, (if x, y), (x', y') be respectively the right coordinate of corresponding point in template and surveillance map picture, its affine Transform Model be expressed as:
In above formula, have 6 parameters [a11, a12, a21, a22, b1, b2], it has determined the affine relation between the coordinate of two width images, therefore at least need 3 pairs of points to determining this 6 parameters;
To transformer station's sleeve pipe infrared image template image, utilize above-mentioned affine Transform Model to obtain the position of template image in surveillance map picture, determine locating area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410213444.3A CN104008544A (en) | 2014-05-20 | 2014-05-20 | Transformer substation casing pipe infrared image locating method based on BRISK |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410213444.3A CN104008544A (en) | 2014-05-20 | 2014-05-20 | Transformer substation casing pipe infrared image locating method based on BRISK |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104008544A true CN104008544A (en) | 2014-08-27 |
Family
ID=51369184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410213444.3A Pending CN104008544A (en) | 2014-05-20 | 2014-05-20 | Transformer substation casing pipe infrared image locating method based on BRISK |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104008544A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934777A (en) * | 2019-01-09 | 2019-06-25 | 深圳市三宝创新智能有限公司 | Image local invariant feature extraction method, apparatus, computer equipment and storage medium |
| CN111160305A (en) * | 2019-12-31 | 2020-05-15 | 武汉工程大学 | Transformer bushing abnormity monitoring method and computer readable medium |
| CN111401289A (en) * | 2020-03-24 | 2020-07-10 | 国网上海市电力公司 | Intelligent identification method and device for transformer component |
| CN112381796A (en) * | 2020-11-16 | 2021-02-19 | 广东电网有限责任公司肇庆供电局 | Wire defect identification and detection method based on infrared data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103136531A (en) * | 2013-03-26 | 2013-06-05 | 华北电力大学（保定） | Automatic identification method of insulator chain infrared image |
| US20130211841A1 (en) * | 2012-02-15 | 2013-08-15 | Fluential, Llc | Multi-Dimensional Interactions and Recall |
| CN103400388A (en) * | 2013-08-06 | 2013-11-20 | 中国科学院光电技术研究所 | Method for eliminating Brisk (binary robust invariant scale keypoint) error matching point pair by utilizing RANSAC (random sampling consensus) |
| US20130343654A1 (en) * | 2012-06-21 | 2013-12-26 | Vincent Demoulin | Generating a binary descriptor representing an image patch |
-
2014
- 2014-05-20 CN CN201410213444.3A patent/CN104008544A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130211841A1 (en) * | 2012-02-15 | 2013-08-15 | Fluential, Llc | Multi-Dimensional Interactions and Recall |
| US20130343654A1 (en) * | 2012-06-21 | 2013-12-26 | Vincent Demoulin | Generating a binary descriptor representing an image patch |
| CN103136531A (en) * | 2013-03-26 | 2013-06-05 | 华北电力大学（保定） | Automatic identification method of insulator chain infrared image |
| CN103400388A (en) * | 2013-08-06 | 2013-11-20 | 中国科学院光电技术研究所 | Method for eliminating Brisk (binary robust invariant scale keypoint) error matching point pair by utilizing RANSAC (random sampling consensus) |
Non-Patent Citations (3)
| Title |
|---|
| ELIAS J. GRIFFITH 等: "Equivalence of BRISK Descriptors for the Registration of Variable Bit-depth Aerial Imagery", 《2013 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS》 * |
| 侯一民 等: "改进的尺度不变特征转换精确图像匹配在电力设备目标定位中的应用", 《中国电机工程学报》 * |
| 王海元: "热红外图像等温线温度场分割研究", 《科学技术与工程》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934777A (en) * | 2019-01-09 | 2019-06-25 | 深圳市三宝创新智能有限公司 | Image local invariant feature extraction method, apparatus, computer equipment and storage medium |
| CN111160305A (en) * | 2019-12-31 | 2020-05-15 | 武汉工程大学 | Transformer bushing abnormity monitoring method and computer readable medium |
| CN111401289A (en) * | 2020-03-24 | 2020-07-10 | 国网上海市电力公司 | Intelligent identification method and device for transformer component |
| CN111401289B (en) * | 2020-03-24 | 2024-01-23 | 国网上海市电力公司 | Intelligent identification method and device for transformer component |
| CN112381796A (en) * | 2020-11-16 | 2021-02-19 | 广东电网有限责任公司肇庆供电局 | Wire defect identification and detection method based on infrared data |
| CN112381796B (en) * | 2020-11-16 | 2021-08-03 | 广东电网有限责任公司肇庆供电局 | Wire defect identification and detection method based on infrared data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103136531B (en) | A kind of insulator chain infrared image automatic identifying method | |
| Zhang et al. | InsuDet: A fault detection method for insulators of overhead transmission lines using convolutional neural networks | |
| CN102980896B (en) | High ferro overhead contact line device auricle fracture detection method | |
| CN104361314A (en) | Method and device for positioning power transformation equipment on basis of infrared and visible image fusion | |
| Yang et al. | Bidirection-fusion-YOLOv3: An improved method for insulator defect detection using UAV image | |
| CN112200178B (en) | Transformer substation insulator infrared image detection method based on artificial intelligence | |
| CN108254077B (en) | GIS thermal fault diagnosis method based on local and global feature information fusion | |
| CN104008544A (en) | Transformer substation casing pipe infrared image locating method based on BRISK | |
| CN111582235A (en) | Alarm method, system and equipment for monitoring abnormal events in station in real time | |
| CN104573702A (en) | Method for automatically identifying sulfur hexafluoride pressure instrument image | |
| CN111046950B (en) | Image processing method and device, storage medium and electronic device | |
| CN111462109A (en) | Defect detection method, device and equipment for strain clamp and storage medium | |
| CN104881861A (en) | High-speed rail contact net suspension device failure state detecting method based on primitive classification | |
| Reza et al. | Deep neural network–based detection and verification of microelectronic images | |
| CN111553176B (en) | Wireless transmission checking method and system suitable for wiring of substation screen cabinet | |
| Zheng et al. | Intelligent diagnosis method of power equipment faults based on single‐stage infrared image target detection | |
| Cao et al. | Power line detection based on symmetric partial derivative distribution prior | |
| Li et al. | Insulator infrared image segmentation algorithm based on dynamic mask and box annotation | |
| CN106845490A (en) | Based on the super-pressure converting equipment infrared image localization method that GPU accelerates | |
| CN105043275A (en) | Image processing-based icing thickness measurement method for power transmission line | |
| Yan et al. | Research on fault diagnosis of transmission line based on SIFT feature | |
| CN113902890A (en) | Self-supervision data enhancement method, system and equipment for visual concept detection | |
| Ying et al. | Detection of the bolt loosening angle through semantic key point extraction detection by using an hourglass network | |
| CN103020601B (en) | Hi-line visible detection method and device | |
| Song et al. | Bolt looseness detection based on Canny edge detection algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140827 |
|
| RJ01 | Rejection of invention patent application after publication |