CN111488820B - Intelligent cable tunnel engineering inspection method and system based on light and shadow separation - Google Patents
Intelligent cable tunnel engineering inspection method and system based on light and shadow separation Download PDFInfo
- Publication number
- CN111488820B CN111488820B CN202010270694.6A CN202010270694A CN111488820B CN 111488820 B CN111488820 B CN 111488820B CN 202010270694 A CN202010270694 A CN 202010270694A CN 111488820 B CN111488820 B CN 111488820B
- Authority
- CN
- China
- Prior art keywords
- image
- rgb
- cable tunnel
- tunnel engineering
- shadow
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000000926 separation method Methods 0.000 title claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 41
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- G06V10/267—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 by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an intelligent inspection method for cable tunnel engineering based on light and shadow separation, which comprises the steps of performing shadow separation and removal on an acquired visible light image; performing feature recognition according to the image information with the shadow information removed to obtain names of all devices in the image and device state information; judging whether the association relation of two kinds of devices in the image meets M ij =0, if yes, deleting detection recognition results of the two types of equipment; and issuing and displaying the inspection alarm information of the cable tunnel engineering. The invention also provides a cable tunnel engineering intelligent inspection system based on light and shadow separation, which comprises an image sensing module, a shadow detection module, a joint detection module and a display alarm module, and is used for publishing and displaying cable tunnel engineering inspection alarm information on the result obtained by the joint detection module. By adopting the technical scheme, the intelligent inspection accuracy of the cable tunnel engineering can be effectively improved.
Description
Technical Field
The invention relates to an intelligent inspection method and system for cable tunnel engineering based on light and shadow separation, and belongs to the technical field of electric power operation inspection.
Background
In recent years, the construction of urban underground distribution networks is becoming more and more sophisticated. The construction and maintenance of the cable tunnel are increasingly important because of the problems of water seepage, dampness, cable aging, equipment corrosion and damage and the like caused by the natural geographical environment of the cable tunnel. At present, the maintenance of cables and matched equipment in a tunnel is mainly finished manually, and a great deal of dense smoke, harmful gas, high-voltage cable leakage, cable tunnel collapse and other problems in the tunnel are likely to threaten the life safety of staff. With the development of robotics and image recognition technologies, some expert scholars propose to detect the internal condition of a cable tunnel by using a routing inspection robot, and gradually become an effective solution, for example, the implementation and application of a routing inspection robot in a cable tunnel disclosed in the journal literature of China (pages 73-74 of 17 th 2019) and the cable tunnel rust recognition algorithm based on a transfer learning convolutional neural network disclosed in the journal literature of China (pages 104-110 of 52 th 2019). However, the cable tunnel is a low-light environment lacking natural illumination, and part of the inspection robots use illumination equipment such as incandescent lamps or LEDs to supplement light, so that shadows generated by the point light sources in the claustrophobic environment seriously affect the quality of image acquisition and restrict the precision of inspection analysis. At present, a method for separating and removing shadows of an acquired video image is available, for example, a shadow detection and removal algorithm for combining colors and gradients in a complex environment is disclosed in Chinese patent document CN107886502A, and an idea based on combining colors and gradients is added into a shadow detection algorithm to be fused with a Gaussian mixture background model, so that the problems of target adhesion, shape change, target loss, false target occurrence and the like caused by shadows in the complex environment are solved after shadow detection, removal and target foreground reconstruction are carried out. Also, for example, chinese patent document CN106296666a discloses a color image shadow removing method and application, which can remove shadows existing in a color image, and is applied as a preprocessing step to various machine vision fields. In addition, besides the influence of shadows on image recognition, recognition accuracy is reduced, and the problem of high false alarm rate exists in the intelligent inspection of the cable tunnel engineering at present.
Disclosure of Invention
Therefore, the invention aims to provide the intelligent inspection method and the intelligent inspection system for the cable tunnel engineering based on light and shadow separation, which realize the improvement of the accuracy and the suppression of the false alarm rate of intelligent inspection and provide technical support for the integral improvement of the intelligent inspection capability of the cable tunnel engineering.
In order to achieve the above purpose, the intelligent inspection method for the cable tunnel engineering based on light and shadow separation comprises the following steps:
(1) Shadow separation and removal are carried out on the collected visible light images;
(2) Performing feature recognition according to the image information with the shadow information removed to obtain names of all devices in the image and device state information;
(3) Obtaining any device Name l Belongs to category Ω l E {1,2, …, S }, retrieving a pre-stored data matrix M e R S×S The method comprises the steps of carrying out a first treatment on the surface of the Judging whether the association relation of two kinds of devices in the image meets M ij =0, if yes, deleting detection recognition results of the two types of equipment;
wherein, the data matrix M epsilon R S×S Storing the association relation of equipment in cable tunnel engineering, wherein S represents the class number of the equipment in the cable tunnel engineering, and M is the number if the equipment of the ith class and the equipment of the jth class can occur simultaneously in the same scene ij =1; otherwise, M ij =0;
(4) And (3) based on the result obtained in the step (3), issuing and displaying the cable tunnel engineering inspection alarm information.
In the step 1, the separating and removing of the shadow portion includes the steps of:
(11) Image I of visible light RGB =(L R ,L G ,L B ) Conversion from RGB color space to intrinsic color space to form intrinsic image I Int =(I 1 ,I 2 ,I 3 ),
I 1 =L R +L G -β 1 L B
I 2 =L R -β 2 L G +L B
I 3 =-β 3 L R +L G +L B
Wherein (I) 1 ,I 2 ,I 3 ) Representing eigenvalues in the eigenvalue color space; (L) R ,L G ,L B ) Representing gray values in an RGB color space; beta i I=1, 2,3, which is the conversion coefficient of RGB color space to intrinsic color space;
(12) By screening I 3 Not less than k as visible light image I RGB Is realized for visible light image I by shadow information mode RGB Shadow information I is separated from the cable tunnel engineering inspection image by detecting and separating the shadow information of the cable tunnel engineering inspection image RGB-sha And intrinsic image information I RGB-cor The method comprises the steps of carrying out a first treatment on the surface of the Wherein I is RGB =I RGB-cor +I RGB-sha K is a preset value.
(β 1 ,β 2 ,β 3 ) = (-0.7261,0.3816,0.3316) is the empirically chosen conversion coefficient of the RGB color space into the intrinsic color space.
k=65。
The invention also provides an intelligent inspection system for the cable tunnel engineering based on light and shadow separation, which comprises the following components:
the image sensing module is used for acquiring visible light images in the cable tunnel engineering inspection;
the shadow detection module is used for carrying out shadow separation and removal on the visible light image acquired by the image sensing module;
the joint detection module comprises a device detection and identification module, an expert priori knowledge module and a semantic logic identification module; the equipment detection and identification module is used for detecting and identifying all equipment names and equipment state information based on the evidence image information; the expert priori knowledge module is used for using the data matrix M epsilon R S×S Pre-storing the association relation of the devices in the cable tunnel engineering in a form, wherein S is the number of device categories in the cable tunnel engineering, and M is the number of the devices in the cable tunnel engineering if the ith device and the jth device can simultaneously appear in the same scene ij =1, otherwise, M ij =0; the semantic logic recognition module is used for acquiring any device Name detected and recognized by the device detection recognition module l Class Ω to which it belongs l E {1,2, …, S }, retrieving a pre-stored data matrix M e R S ×S The method comprises the steps of carrying out a first treatment on the surface of the Judging whether the association relation of two kinds of devices in the image meets M ij =0, if yes, deleting detection recognition results of the two types of equipment;
and the display alarm module is used for publishing and displaying the cable tunnel engineering inspection alarm information for the result obtained by the joint detection module.
Shadow detection module for detecting visible light image I RGB =(L R ,L G ,L B ) Conversion from RGB color space to intrinsic color space, shapeCost characterization image I Int =(I 1 ,I 2 ,I 3 ),
I 1 =L R +L G -β 1 L B
I 2 =L R -β 2 L G +L B
I 3 =-β 3 L R +L G +L B
Wherein (I) 1 ,I 2 ,I 3 ) Representing eigenvalues in the eigenvalue color space; (L) R ,L G ,L B ) Representing gray values in an RGB color space; beta i I=1, 2,3, which is the conversion coefficient of RGB color space to intrinsic color space;
for screening I 3 Not less than k as visible light image I RGB Is realized for visible light image I by shadow information mode RGB Shadow information I is separated from the cable tunnel engineering inspection image by detecting and separating the shadow information of the cable tunnel engineering inspection image RGB-sha And intrinsic image information I RGB-cor The method comprises the steps of carrying out a first treatment on the surface of the Wherein I is RGB =I RGB-cor +I RGB-sha K is a preset value.
Compared with the prior art, the invention has the following beneficial effects:
by adopting the technical scheme, the intelligent inspection method and the intelligent inspection system for the cable tunnel project based on light and shadow separation can effectively improve the accuracy of intelligent inspection of the cable tunnel project by separating and removing the shadow part in the original image and identifying the rest part; and by utilizing expert priori knowledge to verify the semantic relevance of the target detection and identification result, the false alarm rate of intelligent inspection of the cable tunnel engineering can be effectively inhibited.
Drawings
Fig. 1 is a flow chart of the intelligent inspection method of the cable tunnel engineering based on light and shadow separation.
Fig. 2 is a block diagram of a cable tunnel engineering intelligent inspection system based on light and shadow separation.
Detailed Description
The invention is described in further detail below with reference to the drawings and the detailed description.
The embodiment of the invention discloses an intelligent inspection method and system for cable tunnel engineering based on light and shadow separation. In order to eliminate interference of light and shadow overlapping in images acquired in a tunnel on algorithm accuracy, the method comprises the steps of firstly separating a device body and shadows in cable tunnel engineering, and further utilizing semantic relevance of target detection and identification results, and realizing accuracy improvement and false alarm rate suppression of intelligent inspection by connecting the two modules in series. Taking an XXX transmission line 110KV cable tunnel as an example, the present invention is implemented by the following steps S1 to S6:
(S1) the visible light image I of the target equipment acquired by the image sensing module C1 is obtained by the following formula RGB =(L R ,L G ,L B ) Conversion from RGB color space to intrinsic color space to form its intrinsic image I Int =(I 1 ,I 2 ,I 3 )。
I 1 =L R +L G -β 1 L B
I 2 =L R -β 2 L G +L B
I 3 =-β 3 L R +L G +L B
Wherein (I) 1 ,I 2 ,I 3 ) Representing eigenvalues in the eigenvalue color space; (L) R ,L G ,L B ) Representing gray values in an RGB color space; (beta) 1 ,β 2 ,β 3 ) = (-0.7261,0.3816,0.3316) is the empirically pre-selected conversion coefficient of the RGB color space into the intrinsic color space.
(S2) by screening I using shadow detection module C2 3 65 or more as visible light image I RGB The shadow information is detected and separated, and then the shadow information I is removed from the cable tunnel engineering inspection image RGB-sha And intrinsic image information I RGB-cor The method comprises the steps of carrying out a first treatment on the surface of the Wherein I is RGB =I RGB-cor +I RGB-sha 。
(S3) inspection by the device inspection recognition module C31Measuring intrinsic image information I RGB-cor Detecting a device Name identifying a first device l = 'cable joint', position information (x l max ,y l max ,x l min ,y l min ) = (125,48,107,39), device Status l = 'breakage'.
(S4) using expert a priori knowledge module C32 to form data matrix M ε R S×S Storing the association relation of equipment in cable tunnel engineering; s represents the number of equipment categories in cable tunnel engineering; if the ith device and the jth device possibly occur simultaneously in the same scene, M ij =1; otherwise, M ij =0。
For example, as shown in the following table:
(S5) determining any one of the device names Name by using the semantic logic recognition module C33 l Belongs to category Ω l E {1,2, …, S }, further according to the data matrix M e R stored in step S4 S×S Judging the intrinsic image information I RGB-cor Whether the association relation of two kinds of devices meets M ij =0; if M is present ij And (4) deleting detection and identification results of the two types of devices. For example, it is determined that the 'cable' belongs to the first type of device, and the 'switch cabinet' appears in the same scene as the 'cable' through the detection and identification of the device detection and identification module C31, and the 'switch cabinet' belongs to the second type of device, and the association relationship between the first type of device and the second type of device can be obtained through the foregoing table to satisfy M ij And if the device is=0, indicating that errors exist in the identification, and deleting detection and identification results of the two types of devices.
And (S6) utilizing the display alarm module C4 to issue and display the cable tunnel engineering inspection alarm information based on the result obtained in the step S5. For example, "cable joint" broken in 110KV cable tunnel of XXX transmission line "needs to be repaired as soon as possible. And meanwhile, carrying out visual display in an original image in the form of a frame according to the equipment coordinate information output in the step S3.
Fig. 2 is a schematic diagram of an intelligent inspection system for cable tunnel engineering based on light and shadow separation in an embodiment of the invention. Schematic diagram the system comprises: the system comprises an image sensing module, a shadow detection module, a joint detection module and a display alarm module. Taking an XXX transmission line 110KV cable tunnel as an example, the specific module functions are detailed as follows:
the image sensing module C1 supports the acquisition function of visible light image data of equipment such as cables, cable joints, switch cabinets and the like in the 110KV cable tunnel engineering of the power transmission line through a visible light sensor to which the image sensing module C belongs.
The shadow detection module C2 supports detection and separation of shadow information in the cable tunnel engineering inspection image acquired by the image sensing module C1, and further removes the shadow information from the cable tunnel engineering inspection image so as to extract intrinsic image information of the cable tunnel engineering inspection image.
The combined detection module C3 supports the function implementation of the equipment detection and identification module C31, the expert priori knowledge module C32 and the semantic logic identification module C33; the equipment detection and identification module C31 is used for detecting and identifying the position and working condition of equipment in the cable tunnel engineering inspection image based on the intrinsic image information, and outputting equipment names, equipment states and equipment coordinates in an XML file format; the expert priori knowledge module C32 is used for storing the association relation of equipment in the cable tunnel engineering; the semantic logic identification module C33 judges and filters false alarm events based on the association relation of the equipment in the cable tunnel engineering stored by the expert priori knowledge module C32.
The display alarm module C4 issues and displays the inspection alarm information of the cable tunnel engineering, namely the device name and the device state in the 110KV cable tunnel of the XXX power transmission line according to the result obtained by the joint detection module C3, and the inspection alarm information needs to be repaired as soon as possible. For example, "cable joint" broken in 110KV cable tunnel of XXX transmission line "needs to be repaired as soon as possible. And meanwhile, carrying out visual display in an original image in a frame form according to the equipment coordinate information output by the joint detection module C3.
It is apparent that the above examples are given by way of illustration only and are not limiting of the embodiments. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. While still being apparent from variations or modifications that may be made by those skilled in the art are within the scope of the invention.
Claims (4)
1. The intelligent inspection method for the cable tunnel engineering based on the light and shadow separation is characterized by comprising the following steps of:
(1) Shadow separation and removal are carried out on the collected visible light images;
(2) Performing feature recognition according to the image information with the shadow information removed to obtain names of all devices in the image and device state information;
(3) Obtaining any device Name l Belongs to category Ω l E {1,2, …, S }, retrieving a pre-stored data matrix M e R S×S The method comprises the steps of carrying out a first treatment on the surface of the Judging whether the association relation of two kinds of devices in the image meets M ij =0, if yes, deleting detection recognition results of the two types of equipment;
(4) Based on the result obtained in the step 3, issuing and displaying the cable tunnel engineering inspection alarm information;
in the step (1), separating and removing the shadow portion includes the steps of:
(11) Image I of visible light RGB =(L R ,L G ,L B ) Conversion from RGB color space to intrinsic color space to form intrinsic image I Int =(I 1 ,I 2 ,I 3 ),
I 1 =L R +L G -β 1 L B
I 2 =L R -β 2 L G +L B
I 3 =-β 3 L R +L G +L B
Wherein (I) 1 ,I 2 ,I 3 ) Representing eigenvalues in the eigenvalue color space; (L) R ,L G ,L B ) Representing gray values in an RGB color space; beta i I=1, 2,3, which is the conversion coefficient of RGB color space to intrinsic color space;
(12) By screening I 3 Not less than k as visible light image I RGB Is realized for visible light image I by shadow information mode RGB Shadow information I is separated from the cable tunnel engineering inspection image by detecting and separating the shadow information of the cable tunnel engineering inspection image RGB-sha And intrinsic image information I RGB-cor The method comprises the steps of carrying out a first treatment on the surface of the Wherein I is RGB =I RGB-cor +I RGB-sha K is a preset value;
data matrix M epsilon R S×S Storing the association relation of equipment in cable tunnel engineering, wherein S represents the class number of the equipment in the cable tunnel engineering, and M is the number if the equipment of the ith class and the equipment of the jth class can occur simultaneously in the same scene ij =1; otherwise, M ij =0。
2. The intelligent inspection method for cable tunnel engineering based on light and shadow separation as set forth in claim 1, wherein (beta) 1 ,β 2 ,β 3 ) = (-0.7261,0.3816,0.3316) is the empirically chosen conversion coefficient of the RGB color space into the intrinsic color space.
3. The intelligent inspection method for cable tunnel engineering based on light and shadow separation as claimed in claim 1, wherein k=65.
4. Cable tunnel engineering intelligence inspection system based on light shadow separation, its characterized in that includes:
the image sensing module is used for acquiring visible light images in the cable tunnel engineering inspection;
the shadow detection module is used for carrying out shadow separation and removal on the visible light image acquired by the image sensing module;
the joint detection module comprises a device detection and identification module, an expert priori knowledge module and a semantic logic identification module; the equipment detection and identification module is used for detecting and identifying all equipment names and equipment state information based on the evidence image information; the expert priori knowledge module is used for using the data matrix M epsilon R S×S Pre-storing the association relation of the devices in the cable tunnel engineering in a form, wherein S is the number of device categories in the cable tunnel engineering, and M is the number of the devices in the cable tunnel engineering if the ith device and the jth device can simultaneously appear in the same scene ij =1, otherwise, M ij =0; the semantic logic recognition module is used for acquiring any device Name detected and recognized by the device detection recognition module l Class Ω to which it belongs l E {1,2, …, S }, retrieving a pre-stored data matrix M e R S×S The method comprises the steps of carrying out a first treatment on the surface of the Judging whether the association relation of two kinds of devices in the image meets M ij =0, if yes, deleting detection recognition results of the two types of equipment;
the display alarm module is used for issuing and displaying the cable tunnel engineering inspection alarm information on the result obtained by the joint detection module;
the shadow detection module is used for detecting visible light image I RGB =(L R ,L G ,L B ) Conversion from RGB color space to intrinsic color space to form intrinsic image I Int =(I 1 ,I 2 ,I 3 ),
I 1 =L R +L G -β 1 L B
I 2 =L R -β 2 L G +L B
I 3 =-β 3 L R +L G +L B
Wherein (I) 1 ,I 2 ,I 3 ) Representing eigenvalues in the eigenvalue color space; (L) R ,L G ,L B ) Representing gray values in an RGB color space; beta i I=1, 2,3, which is the conversion coefficient of RGB color space to intrinsic color space;
for screening I 3 Not less than k as visible light image I RGB Is realized for visible light image I by shadow information mode RGB Shadow information I is separated from the cable tunnel engineering inspection image by detecting and separating the shadow information of the cable tunnel engineering inspection image RGB-sha And intrinsic image information I RGB-cor The method comprises the steps of carrying out a first treatment on the surface of the Wherein I is RGB =I RGB-cor +I RGB-sha K is a preset value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010270694.6A CN111488820B (en) | 2020-04-08 | 2020-04-08 | Intelligent cable tunnel engineering inspection method and system based on light and shadow separation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010270694.6A CN111488820B (en) | 2020-04-08 | 2020-04-08 | Intelligent cable tunnel engineering inspection method and system based on light and shadow separation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111488820A CN111488820A (en) | 2020-08-04 |
CN111488820B true CN111488820B (en) | 2023-06-23 |
Family
ID=71810938
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010270694.6A Active CN111488820B (en) | 2020-04-08 | 2020-04-08 | Intelligent cable tunnel engineering inspection method and system based on light and shadow separation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111488820B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103778618A (en) * | 2013-11-04 | 2014-05-07 | 国家电网公司 | Method for fusing visible image and infrared image |
CN104218679A (en) * | 2014-09-12 | 2014-12-17 | 国家电网公司 | Remote automatic transformer substation polling method based on remote viewing system |
CN106296666A (en) * | 2016-08-01 | 2017-01-04 | 北京大学深圳研究生院 | A kind of coloured image goes shadow method and application |
CN110197176A (en) * | 2018-10-31 | 2019-09-03 | 国网宁夏电力有限公司检修公司 | Inspection intelligent data analysis system and analysis method based on image recognition technology |
-
2020
- 2020-04-08 CN CN202010270694.6A patent/CN111488820B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103778618A (en) * | 2013-11-04 | 2014-05-07 | 国家电网公司 | Method for fusing visible image and infrared image |
CN104218679A (en) * | 2014-09-12 | 2014-12-17 | 国家电网公司 | Remote automatic transformer substation polling method based on remote viewing system |
CN106296666A (en) * | 2016-08-01 | 2017-01-04 | 北京大学深圳研究生院 | A kind of coloured image goes shadow method and application |
CN110197176A (en) * | 2018-10-31 | 2019-09-03 | 国网宁夏电力有限公司检修公司 | Inspection intelligent data analysis system and analysis method based on image recognition technology |
Non-Patent Citations (2)
Title |
---|
城市航空影像的阴影检测和阴影消除方法研究;鲍海英;李艳;尹永宜;;遥感信息(01);第44-47页 * |
智慧管道站场设备状态监测关键技术;张海峰;蔡永军;李柏松;孙巍;王海明;杨喜良;;油气储运(08);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN111488820A (en) | 2020-08-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112001260A (en) | Cable trench fault detection method based on infrared and visible light image fusion | |
CN108846418B (en) | Cable equipment temperature abnormity positioning and identifying method | |
CN111259892B (en) | Inspection method, inspection device, inspection equipment and inspection medium for state of indicator lamp | |
CN110033453A (en) | Based on the power transmission and transformation line insulator Aerial Images fault detection method for improving YOLOv3 | |
CN108734143A (en) | A kind of transmission line of electricity online test method based on binocular vision of crusing robot | |
CN106780438A (en) | Defects of insulator detection method and system based on image procossing | |
CN113469953B (en) | Transmission line insulator defect detection method based on improved YOLOv4 algorithm | |
WO2012005461A2 (en) | Method for automatically calculating information on clouds | |
CN112365467B (en) | Foggy image visibility estimation method based on single image depth estimation | |
CN112528979B (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
CN114187511A (en) | Intelligent monitoring method for power transmission panoramic big data | |
CN110335309A (en) | Method and device based on camera positioning robot | |
CN109858636A (en) | Power circuit livewire work method and apparatus based on mixed reality | |
CN116310274A (en) | State evaluation method for power transmission and transformation equipment | |
CN114088212A (en) | Diagnosis method and diagnosis device based on temperature vision | |
CN111047598B (en) | Deep learning-based ultraviolet discharge light spot segmentation method and device for power transmission and transformation equipment | |
CN111767826A (en) | Timing fixed-point scene abnormity detection method | |
CN111428987A (en) | Artificial intelligence-based image identification method and system for relay protection device | |
CN111488820B (en) | Intelligent cable tunnel engineering inspection method and system based on light and shadow separation | |
CN107545564A (en) | Grid power transmission circuit insulator umbrella defect inspection method | |
CN113947563A (en) | Cable process quality dynamic defect detection method based on deep learning | |
CN116147632B (en) | Dynamic inspection path planning method and system for newly-added power equipment | |
CN115410154A (en) | Method for identifying thermal fault of electrical equipment of wind power engine room | |
CN115224795A (en) | Intelligent substation equipment operation monitoring and early warning system and method | |
CN113420686A (en) | Power transmission line inspection method, device and system |
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 |