CN112351247A - Electro-optical flash detection method in hydraulic power plant based on image processing - Google Patents
Electro-optical flash detection method in hydraulic power plant based on image processing Download PDFInfo
- Publication number
- CN112351247A CN112351247A CN202011107545.4A CN202011107545A CN112351247A CN 112351247 A CN112351247 A CN 112351247A CN 202011107545 A CN202011107545 A CN 202011107545A CN 112351247 A CN112351247 A CN 112351247A
- Authority
- CN
- China
- Prior art keywords
- contour
- electro
- image
- power plant
- optical flash
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 13
- 238000010586 diagram Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000000034 method Methods 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
-
- 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
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an electro-optic flash detection method in a hydraulic power plant based on image processing, which comprises the steps of extracting a highlight area and a frame difference characteristic diagram from video stream data extracted in real time in a hydraulic power plant area, roughly locking a target area, extracting a contour after image preprocessing, storing edge points of the contour, performing improved IOU calculation, removing a current contour which does not meet a condition of intersection or does not meet a condition of the improved IOU, obtaining an undetermined contour, finally performing color characteristic judgment around the contour, removing misjudgment of a yellow safety helmet, and obtaining an effective contour, thereby judging whether the contour is electro-optic flash or not.
Description
Technical Field
The invention relates to a hydropower station safety monitoring technology, in particular to an electro-optical flash detection method in a hydropower station based on image processing.
Background
A plurality of cameras are usually installed in a water power plant area and used for security monitoring, related workers watch the water power plant area, the workers monitor the water power plant area in real time to find problems and give an alarm in time. Because the number of cameras is large, the number of videos is large, the problem is found out inefficiently when people see the videos in real time, the people are easy to feel tired in vision for a long time, and accidents can be found out or omitted in time to cause loss.
The existing electro-optical flash detection is mainly implemented by routine detection through factory experience or circuit fault detection through electronic equipment, for example, whether short circuit or open circuit exists is judged, but all the methods need a lot of experience, a lot of personnel carry out detection, the timeliness is poor, the problem cannot be found in a short time, and the problem is solved.
The existing electro-optical flash detection method is time-consuming, labor-consuming, poor in real-time performance, and incapable of detecting the electro-optical severity phenomenon due to circuit damage.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides an image processing-based method for detecting the electro-optical flash in the hydraulic power plant, which is accurate in detection and judgment.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
an electro-optical flash detection method in a hydraulic power plant based on image processing comprises the following steps:
s10, acquiring video streams of all cameras in the hydropower plant area in real time, and removing time display interference in the video streams;
s20, carrying out graying processing on each frame of image, extracting a highlight area, and determining the range of a target area;
s30, extracting dynamic characteristics according to the image contrast corresponding to the adjacent frame difference to obtain a frame difference characteristic diagram;
s40, preprocessing the image of the highlight area and the frame difference characteristic image to highlight dynamic characteristics and eliminate interference, wherein the preprocessing at least comprises image binarization, median filtering and morphological operation;
s50, calculating an intersection according to the preprocessed highlight area image and the frame difference characteristic diagram, and determining a contour range which is possible to be electro-optical flash;
s60, extracting the contour, storing the edge points of the contour, and then performing improved IOU calculation on the extracted contour and the stored contour edge points;
s70, filtering the contour areas, eliminating the intersection unsatisfied condition or improving the IOU to calculate the current contour which does not meet the condition, and obtaining the contour to be determined;
s80, eliminating misjudgment of the yellow safety helmet in the undetermined contour according to color features around the contour, if an effective contour exists, detecting the electro-optical flash at present, giving an alarm, otherwise, no electro-optical flash.
Wherein the improved IOU is computed as intersecting sets of points of two contours.
Compared with the prior art, the invention has the following beneficial effects:
the method comprises the steps of extracting a highlight area and a frame difference characteristic diagram from video stream data extracted in real time in a hydropower plant area, roughly locking a target area, extracting a contour after preprocessing the image, storing edge points of the contour, performing improved IOU calculation, eliminating the current contour which does not meet the intersection condition or the improved IOU condition to obtain an undetermined contour, finally performing color characteristic judgment around the contour, eliminating judgment misinformation of a yellow safety helmet to obtain an effective contour, and judging whether the contour is electro-optical flash or not.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention.
Detailed Description
The present invention is further illustrated by the following figures and examples, which include, but are not limited to, the following examples.
Examples
As shown in fig. 1, the method for detecting the electro-optical flash in the hydraulic power plant based on image processing comprises the following steps:
s10, acquiring video streams of all cameras in the hydropower plant area in real time, and removing time display interference in the video streams;
s20, carrying out graying processing on each frame of image, extracting a highlight area, and determining the range of a target area;
s30, extracting dynamic characteristics according to the image contrast corresponding to the adjacent frame difference to obtain a frame difference characteristic diagram;
s40, preprocessing the image of the highlight area and the frame difference characteristic image to highlight dynamic characteristics and eliminate interference, wherein the preprocessing at least comprises image binarization, median filtering and morphological operation;
s50, calculating an intersection according to the preprocessed highlight area image and the frame difference characteristic diagram, and determining a contour range which is possible to be electro-optical flash;
s60, extracting the contour, storing the edge points of the contour, and then performing improved IOU calculation on the extracted contour and the stored edge points of the contour, wherein the improved IOU calculation is to calculate the intersection of the point sets of the two contours;
s70, filtering the contour areas, eliminating the intersection unsatisfied condition or improving the IOU to calculate the current contour which does not meet the condition, and obtaining the contour to be determined;
s80, eliminating misjudgment of the yellow safety helmet in the undetermined contour according to color features around the contour, if an effective contour exists, detecting the electro-optical flash at present, giving an alarm, otherwise, no electro-optical flash.
Through the process, the electro-optical flashing condition in the water power plant can be conveniently, simply and quickly detected.
The above embodiments are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention, but all changes that can be made by applying the principles of the present invention and performing non-inventive work on the basis of the principles shall fall within the scope of the present invention.
Claims (2)
1. An electro-optical flash detection method in a hydraulic power plant based on image processing is characterized by comprising the following steps:
s10, acquiring video streams of all cameras in the hydropower plant area in real time, and removing time display interference in the video streams;
s20, carrying out graying processing on each frame of image, extracting a highlight area, and determining the range of a target area;
s30, extracting dynamic characteristics according to the image contrast corresponding to the adjacent frame difference to obtain a frame difference characteristic diagram;
s40, preprocessing the image of the highlight area and the frame difference characteristic image to highlight dynamic characteristics and eliminate interference, wherein the preprocessing at least comprises image binarization, median filtering and morphological operation;
s50, calculating an intersection according to the preprocessed highlight area image and the frame difference characteristic diagram, and determining a contour range which is possible to be electro-optical flash;
s60, extracting the contour, storing the edge points of the contour, and then performing improved IOU calculation on the extracted contour and the stored contour edge points;
s70, filtering the contour areas, eliminating the intersection unsatisfied condition or improving the IOU to calculate the current contour which does not meet the condition, and obtaining the contour to be determined;
s80, eliminating misjudgment of the yellow safety helmet in the undetermined contour according to color features around the contour, if an effective contour exists, detecting the electro-optical flash at present, giving an alarm, otherwise, no electro-optical flash.
2. The image processing based electro-optical flash detection method in a hydroelectric power plant according to claim 1, wherein the improved IOU is calculated as intersecting sets of points of two contours.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011107545.4A CN112351247A (en) | 2020-10-16 | 2020-10-16 | Electro-optical flash detection method in hydraulic power plant based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011107545.4A CN112351247A (en) | 2020-10-16 | 2020-10-16 | Electro-optical flash detection method in hydraulic power plant based on image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112351247A true CN112351247A (en) | 2021-02-09 |
Family
ID=74360917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011107545.4A Pending CN112351247A (en) | 2020-10-16 | 2020-10-16 | Electro-optical flash detection method in hydraulic power plant based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112351247A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113191313A (en) * | 2021-05-20 | 2021-07-30 | 国能大渡河沙坪发电有限公司 | Video stream discharge identification method and device based on hydraulic power plant and computer equipment |
| CN117253195A (en) * | 2023-11-13 | 2023-12-19 | 广东申立信息工程股份有限公司 | IPC safety monitoring method, monitoring system, computer equipment and readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008293504A (en) * | 2008-05-30 | 2008-12-04 | Honda Motor Co Ltd | Object recognition device |
| CN102306280A (en) * | 2011-07-12 | 2012-01-04 | 央视国际网络有限公司 | Method and device for detecting video scores |
| US20140314302A1 (en) * | 2012-01-05 | 2014-10-23 | Omron Corporation | Inspection area setting method for image inspecting device |
| US20150117750A1 (en) * | 2012-01-27 | 2015-04-30 | Omron Corporation | Image examination method and image examination apparatus |
| CN106600625A (en) * | 2016-12-13 | 2017-04-26 | 广东沅朋网络科技有限公司 | Image processing method and device for detecting small-sized living thing |
| WO2018086299A1 (en) * | 2016-11-11 | 2018-05-17 | 广东电网有限责任公司清远供电局 | Image processing-based insulator defect detection method and system |
| CN109146860A (en) * | 2018-08-03 | 2019-01-04 | 北京工商大学 | Full-automatic mechanical equipment installs leakage detection method and device |
-
2020
- 2020-10-16 CN CN202011107545.4A patent/CN112351247A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008293504A (en) * | 2008-05-30 | 2008-12-04 | Honda Motor Co Ltd | Object recognition device |
| CN102306280A (en) * | 2011-07-12 | 2012-01-04 | 央视国际网络有限公司 | Method and device for detecting video scores |
| US20140314302A1 (en) * | 2012-01-05 | 2014-10-23 | Omron Corporation | Inspection area setting method for image inspecting device |
| US20150117750A1 (en) * | 2012-01-27 | 2015-04-30 | Omron Corporation | Image examination method and image examination apparatus |
| WO2018086299A1 (en) * | 2016-11-11 | 2018-05-17 | 广东电网有限责任公司清远供电局 | Image processing-based insulator defect detection method and system |
| CN106600625A (en) * | 2016-12-13 | 2017-04-26 | 广东沅朋网络科技有限公司 | Image processing method and device for detecting small-sized living thing |
| CN109146860A (en) * | 2018-08-03 | 2019-01-04 | 北京工商大学 | Full-automatic mechanical equipment installs leakage detection method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113191313A (en) * | 2021-05-20 | 2021-07-30 | 国能大渡河沙坪发电有限公司 | Video stream discharge identification method and device based on hydraulic power plant and computer equipment |
| CN117253195A (en) * | 2023-11-13 | 2023-12-19 | 广东申立信息工程股份有限公司 | IPC safety monitoring method, monitoring system, computer equipment and readable storage medium |
| CN117253195B (en) * | 2023-11-13 | 2024-02-27 | 广东申立信息工程股份有限公司 | IPC safety monitoring method, monitoring system, computer equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102842211B (en) | Monitoring and early warning system and monitoring and early warning method for prevention of external force of transmission line based on image recognition | |
| CN111047818A (en) | Forest fire early warning system based on video image | |
| CN101556142B (en) | Visual detection method of ice coating thickness of overhead lines | |
| CN104994334A (en) | Automatic substation monitoring method based on real-time video | |
| CN111461078B (en) | Fishing preventing and monitoring method based on computer vision technology | |
| CN104077872A (en) | Anti-external force monitoring early warning method of electric transmission line based on image recognition | |
| CN105241679A (en) | Method for detecting hidden fault of motor train unit | |
| CN113762171A (en) | Method and device for monitoring safety of railway construction site | |
| CN112784821A (en) | Building site behavior safety detection and identification method and system based on YOLOv5 | |
| CN112184773A (en) | Helmet wearing detection method and system based on deep learning | |
| CN105551056A (en) | Line broken-strand detection method and system | |
| CN115527158A (en) | Method and device for detecting abnormal behaviors of personnel based on video monitoring | |
| CN112526391A (en) | Electrolytic cell fault detection system and method | |
| CN109345787A (en) | A kind of anti-outer damage monitoring and alarming system of the transmission line of electricity based on intelligent image identification technology | |
| CN112351247A (en) | Electro-optical flash detection method in hydraulic power plant based on image processing | |
| CN107977531A (en) | A kind of method that ground resistance hard measurement is carried out based on image procossing and field mathematical model | |
| CN112001336A (en) | Pedestrian boundary crossing alarm method, device, equipment and system | |
| CN104463905A (en) | Method for monitoring vehicles in construction site | |
| CN110207783A (en) | A kind of sensed water level method based on video identification | |
| CN115761644A (en) | Transmission line foreign matter detection method based on deep learning and frame difference method | |
| CN115346170A (en) | Intelligent monitoring method and device for gas facility area | |
| CN114241400A (en) | Monitoring method and device of power grid system and computer readable storage medium | |
| CN109193935B (en) | Power distribution room monitoring method and system based on image processing | |
| CN112101375A (en) | Intelligent substation equipment state detection method and system based on deep learning | |
| CN111105395A (en) | A AI intelligence cloud platform for transmission of electricity operation monitoring |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 614000 No. 1, No. 4 Binhe Road, Jinkouhe District, Leshan City, Sichuan Province Applicant after: Guoneng Dadu River Zhentouba Power Generation Co.,Ltd. Address before: 614000 No. 1, No. 4 Binhe Road, Jinkouhe District, Leshan City, Sichuan Province Applicant before: GUODIAN DADU RIVER ZHENTOUBA POWER GENERATION Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210209 |