Parallel matching based image identification method of power substation mechanism cabinet door
A technology for image recognition and substations, applied in character and pattern recognition, computer parts, instruments, etc., can solve problems such as poor implementability and practicability, difficulty in collecting picture sample databases, and state recognition of mechanism box doors, etc., to achieve improved Extensive practicability and scalability, improved computing performance, and improved real-time effects
Active Publication Date: 2017-11-28
STATE GRID JIANGSU ELECTRIC POWER CO ELECTRIC POWER RES INST +3
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] Therefore, the current technical means cannot well solve the problem of identifying the state of the mechanism box door.
The method that can be adopted is a method based on machine learning. If a method based on machine learning is adopted, a large sample library of pictures of mechanism boxes needs to be constructed. Although the image sample library of the closed state of the mechanism box door can easily collect relevant sample data, however, it is difficult to collect the image sample library of the on-site mechanism box door opened state, and there are few sample libraries for machine learning. , which ultimately leads to poor recognition accuracy of the machine learning method. Therefore, although this method is feasible in technical principle, it is poor in implementability and practicability
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0079] The process of obtaining the status picture of the box door of the substation mechanism is as follows:
[0080] (1) Use the function interface NetSDKInit() provided by the manufacturer to initialize the manufacturer interface, and use the function interface Net_DVR_RealPlay(szDVRIP_address, nDVRPort, szDVRUserName, szDVRPassword, nCameraChannel, RealDataCallBack) realize device connection and obtain real-time video, wherein, RealDataCallBack is a callback function, and the callback data is video image data in YUV format;
[0081] (2) Use the function interface Net_DVR_Control provided by the manufacturer to realize the control of calling the camera preset position, and turn the camera to the angle including the mechanism box;
[0082] (3) Set the system timer. In the callback function RealDataCallBack(), when the time reaches 1 second, take a frame of picture data, the data format is YUV format, and store the YUV data in the array Mat_Orgin_YUV_Pic[];
[0083] (4) Acco...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a parallel matching based image identification method of a power substation mechanism cabinet door. The method comprises the following steps: 1) obtaining a state picture of the power substation mechanism cabinet door; 2) preprocessing the obtained picture to obtain a binary picture; 3) extracting picture segment information and calculating a segment slope; 4) performing parallel line segment matching to obtain slope distribution of all line segments; and 5) judging the opening and closing state of the mechanism cabinet door. The method disclosed by the invention is easy to implement and apply, is applied to intelligent image identification applications of intelligent operation detection of substations, and promotes the development and improvement of the intellectualization level of power grids.
Description
technical field [0001] The invention relates to a parallel matching-based image recognition method for a box door state of a power substation mechanism, and belongs to the technical field of substation video monitoring. Background technique [0002] At present, using the image intelligent recognition algorithm, there is still no effective identification method for the identification of the state of the box door of the substation mechanism. Usually, most of the doors of the entrance and exit adopt the electronic access control method, and the digital information of the access control sensor is used to control the door. The switch state is identified. [0003] Since there are a large number of mechanism boxes in the substation, including mechanism boxes for various equipment such as circuit breakers, floor switches, and isolating switches, the doors of these mechanism boxes are usually locked. During the maintenance work of the substation, there may be artificial In the case ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/38
CPCG06V20/20G06V10/28
Inventor 姚楠吴曦蔡越王祥
Owner STATE GRID JIANGSU ELECTRIC POWER CO ELECTRIC POWER RES INST