Power distribution cabinet on-off state identification method based on binocular vision
A technology of switch state and identification method, applied in character and pattern recognition, image data processing, 3D modeling, etc., can solve the problems of infeasibility of manual inspection, low efficiency of manual inspection, and high missed inspection rate. Achieve the effect of improving algorithm efficiency, reducing algorithm complexity, and high accuracy
Active Publication Date: 2020-06-09
SOUTH CHINA UNIV OF TECH
View PDF7 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
At present, manual inspection is the main method for monitoring the status of switches in power distribution rooms, but manual inspection has defects such as low efficiency, poor real-time performance, and high missed detection rate, especially in some scenarios that are not suitable for personnel to enter, such as distribution in high-voltage environments. Electric room, manual inspection is very dangerous and infeasible
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 Construction
[0053] The present invention will be further described below in conjunction with specific embodiments.
[0054] Such as figure 1 As shown, the binocular vision-based power distribution cabinet switch state recognition method provided in this embodiment includes the following steps:
[0055] 1) Print a black and white checkerboard of known size as the calibration board, fix the relative position between the left and right cameras, and use the binocular camera to shoot the calibration board at different distances, angles and postures. The left and right cameras need to shoot at least three times. The parameters of the left and right cameras, including the internal parameter matrix, distortion matrix and external parameter matrix of the left and right cameras, are obtained by systematically calibrating the binocular camera with Zhang Zhengyou’s calibration method. The internal parameter matrix includes S X , S y , u 0 , v 0 , f, where S X , S y is the physical length and wi...
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 power distribution cabinet on-off state identification method. The method comprises the steps of 1) obtaining parameters of a left camera and a right camera in a binocular camera and a relative position relationship matrix between the left camera and the right camera; 2) performing stereo correction on the left camera and the right camera, detecting feature points in thecorrected image through an image processing technology, and realizing three-dimensional reconstruction of the feature points through a parallax method; 3) collecting the size information of the circular switch and the linear switch in the image under different distance conditions, and respectively fitting the linear relationship between the distance and the size of the circular switch and the linear relationship between the distance and the linear switch; 4) preprocessing the corrected image of the left camera, and obtaining the positions of the circular switch and the linear switch through animage processing algorithm, and 5) carrying out the state recognition of the circular switch image and the linear switch image, so as to obtain a high-accuracy power distribution cabinet switch staterecognition effect on the premise of guaranteeing the real-time performance.
Description
technical field [0001] The invention relates to the technical field of machine vision and image processing, in particular to a binocular vision-based recognition method for a switch state of a power distribution cabinet. Background technique [0002] Power distribution cabinets widely exist in social scenarios such as factories, communities, and power transmission, providing an important guarantee for the normal operation of the power system. A variety of switches are installed on the power distribution cabinet. Real-time and accurate detection of these switch states is of great significance to ensure the safe supply of electricity, and it helps to improve power supply efficiency, save energy, and provide convenience for production and life. At present, manual inspection is the main method for monitoring the status of switches in power distribution rooms, but manual inspection has defects such as low efficiency, poor real-time performance, and high missed detection rate, esp...
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 IPC IPC(8): G06T17/10G06T7/80G06T7/90G06K9/62
CPCG06T17/10G06T7/80G06T7/90G06V10/751
Inventor 田联房郭月阳杜启亮
Owner SOUTH CHINA UNIV OF TECH