An image detection method for broken strands of distribution line towers and ground conductors based on unmanned aerial vehicle images
A technology for distribution line and image detection, applied in the field of image recognition, can solve problems such as low detection accuracy, and achieve the effect of increasing training weight, enhancing sensitivity, and improving detection performance
Active Publication Date: 2022-07-01
STATE GRID ZHEJIANG JIASHAN POWER SUPPLY CO LTD +1
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The technical problem to be solved by the present invention is: the technical problem of low detection accuracy of the current image detection method for ground wire broken strands
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 1
[0019] An image detection method for broken strands of ground conductors of distribution line towers and towers based on drone images, such as figure 1 As shown, the following steps are involved: A) Build a data set of images of broken strands of the ground wire, label and locate large objects in the image. B) The picture data taken by the drone is transmitted from the drone to the PC through the cable, and enters the intelligent analysis module of typical defects, provides a model to intelligently identify the area to be analyzed, establishes an analysis frame, manually marks the defects, and obtains sample data. The method of identifying the area to be analyzed and establishing the analysis frame includes: B1) obtaining a picture with the area to be analyzed and the large target, manually marking the area to be analyzed and the large target area, and pre-building an analysis frame; B2) manually marking the large target area , align with the large target area marked in the pi...
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 relates to the technical field of image recognition, and in particular to a method for detecting broken strands of ground conductors of power distribution lines and towers based on drone images, comprising the following steps: A) establishing a picture data set of broken strands of conductors, marking and locating them The big target in the image; B) The picture data taken by the drone is transmitted from the drone to the PC through the cable, and enters the intelligent analysis module of typical defects, identifies the area to be analyzed, establishes the analysis frame, manually marks the defects, and obtains samples Data; C) Build the Cascade R-CNN network, use the sample data to train and test the Cascade R-CNN network; D) Obtain the pictures taken by the drone patrol, identify the area to be analyzed, import the Cascade R-CNN network, and obtain the detection results. The substantial effects of the invention are: improving the performance of detecting small targets; and improving the accuracy of detecting the broken strand fault of the guide ground wire of the distribution line tower.
Description
technical field [0001] The invention relates to the technical field of image recognition, in particular to an image detection method for broken strands of conductors and ground wires of power distribution lines, towers and towers based on unmanned aerial vehicle images. Background technique [0002] Transmission line is the artery of the power system, and the transmission wire is an important part of the transmission line. Broken strands and damage of transmission wires caused by external force damage, meteorological disasters, aging lines and other factors seriously threaten the stable operation of lines, and have a serious impact on people's normal production and life. Through the image processing of the aerial video / image of the transmission wire of the UAV patrol line, the real-time detection of the running state of the transmission wire can be realized, and the safe operation of the power grid can be effectively guaranteed. Therefore, it is of great practical significa...
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 Patents(China)
IPC IPC(8): G06V20/17G06V10/80G06V10/774G06V10/82G06N3/04G01R31/08G01R31/54G01R31/58
CPCG01R31/086G01R31/088G01R31/54G01R31/58G06V20/13G06V2201/07G06N3/045G06F18/253G06F18/214
Inventor 李飞伟郁云忠袁林峰许超陈佳煜李俊刘争俞渊张冲标
Owner STATE GRID ZHEJIANG JIASHAN POWER SUPPLY CO LTD