Unlock instant, AI-driven research and patent intelligence for your innovation.

Generative adversarial network-based method for extracting power transmission line information from images acquired by unmanned aerial vehicle

A technology for power transmission lines and image acquisition, applied in biological neural network models, image analysis, image data processing, etc., can solve problems such as poor recognition efficiency, and achieve the effects of accelerating network learning, improving recognition function, and high recognition efficiency.

Pending Publication Date: 2022-07-29
STATE GRID HEILONGJIANG ELECTRIC POWER CO LTD ELECTRIC POWER RES INST +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem that the existing image transmission line information is identified through manual or semi-manual line defects, and the recognition efficiency is poor, and a method for extracting transmission line information from images collected by drones based on generative confrontation networks is proposed

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Generative adversarial network-based method for extracting power transmission line information from images acquired by unmanned aerial vehicle
  • Generative adversarial network-based method for extracting power transmission line information from images acquired by unmanned aerial vehicle
  • Generative adversarial network-based method for extracting power transmission line information from images acquired by unmanned aerial vehicle

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0032] Embodiment 1: Combining figure 1 Describing this embodiment, the method for extracting transmission line information from images captured by UAVs based on generative adversarial networks described in this embodiment includes the following steps:

[0033] Step 1: Preprocess the original image to generate a preprocessed image;

[0034] Step 2, classify and label the preprocessed image generated in step 1 to generate a label image;

[0035] Step 3: Select a plurality of original images and their corresponding label images for pairing to form a training set;

[0036] Step 4. Build a generative adversarial network ensemble learning model;

[0037] Step 5: Input the training set formed in step 3 into the generative adversarial network ensemble learning model constructed in step 4, and combine the real application data of the transmission line to solidify the parameters of the generative adversarial network ensemble learning model constructed in step 2, and obtain The solid...

specific Embodiment approach 2

[0040] Embodiment 2: This embodiment further defines the method for extracting transmission line information from images collected by UAVs based on Generative Adversarial Networks described in Embodiment 1. In this embodiment, the process of generating a preprocessed image in step 1 includes: : Perform pitch adjustment, roll operation, or yaw mode image correction on the original image.

specific Embodiment approach 3

[0041] Embodiment 3: This embodiment further defines the method for extracting transmission line information from images collected by drones based on generative adversarial networks described in Embodiment 1. In this embodiment, the label image generated in step 2 is in The tower area, sky area, forest area, river area and open space area are marked on the preprocessed image.

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

No PUM Login to View More

Abstract

The invention discloses an unmanned aerial vehicle collected image power transmission line information extraction method based on a generative adversarial network, relates to a power transmission line information extraction technology, and aims to solve the problem that the existing image power transmission line information is recognized through manual or semi-manual line defects, and the recognition efficiency is poor. The method comprises the following steps: preprocessing an original image to generate a preprocessed image; classifying and labeling the generated preprocessed image to generate a label image; selecting a plurality of original images and paired label images to form a training set; constructing a generative adversarial network integrated learning model; inputting the formed training set into a generative adversarial network ensemble learning model, and obtaining a solidified generative adversarial network ensemble learning model in combination with real application data of the power transmission line; and inputting the unmanned aerial vehicle collection image of which the information is to be extracted into the solidified generative adversarial network ensemble learning model to extract the power transmission line information in the unmanned aerial vehicle collection image of which the information is to be extracted. The beneficial effect is that the identification efficiency is high.

Description

technical field [0001] The invention relates to a transmission line information extraction technology. Background technique [0002] As an important power grid infrastructure, transmission lines play an important role in the process of power transmission; with the large-scale use of high-resolution drone photography technology, long-range aerial photography has become a routine line inspection method, but how quickly , Accurately extracting the information of transmission lines and towers from aerial images has attracted attention; in the identification method of transmission line defects, at present, most of the cases still use manual methods to judge by directly viewing the images with the naked eye, or use semi-automatic extraction methods. That is, simple image recognition and manual judgment; however, due to the existence of massive aerial image data and complex image information, this manual or semi-manual line defect identification process is not only inefficient, unt...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06V10/774G06V10/82G06V10/80G06V20/70G06V20/17G06N3/04G06N3/08
CPCG06T7/0002G06V10/774G06V10/82G06V10/806G06V20/70G06V20/17G06N3/08G06N3/045
Inventor 宋杭选刘智洋尚方王孝余孙泽锋林扬宋柏越
Owner STATE GRID HEILONGJIANG ELECTRIC POWER CO LTD ELECTRIC POWER RES INST