Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Electric power line patrol electric tower detection and identification method and system based on unmanned aerial vehicle

A technology of line patrol tower and identification method, applied in the field of machine learning, can solve problems such as low efficiency, and achieve the effects of improving work efficiency, high detection accuracy, and saving labor costs

Inactive Publication Date: 2020-06-12
GUANGDONG POWER GRID CO LTD +1
View PDF7 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention provides a method and system for detecting and identifying electric power line inspection towers based on unmanned aerial vehicles, which solves the problem that in the prior art, when using unmanned aerial vehicles to inspect transmission lines and towers, it is necessary to manually control the unmanned aerial vehicles and artificially inspect the transmission towers. To identify, there is a technical problem of inefficiency

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
  • Electric power line patrol electric tower detection and identification method and system based on unmanned aerial vehicle
  • Electric power line patrol electric tower detection and identification method and system based on unmanned aerial vehicle
  • Electric power line patrol electric tower detection and identification method and system based on unmanned aerial vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] see figure 1 , figure 1 It is a method flow chart of a UAV-based power line inspection and tower detection and identification method and system provided by an embodiment of the present invention.

[0044] A method for detecting and identifying electric power line inspection towers based on drones provided in this embodiment is applicable to a pre-trained tower recognition neural network model, including the following steps:

[0045] According to the visual positioning method, the UAV is controlled for automatic inspection. During the inspection process, no staff is required to control the UAV. The UAV completes the flight control independently during the inspection process, thereby reducing labor costs.

[0046] Collect images during the inspection process of drones, generate synthetic data based on the images, and transmit the synthetic data to the trained tower recognition neural network model;

[0047] The tower recognition neural network model generates a belief m...

Embodiment 2

[0082] In Example 2, a plug-in is developed based on UE4, which can generate massive amounts of high-quality synthetic data, including RGB images, depth maps, segmentation maps, and tag data files for each frame. By utilizing asynchronous, multi-threaded sequential frame grabbing, the plugin generates data at 50-100Hz, which is much faster than the default UE4 screenshot function. In addition to synthesizing data, the plugin also includes different components, such as scene management components, virtual camera components; by configuring their properties, it is possible to generate highly randomized images. This randomization includes lighting, object and camera positions, poses, textures and disturbances, and camera path following, among other things. These components allow researchers to easily create randomized scenarios to train deep neural networks.

[0083] By importing the model tower into the UE4 scene, using the automatic transmission virtual camera provided by the p...

Embodiment 3

[0087] In the mainstream UAV positioning system, the main implementation method is to use various sensors, such as: laser range finder, ultrasonic sensor, electromagnetic detection sensor, etc., the use of sensors for positioning is relatively disturbed by the surrounding environment, especially in the wireless environment. Various electromagnetic interferences will affect the performance of sensors during human-machine power line inspection, and using machine vision modules to replace these sensors to realize the autonomous flight positioning of drones can avoid these interferences. The working process is as follows: image 3 Shown:

[0088]In this embodiment, the microcomputer uses NVIDIA's latest TX2 development board for deep learning, which integrates many frameworks and environments for deep learning. image signal, and then build a tower recognition neural network model on it to realize 3D object attitude estimation and recognition, so as to realize the autonomous positi...

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 electric power line patrol electric tower detection and identification method and system based on an unmanned aerial vehicle, which are suitable for a pre-trained tower identification neural network model, and the method comprise the following steps: controlling the unmanned aerial vehicle to perform automatic patrol according to a visual positioning method; collecting an image in the unmanned aerial vehicle inspection process, generating synthetic data according to the image, and transmitting the synthetic data to the trained tower identification neural network model; and the tower identification neural network model generates belief mapping based on the synthetic data, identifies the tower according to the belief mapping, and outputs a final identification result. The tower in the image acquired in the unmanned aerial vehicle inspection process is automatically identified through the tower identification neural network model, the unmanned aerial vehicle iscontrolled to perform automatic inspection through the visual positioning method, human intervention is not needed in the whole process, the detection precision is high, the labor cost is saved, and the working efficiency is greatly improved.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to a method and system for detecting and identifying power line inspection towers based on unmanned aerial vehicles. Background technique [0002] At present, UAVs have been widely used in the technical field of power line inspection. In order to realize the autonomous positioning of UAVs during power line inspection, and to stably hover around the transmission towers; so the detection and identification of transmission towers is very important. Necessary. And when it comes to artificial intelligence, in order for robots to work safely and effectively alongside humans, robots must be aware of their surroundings. One aspect of this awareness is the knowledge of the three-dimensional position and orientation of objects in the scene, often referred to as 6-DOF pose. This cognition is important for performing object pick-and-place, passing from one person to another, ...

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): G06K9/00G06N3/08
CPCG06N3/08G06V20/20
Inventor 李国强李雄刚翟瑞聪张峰彭炽刚陈浩周华敏陈义龙林俊省郭锦超王丛廖如超刘高
Owner GUANGDONG POWER GRID CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com