Automatic transmission tower scanning method based on hovering state of aircraft

A technology of power transmission towers and scanning methods, which is applied in the direction of neural learning methods, instruments, biological neural network models, etc., can solve the problems of large influence, manual design features, etc., and achieve the effect of improving imaging quality and realizing high-definition imaging

Active Publication Date: 2018-06-29
GUIZHOU POWER GRID CO LTD
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above method of automatic locking and shooting of objects adopts the traditional feature extraction method, which not only requires manual design of features, but also requires a lot of debugging work; in addition, the traditional feature extraction method is greatly affected by complex environments

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
  • Automatic transmission tower scanning method based on hovering state of aircraft
  • Automatic transmission tower scanning method based on hovering state of aircraft
  • Automatic transmission tower scanning method based on hovering state of aircraft

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] Example: such as Figure 1-Figure 3As shown, an autonomous scanning method for power transmission towers based on the hovering state of the aircraft includes the following steps:

[0038] The first step, offline deep learning: For the original image with labels, the training of the tower recognition model and the multi-target detection model are carried out respectively. Both trainings use a deep convolutional neural network. The image data of labels and background labels, the input data for multi-target detection model training is image data with various power component labels and background labels;

[0039] The second step, online autonomous scanning: Obtain the tower identification model through step 2), combine the tower area and the tower POS information, and obtain the autonomous scanning route of the transmission tower under manual intervention;

[0040] The third step, online automatic high-definition imaging: through step 2), the multi-target recognition model...

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 automatic transmission tower scanning method based on hovering state of an aircraft. The method comprises steps of offline deep learning, online automatic scanning and online automatic high-definition imaging, wherein for offline deep learning, a transmission tower is positioned online in real time with a deep learning method, a pod is controlled through feedback of areainformation and POS information of the tower, automatic scanning of the transmission tower is realized, multistage internal features of various electric components are learned and described automatically and step-by-step abstraction is performed with a deep convolutional neural network, feature learning and classified detection are realized simultaneously, the problems that the optimal detectioneffects of feature learning and classified detection cannot be realized simultaneously with the traditional feature extraction method and the like are solved effectively, and online real-time detection of multiple targets is realized; the information feedback mechanism is introduced on the basis of multi-target recognition, load is controlled automatically, a test field of imaging equipment is adjusted, high-definition imaging of the electric components is realized, and imaging quality is improved effectively.

Description

technical field [0001] The invention relates to an autonomous scanning method for transmission poles and towers based on the hovering state of an aircraft, and belongs to the technical field of transmission poles and towers scanning. Background technique [0002] As an important part of electric power construction, transmission lines have increased investment in transmission lines in recent years. Most of the transmission lines under the jurisdiction of the company are located in mountainous areas, with the characteristics of variable climate, complex geological environment, high mountains and dense forests, thick fog and strong wind, and have special requirements for machine patrol. During the dynamic flight process, the relative positional relationship between the pod and the transmission line is also dynamic. Sometimes it is necessary to hover at multiple points and to fly at a higher altitude. It is necessary to manually operate the remote control of the aircraft and the...

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): G06K9/62G06K9/46G06K9/32G06N3/04G06N3/08
CPCG06N3/08G06V10/25G06V10/462G06N3/045G06F18/214
Inventor 陈科羽刘锐许良柱杨磊虢韬彭赤陈凤翔张伟周小红石书山陈海华方广东
Owner GUIZHOU POWER GRID CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap