Image intelligent identification method based on unmanned aerial vehicle

An intelligent recognition and drone technology, applied in scene recognition, character and pattern recognition, image enhancement, etc., can solve the problems of unsuitability for large-scale promotion, high price, low efficiency, etc., to improve the level of prevention and control and improve the utilization rate , detect accurate effects

Inactive Publication Date: 2019-04-26
武汉伊莱维特电力科技有限公司
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, the inspection of transmission lines mainly adopts manual methods to find defects by naked eyes or by taking photos. Although this method is simple, it is inefficient and takes a long period, and the images taken by inspections need to be manually judged, but Manual observation is limited by shooting angles, video pixels and other factors. It is difficult to accurately determine quantitative parameters such as tree heights and tree line distances under the line corridor. If a high-definition laser scanning camera is equipped, its expensive price is not suitable for large Scale promotion

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
  • Image intelligent identification method based on unmanned aerial vehicle

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to make the technical means, creative features, goals and effects achieved by the present invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.

[0030] see figure 1 , the present invention provides a technical solution: an intelligent identification method based on drone images, the identification method comprising the following steps:

[0031] Step 1: Image preprocessing; first obtain image information data, and then perform intelligent analysis and processing on the image to extract feature points;

[0032]Step 2: Intelligent analysis of wire broken strands; use Hough transform line detection method to extract straight lines in the image. This method has the characteristics of strong noise suppression ability and little influence by curve discontinuity. For the captured wire image, when shooting at close range, The wire is thicker, showing a larger pixel width in the image, and when it ...

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 provides an image intelligent identification method based on an unmanned aerial vehicle. The identification method comprises the following steps of image intelligent analysis, wire broken strand intelligent analysis, insulator defect intelligent analysis, tree line distance intelligent analysis, channel building elevation analysis, wire sag calculation and dangerous point display. According to the unmanned aerial vehicle-based image intelligent identification method, images shot by a manual or airborne common camera are used for carrying out line tree barrier development for thefirst time in a power system; and channel hidden dangers such as wire breakage, abnormal sag and insulator damage can be intelligently checked, so that the utilization rate of the unmanned aerial vehicle can be improved, the prevention and control level of line hidden dangers can be improved, and the method has important significance for safe operation of a power transmission network.

Description

technical field [0001] The invention is based on an image intelligent recognition method of an unmanned aerial vehicle, and belongs to the technical field of transmission line hidden danger recognition. Background technique [0002] At present, the inspection of transmission lines mainly adopts manual methods to find defects by naked eyes or by taking photos. Although this method is simple, it is inefficient and takes a long period, and the images taken by inspections need to be manually judged, but Manual observation is limited by shooting angles, video pixels and other factors. It is difficult to accurately determine quantitative parameters such as tree heights and tree line distances under the line corridor. If a high-definition laser scanning camera is equipped, its expensive price is not suitable for large Scale promotion. [0003] In this context, using the latest image intelligent recognition technology, through photos or video images taken manually or by an airborne...

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): G06K9/00G06T7/00G06T7/13G06T7/136G06T7/30
CPCG06T7/0002G06T7/13G06T7/136G06T7/30G06T2207/10028G06T2207/10024G06V20/13G06V20/10
Inventor 刘伟
Owner 武汉伊莱维特电力科技有限公司
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