High-voltage line detection method combining deep semantic segmentation with Hough transform

A technology of semantic segmentation and Hough transform, applied in the field of high-voltage line detection combined with deep semantic segmentation and Hough transform, can solve the problems of reduced detection ability, small size of high-voltage lines, weather interference, etc., to improve detection ability and avoid too many false alarms , the effect of simple algorithm process

Pending Publication Date: 2020-12-15
LEIHUA ELECTRONICS TECH RES INST AVIATION IND OF CHINA
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with other objects, high-voltage lines are small in size, and it is difficult to find them from a long distance with vision or optical equipment
Existing technologies mostly use laser and infrared sensors to detect high-voltage lines, but the detection distance of these two methods is limited, and they are easily interfered by the weather
[0003] The echo of power lines such as high-voltage lines has Bragg scattering characteristics, and conventional constant false alarm detection technology cannot achieve good results in detecting high-voltage lines
Especially for the situation that needs to detect high-voltage lines at a longer distance, the detection ability of the existing technology will be greatly reduced, and too many false alarms will be generated

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
  • High-voltage line detection method combining deep semantic segmentation with Hough transform
  • High-voltage line detection method combining deep semantic segmentation with Hough transform
  • High-voltage line detection method combining deep semantic segmentation with Hough transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] like figure 1 As shown in the figure, a high-voltage line detection method combined with deep semantic segmentation and Hough transform includes the following steps:

[0022] Step 100: Using the sample echo data as input information and the position data of the real high-voltage line as label information, establish a high-voltage line deep semantic segmentation network model through semantic segmentation model training.

[0023] Step 102: Initial echo data detected by the radar Perform preprocessing to obtain intermediate echo data Scaling the intermediate echo data. The scaling includes converting the intermediate echo data into a range between 0 and 255 according to the minimum and maximum values ​​of the intermediate echo data, so as to obtain the preprocessed echo data.

[0024] Step 104: Preprocess the echo data through the high-voltage line deep semantic segmentation network model Perform semantic segmentation processing to obtain output output is 1 or...

Embodiment 2

[0029] In another embodiment, the technical solution of the present invention is further described through specific experiments.

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 a high-voltage line detection method combining deep semantic segmentation with Hough transform, and the method employs a deep learning semantic segmentation technology to makethreshold judgment of a target through combining with the Hough transform, achieves high-performance detection of a high-voltage line, can achieve further confirmation of a detection target through the threshold after the Hough transform, and improves detection accuracy. The false target of an original image is suppressed, and the dual effects of target detection and false alarm reduction are achieved. According to the technical scheme disclosed by the invention, an algorithm flow is concise, detection rate is higher than that of a traditional parameter adjustment method, the false alarm rateis further reduced through Hough transform, and the problem of excessive false alarms of the high-voltage line caused by semantic segmentation is avoided.

Description

technical field [0001] The invention relates to the technical field of radar detection, in particular to a high-voltage line detection method combining deep semantic segmentation and Hough transform. Background technique [0002] The biggest threat to helicopters flying at low altitudes is high-voltage power lines, with which many helicopters have been reported to have collided with high-voltage power lines. Because the helicopter is fast, heavy, and difficult to turn, the helicopter needs a long warning time and braking distance to avoid the high-voltage line. Relative to other objects, high-voltage lines are small and difficult to find from long distances with visual or optical devices. The existing technology mostly uses laser and infrared sensors to detect high-voltage lines, but the detection distance of these two methods is limited, and they are easily disturbed by the weather. [0003] The echoes of power lines such as high-voltage lines have Bragg scattering charac...

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): G06K9/00G06N3/04G06N3/08G01S13/95G01S7/41
CPCG06N3/08G01S13/953G01S7/415G01S7/418G06V20/13G06N3/045Y02A90/10
Inventor 陈春风罗旌胜李志科
Owner LEIHUA ELECTRONICS TECH RES INST AVIATION IND OF CHINA
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