Power transmission line external damage prevention identification method and terminal

A transmission line and identification method technology, applied in the field of image recognition, can solve problems such as limited improvement, and achieve the effect of fast recognition speed and high recognition accuracy

Active Publication Date: 2020-11-03
SANLI VIDEO FREQUENCY SCI & TECH SHENZHEN
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] 3. Change the prediction mode of the detection algorithm, from the upper, lower, left, and right coordinates of the predicted target to the predicted center coordi

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
  • Power transmission line external damage prevention identification method and terminal
  • Power transmission line external damage prevention identification method and terminal
  • Power transmission line external damage prevention identification method and terminal

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0079] Example one

[0080] Please refer to figure 1 and figure 2 , The first embodiment of the present invention is a method for identifying the transmission line to prevent external damage, including the following steps:

[0081] S1. Establish a sample library of external failures of transmission lines and develop evaluation standards.

[0082] In this embodiment, the external damage sample library includes pictures of different external damage categories, such as pictures of external damage targets such as cranes, tower cranes, bulldozers, pump trucks, excavators, and forklifts. The evaluation standard is the mAP value of Pascal VOC challenge.

[0083] S2. Establish an external damage detector.

[0084] In this embodiment, step S2 is specifically:

[0085] S21. Obtain an overall feature map.

[0086] Use the DLA34 network as the backbone of the deep neural network to extract features to obtain a deep feature map (ie, the overall feature map). The overall feature map includes several ...

Example Embodiment

[0116] Example two

[0117] Please refer to image 3 , The second embodiment of the present invention is:

[0118] An identification terminal 100 for preventing external damage of a power transmission line, corresponding to the method of the first embodiment, includes a memory 1, a processor 2, and a computer program stored on the memory 1 and running on the processor 2. The processing When the device 2 executes the computer program, the following steps are implemented:

[0119] Establish a sample library for external damage of transmission lines and formulate evaluation standards;

[0120] Establish external damage detector;

[0121] Use the coco data set to train the external damage detector to convergence to obtain a pre-training model;

[0122] Migrating the pre-training model to the externally broken sample library for training to obtain a training model;

[0123] Evaluate the training model according to the evaluation standard to obtain an optimal model;

[0124] The image to be rec...

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 power transmission line external damage prevention identification method and terminal, and the method comprises the steps: establishing an external damage sample library of apower transmission line, and formulating an evaluation standard; establishing an external damage detector; training the external damage detector to converge by using a coco data set to obtain a pre-training model; migrating the pre-training model to the external damage sample library for training to obtain a training model; evaluating the training model according to the evaluation standard to obtain an optimal model; and identifying a to-be-identified image by using the optimal model. According to the method, the external damage target on the power transmission line can be rapidly identified,the identification precision is high, and the reliability is good.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method and terminal for anti-breakage recognition of transmission lines. Background technique [0002] In recent years, with the rapid development of the economy, the construction of urban and rural infrastructure has increased, resulting in sudden and seasonal external force damage to overhead transmission lines caused by illegal tree planting, house building, and construction operations. 1. The mobility of the machinery is strong, the randomness is large, and it is difficult to prevent it. The invasion and damage of foreign objects has become one of the biggest threats and hidden dangers to the safe and stable operation of overhead transmission lines. [0003] Currently, target detection methods mainly focus on video surveillance and video image processing. For example: [0004] 1. Divide the target detection into two stages, that is, first use deep CNN to disting...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/20G06N3/045G06F18/24G06F18/214
Inventor 潘成龙张宇刘东剑
Owner SANLI VIDEO FREQUENCY SCI & TECH SHENZHEN
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