Power equipment identification efficiency optimization method based on template tracking

A technology for power equipment and recognition efficiency, applied in character and pattern recognition, neural learning methods, biological neural network models, etc., can solve the problems of slow power equipment recognition and detection, improve the recognition frame rate and false detection rate, reduce Invalid area, the effect of improving the recognition speed

Active Publication Date: 2020-07-28
GUIZHOU POWER GRID CO LTD
View PDF10 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Therefore, the technical problem to be solved by the present invention is the problem of slow identification and detection speed of electric equipment in the prior art

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 equipment identification efficiency optimization method based on template tracking
  • Power equipment identification efficiency optimization method based on template tracking
  • Power equipment identification efficiency optimization method based on template tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0033] refer to Figure 1~5 , this embodiment provides a method for optimizing the identification efficiency of electric equipment based on template tracking, including the following steps:

[0034] S1: Build a deep classification network and train it;

[0035] S2: Use the deep classification network model for video key frame detection and recognition;

[0036] S3: Extract the key frame target recognition area as the target template, and extract template features;

[0037] S4: Perform template matching within twice the range of the non-keyframe target area, and calculate the matching rate;

[0038] S5: Judge the relationship between the matching rate and the threshold. If the extreme value of the matching rate is greater than or equal to the threshold, update the coordinates of the template area and re-extract the template features. If the matching rate is less than the threshold, jump to the deep neural network model for identification;

[0039] S6: Judging whether to end ...

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 equipment identification efficiency optimization method based on template tracking, and the method comprises the following steps: building a deep classification network, and carrying out the training of the deep classification network; performing video key frame detection and identification by using a deep classification network model; extracting a key frame targetidentification area as a target template, and extracting template features; carrying out template matching in a double range of a non-key frame target area, and calculating a matching rate; judging the relationship between the matching rate and a threshold value, if the extreme value of the matching rate is greater than or equal to the threshold value, updating the coordinates of the template region, re-extracting template features, and if the matching rate is less than the threshold value, skipping to a deep neural network model for identification; judging whether power equipment identification is ended or not, and if so, exiting. By using the method, the tracking speed is high, the invalid area recognized by the deep learning classifier is effectively reduced, and the recognition frame rate and the false detection rate are improved.

Description

technical field [0001] The invention relates to the field of electrical equipment identification, in particular to a method for optimizing identification efficiency of electrical equipment based on template tracking. Background technique [0002] At present, a series of target detection algorithms based on deep learning algorithms can be roughly divided into two schools: 1. Two-stage algorithm: first generate candidate regions and then perform CNN classification (RCNN series), 2. One-step (one-stage) algorithm: directly apply the algorithm to the input image and output the category and corresponding positioning (YOLO series); YOLO has both efficiency and recognition rate, and is currently the preferred framework for target recognition in the industry. Image recognition processing technology plays a very important role in daily life and industrial production. The monitoring of power equipment in the power industry is also inseparable from image processing technology. However,...

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
CPCG06N3/08G06V20/41G06V20/46G06V10/751G06N3/045G06F18/22G06F18/23213Y04S10/50
Inventor 杨凤生曾惜王林波王元峰王冕杨金铎王恩伟王宏远刘畅熊萱龙思璇马庭桦兰雯婷陈子敬
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