A liquid level instrument identification method based on a patrol inspection robot

An inspection robot and identification method technology, applied in the field of electric inspection robots, can solve the problems of unstable indication, complex lighting conditions, different shooting angles of inspection robots, etc., and achieve the effect of reducing missed inspections and high position repetition.

Inactive Publication Date: 2019-02-19
NANJING UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most liquid level instruments are located outdoors, with complex lighting conditions and different shooting angles of inspection robots. When traditional image processing methods are used for detection and identification, the detected readings are unstable, and the deviation from the actual readings is also large.

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
  • A liquid level instrument identification method based on a patrol inspection robot
  • A liquid level instrument identification method based on a patrol inspection robot
  • A liquid level instrument identification method based on a patrol inspection robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0011] The solutions of the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0012] Such as figure 1 As shown, the liquid level instrument identification method based on the inspection robot includes the following steps:

[0013] Step 1. Classifier training: Use the instrument image dataset to train the Adaboost classifier, and select an image centered on the instrument as a template image for each inspection point. Since the instrument image data set contains instrument images under different lighting and attitude conditions, any changes in the subsequent instrument detection environment can be accurately extracted.

[0014] Step 2. Instrument area positioning: Obtain the image of the instrument to be inspected at the specified inspection point, combine the Adaboost classifier and the template image for rough positioning and precise positioning, and filter out the dial area. The specific method is:

...

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 liquid level instrument identification method based on a patrol inspection robot, which includes training an Adaboost classifier by utilizing instrument image data set, and selecting an image centered by the instrument as a template image for each patrol inspection point; obtaining the pictures of the instruments to be detected at the designated patrol points, combining the adaboost classifier and template images for rough positioning and accurate positioning, and screening out the dial area; extracting the oil level region from the dial region according to the colordifference between the oil level region and the background region; according to the difference in shape and brightness, extracting the oil level gauge block from the oil level area, and calculating the liquid level gauge representation number according to the upper and lower boundaries of the oil level gauge area and the position of the block. The invention utilizes machine learning, and can detect and identify the liquid level meter representation number under various illumination and attitude changes.

Description

technical field [0001] The invention relates to the field of electric inspection robots, in particular to a method for identifying a liquid level instrument based on an inspection robot. Background technique [0002] The power inspection robot needs to realize basic functions such as autonomous positioning and navigation in the substation, on-site instrument display number recognition, and automatic charging. Among them, detecting the instrument display number of on-site power equipment is the core function of the power inspection robot. Due to cost and historical reasons, most liquid level instruments do not have the remote transmission function of smart instruments, and can only use inspection robots to read instrument indications through computer vision. In order to accurately identify the indication of the liquid level instrument, it is necessary to accurately detect the position of the liquid level instrument in the visual image. Most liquid level instruments are locat...

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): G06K9/20G06K9/34G06K9/40G06K9/62
CPCG06V10/22G06V10/26G06V10/30G06V2201/02G06F18/24
Inventor 李胜黄紫霄郭健吴益飞袁佳泉施佳伟朱禹璇危海明王艳琴王天野
Owner NANJING UNIV OF SCI & TECH
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