Thermal imaging temperature diagram reading method and device, electronic equipment and storage medium

A technology of temperature map and thermal imaging, which is applied in the field of metallurgy, can solve problems such as thermal image temperature map readings that cannot meet the metallurgical process, affect accurate temperature collection, and font edges are blurred, so as to improve input efficiency and reduce input costs.

Pending Publication Date: 2021-06-18
开放智能机器(上海)有限公司
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in the field of metallurgy, due to the limitations of the infrared camera itself, the traditional OCR recognition process will cause the edges of the recognized fonts to be blurred, which will affect the accurate acquisition of temperature, so it cannot meet the readings of the thermal imaging temperature map of the metallurgical process.

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
  • Thermal imaging temperature diagram reading method and device, electronic equipment and storage medium
  • Thermal imaging temperature diagram reading method and device, electronic equipment and storage medium
  • Thermal imaging temperature diagram reading method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as figure 1 As shown, this embodiment provides a method for reading a thermal imaging temperature map, including:

[0057] The S100 uses the text detection model trained by the PSEnet algorithm to locate the text image of the current thermal imaging temperature map.

[0058]Specifically, due to the limitations of the infrared camera itself, the traditional OCR recognition process will cause the edges of the recognized fonts to be blurred, which will affect the accurate acquisition of temperature, so it cannot meet the readings of the thermal imaging temperature map of the metallurgical process.

[0059] This embodiment is mainly aimed at recognizing the temperature readings of the thermal image in the OCR recognition scene, which is used in the metallurgical process, and the readings of the temperature sensors on the ladle are recognized by this method. The ladle is provided with a temperature sensor for displaying temperature readings. In this method, an infrare...

Embodiment 2

[0072] Based on the above-mentioned embodiment, in this embodiment, the parts that are the same as those in the above-mentioned embodiment will not be described one by one. This embodiment provides a method for reading a thermal imaging temperature map, which specifically includes:

[0073] The text detection model trained by the PSEnet algorithm described in step S100 locates the text image of the current thermal imaging temperature map, including:

[0074] The background area and the text image of the current thermal imaging temperature map are segmented by the text detection model.

[0075] Exemplary, such as image 3 As shown, there are two main reasons for applying this text detection algorithm:

[0076] The background of the thermal imaging temperature map is relatively complex, and areas with higher temperatures will be affected by highlights, resulting in false detection of text areas. The PSEnet algorithm is a pixel-level text segmentation, which can accurately segm...

Embodiment 3

[0120] The present invention also provides a reading device for a thermographic temperature map, such as Figure 10 shown, including:

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 belongs to the field of metallurgy, and discloses a thermal imaging temperature map reading method and device, electronic equipment and a storage medium, and the method comprises the steps: positioning a text image of a current thermal imaging temperature map through a text detection model trained by a PSEnet algorithm; identifying a tag sequence in the text image through a text identification model trained by a CRNN + CTC algorithm; and on the basis of the label sequence of the text image, utilizing an NLP text classification model obtained by training through a TextCNN algorithm to obtain characters and character box positions of the current thermal imaging temperature map. According to the invention, the temperature of the imaging picture can be accurately and automatically identified, and related information is recorded, so that the recording efficiency of the temperature of the imaging picture is greatly improved, and the recording cost is reduced.

Description

technical field [0001] The invention relates to the field of metallurgy, in particular to a reading method, device, electronic equipment and storage medium for a thermographic temperature map. Background technique [0002] At present, the OCR recognition algorithm has gradually reached a mature stage, and the OCR recognition technology has gradually landed in various scenarios, such as ID card recognition, bank card recognition, driver's license recognition, etc. The demand for temperature identification of imaging images has gradually emerged in the market, and it is becoming more and more a future trend to use automatic identification of thermal imaging temperature methods to replace manual input. [0003] However, in the field of metallurgy, due to the limitations of the infrared camera itself, the traditional OCR recognition process will cause the edges of the recognized fonts to be blurred, which will affect the accurate acquisition of temperature, so it cannot meet the...

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): G06K9/34G06F16/35G06K9/20G06N3/04G06N3/08G06T7/194
CPCG06T7/194G06F16/35G06N3/08G06T2207/10004G06V10/225G06V30/153G06N3/045
Inventor 王普黄明飞姚宏贵
Owner 开放智能机器(上海)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