Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image-based air quality grade evaluation method

An air quality level and image technology, applied in the field of image processing technology, can solve the problems of limited image collection location and poor applicability.

Inactive Publication Date: 2020-04-28
HARBIN UNIV OF SCI & TECH
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the limitations of the selected features and machine learning methods, the methods proposed so far have shortcomings such as poor applicability or limited image acquisition locations.

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
  • Image-based air quality grade evaluation method
  • Image-based air quality grade evaluation method
  • Image-based air quality grade evaluation method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0025] Specific implementation methods: such as figure 1 As shown, the image-based air quality level assessment method described in this embodiment includes the following steps:

[0026] Step 1. Since there is no public image library for the research on image-based assessment of air quality levels, we selected 100 images with air quality level labels and related pollutant information from the Internet, and used these images as the model building Air Quality Image Library.

[0027] Step 2. Since the HSI space is more in line with the visual characteristics of the human eye, and its component correlation is much smaller than that of the RGB space, we first transfer the images in the air quality image library from the RGB space to the HSI space. The conversion formula is as follows:

[0028]

[0029]

[0030]

[0031]

[0032] Then the images of different air quality levels are explored and analyzed in the HSI space.

[0033] Step 3. From step 2, we can see that in ...

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 an image-based air quality grade evaluation method, and relates to a machine learning related technology, in particular to an image processing technology. The objective of theinvention is to solve the problems of high air quality detection cost and incapability of covering each corner in a city in the prior art. The method comprises the following steps: firstly, performingHSI space conversion on an image; performing DCT transformation on the saturation channel S and the brightness channel I of the image, converting the saturation channel S and the brightness channel Iinto a frequency domain, finally, the edge pixel ratio, the high-brightness pixel ratio, the low-saturation pixel ratio and the low-frequency pixel ratio of the image are extracted to serve as features, the features are input into an SVM to be classified, and therefore an evaluation model of the air quality grade is constructed. The air quality grade evaluation model constructed by the method canaccurately estimate the air quality condition of an image acquisition place, air quality detection becomes low in cost and fine in granularity, and people can conveniently monitor the surrounding airpollution condition anytime and anywhere. And the method is more suitable for evaluating the image with moderate air humidity, rich image content and sky area proportion less than 1 / 2.

Description

technical field [0001] An image-based air quality level assessment method involves machine learning related technologies, especially image processing technology. Background technique [0002] In recent years, with the continuous advancement of my country's industrialization process and the rapid development of the country's economy, environmental pollution has also continued to intensify, and most cities have experienced different levels of pollution. Air pollution not only affects traffic and living in daily life, but also endangers our health. Therefore, daily monitoring and control of air pollution is very important. At present, the method of obtaining air quality in my country is mainly to detect and calculate the concentration of pollutants through various sophisticated instruments in monitoring stations set up in cities, and then convert it into air quality grades or indexes, and finally publish it to the Meteorological Bureau for people to inquire. However, the cost ...

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): G06K9/62G06K9/46
CPCG06V10/44G06V10/462G06F18/2411
Inventor 于天河葛宝中
Owner HARBIN UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products