Single outdoor color image-based sunny and cloudy weather classification method

A color image, classification method technology, applied in the field of computer vision, can solve the problem of low classification effect, achieve the effect of fast training speed and high tolerance

Active Publication Date: 2017-11-10
YANSHAN UNIV
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The overall classification effect of the method proposed by Zhang Z and Ma H in the article "Multi-class weather classification on single images.International Conference on Image Processing.IEEE,2015:4396-4400" is relatively low

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
  • Single outdoor color image-based sunny and cloudy weather classification method
  • Single outdoor color image-based sunny and cloudy weather classification method
  • Single outdoor color image-based sunny and cloudy weather classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described below in conjunction with accompanying drawing:

[0042] figure 1 It is a flow chart of the method of the present invention, and the method comprises the following steps:

[0043] Step 1. For outdoor color images, extract sky frequency histogram features, shadow energy features and transmittance features, and combine these three features with existing features to form a candidate weather feature set.

[0044] Step 1-1, on the basis of in-depth analysis and research on weather-related features, define the sky frequency histogram feature f sk , shadow energy feature f sh and the introduction of the transmittance feature f t , respectively extract the corresponding features;

[0045] Step 1-1-1, for the sky frequency histogram feature f sk , first apply the sky detection algorithm to detect the sky area of ​​the outdoor color image with the sky area, and then extract the RGB three-channel pixel values ​​for the sky area ...

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 single outdoor color image-based sunny and cloudy weather classification method. The method comprises the steps of for an outdoor color image, firstly extracting a sky frequency histogram feature, a shadow energy feature and a transmissivity feature of the outdoor color image, and combining the three features with existing weather features to form candidate weather feature sets; calculating the importance of features in the candidate weather feature sets according to a Fisher-Random Forest feature importance calculation method, and performing feature selection; and inputting the weather features after the feature selection to a trained random forest classifier in a vector form, and finally realizing sunny and cloudy weather classification of the outdoor color image. The outdoor color image used in the method does not need to be collected by a specific image collection device; and the method is suitable for outdoor color images in different scenes and has the advantages of high training speed, capability of processing high-dimensional data, high noise tolerance and the like.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a method for classifying sunny and cloudy weather based on a single outdoor color image. Background technique [0002] Weather classification has always been one of the important and difficult topics in the fields of weather forecasting, disaster warning, video surveillance, autonomous driving, scene understanding, and image restoration, and has attracted extensive attention from scholars. [0003] Existing weather classification algorithms are mainly implemented based on the following three types of information: historical weather data, outdoor video and single outdoor color image. In recent years, weather classification research is usually based on a single outdoor color image. The main reason is that weather classification based on historical weather data involves the collection and processing of past historical data, which has too many limitations. The essence of weather classi...

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): G06K9/00G06K9/46G06K9/62
CPCG06V20/13G06V10/40G06F18/241
Inventor 张世辉杜雪哲
Owner YANSHAN UNIV
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