Supercharge Your Innovation With Domain-Expert AI Agents!

Smoke detection application-oriented preprocessing method

An image preprocessing and smoke technology, applied in the field of computer vision, can solve problems such as contrast reduction and image blur, and achieve the effect of improving the accuracy rate and detection efficiency

Active Publication Date: 2018-05-04
DALIAN UNIV OF TECH
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The preprocessing operation of the present invention mainly solves three types of problems: 1. According to the analysis, in the detection process, the main factors affecting the image quality are blurred images and decreased contrast caused by haze weather

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
  • Smoke detection application-oriented preprocessing method
  • Smoke detection application-oriented preprocessing method
  • Smoke detection application-oriented preprocessing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention is based on opencv2.4.9, by intercepting the frame image in the monitoring video in real time, performing preprocessing operation on the intercepted image, and then sending it back to the smoke detection program for smoke detection. The preprocessing operation is divided into three steps, as follows:

[0021] The first step is to classify the input image. The purpose is to be divided into three categories: no fog, light fog and dense fog.

[0022] The images used in this step are divided into two categories: one is the input image to be classified, and the other is the training image used to train the model.

[0023] step1: Extract four features from the training image: S mean , S rate , T mean , T rate .

[0024] where S mean , S rate is extracted from the semi-inverse image of the training image.

[0025] Get the semi-inverse of the training images

[0026]

[0027] where c represents the channel value, c∈{r,g,b}. x is the pixel l...

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 technical field of computer vision, and provides a smoke detection application-oriented preprocessing method. The method comprises three steps of: pre-classifying input images into foggy images, light-fog images and fogless images; carrying out a defogging enhancement operation on the light-fog images according to brightness information; and carrying out a sky segmentation operation on the defogged images and the light-fog images to remove sky areas. According to the method, smoke detection is carried out on preprocessed images, so that the correctness and detection efficiency are improved.

Description

technical field [0001] The invention belongs to the technical field of computer vision and relates to a preprocessing method for smoke detection applications. Background technique [0002] With the frequent reporting of smog in major cities in China in recent years, the control of air pollution is imminent. Air pollution control involves all aspects from prevention to purification. Starting from the direction of air pollution prevention, by distributing cameras widely in rural fields, collecting field status information in real time, and automatically detecting the collected images and locating smoke targets through the smoke detection system, and monitoring and alarming the phenomenon of straw burning in rural areas, it can achieve The purpose of reducing pollution sources. Based on the straw burning smoke detection project, the present invention preprocesses the monitoring video, including three processes of fog map classification, fog removal operation, and sky segmenta...

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): G06K9/00G06K9/62G06K9/36
CPCG06V20/41G06V10/20G06F18/2411G06F18/214
Inventor 王智慧张宏李建军李豪杰罗钟铉
Owner DALIAN UNIV OF TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com