Smog detection method and device based on video image

A video image, fireworks detection technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of easy false detection, slow running speed, etc., to reduce the false alarm rate, reduce the amount of calculation, and ensure detection. rate effect

Inactive Publication Date: 2018-01-26
清华大学苏州汽车研究院(吴江)
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the general image-based firework detection method needs to traverse the entir

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
  • Smog detection method and device based on video image
  • Smog detection method and device based on video image
  • Smog detection method and device based on video image

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0034] Examples:

[0035] The preferred embodiments of the present invention will be further described with reference to the accompanying drawings.

[0036] Such as figure 1 As shown, a firework detection method based on video images includes the following steps:

[0037] Step 1: Obtain the surveillance image from the surveillance camera and use the Gaussian mixture model to build the background;

[0038]

[0039]

[0040] τ i,t =δ i,t 2 I

[0041] Where K is the total number of distribution models, x t Is the value of the sampling pixel of the current image, p(x t ) Is the probability of obtaining the current pixel value, η(x t ,μ i,t ,τ i,t ) Is the i-th Gaussian distribution at time t, μ i,t Is its mean value, τ i,t Is its covariance matrix, δ i,t Is the variance, I is the three-dimensional identity matrix, w i,t Is the weight of the i-th Gaussian distribution at time t.

[0042] Step 2: Subtract the current frame image from the background obtained in step 1 to obtain a foregr...

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 smog detection method based on a video image. The method comprises steps that a Gaussian hybrid model is utilized to construct the background for a video image; the present image subtracts the acquired background to acquire a foreground image; a dark channel image of the present image is calculated; and operation of the acquired foreground binary image and the acquired dark channel binary image is carried out; contour search of the acquired binary image is carried out, the present contour is compared with a previous contour, if the contour of the fixed position expands, the contour is a suspected smog contour; if the suspected smog contour is detected at similar positions of the continuous set images, the contour is the suspected smog area, sliding window detection on the area is carried out, if a window surpassing a certain threshold is identified by a smog classifier to be smog, and the area is a smog area. The method is advantaged in that the Gaussian hybrid model is utilized to construct the background and extract the foreground, the smog dark channel characteristics are further utilized, interference of other factors is reduced, and the false report rate is further reduced.

Description

technical field [0001] The invention belongs to the technical field of image processing and recognition, and in particular relates to a smoke detection method and device based on video image-based motion region detection combined with a dark channel. Background technique [0002] In modern intelligent transportation systems, surveillance cameras have been widely used in urban roads, intersections and road sections of expressways. Scenario analysis based on surveillance video has become an indispensable module of intelligent transportation systems, and with the continuous advancement of technology, video-based scenario analysis has developed from a single analysis of running a red light to detection of various violations and even some special scenarios. Such as fire and smoke caused by traffic accidents. The burning of vehicles caused by traffic accidents, etc. or the impact of burning on traffic safety is very huge. [0003] The video-based smoke and fire detection technol...

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): G06K9/00G06K9/38G06K9/46G06K9/62
Inventor 黄晟顾会建
Owner 清华大学苏州汽车研究院(吴江)
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