Flame recognition method and device based on video quality evaluation, equipment and storage medium

A technology for flame recognition and video quality, applied in character and pattern recognition, image data processing, instruments, etc., can solve problems such as low accuracy rate and increased calculation amount, and achieve the effect of improving accuracy rate and speed

Inactive Publication Date: 2019-09-24
JINAN UNIVERSITY +2
View PDF0 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0013] In order to overcome the defects of low accuracy or increase the amount of calculation in the fire detection and recognition b

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
  • Flame recognition method and device based on video quality evaluation, equipment and storage medium
  • Flame recognition method and device based on video quality evaluation, equipment and storage medium
  • Flame recognition method and device based on video quality evaluation, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] Please refer to figure 1 Shown, a flame recognition method based on video quality assessment, which includes the following steps:

[0071] 110. Real-time acquisition of video images of the fire monitoring scene.

[0072] The fire monitoring site is monitored by a camera or video camera, and images of the video of the fire monitoring site can be obtained in real time. The camera or the video images collected by the camera are transmitted to the data processing system through the network (wireless network or wired network) to perform the operations of steps 120-170.

[0073] 120. Calculate blur and color shift of the image.

[0074] 120.1. Calculate the blurriness of the image.

[0075] Please refer to the attached figure 2 , the improved no-reference image sharpness algorithm of the present invention comprises the following steps:

[0076] (1) F represents the image to be tested, with a size of m×n pixels, and the reference image B is obtained by blurring F.

[00...

Embodiment 2

[0191] Embodiment 2 discloses a flame recognition device based on video quality assessment corresponding to the above embodiment, which is the virtual device structure of the above embodiment, please refer to Figure 4 shown, including:

[0192] Image acquisition module 210: for acquiring video images;

[0193] Image evaluation module 220: used to calculate the degree of blur and color cast of the image;

[0194] Suspected flame segmentation module 230: used to segment suspected flame regions from the image;

[0195] Flame discrimination feature screening module 240: used to screen out image features with an accuracy rate above the screening threshold as flame discriminant features according to the fuzziness and color cast, and compare the feature accuracy rate reference table, and record the feature accuracy rate reference table The accuracy rate of distinguishing the flame from each image feature under different blur and color cast;

[0196] Flame identification feature m...

Embodiment 3

[0200] Figure 5 A schematic structural diagram of an electronic device provided in Embodiment 3 of the present invention, such as Figure 5 As shown, the electronic device includes a processor 310, a memory 320, an input device 330, and an output device 340; the number of processors 310 in a computer device may be one or more, Figure 5 Take a processor 310 as an example; the processor 310, memory 320, input device 330 and output device 340 in the electronic device can be connected by bus or other methods, Figure 5 Take connection via bus as an example.

[0201] The memory 320, as a computer-readable storage medium, can be used to store software programs, computer-executable programs and modules, such as program instructions / modules corresponding to the flame recognition method based on video quality assessment in the embodiment of the present invention (for example, based on video Image acquisition module 210, image evaluation module 220, suspected flame segmentation modu...

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 flame recognition method based on video quality evaluation. The method comprises the following steps: obtaining an image of a video; calculating the ambiguity and the color cast degree of the image; segmenting a suspected flame area from the image; according to the ambiguity and the color cast degree, screening out image features with the accuracy higher than a screening threshold value as flame discrimination features by comparing with a feature accuracy reference table; extracting the discrimination characteristics of the suspected flame area, judging whether the discrimination characteristics are flame characteristics or not, and if the discrimination characteristics are flame characteristics, marking the discrimination characteristics as flame recognition characteristics; according to the ambiguity and the color cast degree, determining the weight of the flame recognition feature by comparing with a feature weight reference table; summing the weights of the flame recognition characteristics to obtain a comprehensive recognition value, and judging whether the suspected flame region is a flame region or not according to the size of the comprehensive recognition value. According to the invention, the flame discrimination speed and accuracy are improved.

Description

technical field [0001] The invention relates to the field of fire safety, in particular to a flame identification method, device, electronic equipment and storage medium based on video quality assessment. Background technique [0002] At present, fire detectors on the market are mainly divided into two categories: traditional type and image type. [0003] Traditional fire detectors judge whether there is a fire by detecting temperature, smoke, etc., but the scope of use is relatively limited, and it is impossible to observe the scene intuitively. [0004] The image type fire detector realizes the detection of fire through the recognition of video images, and has a wide range of applications. It can make more accurate judgments on real-time fire conditions through video observation. [0005] Due to the advantages of image-based fire detectors over traditional fire detectors, research on image-based fire detection methods has been increasing in recent years. The realization o...

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): G06K9/00G06T7/00G06T7/11
CPCG06T7/0002G06T7/11G06T2207/30168G06V20/00
Inventor 郭江凌廖春生孟令昀李景陈峰
Owner JINAN UNIVERSITY
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