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

Deep learning-based smoke and fire identification model establishment method and smoke and fire identification method

A recognition model and deep learning technology, applied in the field of image processing, can solve problems such as indistinct features, abstract and non-specific pyrotechnic features, etc.

Pending Publication Date: 2020-10-23
SHANDONG SYNTHESIS ELECTRONICS TECH
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a pyrotechnic recognition model establishment method and a pyrotechnic recognition method based on deep learning, which are used to solve the problems of abstract pyrotechnic features, diverse shapes, and inconspicuous and unspecific features in traditional pyrotechnic recognition methods, and at the same time solve In actual application scenarios, there are few or no pyrotechnic image data

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
  • Deep learning-based smoke and fire identification model establishment method and smoke and fire identification method
  • Deep learning-based smoke and fire identification model establishment method and smoke and fire identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] This embodiment discloses a method for establishing a firework recognition model based on deep learning, such as figure 1 shown, including the following steps:

[0035] S01), image collection, the collected images include two types, one is fireworks pictures, and the other is normal pictures of the area to be detected, and the normal pictures are used as background images;

[0036] S02), gan network synthesis, using gan network synthesis technology to synthesize two types of pictures to generate a synthetic picture with a normal picture as the background, to increase the number of samples of the data set in the actual application scene;

[0037] S03), image labeling, during the image labeling process, compare whether the proportion of fireworks in the labeling frame exceeds 1 / 2, if yes, go to step S04, if not, go to step S05;

[0038] S04), directly mark the pyrotechnics;

[0039] S05), carry out pyrotechnics relabeling, divide the pyrotechnics part, and ensure that t...

Embodiment 2

[0044] This embodiment discloses a pyrotechnic recognition method based on deep learning. This method is based on the pyrotechnic recognition model established in Embodiment 1. After the pyrotechnic recognition model is imported into the detection system, as figure 2 shown, perform the following steps:

[0045] S21), start normal line inspection, and the camera performs line inspection along with the gimbal;

[0046] S22), detecting the images in the process of line inspection, giving an early warning when a target with a confidence degree greater than the threshold T1 is found, and judging the number of current early warning targets;

[0047] S23), record the current position of the pan / tilt and the focal length of the camera, for subsequent return of the pan / tilt and the camera to the initial position;

[0048] S24), start early warning detection from the point with the highest confidence;

[0049] S25), transfer the abscissa and ordinate in the image to the bottom platform...

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 smoke and fire identification model establishing method based on deep learning and a smoke and fire identification method. According to the smoke and fire identification model establishing method, a can network is used for synthesizing a smoke and fire picture and a normal picture of a to-be-detected area, the number of samples of a data set in an actual application scenecan be increased, and then the to-be-established smoke and fire identification model is obtained through yolov3 labeling, training and verification. According to the method, the problems of abstractsmoke and fire characteristics, diverse shapes and unobvious and unspecific characteristics in a traditional smoke and fire identification method can be solved, and meanwhile, the situation that smokeand fire image data is small or does not exist in an actual application scene is solved. The smoke and fire identification method is based on the established smoke and fire identification model, andthe misjudgment problem generated in large-scale scene long-distance image identification is solved.

Description

technical field [0001] The invention relates to the field of image processing methods, in particular to a deep learning-based method for establishing a firework recognition model and a firework recognition method. Background technique [0002] With the development of society, people's awareness of disaster prevention in advance is constantly improving, and the demand is gradually increasing. For example, fire prevention is what we need. Whether the fire can be protected in advance at the initial stage of the fire is very important to the safety of life and property. However, the difficulty of pyrotechnics recognition lies in the abstract features, various shapes, and unobvious features, and there are few samples in the actual scene, and it is not easy to obtain. And it is easy to cause misjudgment in long-distance image recognition of large scenes [0003] Patent CN 110728284 A "A Fireworks Recognition Method Based on Edge Computing and Intelligent Terminal Based on Deep ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/52G06N3/045G06F18/241
Inventor 于鹏刘辰飞郭学英席道亮高朋刘明顺
Owner SHANDONG SYNTHESIS ELECTRONICS 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com