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

Fire behavior recognition method and system based on deep learning

A technology of deep learning and identification methods, applied in the field of fire identification, can solve the problems of high layout cost, inaccurate identification results, and large use limitations, and achieve the effect of low layout cost, wide application range, and improved accuracy.

Pending Publication Date: 2020-09-08
北京思湃德信息技术有限公司
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a fire recognition method and system based on deep learning to solve the problems of the above-mentioned existing fire recognition methods and systems with large limitations, high layout costs and inaccurate recognition results

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
  • Fire behavior recognition method and system based on deep learning
  • Fire behavior recognition method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] The present embodiment provides a fire identification method based on deep learning, the method includes the following steps:

[0051] S1. Use the acquisition equipment to collect fire image samples, mark the smoke and flame information in the image samples to obtain training samples, and then use the computer to train the training samples to establish a neural network model and perform reasoning and identification on real-time visible light video. Whether the smoke and / or flames in the visible light video meet the fire standard;

[0052] S2. Use a computer to build a convolutional neural network to extract the image features of the smoke and flame information in a single picture, and then use a computer to build a recurrent neural network to extract the image features of the smoke and flame information in the multi-picture time series of the video , and finally use the fully connected neural network to infer and identify the image features of a single picture and the t...

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 fire behavior recognition method and system based on deep learning. Deep learning technology, existing fire behavior images are analyzed and trained; obtaining neural networkmodel, fire recognition is performed on images acquired by a visible light real-time video, single-frame image features and multi-frame image time sequence features are combined, weather and geographic data information is combined, fire judgment, influence analysis and prevention and control assistance are comprehensively performed, the influence of environmental factors on an recognition resultis avoided, and the recognition accuracy is greatly improved.

Description

technical field [0001] The invention relates to the field of fire recognition, in particular to a fire recognition method and system based on deep learning. Background technique [0002] In the fire safety system, image recognition technology is often used for fire identification. The principle of using image recognition technology for fire identification is generally as follows: 1. Target segmentation, which is mainly used to find the position where fire may exist in the digital image, through edge detection, 2. Feature extraction, which is mainly used to extract the visual features of pyrotechnic targets, such as color, shape, texture, spatial relationship, etc.; The similarity between the feature and the prior feature of the target object. [0003] At present, the existing fire identification system, such as the infrared video fire identification system disclosed in the patent document CN201120213456.8, uses infrared thermal imaging technology for fire identification, bu...

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
CPCG06N3/049G06N3/08G06V20/52G06N3/045G06F18/241
Inventor 谭肇
Owner 北京思湃德信息技术有限公司
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