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

Smoke detection method based on deep learning

A deep learning and detection method technology, applied in the field of smoke detection based on deep learning, can solve the problems of smoke detection false positives, failure to detect and respond in time, and limited shooting angles, so as to reduce the false alarm rate and improve real-time detection. Effect on Response Rate

Pending Publication Date: 2021-12-31
的卢技术有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in outdoor scenes, due to the limited shooting angle, smoke detection still has false positives and false positives and fails to detect and respond in time

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 method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] Such as figure 1 As shown, a smoke detection method based on deep learning includes the following steps:

[0031] (1) Collect the original image data set;

[0032] (2) Preprocessing the image;

[0033] (3) image input into the convolutional neural network model for training;

[0034] (4) Apply the model in the actual scene for smoke detection;

[0035] (5) Output the detection result and save the detected smoke image.

[0036] Described step (1) is specifically:

[0037] (1.1) Use smoke sheets to conduct a cigarette lighting experiment in the scene to be detected;

[0038] (1.2) Obtain the smoke image and the non-smog image under the scene when the smoke is generated under the scene;

[0039] (1.3) Smoke and non-smoke images are saved in bmp format.

[0040] Described step (2) is specifically:

[0041] (2.1) Convert the image format from bmp to png;

[0042] (2.2) Classify and preprocess the image, change the size and resolution of the image to meet the input r...

Embodiment 2

[0051] A computer storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned smoke detection method based on deep learning is realized.

Embodiment 3

[0053] A computer device includes a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the computer program, the above-mentioned smoke detection method based on deep learning is realized.

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 detection method based on deep learning. The method comprises the following steps: (1) collecting an original image data set; (2) preprocessing the image; (3) inputting the image into a convolutional neural network model for training; (4) applying the model in an actual scene, and performing smoke detection; and (5) outputting a detection result, and storing a detected smoke image. According to the method, different types of smoke generated in a large scene can be effectively identified, the false alarm rate caused by non-smoke objects in the scene is reduced, an experiment is performed in combination with an actual scene, and the smoke detection rate and the real-time response rate in the scene are effectively improved.

Description

technical field [0001] The invention relates to smoke detection, in particular to a smoke detection method based on deep learning. Background technique [0002] Once a fire occurs, it will bring serious loss of life and property to the society. Smoke is an early sign of fire, and timely, effective and accurate detection of smoke is of great significance for fire prevention and disaster relief. At present, most indoor and outdoor sensors are used to detect and warn smoke particles. Due to the diffusivity of smoke, when smoke is detected, the smoke has already diffused, and real-time detection and warning cannot be performed. The main task of smoke detection is to detect the smoke in time and accurately at the first time when the smoke is generated, locate it, respond in time and issue an early warning, so as to avoid the occurrence of fire and reduce losses. From the traditional sensor detection of smoke to the analysis of each frame of image based on image and video input,...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 卫玉蓉
Owner 的卢技术有限公司
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