Unlock instant, AI-driven research and patent intelligence for your innovation.

Fire detection method and system based on color edge depth perception

A technology of depth perception and color edge, applied to instruments, biological neural network models, character and pattern recognition, etc., can solve the problems of limited mobile devices embedded in network models, large network models, and low monitoring efficiency, and achieve simplified fire detection model, improve accuracy, and reduce the effect of model calculation

Pending Publication Date: 2022-07-08
中山大学深圳 +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a fire detection method and system based on color edge depth perception to solve the problem that the existing fire detection method has a large amount of calculation and low monitoring efficiency, resulting in a large network model built and mobile devices embedded in the network model being affected. limited technical issues

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 detection method and system based on color edge depth perception
  • Fire detection method and system based on color edge depth perception
  • Fire detection method and system based on color edge depth perception

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Please refer to figure 1 , a fire detection method based on color edge depth perception provided by an embodiment of the present invention, comprising:

[0057] Step S1: Acquire the to-be-recognized image, and input the to-be-recognized image into the fire detection model, so that the fire detection model performs feature extraction on the to-be-recognized image to obtain a first color feature map and a first edge feature map of the to-be-recognized image.

[0058] Further, step S1 specifically includes steps S11 to S17, and each step is as follows:

[0059] Step S11: Acquire the image to be recognized, and input the image to be recognized into the fire detection model.

[0060] Among them, the fire detection model is a two-stage feature extraction architecture. The two-stage feature extraction architecture includes an explicit feature extraction stage and an implicit feature extraction stage. The explicit feature extraction stage is used for color feature extraction a...

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 detection method and system based on color edge depth perception, and the method comprises the steps: obtaining a to-be-recognized image, inputting the to-be-recognized image to a fire detection model, enabling the fire detection model to carry out the feature extraction of the to-be-recognized image, and obtaining a to-be-recognized image; and obtaining a first color feature map and a first edge feature map of the to-be-recognized image, performing implicit feature extraction on a first feature map formed by combining the first color feature map and the first edge feature map, and then outputting a fire detection result according to an implicit feature extraction result. The fire detection model disclosed by the invention is a two-stage feature extraction architecture, comprises an explicit feature extraction stage and an implicit feature extraction stage, and realizes feature extraction of image colors, edges, spatial details and depths. Meanwhile, by optimizing the internal architecture of the fire detection model, the model is further simplified, the calculation amount of the model is reduced, and the processing speed and accuracy of the model are improved.

Description

technical field [0001] The invention relates to the field of fire detection, in particular to a fire detection method and system based on color edge depth perception. Background technique [0002] Fires caused by uncontrolled combustion in time or space are often accompanied by severe property damage and personal injury. According to the statistical analysis of relevant data from the Fire and Rescue Bureau of the Ministry of Emergency Management of China, the proportion of fires in rural areas is relatively large, the probability of fires is relatively high, and the proportion of people killed on the spot is high. At the same time, residential fires are the main cause of fire deaths. The challenges are severe; in addition, the gathering of people in industrial and entertainment places, the concentration of production and operation facilities, the large load of electricity, oil and gas, and the accumulation of finished raw materials, once a fire occurs, it is easy to spread a...

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): G06V10/44G06V10/56G06V10/74G06K9/62G06N3/04
CPCG06N3/045G06F18/22
Inventor 陈俊周王坚成蒲佳俊谭光
Owner 中山大学深圳