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

Flame detection method and system based on BiHR-Net and YOLOv3-head

A flame detection and flame technology, which is applied in the field of image processing and fire prevention, can solve the problems that the detection speed needs to be further improved, and achieve the effects of wide application value, improved accuracy and good robustness

Pending Publication Date: 2021-12-03
HUAIYIN INSTITUTE OF TECHNOLOGY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The method based on deep learning is better than other methods in generalization, but the detection speed still needs to be further improved

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 detection method and system based on BiHR-Net and YOLOv3-head
  • Flame detection method and system based on BiHR-Net and YOLOv3-head
  • Flame detection method and system based on BiHR-Net and YOLOv3-head

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0041] A large number of variables are involved in this embodiment, each variable is described as follows, as shown in Table 1.

[0042] Table 1 variable description table

[0043]

[0044]

[0045]

[0046] A light-weight flame detection flame detection method proposed by the present invention, firstly, construct a flame detection model, the backbone network in the model uses two times of downsampling to obtain a feature map of a quarter of the size of the input image, to reduce subsequent The amount of parameters for convolution; then a feature extraction and feature fusion method BiHR-Net is proposed, which performs two convolutions on the input feature map, performs upsampling and downsampling to generate two sub-routes to obtain additional Features, and integrate the features of the three scales at the end of BiHR-Net to achieve the purpose of im...

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 detection method and system based on BiHR-Net and YOLOv3-head, and the method comprises the steps: firstly, constructing a flame detection model, enabling a backbone network in the model to obtain the small-resolution features of an input image in a two-time down-sampling manner, and reducing the parameter quantity of the detection model; then, providing a feature extraction and feature fusion method BiHR-Net, carrying out up-sampling and down-sampling on a feature map obtained by carrying out two times of convolution on an input feature map to generate two sub-routes to obtain additional features, and fusing features of three scales at the last of the BiHR-Net to achieve the purpose of improving the detection effect; inputting the features obtained by the BiHR-Net into a YOLO-head network for prediction and regression; and finally, training the flame detection model by using the data set to obtain a detector for flame detection. The flame detection speed reaches 112 frame / s, the flame can be rapidly detected and early warned, and the model has good robustness.

Description

technical field [0001] The invention belongs to the technical field of image processing and fire prevention, and in particular relates to a flame detection method and system based on BiHR-Net and YOLOv3-head. Background technique [0002] The occurrence of fires will threaten human life and safety. For example, since September 2019, Australian forest fires have burned an area of ​​11.2 million hectares, with 34 casualties and about 3 billion animals killed or displaced. On March 30, 2020, a forest fire broke out in Jingjiu Township, Xichang City, Liangshan Prefecture, Sichuan Province, killing 19 fire fighters. How to prevent fires or find out as early as possible when there are hidden fires is a problem that we have to solve all the time. [0003] In recent years, flame detection methods are mainly divided into: [0004] 1) A detection method based on flame features, using manually extracted flame features to identify flames. For example: Wu et al. (2018) combined static...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/253Y02P90/30
Inventor 高尚兵陈浩霖邱千禧张莹莹郭舒心张秦涛于永涛相林王媛媛李翔
Owner HUAIYIN INSTITUTE OF TECHNOLOGY