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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


