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

End-to-end 3D-CapsNet flame detection method and end-to-end 3D-CapsNet flame detection device

A flame detection device and flame detection technology, applied in the field of image processing, can solve problems such as low detection efficiency

Active Publication Date: 2020-06-30
HENAN POLYTECHNIC UNIV
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005]Due to the application limitations of the capsule network model itself, if the CapsNet network is directly applied to detect the entire frame of images, the entire frame of images needs to be divided into different regions, Then apply the pre-trained flame detection CapsNet network for different area blocks to detect, the detection efficiency is low, and it cannot meet the requirements for occasions with high real-time requirements

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
  • End-to-end 3D-CapsNet flame detection method and end-to-end 3D-CapsNet flame detection device
  • End-to-end 3D-CapsNet flame detection method and end-to-end 3D-CapsNet flame detection device
  • End-to-end 3D-CapsNet flame detection method and end-to-end 3D-CapsNet flame detection device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Embodiment 1 of the present invention discloses an end-to-end 3D-CapsNet flame detection method, please refer to figure 1 As shown, it includes the following steps:

[0056] S110. Select a flame sample image, and construct a flame sample set; the flame sample set includes a positive sample and a negative sample.

[0057] In order to ensure the diversity and feasibility of the samples, the samples in the flame sample set include positive and negative samples, and the selection of positive samples includes the situations where the flame occurs in daytime, night, cloudy day, sunny day, small fire point and big fire point. Negative samples include images of red areas such as sunset, fire clouds, etc. The flame sample collection is constructed by collecting standard datasets related to flame identification from the web. Construct the sample label value corresponding to the positive and negative samples for the corresponding positive and negative samples, and the label valu...

Embodiment 2

[0079] Embodiment 2 discloses a forest fire online recognition device based on CN and CapsNet, which is the virtual device of the above-mentioned embodiment, please refer to image 3 shown, which includes:

[0080] Selecting module 210, is used for selecting flame sample image, constructs flame sample set; Described flame sample set includes positive sample and negative sample;

[0081] Create module 220, be used to create the initial model of flame detection, described initial model of flame detection comprises two VGG16 networks, depth feature pre-selection layer and partial structure of CapsNet network, the partial structure of described CapsNet network comprises main capsule layer, digital capsule layer And a fully connected layer; the output ends of the two VGG16 networks sequentially output detection results through the depth feature preselection layer and the partial structure of the CapsNet network;

[0082] The first training module 230 is used to train the CapsNet n...

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 an end-to-end 3D-CapsNet flame detection method and device, and the method comprises the following steps: selecting a flame sample image, and constructing a flame sample set; creating a flame detection initial model; training the CapsNet network through the Mnist data set, and migrating main capsule layer parameters, digital capsule layer parameters and full connection layer parameters formed by training the CapsNet network to a main capsule layer, a digital capsule layer and a full connection layer of the flame detection initial model; training the flame detection initial model through the flame sample set to form a final flame detection model; and collecting a target image, respectively inputting the RGB three-channel images of the flame standard image and the target image into the first input end and the second input end of the flame detection model, and outputting a final detection result through the flame detection model. According to the invention, accurate detection of flame is realized.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an end-to-end 3D-CapsNet flame detection method and device. Background technique [0002] Forest fire is one of the factors that seriously affect the ecological environment. The harm it brings to the forest is destructive, and the harm it brings to the environment is also destructive. Once a forest fire occurs, it is very difficult to extinguish it. Therefore, timely warning of forest fires is extremely important. With the advancement of science and technology, the early warning of forest fires has made great progress. [0003] There are many forest fire detection methods, and there are many forest fire detection algorithms based on image recognition. Among them, there are a variety of algorithms based on color space fire detection and recognition algorithms. The color-based fire recognition algorithm cannot get rid of the inherent defects of the color space in the ...

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
CPCG06N3/08G06V20/64G06V20/41G06N3/045G06F18/29G06F18/214Y02A40/28
Inventor 赵运基张楠楠周梦林魏胜强刘晓光孔军伟张新良
Owner HENAN POLYTECHNIC UNIV
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