Video smoke detection and recognition method based on transfer learning

A technology of transfer learning and recognition methods, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as low scalability and high false alarm rate, and achieve reduced training difficulty, high precision, and reduced overfitting risks Effect

Inactive Publication Date: 2019-07-05
ZHEJIANG UNIV OF TECH
View PDF6 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the shortcomings of low expansibility and high false alarm rate of existing video smoke recognition methods, the present invention proposes a video smoke recognition and detection method based on migration learning with strong generalization ability and high precision, using the improved Faster R- The CNN neural network identifies and locates the smoke area in the video, and at the same time uses transfer learning technology to reduce the training difficulty of the deep neural network. location in the area

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
  • Video smoke detection and recognition method based on transfer learning
  • Video smoke detection and recognition method based on transfer learning
  • Video smoke detection and recognition method based on transfer learning

Examples

Experimental program
Comparison scheme
Effect test

example

[0059] Example: The smoke image datasets used in this case are all three-channel RGB images containing smoke areas. The data sources include experimental shooting collection, Internet collection, and simulation generation, with a total of 3000 samples. Among them, 1680 samples are randomly selected as the training set, 420 samples are used as the verification set, and 900 samples are used as the test set. Because the RPN layer in the Faster R-CNN network can automatically generate candidate regions, and mark positive and negative samples according to the label information, and input them into the network for training, the setting of positive and negative samples does not require manual intervention. The following section specifically introduces the process of model construction, training and testing.

[0060] Step 1, build an improved Faster R-CNN neural network, the specific structure is as follows figure 2 shown.

[0061] Step 1.1: The sample is input into the network aft...

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 video smoke identification detection method based on transfer learning. The method comprises the steps of generating analog data to enlarge the number of smoke image samples;preprocessing the image data set; constructing a target detection network; using an ImageNet image dataset to pre-training an improved VGG-16 network; training a target detection network on the labeled smoke data set by adopting a transfer learning mode, wherein the feature extraction network part uses improved VGG-16 network pre-training weights to perform feature initialization; and extractinga key frame from the video, inputting the key frame into the model for identification and detection, and if smoke is found, returning coordinate information and positioning an area thereof in the video image. Model performance under the condition of limited smoke data is improved by using a transfer learning technology, and a smoke area in a video image can be automatically identified and positioned.

Description

technical field [0001] The present invention relates to the field of image analysis and recognition and the field of machine learning, in particular to a video smoke recognition method, which belongs to the field of image target detection based on deep learning. Background technique [0002] As a common disaster, fire has the characteristics of rapid spread, large losses, and difficulty in fighting. In 2016, a total of 312,000 fires were reported across the country, causing more than 2,600 casualties and direct property losses of 3.72 billion yuan. Especially forest fire, which occurs in an open and complex space environment like a forest, burns, spreads and expands freely. Once it occurs, it will cause huge losses and serious harm to forest resources, ecosystems and human life. The so-called no smoke does not cause fire. Smoke, as a visible mixture produced during the combustion of substances, is often produced before the open flame is observed. It is an important visual f...

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): G06K9/00G06K9/40G06K9/44G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/47G06V20/52G06V10/34G06V10/30G06N3/044G06N3/045G06F18/241G06F18/253G06F18/214
Inventor 郝鹏翼徐震宇高翔李芝禾吴福理白琮
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products