3.8 Proceedings Paper

Flame and Smoke Detection in Substation Based on Wavelet Analysis and Convolution Neural Network

Publisher

ASSOC COMPUTING MACHINERY
DOI: 10.1145/3319921.3319962

Keywords

fire detection; substation; smoke detection; color characteristics

Funding

  1. technology project of State Grid Corporation of China

Ask authors/readers for more resources

In this paper, a fire detection method based on color features, wavelet analysis, and convolution neural network is proposed. Firstly, the candidate region of flame is extracted by color segmentation method, and then the candidate region of smoke is generated by the background fuzzy model based on wavelet analysis. Then the candidate region is filtered by the trained CNN model, and the position of flame and smoke in a picture is located. Finally, a large number of fire pictures in different scenes are used to test the algorithm. The results show that this method can detect the location of flame and smoke accurately and quickly from images or videos, and can be applied to fire detection tasks in substation scenarios.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

3.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available