Flue gas layer feature segmentation based on multi-channel pixel adaptive
- PDF / 1,601,704 Bytes
- 17 Pages / 439.37 x 666.142 pts Page_size
- 106 Downloads / 168 Views
Flue gas layer feature segmentation based on multi-channel pixel adaptive Yunfei Yin 1 & Hui Cheng 1 & Huan Liu 1 Received: 17 November 2019 / Revised: 21 June 2020 / Accepted: 28 July 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Itisverydifficulttoaccuratelyseparatethesmokecontourinfirevideo.Becausethesceneofafire is complex and changeable, and there are often many interference factors, such as continuously changing light and fast switching scenes, it is difficult to accurately guarantee the separation of smoke contours. In this paper, an aggregate channel feature algorithm that combines color, saturation and texture is designed, and a fast pixel block feature matching method is used to build the background model. In order to overcome the error caused by scene switching, a dynamic threshold control method based on the background switching speed is proposed, which eliminates the interference caused by the dynamic background update, and effectively extracts the foreground smoke pixels and smoke contour map. The experimental results show that the algorithm can accurately extract the smoke layer contour map, and compared with the traditional foreground extraction algorithms, the algorithm is faster and more accurate. Keywords Flue gas layer segmentation . Multi-scale Aggregate Channel features . Pixel block feature matching
1 Introduction Smoke layer segmentation, which is the accurate separation of smoke and air section. The usual practice is to shoot the fire smoke occurrence and development video through the camera, periodically extract the image from the smoke video through the video processing
* Yunfei Yin [email protected] Hui Cheng [email protected] Huan Liu [email protected]
1
College of Computer Science, Chongqing University, Chongqing, China
Multimedia Tools and Applications
program, separate the smoke from the background through the image segmentation algorithm, and calculate the smoke layer height through the coordinate conversion algorithm. Finally, the curve of the flue gas layer with time is drawn. By analyzing the change trend of the smoke layer, it can be judged whether a fire will occur. By analyzing the change trend of the smoke layer at each location, the optimal fire escape route and fire escape plan can be worked out. The most obvious feature at the beginning of the fire is the flow of smoke, so fire warning is based on smoke detection. The traditional fire warning is detected by a sensor that senses smoke and temperature, and this method requires the sensor to be installed near the fire point, which has many inconveniences in implementation, and the efficiency is very low and the cost is large, so it is difficult to achieve Monitoring of large scenes. Therefore, with the development of computer vision technology, smoke layer detection based on image analysis has attracted more and more attention [27]. However, because the scenes of fire occurrence are complex and changeable, and there are many interference factors, the segmentation of the fire smo
Data Loading...
