Abstract
Aiming at the problem that the fire smoke image segmentation algorithm cannot obtain integral smoke information, the adaptive background updating smoke foreground object extraction algorithm based on block segmentation is proposed. According to the characteristics that the smoke internal pixels continuously roll in the heat of the driver and the pixel concentration from near the fire source to edge decreases in turn, the method for different blocks using different difference threshold is adopted to ensure the integrity of the extracted foreground target. Under the difference between the current frame and the background frame, block difference thresholds are updated to let the differential threshold adjustment with continuous adaptive monitoring. In the new weighted average updated background image corrected by the original background image, the interference suspicious target edge pixels are removed. Simulation experimental results show that the method is able to extract more complete information of smoke in a suspected area of the edge, and eliminate the interference of light and pedestrian in complex space.
Highlights
The smoke produced in the smoldering stage is a very significant character of early fire
The hidden Markov tree model is structured to express the smoke texture, and the smoke is detected by support vector machine
Using the characteristics of wavelet transform spatial frequency, smoke texture enhancement image is achieved by weighted average processing of the image after wavelet transform coefficients decomposition into multilayer
Summary
The smoke produced in the smoldering stage is a very significant character of early fire. Because the smoke affected by plume effect is not sheltered by an obstacle, the analysis and recognition of smoke image can help achieve early realization of the fire warning [1]. Accurate segmentation of smoke image is the premise and foundation for feature extraction and target recognition. Are not clear, and more vulnerable to the outside interferences Those factors makes the smoke image segmentation relatively complex. When the texture information of an image is not rich, this method can produce the over segmentation [4]. In the early fire smoke image detection, the difference in smoke concentration leads to different extents of shading for the background. Using the characteristics of early smoke, blocking technology will be applied to image segmentation to improve smoke image segmentation effect.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
