Railway wagon carriage smoke and fire monitoring method based on image processing technology

Abstract

The invention discloses a railway wagon carriage smoke and fire monitoring method based on an image processing technology, and the method comprises the following steps of S1, obtaining the carriage image information in a monitoring region, S2, carrying out the binarization processing of an RGB image, and segmenting a suspected flame region; and S3, segmenting an HSV image for N times according tothe concentrations of black, grey and green colors; S4, calculating the area of a suspected smoke area and the area of the horizontal circumscribed rectangle of the suspected smoke area, and calculating a regularity proportion according to the area of the suspected smoke area and the area of the horizontal circumscribed rectangle of the suspected smoke area; S5, if the regularity proportion is greater than the threshold value y1, determining that the suspected smoke area is a non-smoke area; and if the regularity ratio is smaller than the threshold y1, calculating the ratio of the area of thecircumscribed rectangle to the whole image, if the ratio is larger than the threshold y2, judging that the suspected smoke area is a smoke area, and if the ratio is smaller than the threshold y2, judging that the suspected smoke area is a non-smoke area.

Description

technical field [0001] The invention relates to the technical field of smoke and fire monitoring in railway freight car compartments, in particular to a fire and fire monitoring method in railway freight car compartments based on image processing technology. Background technique [0002] At present, in the daily inspection of railway freight car transportation, pyrotechnics is an important link that needs to be monitored, and it is an effective means to reduce losses. In the past, the fire and fire monitoring method in the carriage was mainly manual, which not only consumed a lot of manpower and material resources, but also had poor real-time performance, and the driver could not detect danger in time while the truck was driving. Although with the rapid development of science and technology, more new technologies have been applied to the field of fire monitoring, including fire detector monitoring, infrared image recognition monitoring and satellite monitoring. However, the...

AI Technical Summary

Problems solved by technology

However, more than 90% of the current effective visual methods are monitored by video. Image-based fire monitoring methods generally have relatively large defects, such as only detecting smoke of a specific color, high false alarm rate, and susceptibility to background interference. and many more

Therefore, image-based fire monitoring methods are not mature enough, especially image-based field fire monitoring is more difficult.

Images