Search

In order to solve the problem that most of the current mine external fire monitoring methods do not have fire source positioning function, a binocular vision-based perception and positioning method of mine external fire is proposed. Firstly, the method sets up mine visible binocular cameras or near-infrared binocular cameras at multiple points in roadways, chambers and working faces with cables, tapes and electromechanical equipment to capture images of the monitoring area. Then, the adopted images are preprocessed and binarized images are obtained by threshold segmentation. The roundness, rectangularity and number of sharp corners in the image are calculated, and the images are identified by flames according to the roundness, rectangularity and number of sharp corners. If there is flame in the image detection area, a fire alarm signal will be issued and the temperature, smoke, carbon dioxide, carbon monoxide, oxygen and infrared sensor information are taken into consideration to improve the accuracy of alarms. Finally, the method uses mine visible binocular cameras or near-infrared binocular cameras to measure the distance of the fire source, locates the fire source based on the camera position, and outputs the fire source location information to control the fire extinguishing device near the fire source. Far-infrared binocular cameras can also be used for fire perception and fire source positioning, but the cost is high. The binocular vision-based perception and positioning method of mine external fire can sense and locate the fire source. This method has the advantages of wide monitoring range, low cost, fast response and visualization, and solves the problem of locating the fire source of mine external fire.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)