Method and device for detecting moving target in underground dangerous area

Abstract

The invention discloses a method and device for detecting a moving target in an underground dangerous area, and the device comprises a video collection module which is used for collecting the video information of the underground area; a target detection module which is used for reading the image data, converting the video image data into a grayscale image sequence, performing de-noising and smoothpreprocessing on the grayscale image sequence, and obtaining an accurate complete contour and structure of the moving target through LOG edge detection and geometric curvature texture information detection; a PC end control module which is used for controlling the operation of the target detection module; a display module which is used for displaying the detected position information of the moving target in real time; wherein one end of the video acquisition module is connected with the display module, the other end of the video acquisition module is connected with the PC end control module,and the other end of the PC end control module is connected with the target detection module; the method has good robustness for illumination change, and can accurately and completely extract personnel in a mine dangerous area.

Description

technical field [0001] The invention relates to the technical field of mine safety monitoring, in particular to a method and device for detecting a moving target in an underground dangerous area. Background technique [0002] In recent years, with the rapid development of science and technology and the improvement of the coal industry system, coal mining has gradually developed in the direction of safety, efficiency and automation. The main form of coal mines in my country is underground mines, and its mining conditions are extremely complicated, especially large-scale mobile mining equipment underground In the working area, due to complex working conditions, mobile mining, relatively concentrated personnel, and frequent safety accidents, automatic detection and monitoring of workers in underground dangerous areas can not only accurately locate the exact location of underground personnel, but also provide automatic safety for coal mine mining and alarm. And linkage processing ...

AI Technical Summary

Problems solved by technology

[0003] Under the special industrial and mining environment, the video images collected in coal mines have low illumination, large changes, large background noise and uneven noise distribution. In addition, some underground coal mine videos include both fixed cameras and vehicle-mounted cameras (cameras). Mobile) recorded video images, coal mine all-weather artificial lighting environment, dust and humidity and other factors make image acquisition quality poor, all of which greatly affect the presentation quality of on-site scenes and the linkage effect of remote active warning, limiting the mine video high-speed For the application of quality acquisition and target recognition, the traditional coal mine video surveillance system can only record the monitoring scene, which requires the staff to observe carefully and continuously, which not only requires a high concentration of attention, but also cannot quickly respond to the accident when an accident occurs. Accident alarm and linkage processing

In the process of personnel detection and identification of underground video images, miners’ overalls are generally dark gray or dark blue, and there is a high possibility of being contaminated with coal ash, which is very close to the background gray under low illumination. The recorded images are as follows: Black, gray, and white are the main colors, and there is no color information available for processing. In the current detection method, color is the main feature adopted, so the existing detection method has poor detection effect on moving objects.

Moreover, due to the shooting angle of the video capture device of the mobile equipment and the influence of the uneven distribution of light on the underground lighting equipment, which is different from natural light, some human bodies will enter the viewing angle. It is very difficult, and it also makes the existing detection methods limited in the application of underground video personnel detection

Images