Mine fire recognition and alarm method based on inscribed straight line features of image contour

Abstract

This invention discloses a mine fire identification and alarm method based on the inscribed straight line features of image contours. This method installs cameras in fire-prone areas, such as those with cables, tapes, electromechanical chambers, tunnels, coal mining faces, and tunneling faces. The method collects and identifies images of suspected fires in the monitored areas in real time, and detects irregular patterns in the flames to identify and alarm mine fires. This method fully considers the characteristics of fire combustion images and those of underground interference sources, resulting in rapid, accurate, and simple identification, potentially saving valuable time for rescue and escape for those in distress underground.

Description

Technical Field

[0001] The present invention relates to a mine fire identification and alarm method based on inscribed straight line features of image contours, and the method relates to fields such as digital image processing technology and communication technology. Background Art

[0002] In the coal industry, accidents such as gas, fire, flooding, roof collapse, and coal dust plague coal mine safety. Once a mine fire occurs, if it cannot be promptly controlled, its spread will rapidly expand, causing massive casualties and property damage. It can also serve as a detonation source, causing explosions in areas of high gas and coal dust concentration underground, causing secondary damage to the underground environment. Therefore, rapid identification of underground fires, timely reporting, and targeted activation of emergency plans and rescue efforts are crucial to coal mine safety.

[0003] Existing mine fire monitoring technologies include comprehensive monitoring methods using various sensors, such as temperature, smoke, and gas sensors. Although this type of monitoring has the advantages of high reliability and simple operation, due to the complex underground operation scenes, its layout and maintenance workload is large, and it is greatly affected by interference sources; the infrared radiation temperature measurement equipment monitoring method can measure the temperature of the fire source, but the temperature measurement accuracy is greatly affected by underground environmental factors and fire interference sources; the visual feature monitoring method is the current mainstream mine fire monitoring technology, but the existing monitoring technology uses more characteristic variables to determine the fire. Although the information features are rich, they also contain more unstable factors. The comprehensive determination of the fire disaster based on multi-lens and multi-frame images will result in a longer determination time, and will be affected by suspected fire interference sources, resulting in high omission and false alarm rates.

[0004] Therefore, it is necessary to develop new methods for rapid mine fire identification to shorten detection time and reduce the false alarm and missed alarm rates of existing monitoring technologies. Rapidly identifying fire interference sources, detecting mine fires as early as possible, and providing immediate fire alarms are crucial for timely emergency rescue and saving the lives of those in distress underground. Summary of the Invention

[0005] The purpose of the present invention is to provide a mine fire identification and alarm method based on the straight line features of the image contour vertices. The method fully considers the characteristics of the fire combustion image, can quickly identify the fire and the source of the fire interference, is accurate and simple, and can buy more rescue and escape time for people in distress underground. The fire identification and alarm method includes installing cameras in areas prone to fires such as cables, tapes, electromechanical chambers, tunnels, coal mining faces, and excavation faces to monitor the monitoring area in real time, and making a fire alarm judgment based on whether the length characteristic relationship of the inscribed straight line of the suspected fire area on the suspected fire image meets the set conditions, and making a fire judgment in the underground monitoring area based on whether the ratio of the number of fire alarms determined within a set time to the total number of judgments meets the set conditions. When it is determined that a fire has occurred in the underground monitoring area, a fire alarm signal is immediately sent to the monitoring terminal;

[0006] The working process of fire alarm determination includes:

[0007] Step 1: The camera collects images of the monitoring area in real time. After the monitoring image is filtered, denoised, enhanced and binarized, if the pixel feature value m1 of a single area on the image is greater than the set threshold n, the image is judged to be a suspected fire image of the single area; if the pixel feature value m1 of multiple unconnected areas on the image is greater than the set threshold n, the image is judged to be a suspected fire image of the single area. i When (i≥2) are all greater than the set threshold n, the image is determined to be a suspected fire image of multiple areas, and step 2 is executed; when the suspected fire image determination condition is not met, continuous monitoring is performed;

[0008] Step 2: When there is only a single suspected fire area on the suspected fire image, directly perform contour edge feature processing on the suspected fire area on the suspected fire image; or when there are multiple suspected fire areas on the suspected fire image, perform image segmentation on the multiple suspected fire areas, perform contour edge feature processing on the suspected fire areas in blocks, and then execute step 3;

[0009] Step 3: Calculate the maximum inscribed straight line and its length within the suspected fire area outline, set the straight line as the reference leading edge, and proceed to step 4;

[0010] Step 4: Draw equidistant parallel lines to the line within the contour based on the reference first edge, and further determine the number of intersection points between each equidistant parallel line and the contour boundary. When each equidistant parallel line intersects the contour boundary at two coordinate points, execute step 5. When each equidistant parallel line intersects the contour boundary at more than two coordinate points, execute step 7.

[0011] Step 5: Calculate the lengths of the equidistant parallel straight lines inscribed in the outline of the suspected fire area on the suspected fire image, and proceed to step 6.

[0012] Step 6: When the length characteristic relationship between the maximum straight line inscribed in the outline of the suspected fire area on the suspected fire image and the parallel straight line on the same side meets the condition When , execute step 7, otherwise return to step 1; where {a t} and t∈(1,r) is the length of the reference first side and each equidistant parallel straight line, u1 and u2 are set thresholds, and u1 and u2 are obtained by experimental measurement or artificial setting;

[0013] Step 7: Trigger a fire alarm and return to step 1.

[0014] 1. The fire identification and alarm method further includes: the inscribed straight lines of the suspected fire area outline on the suspected fire image include the maximum inscribed straight line of the outline obtained based on the coordinates of points on the boundary of the suspected fire area outline, and unilateral or bilateral equidistant parallel straight lines drawn based on the position of the maximum inscribed straight line of the suspected fire area outline, wherein the unilateral or bilateral equidistant parallel straight lines are parallel straight lines drawn within the suspected fire area outline with a set fixed step distance H and parallel to the maximum straight line and distributed on one side or both sides of the straight line.

[0015] 2. The fire identification and alarm method further includes: determining the maximum straight line inscribed in the outline of the suspected fire area and its length in step 3. The maximum straight line inscribed in the outline is the straight line where the distance between the coordinates of any two points on the outline boundary is the maximum. The length calculation formula is: Where {(x i ,y i )、(x j ,y j )} are the coordinates of any point on the contour boundary.

[0016] 3. The fire identification and alarm method further includes: the step of sequentially calculating the lengths of the equidistant parallel straight lines inscribed in the outline of the suspected fire area on the suspected fire image in step 5 is based on the largest straight line inscribed in the outline of the suspected fire area as a reference starting edge, and sequentially calculating the lengths of the parallel straight lines drawn in multiples of the set step size.

[0017] 4. The fire identification and alarm method further includes: the underground monitoring area fire determination process includes a fire alarm determination work that is performed cyclically for a duration of T seconds. When the ratio of the suspected fire image alarm count variable X that meets the fire alarm determination conditions to the total image determination count variable Y is greater than a set threshold S, that is, X / Y>S, it is determined that a fire has occurred in the underground monitoring area.

[0018] The mine fire identification and alarm method based on image contour vertex straight line features has the following characteristics:

[0019] 1. The fire identification method of the present invention fully analyzes the contour features of the fire combustion image and the image contour features of the underground fire interference source. The fire alarm judgment is made based on the length characteristic relationship of the inscribed straight line of the contour of the suspected fire area on the suspected fire image, which is more conducive to identifying and eliminating the fire interference source, and can reduce false alarms and missed alarms of fire disasters.

[0020] 2. The method of the present invention not only efficiently utilizes the characteristic information of the fire image, but also the algorithm of the image processing part is simple and efficient. A single-frame image can quickly determine the fire information, and multiple-frame images can be used to verify the fire alarm. The feature extraction of the method has high recognition and few variables, thereby shortening the judgment time of suspected fires and further buying more escape time for trapped and affected people underground. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Schematic diagram of the implementation plan of the mine fire recognition and alarm method based on the inscribed straight line features of the image contour.

[0022] Figure 2 Schematic diagram of the fire monitoring and alarm equipment structure.

[0023] Figure 3 Schematic diagram of the fire alarm process of the mine fire recognition and alarm method based on the inscribed straight line feature of the image contour

[0024] Figure 4 Schematic diagram of the fire determination process of the mine fire recognition and alarm method based on the inscribed straight line features of the image contour. DETAILED DESCRIPTION

[0025] Figure 1 An example implementation scheme for a mine fire identification and alarm method based on inscribed straight line features of image contours, mainly comprising:

[0026] 1. A storage server (101), wherein the storage server is in communication with an image acquisition camera (105) and is responsible for storing and forwarding real-time video image data of a monitoring area provided by the camera; the storage server is in communication with a fire monitoring alarm device (106) and is responsible for storing and forwarding fire alarm data provided by the fire monitoring alarm device; and provides a monitoring terminal (102) with a service for viewing on-site monitoring data of a monitored area or retrieving historical monitoring image data.

[0027] 2. A monitoring terminal (102), installed above the well, is used to receive the alarm signal from the fire monitoring alarm device (106); it is responsible for providing underground environment monitoring data display services, and the storage server (101) provides real-time, historical data and fire alarm data, and has an audible and visual alarm function; production management personnel can retrieve and query the historical data stored in the storage server (101) through the monitoring terminal.

[0028] 3. Core switch (103), the core management and switching device of the mining Ethernet, is responsible for the management and data exchange of all devices connected to the mining Ethernet, has routing functions, and connects to the Internet.

[0029] 4. Ring network switch (104), underground switching equipment for mine Ethernet, installed underground, multiple ring network switches are connected in a ring network manner.

[0030] 5. Camera (105), image acquisition equipment, installed in underground tunnels, coal mining working faces and excavation working faces, responsible for collecting real-time video images of fire-prone areas such as underground tunnels and working faces; the camera includes a visible light camera, a far infrared camera, a near infrared camera and an ultraviolet camera; the camera has network output and analog video output functions; the network interface is directly connected to the ring network switch (104), and the real-time collected video image data of the monitoring area is transmitted to the storage server (101); the analog video output port is connected to the fire monitoring alarm device (106).

[0031] 6. Fire monitoring and alarm equipment (106), which is responsible for receiving and processing the monitoring video image data collected by the camera (105), has built-in graphic image processing software. When the processed suspected fire image meets the set fire alarm conditions, it sends fire alarm data to the storage server (101); and sends a fire alarm signal to the monitoring terminal (102); it has wired and wireless communication functions.

[0032] 7. Suspected fire area: The camera monitors the suspected fire point area in real time. The image data is monitored and collected and uploaded by the camera in real time.

[0033] Figure 2 This is a schematic diagram of the structure of a fire monitoring and alarm device. The main components of the fire monitoring and alarm device structure include:

[0034] Core processor, graphics processor, storage unit, clock unit, power supply unit, USB interface unit, video image acquisition module, wireless communication unit, network interface unit, SD card interface unit.

[0035] 1. Core processor (201), using Broadcom BCM2837 processor, using ARM Cortex-A53 architecture, 64-bit quad-core 1.2GHz.

[0036] 2. Graphics processor (202), which uses a Dual Core VideoCore IV GPU processor.

[0037] 3. Storage unit (203), using 1GB LPDD2 memory.

[0038] 4. Clock unit (204), using 19.2MHz crystal oscillator.

[0039] 5. The power supply unit (205) uses an AC / DC module with an input of 100V to 240VAC and an output of 12VDC for powering the equipment.

[0040] 6. USB interface unit (206), supporting 4 USB interfaces.

[0041] 7. Video image acquisition module (207), converts the analog video signal into digital video data, inputs the analog video output port connected to the camera (105), transmits the digital video data to the core processor (201) through the USB port, and supports multi-channel video acquisition.

[0042] 8. Communication module (208), responsible for converting the RS485 communication interface to a USB communication interface to connect to other data monitoring devices.

[0043] 9. A wireless communication unit (209), supporting 802.11b / g / n protocols, for wireless communication with monitoring equipment supporting wireless communication.

[0044] 10. Network interface unit (210), responsible for accessing the mining Ethernet and connecting to the ring network switch (104).

[0045] 11. SD card unit (211), used to store system files, library files, monitoring program files, etc., using Linux system management, built-in OpenCV library for video data processing, using a Micro SD card of no less than 4GB.

[0046] An example of a fire alarm process for a mine fire identification and alarm method based on the inscribed straight line feature of an image contour is shown below: Figure 3 As shown, the main process includes:

[0047] 1. (301) The internal timer T of the fire monitoring alarm device is set to zero and the timing is started. At the same time, the total number of judgments of images that execute the fire alarm judgment condition is set to 0, and the number of fire alarms of suspected fire images that meet the fire judgment alarm condition is set to 0, and the variable X is executed. Step (302) is executed.

[0048] 2. (302) Further set the total number of judgments of the image executing the fire alarm judgment condition to Y=Y+1. Each time the monitoring image executes the fire alarm judgment condition, the number of judgments variable is accumulated and added by one, and step (303) is executed.

[0049] 3. (303) The fire monitoring alarm device processes the image and performs a fire alarm determination on the suspected fire image. When the set fire alarm determination conditions are met, step (304) is executed, otherwise the process returns to step (302).

[0050] 4. (304) Each time the suspected fire image satisfies the fire alarm determination condition, the fire alarm count variable is incremented by one, i.e. X=X+1, and a fire warning is issued to the monitoring terminal, and step (305) is executed.

[0051] 5. (305) Loop through the fire alarm determination workflow within the set time to determine whether the timer value T is greater than the set time threshold t. When the time value T>t, execute step (306), otherwise return to execute step (302).

[0052] 6. (306) Further determine whether the ratio of the number of fire image alarms X that meet the fire alarm determination condition to the total number of determinations Y of images that execute the fire alarm determination condition is greater than the set threshold value S. When X / Y>S, execute step (307), otherwise return to execute step (301).

[0053] 7. (307) The fire monitoring alarm device sends a fire alarm signal to the storage server (101) and the monitoring terminal (102).

[0054] An example of the fire determination process of the mine fire identification and alarm method based on the inscribed straight line feature of the image contour is as follows: Figure 4 As shown, the process includes:

[0055] 1. (401) Cameras are installed in underground tunnels, coal mining faces and excavation faces to collect images of the monitored area in real time and upload them to fire monitoring and alarm equipment for image recognition processing, and further execute step (402).

[0056] 2. (402) The fire monitoring alarm device pre-processes the monitoring image. After the monitoring image is subjected to image denoising, image enhancement and image pixel binarization, if there is a single block of pixel brightness characteristic value m1>n on the image, the image is determined to be a suspected fire image of the single block area; if there are multiple unconnected pixel brightness characteristic values ​​on the image , it is determined that the image is a suspected fire image of multiple areas, and step (403) is further executed, otherwise the process returns to step (401).

[0057] 3. (403) Determine whether there are multiple suspected fire areas on the suspected fire image. If there are no multiple suspected fire areas on the suspected fire image, determine that there is only a single suspected fire area and execute step (404). Otherwise, execute step (406).

[0058] 4. (404) Find the maximum straight line and length value inscribed in the outline of the suspected fire area on the suspected fire image. The coordinates of all points on the boundary {(x1, y1), (x2, y2), ···, (x n ,y n )}, using the formula Calculate and find the maximum straight line inscribed in the outline, and execute step (405).

[0059] 5. (405) Set the maximum inscribed straight line of the contour obtained in step (404) as the reference first edge, and use the formula according to the coordinates of the intersection of the straight line and the contour boundary Find the equation of the maximum straight line, where k ij is the slope of the straight line, C1 is the constant of the straight line equation; according to all the coordinate points {(x1,y1),(x2,y2),···,(x n ,y n )} and formula Find the colinear coordinate points {(x p ,y p ),···,(x q ,y q )} and p∈(1,n),q∈(1,n), further according to the formula Find the length of the boundary collinearity, when K pq =A ij If the corresponding boundary collinear coordinate points are all on the linear equation of the maximum line, then the maximum line is the contour boundary. Otherwise, the maximum line is inside the contour boundary. Then, according to the linear equation and position of the maximum line, the equidistant parallel lines in the single or double-sided contour of the reference first side are obtained. The linear equations of the parallel lines are given by the formula Find, and C r is a constant number of equal step multiples, and step (408) is further executed.

[0060] 6. (406) According to the determination in step (403), when there are multiple suspected fire areas on the suspected fire image, the suspected fire areas on the suspected fire image are segmented and divided into blocks, and step (407) is executed.

[0061] 7. (407) The maximum straight line inscribed in the outline of the suspected fire area is obtained in blocks, and the length of the maximum straight line is obtained. Based on the linear equation of the maximum straight line, each equidistant parallel straight line in the outline is obtained. The method is solved according to the formulas of steps (404) and (405), and step (408) is further executed.

[0062] 8. (408) Determine the intersection points of the equidistant parallel straight lines inscribed in the suspected fire area outline and the outline boundary, and convert the boundary intersection coordinates {(x1, y1), (x2, y2), ···, (x n ,y n )} respectively substitute the straight line equations of each equidistant parallel straight line, and when the straight line equation intersects the contour boundary at two points, execute step (409), otherwise execute step (411).

[0063] 9. (409) According to the coordinates of the two intersection points of each equidistant parallel line and the contour boundary, calculate the distance between the coordinates of the two intersection points on the contour boundary respectively, and calculate according to the formula Obtain the distance value and execute step (410), where {(x re ,y re )、(x rg ,y rg )} and e∈(1,n) and g∈(1,n) are the coordinates of the intersection of the parallel lines and the contour boundary.

[0064] 10.(410) When the fire monitoring alarm equipment detects that the length characteristic relationship between the maximum straight line inscribed in the outline of the suspected fire area and the parallel straight line on the same side of the suspected fire image meets the condition And when t∈(1,r), execute step (411) otherwise return to execute step (401).

[0065] 11. (411) Process the fire alarm.

Claims

1. A mine fire identification and alarm method based on the inscribed straight line feature of an image contour, characterized by: Cameras are installed in tunnels, coal mining faces, and tunneling faces in areas prone to fire to monitor the monitoring area in real time. Fire alarms are determined based on whether the length characteristic relationship of the inscribed straight line in the outline of the suspected fire area on the suspected fire image meets the set conditions. Fire determination in the underground monitoring area is performed based on whether the ratio of the number of fire alarms determined within a set time to the total number of determinations meets the set conditions. When a fire is determined to have occurred in the underground monitoring area, a fire alarm signal is immediately sent to the monitoring terminal. The working process of fire alarm determination includes: Step 1: The camera collects images of the monitoring area in real time. After the monitoring image is filtered, denoised, enhanced and binarized, if the pixel feature value m1 of a single area on the image is greater than the set threshold n, the image is judged to be a suspected fire image of the single area; if the pixel feature value m1 of multiple unconnected areas on the image is greater than the set threshold n, the image is judged to be a suspected fire image of the single area. i When (i≥2) are all greater than the set threshold n, the image is determined to be a suspected fire image of multiple areas, and step 2 is executed; when the suspected fire image determination condition is not met, continuous monitoring is performed; Step 2: When there is only a single suspected fire area on the suspected fire image, directly perform contour edge feature processing on the suspected fire area on the suspected fire image; Or when there are multiple suspected fire areas on the suspected fire image, the multiple suspected fire areas are segmented, and the contour edge features of the suspected fire areas are processed in blocks, and step 3 is executed; Step 3: Calculate the maximum straight line and length inscribed in the suspected fire area outline, set the straight line as the reference first edge, and proceed to step 4; Step 4: Draw equidistant parallel lines to the line within the contour based on the reference first edge, and further determine the number of intersection points between each equidistant parallel line and the contour boundary. When each equidistant parallel line intersects the contour boundary at two coordinate points, execute step 5. When each equidistant parallel line intersects the contour boundary at more than two coordinate points, execute step 7. Step 5: Calculate the lengths of the equidistant parallel straight lines inscribed in the outline of the suspected fire area on the suspected fire image, and proceed to step 6. Step 6: When the length characteristic relationship between the maximum straight line inscribed in the outline of the suspected fire area on the suspected fire image and the parallel straight line on the same side meets the condition When , execute step 7, otherwise return to execute step 1; where {a t } and t∈(1,r) is the length of the reference first side and each equidistant parallel straight line, u1 and u2 are set thresholds, and u1 and u2 are obtained by experimental measurement or artificial setting; Step 7: Trigger a fire alarm and return to step 1.

2. The mine fire identification and alarm method based on the inscribed straight line feature of the image contour according to claim 1, characterized in that: The inscribed straight lines of the suspected fire area outline on the suspected fire image include the maximum inscribed straight line of the outline obtained based on the coordinates of points on the boundary of the suspected fire area outline, and unilateral or bilateral equidistant parallel straight lines made based on the position of the maximum inscribed straight line of the suspected fire area outline. The unilateral or bilateral equidistant parallel straight lines are parallel straight lines parallel to the maximum straight line and distributed on one or both sides of the straight line within the suspected fire area outline with a set fixed step distance H.

3. The mine fire identification and alarm method based on the inscribed straight line feature of the image contour according to claim 1, characterized in that: In step 3, the maximum straight line inscribed in the outline of the suspected fire area and its length are obtained. The maximum straight line inscribed in the outline is the straight line where the distance between the coordinates of any two points on the outline boundary is the maximum. The length calculation formula is: Where {(x i ,y i )、(x j ,y j )} is the coordinate of any point on the contour boundary, m, n are the number of coordinate points on the contour boundary and m, n∈N + .

4. The mine fire identification and alarm method based on the inscribed straight line feature of the image contour according to claim 1, characterized in that: The step 5 of sequentially calculating the lengths of the equidistant parallel straight lines inscribed in the outline of the suspected fire area on the suspected fire image is to use the largest straight line inscribed in the outline of the suspected fire area as a reference starting edge, and sequentially calculate the lengths of the parallel straight lines in the order of the multiples of the set step size.

5. The mine fire identification and alarm method based on the inscribed straight line feature of the image contour according to claim 1, characterized in that: The underground monitoring area fire determination process includes executing the fire alarm determination work in a loop for a duration of T seconds. When the ratio of the suspected fire image alarm count variable X that meets the fire alarm determination conditions to the total image determination count variable Y is greater than a set threshold S, that is, X / Y>S, it is determined that a fire has occurred in the underground monitoring area.

Images