Mine fire identification and alarm method based on image contour vertex straight line features

Abstract

The application discloses a mine fire identification and alarm method based on image contour vertex straight line features, which is characterized by installing a camera in a roadway, a coal mining face and a tunneling face and the like fire-prone areas, collecting and identifying a suspected fire image of a monitoring area in real time, and identifying and alarming a mine fire by monitoring irregular shape features of flame combustion. The mine fire identification and alarm method fully considers fire combustion image features and underground fire interference source image features, and is fast, accurate and simple in identification, and can help underground people in distress to gain valuable rescue and escape time.

Description

TECHNICAL FIELD

[0001] The present application relates to a mine fire identification and alarm method based on image contour vertex straight line features. BACKGROUND

[0002] In the coal industry, gas, fire, flood, roof, coal dust and other accidents have plagued coal mine safety production. Once a mine fire occurs, if the fire cannot be controlled in time, the scope of the fire will quickly expand, causing a large number of casualties and property losses; further, it may cause an explosion in the high-concentration gas and coal dust area underground as an ignition source, causing secondary trauma to the underground environment. Therefore, it is crucial for coal safety production to quickly identify the mine fire disaster and timely alarm, and to start the emergency plan and emergency rescue in a targeted manner.

[0003] In the existing mine fire monitoring technology, there are various types of sensor comprehensive monitoring methods, such as temperature, smoke, gas, etc. sensors. Although this type of monitoring has the advantages of high reliability and simple operation, it has a large workload in layout and maintenance due to the complex underground operation scene, and 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 the underground environmental factors and fire interference sources. The visual feature monitoring method is the current mainstream mine fire monitoring technology. However, the existing monitoring technology adopts many characteristic variables to determine the fire, although the information features contain a lot of information, there are also many unstable factors. Based on multiple cameras and multiple frame images to determine the fire disaster, it will lead to a long determination time, high false alarm rate and high false alarm rate.

[0004] Therefore, it is necessary to study a new mine fire rapid identification method to shorten the determination time and reduce the false alarm rate and false alarm rate of the existing monitoring technology for mine fire perception. Quickly identifying fire interference sources, discovering mine fires as soon as possible, and being able to alarm the fire disaster in the first time, is an important guarantee for timely emergency rescue and saving the lives of people in distress underground. SUMMARY

[0005] The present application aims to provide a mine fire identification and alarm method based on image contour vertex straight line features, which fully considers the image features of fire burning, can quickly identify fire and fire interference sources, is accurate and simple, and can save more rescue and escape time for people in distress in the mine. The fire identification and alarm method comprises installing a camera in a roadway, a coal mining face and a tunneling face to monitor a monitoring area in real time, determining whether the length feature relationship of all straight lines passing through the contour reference vertex of a suspected fire area on a suspected fire image satisfies a set condition to make a fire alarm determination, determining whether the ratio of the number of times of determining fire alarm in a set time to the total number of determinations satisfies a set condition to make a fire determination for the monitoring area in the mine, and immediately sending a fire alarm signal to a monitoring terminal when a fire is determined to occur in the monitoring area in the mine.

[0006] The working process of the fire alarm determination comprises:

[0007] Step 1: The camera collects images of the monitoring area in real time. After the monitoring images are filtered, denoised, enhanced and binarized, when the pixel feature value D1 of a single block area on the image is greater than a set threshold G, it is determined that the image is a suspected fire image of a single block area. When the pixel feature values D1, D2, D3, ···, Dn of multiple unconnected areas on the image are all greater than the set threshold G, it is determined that the image is a suspected fire image of multiple block areas, and step 2 is performed. If the suspected fire image determination condition is not satisfied, the monitoring is continued. i (i≥2 and i∈N + Step 2: When there is only a single suspected fire area on the suspected fire image, the suspected fire area on the suspected fire image is directly processed for contour edge features. When there are multiple suspected fire areas on the suspected fire image, the suspected fire areas are segmented and processed for contour edge features, and step 3 is performed.

[0008] Step 3: All straight lines passing through the reference vertex are drawn according to the contour boundary reference vertex, and the length values of all straight lines are sequentially calculated, and step 4 is performed.

[0009] Step 4: When the length feature relationship of all straight lines passing through the contour reference vertex of the suspected fire area on the suspected fire image satisfies the condition

[0010] Step 4: When the length feature relationship of all straight lines passing through the contour reference vertex of the suspected fire area on the suspected fire image satisfies the condition , it is determined that the interference source is determined, and step 1 is returned. When the length feature relationship does not satisfy the condition, it is determined that the fire is determined, and step 5 is performed. In the formula, {Al, Ah, An} are the length values of the straight lines passing through the reference vertex, and l 12 ···A 1i ···A 1n

[0011] ​Step 5: fire alarm is performed, and step 1 is returned to execute.

[0012] 1. The fire identification and alarm method further comprises: all straight lines of a reference vertex on a suspected fire region contour boundary of the suspected fire image are straight lines formed by connecting the remaining coordinate points on the contour boundary to the reference vertex in sequence.

[0013] 2. The fire identification and alarm method further comprises: the solving process of the length values of all straight lines in step 3 is that a reference vertex is found on the suspected fire region contour boundary and is set as (x1, y1), then the remaining coordinate points on the contour boundary are set in sequence as {(x2, y2), (x3, y3)···(xn, yn)} in a clockwise direction or an anticlockwise direction, and the length values of all straight lines are solved in sequence by using a calculation formula n , n wherein p ∈ [2, n]. 12 ···A 1i ···A 1n .

[0014] 3. The fire identification and alarm method further comprises: the fire determination process of the underground monitoring area comprises: the fire alarm determination is executed in a cycle with a duration T seconds, when the ratio of the alarm times variable X of the suspected fire image satisfying the fire alarm determination condition to the total determination times variable Y of the image is greater than a set threshold S, that is, X / Y > S, it is determined that a fire occurs in the underground monitoring area.

[0015] The mine fire identification and alarm method based on the straight line features of the image contour vertex has the following characteristics:

[0016] 1. The fire identification method fully analyzes the contour features of the fire burning image and the contour features of the interference source of the underground fire, the length features of all straight lines of a reference vertex on a suspected fire region contour boundary of the suspected fire image are used for fire alarm determination, which is more conducive to distinguishing and eliminating the interference source of the fire, and can reduce the false alarm and the missed alarm of the fire disaster.

[0017] 2. The method not only efficiently uses the feature information of the fire image, but also has a simple and efficient algorithm construction of the image processing part, and the fire information can be quickly determined by a single frame of image, the feature extraction recognition degree of the method is high, the number of variables is small, and the discrimination time of the suspected fire is shortened, and more escape time is further obtained for the trapped and affected personnel in the underground. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 ​An embodiment schematic diagram of a mine fire identification and alarm method based on image contour vertex straight line features.

[0019] Figure 2 A schematic diagram of a fire monitoring and alarm device structure.

[0020] Figure 3 A schematic diagram of a fire alarm process of a mine fire identification and alarm method based on image contour vertex straight line features

[0021] Figure 4 A schematic diagram of a fire determination process of a mine fire identification and alarm method based on image contour vertex straight line features. DETAILED DESCRIPTION

[0022] Figure 1 An embodiment example of a mine fire identification and alarm method based on image contour vertex straight line features, the main components include:

[0023] 1. A storage server (101) is in communication connection with an image acquisition camera (105), responsible for storing and forwarding real-time video image data of a monitored area provided by the camera; the storage server is in communication connection with a fire monitoring and alarm device (106), responsible for storing and forwarding fire alarm data provided by the fire monitoring and alarm device; provides a service for a monitoring terminal (102) to view on-site monitoring data of a monitored area or to call historical monitoring image data.

[0024] 2. The monitoring terminal (102) is installed on the surface of the mine, used to receive the alarm signal of the fire monitoring and alarm device (106); responsible for providing mine environment monitoring data display service, providing real-time, historical data and fire alarm data by the storage server (101), with sound and light alarm function; production management personnel can call and query the historical data stored in the storage server (101) through the monitoring terminal.

[0025] 3. A core switch (103) is a core management and switching device of a mine Ethernet, responsible for the management and data exchange of all devices connected to the mine Ethernet, with routing function, connected to the Internet.

[0026] 4. A ring network switch (104) is a mine Ethernet underground switching device, installed underground, and multiple ring network switches are connected in a ring network mode.

[0027] 5. A camera (105) is installed in the underground roadway, coal mining face and tunneling face, responsible for collecting real-time video images of the underground roadway and working face where fire is likely to occur; 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 a ring network switch (104), and the video image data of the monitored area collected in real time is transmitted to a storage server (101); the analog video output port is connected to a fire monitoring and alarm device (106).

[0028] 6. A fire monitoring and alarm device (106) is responsible for receiving and processing the monitoring video image data collected by the camera (105), and has built-in graphic image processing software; when the processed suspected fire image meets the set fire alarm conditions, the fire monitoring and alarm device (106) sends fire alarm data to the storage server (101) and sends a fire alarm signal to the monitoring terminal (102); and has wired and wireless communication functions.

[0029] 7. A suspected fire area, a suspected ignition point area appearing in the real-time monitoring area of the camera, and the image data is monitored and collected by the camera in real time.

[0030] Figure 2 is a schematic diagram of the structure of the fire monitoring and alarm device, and the main components of the structure of the fire monitoring and alarm device include:

[0031] Core processor, graphic 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.

[0032] 1. Core processor (201), using Broadcom BCM2837 processor, using ARM Cortex-A53 architecture, 64-bit quad-core 1.2GHz.

[0033] 2. The graphic processor (202) is a Dual Core VideoCore IV GPU processor.

[0034] 3. The storage unit (203) uses 1GB LPDD2 memory.

[0035] 4. The clock unit (204) uses a 19.2MHz crystal oscillator.

[0036] 5. The power supply unit (205) uses an AC / DC module, input 100V-240V AC, output 12V DC, for device power supply.

[0037] 6. The USB interface unit (206) supports 4 USB interfaces.

[0038] 7. Video image acquisition module (207), converts the mode video signal into digital video data, inputs the analog video output port of the camera (105), and transmits the digital video data to the core processor (201) through the USB port, supporting multi-channel video acquisition.

[0039] 8. Communication module (208), responsible for converting the RS485 communication interface into a USB communication interface, connecting other data monitoring devices.

[0040] 9. Wireless communication unit (209), supporting 802.11b / g / n protocol, used for wireless communication with monitoring devices supporting wireless communication.

[0041] 10. Network interface unit (210), responsible for accessing the mine Ethernet, connecting the ring network switch (104).

[0042] 11. SD card unit (211), used for storing 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 with a capacity of not less than 4GB.

[0043] The fire alarm flowchart of the mine fire identification and alarm method based on the straight line feature of the image contour vertex is shown in FIG. 8. Figure 3 The main flowchart includes:

[0044] 1. (301) Set the internal timer time T of the fire monitoring and alarm device to zero and start timing, set the total number of times Y=0 of the image executing the fire alarm judgment condition, set the number of times X=0 of the suspected fire image satisfying the fire alarm condition, and execute step (302).

[0045] 2. (302) Further set the total number of times Y=Y+1 of the image executing the fire alarm judgment condition, and the judgment number of times is accumulated by one every time the monitoring image executes the fire alarm judgment condition, and execute step (303).

[0046] 3. (303) The fire monitoring and alarm device processes the image and makes a fire alarm judgment on the suspected fire image, when the set fire alarm judgment condition is met, execute step (304), otherwise return to execute step (302).

[0047] 4. (304) The suspected fire image satisfies the fire alarm judgment condition every time, the fire alarm number of times is accumulated by one, that is, X=X+1, and a fire warning is sent to the monitoring terminal, and step (305) is executed.

[0048] 5. (305) The workflow of fire alarm judgment is executed in a cycle within a set time, and it is judged whether the judgment timer time value T is greater than the set time threshold t. When the time value T > t, step (306) is executed, otherwise, step (302) is returned to be executed.

[0049] 6. (306) It is further judged whether the ratio of the fire image alarm number X satisfying the fire alarm judgment condition to the total judgment number Y of the image executing the fire alarm judgment condition is greater than the set threshold S. When X / Y > S, step (307) is executed, otherwise, step (301) is returned to be executed.

[0050] 7. (307) The fire monitoring alarm device sends a fire alarm signal to the storage server (101) and the monitoring terminal (102).

[0051] The fire judgment process example of the mine fire identification and alarm method based on the straight line feature of the image contour vertex is shown in Figure 4 The process includes:

[0052] 1. (401) The camera is installed in the underground roadway, the coal mining face and the tunneling face, and the images of the monitoring area are collected in real time and uploaded to the fire monitoring alarm device for image recognition processing, and further step (402) is executed.

[0053] 2. (402) The fire monitoring alarm device pre-processes the monitoring image. After the image denoising, image enhancement and image pixel binarization, when there is a single block area pixel brightness feature value D1 > G on the image, it is judged that the image is a single block area suspected fire image; when there are multiple unconnected area pixel brightness feature values on the image, it is judged that the image is a suspected fire image of multiple block areas, and further step (403) is executed, otherwise, step (401) is returned to be executed.

[0054] 3. (403) It is judged whether there are multiple suspected fire areas on the suspected fire image. When there are no multiple suspected fire areas on the suspected fire image, it is judged that there is only a single suspected fire area, and step (404) is executed, otherwise, step (406) is executed.

[0055] 4. (404) The contour boundary reference vertex of the suspected fire area on the suspected fire image is found. The contour boundary can obtain all coordinate points {(c1, d1), (c2, d2), ···, (c e , d e ), ···, (c n , d n )} on the boundary, and the vertex coordinate point in all coordinate points on the contour boundary is further found. The vertex coordinate point is obtained by the formula The vertex coordinate point (c e ,d e ) among all coordinate points on the boundary is calculated. e-1 e-1 e e e+1 e+1 , and (c e ,d e ) are any adjacent coordinate point groups on the contour boundary. If (c e ,d e ) is the vertex coordinate point among all coordinate points on the boundary, all vertex coordinates are calculated by sequentially traversing all coordinate points on the boundary, and step (405) is executed.

[0056] 5. (405) A vertex coordinate (c n ,d n ) is randomly selected as a reference vertex according to the vertex coordinates calculated in step (404), and the reference vertex coordinate is re-labeled as (x1, y1). The remaining coordinate points on the contour boundary are sequentially labeled as {(x2, y2), (x3, y3), ··· (x n ,y n )} in a clockwise direction or a counterclockwise direction. The distances between the remaining coordinate points {(x2, y2), (x3, y3), ··· (x n ,y n )} and the reference vertex (x1, y1), i.e., the length values of all straight lines {A 12 ···A 1i ···A 1n}, are sequentially calculated using the formula , and step (408) is further executed.

[0057] 6. (406) When there are multiple suspected fire regions on the suspected fire image, the suspected fire image is subjected to image segmentation and block processing, and step (407) is executed.

[0058] 7. (407) The reference vertex of the suspected fire region contour boundary of the suspected fire region is calculated by block processing, and the length values of all straight lines passing through the reference vertex are further calculated according to the formulas in steps (404) and (405), and step (408) is executed.

[0059] 8. (408) When the length characteristic relationship of all straight lines passing through the reference vertex of the suspected fire region contour of the suspected fire image satisfies the condition or ​When the length feature relationship satisfies the condition, it is determined that the source is a fire, and the step (409) is executed.

[0060] When the length feature relationship satisfies the condition, it is determined that the source is a fire, and the step (409) is executed.

[0061] 9. (409) Fire alarm processing is performed.

Claims

1. A mine fire identification and alarm method based on image contour vertex straight line features, characterized in that: The camera is installed in the roadway, coal mining face and tunneling face to monitor the monitoring area in real time, fire alarm judgment is made according to whether the length characteristic relation of all straight lines passing through the reference vertex of the contour boundary of the suspected fire area on the suspected fire image meets the set condition, underground monitoring area fire judgment is made according to whether the ratio of the number of times of fire alarm judgment to the total number of times of judgment in the set time meets the set condition, when it is judged that fire occurs in the underground monitoring area, a fire alarm signal is immediately sent to the monitoring terminal; The working process of the fire alarm judgment comprises: Step 1: the camera real-time collects the image of the monitoring area, the monitoring image is filtered and denoised, image enhanced and image pixel binarized, when the pixel characteristic value D1 of a single block area on the image is greater than the set threshold G, it is determined that the image is a suspected fire image of a single block area; when the pixel characteristic values D1, D2, D3, …, D i (i≥2 and i∈N + ) of multiple unconnected areas on the image are all greater than the set threshold G, it is determined that the image is a suspected fire image of multiple block areas, and step 2 is executed; if the suspected fire image determination condition is not met, continuous monitoring is carried out. Step 2: when there is only a single suspected fire area on the suspected fire image, the suspected fire area on the suspected fire image is directly subjected to contour edge feature processing; or when there are multiple suspected fire areas on the suspected fire image, the multiple suspected fire areas are subjected to image segmentation, the suspected fire areas are subjected to contour edge feature processing in blocks, and step 3 is executed; Step 3: all straight lines passing through the reference vertex are made according to the reference vertex, the length values of all straight lines are sequentially calculated, and step 4 is executed; Step 4: When the length characteristic relation of all straight lines of the suspected fire region contour reference vertex on the suspected fire image meets the condition , the interference source is determined, and step 1 is returned to execute; when the length characteristic relation does not meet the condition, the fire is determined, and step 5 is executed, wherein 12 ···A 1i ···A 1n} is the length value of each straight line of the reference vertex, and l Step 5: fire alarm is made, and step 1 is returned to be executed.

2. The mine fire identification and alarm method based on straight line features of image profile vertexes according to claim 1, characterized in that: The straight lines passing through the reference vertex of the contour boundary of the suspected fire area on the suspected fire image are straight lines formed by connecting the reference vertex to the remaining coordinate points on the contour boundary.

3. The mine fire identification and alarm method based on straight line features of image profile vertexes according to claim 1, characterized in that: The solving process of sequentially obtaining the length values of all straight lines in step 3 is to find a reference vertex on the contour boundary of the suspected fire area and set it as (x1, y1), then set the remaining coordinate points of the contour boundary in turn as {(x2, y2), (x3, y3) ··· (xn, yn)} in the clockwise direction or the counterclockwise direction, further utilize the calculation formula n , n , , and p ∈ [2, n], sequentially obtain the length values of all straight lines {A 12 ···A 1i ···A 1n}.

4. The mine fire identification and alarm method based on straight line features of image profile vertexes according to claim 1, characterized in that: The underground monitoring area fire judgment process comprises that the working of fire alarm judgment is cyclically executed for a duration T seconds, when the ratio of the suspected fire image alarm number variable X meeting the fire alarm judgment condition to the total number of times of judgment of the image variable Y is greater than the set threshold S, that is, X / Y>S, it is judged that fire occurs in the underground monitoring area.

Images