Factory safety monitoring method and system based on data fusion analysis

Abstract

The invention relates to the technical field of factory safety monitoring scheme design based on data fusion analysis, in particular to a factory safety monitoring method and system based on data fusion analysis. The method comprises the following steps: shooting a first infrared thermal imaging image and a second infrared thermal imaging image of a target area at the same time point of two adjacent days by using an infrared thermal imager arranged on an unmanned aerial vehicle; according to the method, whether the building is suspected to be subjected to fire disasters or not can be judged through the infrared thermal imager arranged on the unmanned aerial vehicle, whether fire disasters are suspected to be subjected to fire disasters or not can be judged through the infrared thermal imager arranged on the unmanned aerial vehicle, a hardware system is simplified to a great extent, and the system reliability is improved. According to the method, the hardware deployment efficiency of building fire monitoring is greatly improved, whether a large number of target buildings are suspected to have fire can be judged at the same time, and the intelligent degree, the reliability and the fire detection efficiency of the method are improved to a great extent.

Description

Technical Field

[0001] This invention relates to the field of design technology for factory safety monitoring schemes based on data fusion analysis, and specifically to a factory safety monitoring method and system based on data fusion analysis. Background Technology

[0002] Fire warning systems in buildings typically rely on smoke detectors. However, monitoring all target buildings within a specific area requires deploying a large number of smoke detectors, resulting in massive data collection, high hardware costs, and low deployment efficiency. Furthermore, when all windows are closed, poor air circulation can lead to monitoring delays and susceptibility to environmental influences, making smoke detection unreliable. Infrared thermal imaging technology converts the invisible infrared energy emitted by objects into visible thermal images. Compared to visible light cameras, it can determine an object's temperature based on its infrared radiation intensity, eliminating significant interference and ensuring that the captured bright areas are those emitting strong infrared radiation. However, technical challenges remain. The number of people staying in a building at different times of the day, their locations, and their activities vary, resulting in different amounts of heat generated. Therefore, effectively applying infrared thermal imaging technology to fire monitoring of target buildings within a specific area is a pressing issue that needs to be addressed.

[0003] Therefore, existing technologies still need further development. Summary of the Invention

[0004] The purpose of this invention is to overcome the above-mentioned technical deficiencies and provide a factory safety monitoring method and system based on data fusion analysis to solve the problems existing in the prior art.

[0005] To achieve the above-mentioned technical objectives, according to a first aspect of the present invention, the present invention provides a factory area safety monitoring method based on data fusion analysis, the method comprising: S100: Control the drone to start flying along a preset route at a first preset time point on the current date. The preset route includes a first preset waypoint. Control the drone to fly to the first preset waypoint and use the infrared thermal imager set on the drone to take a first infrared thermal image of the target area of ​​the production plant at a second preset time point. S200: Control the drone to start flying along a preset route at the first preset time point of the next day of the current date. The preset route includes a first preset waypoint. Control the drone to fly to the first preset waypoint and use the infrared thermal imager set on the drone to take a second infrared thermal image of the target area of ​​the production plant at the second preset time point. S300: The first and second infrared thermal imaging images are denoised using median filtering. Preprocessing is performed on both images to obtain a first preprocessed image and a second preprocessed image. The first preprocessed image includes background noise, multiple target buildings, and edge regions. A quantization threshold is selected to transform the first and second preprocessed images into two grayscale images with only two grayscale levels, corresponding to temperature values ​​above 150 degrees Celsius and below 150 degrees Celsius, respectively. The first grayscale image is segmented using connected component analysis to identify the first target building. A first target building is then established based on the first target building. The search box performs image segmentation on the second grayscale image using connected component analysis to segment out the second target building. A second target search box is then established based on the second target building. The first actual geographic coordinates corresponding to the four vertices of the first target search box are calculated based on the pixel coordinates of the four vertices of the second target search box. The second actual geographic coordinates are then calculated based on the pixel coordinates of the four vertices of the second target search box. Based on the first and second actual geographic coordinates, it is determined whether the first target building and the second target building refer to the same building. It is also determined whether the grayscale level of the building in the first and second grayscale images has increased from a low temperature to a high temperature. Based on the determination results, it is decided whether to output an alarm signal regarding a suspected fire in the building.

[0006] Specifically, the pan-tilt angle of the infrared thermal imager remains unchanged when capturing the first and second infrared thermal images.

[0007] Specifically, the connected component is an eight-way connected component.

[0008] Specifically, determining whether the first target building and the second target building refer to the same building based on the first actual geographic coordinates and the second actual geographic coordinates includes: Calculate the first Euclidean distance between the geographic coordinates of the top left corner vertex of the first target search box and the geographic coordinates of the top left corner vertex of the second target search box, and determine whether the first Euclidean distance is less than or equal to a first preset threshold. Calculate the second Euclidean distance between the geographic coordinates of the top right corner vertex of the first target search box and the geographic coordinates of the top right corner vertex of the second target search box, and determine whether the second Euclidean distance is less than or equal to a first preset threshold. Calculate the third Euclidean distance between the geographic coordinates of the lower left corner vertex of the first target search box and the geographic coordinates of the lower left corner vertex of the second target search box, and determine whether the third Euclidean distance is less than or equal to a first preset threshold. Calculate the fourth Euclidean distance between the geographic coordinates of the lower right corner vertex of the first target search box and the geographic coordinates of the lower right corner vertex of the second target search box, and determine whether the fourth Euclidean distance is less than or equal to a first preset threshold. Based on the above judgment results, determine whether the first target building and the second target building refer to the same building.

[0009] Specifically, determining whether the first target building and the second target building refer to the same building based on the above judgment results includes: If the first Euclidean distance, the second Euclidean distance, the third Euclidean distance, and the fourth Euclidean distance are all less than or equal to the first preset threshold, it is determined that the first target building and the second target building refer to the same building.

[0010] Specifically, determining whether the first target building and the second target building refer to the same building based on the above judgment result also includes: If the first Euclidean distance is greater than or equal to the first preset threshold, or the second Euclidean distance is greater than or equal to the first preset threshold, or the third Euclidean distance is greater than or equal to the first preset threshold, or the fourth Euclidean distance is greater than or equal to the first preset threshold, it is determined that the first target building and the second target building do not refer to the same building.

[0011] Specifically, the step of determining whether the first target building and the second target building refer to the same building based on the first and second actual geographic coordinates, and determining whether the gray level of the building in the first and second grayscale images changes from low to high temperature, and determining whether to output an alarm signal regarding a suspected fire in the building based on the determination result, includes: If it is determined that the first target building and the second target building refer to the same building, and the gray level of the building in the first grayscale image and the second grayscale image increases from low temperature to high temperature, an alarm signal is output regarding the suspected fire in the building.

[0012] Specifically, the step of determining whether the first target building and the second target building refer to the same building based on the first and second actual geographic coordinates, and determining whether the gray level of the building in the first and second grayscale images changes from low to high temperature, and determining whether to output an alarm signal regarding a suspected fire in the building based on the determination result, further includes: If it is determined that the first target building and the second target building do not refer to the same building, or if the gray level of the building in the first grayscale image and the second grayscale image does not rise from a low temperature to a high temperature, an alarm signal indicating that no fire has occurred in the building is output.

[0013] Specifically, the method further includes: If an alarm signal is output regarding a suspected fire in the building, the centroid coordinates of the second target search box are calculated based on the second actual geographic coordinates corresponding to the four vertices of the second target search box, and an alarm signal regarding a suspected fire in the building corresponding to the centroid coordinates is output.

[0014] According to a second aspect of the present invention, a factory area safety monitoring system based on data fusion analysis is provided, comprising: The acquisition module includes an infrared thermal imager mounted on a drone, used to capture a first infrared thermal image of a target area in the production plant area, and also used to capture a second infrared thermal image of the target area in the production plant area. The control module is used to control the UAV to start flying along a preset route at a first preset time point on the current date. The preset route includes a first preset waypoint. The module controls the UAV to fly to the first preset waypoint and use an infrared thermal imager mounted on the UAV to capture a first infrared thermal image of the target area of ​​the production plant at a second preset time point. The module is also used to control the UAV to start flying along a preset route at a first preset time point on the next day. The preset route includes a first preset waypoint. The module controls the UAV to fly to the first preset waypoint and use an infrared thermal imager mounted on the UAV to capture a second infrared thermal image of the target area of ​​the production plant at a second preset time point. The module further uses median filtering to denoise the first and second infrared thermal images, preprocessing them to obtain a first preprocessed image and a second preprocessed image. The first preprocessed image includes background noise, multiple target buildings, and edge regions. A quantization threshold is selected to transform the first and second preprocessed images. The image is replaced with a first grayscale image and a second grayscale image, each with only two grayscale levels. These two grayscale levels correspond to temperature values ​​above 150 degrees Celsius (high temperature) and below 150 degrees Celsius (low temperature), respectively. The first grayscale image is segmented using connected component analysis to identify the first target building. A first target search box is then created based on the first target building. Similarly, the second grayscale image is segmented using connected component analysis to identify the second target building. A second target search box is then created based on the second target building. The first and second actual geographic coordinates are used to calculate the first and second actual geographic coordinates of the four vertices of the first and second target search boxes. Based on these coordinates, it is determined whether the first and second target buildings refer to the same building, and whether the grayscale level of the building in the first and second grayscale images changes from low to high temperature. Based on the results, an alarm signal indicating a suspected fire in the building is output.

[0015] Beneficial effects: This invention controls a drone to fly along a preset route starting at a first preset time on the current date. The preset route includes a first preset waypoint. The drone flies to the first preset waypoint and uses an infrared thermal imager mounted on the drone to capture a first infrared thermal image of the target area of ​​the production plant at a second preset time. The invention then controls the drone to fly along the preset route again starting at a first preset time on the next day, again including the first preset waypoint. The drone flies to the first preset waypoint and uses the infrared thermal imager mounted on the drone to capture a second infrared thermal image of the target area of ​​the production plant at the second preset time. Based on the first and second infrared thermal images, the invention determines whether the grayscale level of buildings in the target area of ​​the production plant has increased, thereby determining whether a fire is suspected. This invention enables the determination of whether a fire is suspected in all production areas along a preset route using only an infrared thermal imager mounted on the drone. It solves the problem that relying solely on real-time analysis of infrared thermal images captured in existing technologies is clearly insufficient for intelligent analysis of high-temperature production equipment or high-temperature production projects. Furthermore, it reasonably eliminates technical problems that could lead to system misjudgments, thus solving the technical problems that existing infrared thermal imaging monitoring solutions still have shortcomings. It enables the application of infrared thermal imaging technology to fire monitoring in production plants, allowing for the intelligent and reasonable elimination of high-temperature points generated by high-temperature production equipment or projects. This significantly simplifies the hardware system, greatly improves the hardware deployment efficiency of building fire monitoring, and, at higher flight altitudes, can simultaneously capture images of numerous buildings in the target area of ​​the production plant, achieving the technical effect of simultaneously judging whether a large number of target buildings are suspected of being on fire. It can also judge whether all production areas along a preset flight path are suspected of being on fire, greatly simplifying the hardware system and significantly improving the hardware deployment efficiency of building fire monitoring. At higher flight altitudes, it can simultaneously capture images of numerous buildings in the target area of ​​the production plant, achieving the simultaneous judgment of whether a large number of target buildings are suspected of being on fire, without requiring complex algorithm modeling. This greatly improves the intelligence, usability, reliability, and fire detection efficiency of the invention, and significantly expands its application scenarios. Attached Figure Description

[0016] Figure 1 This is a flowchart of a factory safety monitoring method based on data fusion analysis provided in a specific embodiment of the present invention; Figure 2 The infrared thermal imaging image taken by the UAV of the present invention is provided in a specific embodiment of the present invention; Figure 3 This is a schematic diagram of the system composition of a factory safety monitoring system based on data fusion analysis provided in a specific embodiment of the present invention. Detailed Implementation

[0017] To enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Based on the embodiments in this application, other similar embodiments obtained by those skilled in the art without creative effort should all fall within the scope of protection of this application. Furthermore, directional terms mentioned in the following embodiments, such as "up," "down," "left," and "right," are only for reference to the directions in the accompanying drawings; therefore, the directional terms used are for illustrative purposes and not for limiting the invention.

[0018] The present invention will be further described below with reference to the accompanying drawings and preferred embodiments.

[0019] Please see Figures 1 to 3 This invention provides a factory safety monitoring method based on data fusion analysis, comprising: S100. Control the drone to start flying along a preset route at a first preset time point on the current date. The preset route includes a first preset waypoint. Control the drone to fly to the first preset waypoint and use the infrared thermal imager installed on the drone to take a first infrared thermal image of the target area of ​​the production plant at a second preset time point.

[0020] It is understood that the following are included before step S100: In the control module, a first preset time point, a second preset time point, a preset route, a first preset threshold, a second preset threshold, a third preset threshold, a fourth preset threshold, and a fifth preset threshold are preset.

[0021] It is understood that the first preset time point, the second preset time point, the preset route, the first preset threshold, the second preset threshold, the third preset threshold, the fourth preset threshold, and the fifth preset threshold can be specifically set according to the actual needs of the user according to the present invention. The present invention does not limit the specific values ​​of the first preset time point, the second preset time point, the preset route, the first preset threshold, the second preset threshold, the third preset threshold, the fourth preset threshold, and the fifth preset threshold, as long as they are applicable to the factory area safety monitoring method based on data fusion analysis proposed in the present invention.

[0022] Preferably, the present invention sets the first preset threshold, the second preset threshold, the third preset threshold, and the fourth preset threshold to 2 meters, and sets the flight altitude in the preset flight path to 300 meters. Figure 2The infrared thermal imaging image taken by the UAV of this invention at an altitude of 300 meters and a first preset waypoint, with the flight altitude set to 300 meters and the first, second, third, and fourth preset thresholds all set to 2 meters, was determined by the technical personnel of this invention through extensive testing. This method can effectively ensure the resolution of buildings in the target area of ​​the production plant, and at the same time, it can better ensure that all target buildings on the preset flight path can be judged as potentially experiencing a fire in a very short time. This greatly improves the intelligence, reliability, and fire detection efficiency of this invention.

[0023] Preferably, the smallest unit of the first preset time point and the second preset time point is accurate to the second.

[0024] Preferably, the fifth preset threshold is set to two percent of the area of ​​the second target search box. This setting was determined by the technical personnel of the present invention through a large number of tests and can effectively ensure the building fire monitoring effect.

[0025] It is understandable that, at the same time on two adjacent days, although the number of people staying in the same building, their locations, and their actions may differ at different times on the same day, resulting in different amounts of heat generated, the grayscale level of the building in the first and second grayscale images should not rise from low to high temperature. Based on this, the present invention designs a factory area safety monitoring scheme based on data fusion analysis, solving the technical problem of how to apply infrared thermal imaging technology to fire monitoring of target buildings in a certain area, and greatly improving the intelligence, reliability, and fire detection efficiency of the present invention.

[0026] S200: Control the drone to start flying along a preset route at the first preset time point of the next day of the current date. The preset route includes a first preset waypoint. Control the drone to fly to the first preset waypoint and use the infrared thermal imager installed on the drone to take a second infrared thermal image of the target area of ​​the production plant at the second preset time point.

[0027] Specifically, the pan-tilt angle of the infrared thermal imager remains unchanged when capturing the first and second infrared thermal images.

[0028] S300: The first and second infrared thermal imaging images are denoised using median filtering. Preprocessing is performed on both images to obtain a first preprocessed image and a second preprocessed image. The first preprocessed image includes background noise, multiple target buildings, and edge regions. A quantization threshold is selected to transform the first and second preprocessed images into two grayscale images with only two grayscale levels, corresponding to temperature values ​​above 150 degrees Celsius and below 150 degrees Celsius, respectively. The first grayscale image is segmented using connected component analysis to identify the first target building. A first target building is then established based on the first target building. The search box performs image segmentation on the second grayscale image using connected component analysis to segment out the second target building. A second target search box is then established based on the second target building. The first actual geographic coordinates corresponding to the four vertices of the first target search box are calculated based on the pixel coordinates of the four vertices of the second target search box. The second actual geographic coordinates are then calculated based on the pixel coordinates of the four vertices of the second target search box. Based on the first and second actual geographic coordinates, it is determined whether the first target building and the second target building refer to the same building. It is also determined whether the grayscale level of the building in the first and second grayscale images has increased from a low temperature to a high temperature. Based on the determination results, it is decided whether to output an alarm signal regarding a suspected fire in the building.

[0029] Specifically, the conversion between pixel coordinates and geographic coordinates is based on existing technologies, which will not be elaborated upon in this invention.

[0030] Specifically, establishing a first target search box based on the first target building includes: Establish the minimum bounding rectangle of all image corner points of the first target building. The minimum bounding rectangle includes all image corner points of the first target building and is the first target search box.

[0031] Specifically, the step of establishing a second target search box based on the second target building includes: Establish the minimum bounding rectangle of all image corner points of the second target building. The minimum bounding rectangle includes all image corner points of the second target building and is the second target search box.

[0032] Specifically, the connected component is an eight-way connected component.

[0033] Specifically, determining whether the first target building and the second target building refer to the same building based on the first actual geographic coordinates and the second actual geographic coordinates includes: Calculate the first Euclidean distance between the geographic coordinates of the top left corner vertex of the first target search box and the geographic coordinates of the top left corner vertex of the second target search box, and determine whether the first Euclidean distance is less than or equal to a first preset threshold. Calculate the second Euclidean distance between the geographic coordinates of the top right corner vertex of the first target search box and the geographic coordinates of the top right corner vertex of the second target search box, and determine whether the second Euclidean distance is less than or equal to a first preset threshold. Calculate the third Euclidean distance between the geographic coordinates of the lower left corner vertex of the first target search box and the geographic coordinates of the lower left corner vertex of the second target search box, and determine whether the third Euclidean distance is less than or equal to a first preset threshold. Calculate the fourth Euclidean distance between the geographic coordinates of the lower right corner vertex of the first target search box and the geographic coordinates of the lower right corner vertex of the second target search box, and determine whether the fourth Euclidean distance is less than or equal to a first preset threshold. Based on the above judgment results, determine whether the first target building and the second target building refer to the same building.

[0034] Specifically, determining whether the first target building and the second target building refer to the same building based on the above judgment results includes: If the first Euclidean distance, the second Euclidean distance, the third Euclidean distance, and the fourth Euclidean distance are all less than or equal to the first preset threshold, it is determined that the first target building and the second target building refer to the same building.

[0035] Specifically, determining whether the first target building and the second target building refer to the same building based on the above judgment result also includes: If the first Euclidean distance is greater than or equal to the first preset threshold, or the second Euclidean distance is greater than or equal to the first preset threshold, or the third Euclidean distance is greater than or equal to the first preset threshold, or the fourth Euclidean distance is greater than or equal to the first preset threshold, it is determined that the first target building and the second target building do not refer to the same building.

[0036] It is understood that the present invention sets an error of 2 meters for each of the four vertices of the target search box, which further improves the reliability of the analysis results of the present invention.

[0037] Specifically, the step of determining whether the first target building and the second target building refer to the same building based on the first and second actual geographic coordinates, and determining whether the gray level of the building in the first and second grayscale images changes from low to high temperature, and determining whether to output an alarm signal regarding a suspected fire in the building based on the determination result, includes: If it is determined that the first target building and the second target building refer to the same building, and the gray level of the building in the first grayscale image and the second grayscale image increases from low temperature to high temperature, an alarm signal is output regarding the suspected fire in the building.

[0038] Specifically, determining whether the gray level of the building in the first grayscale image and the second grayscale image has increased from a low temperature to a high temperature includes: The system determines whether the area of ​​the building in the first and second grayscale images where the grayscale level rises from a low temperature to a high temperature is greater than or equal to a fifth preset threshold. If the area of ​​the building in the first and second grayscale images where the grayscale level rises from a low temperature to a high temperature is greater than or equal to the fifth preset threshold, then the building's grayscale level in the first and second grayscale images is determined to have risen from a low temperature to a high temperature; otherwise, the building's grayscale level in the first and second grayscale images is determined not to have risen from a low temperature to a high temperature.

[0039] Specifically, the step of determining whether the first target building and the second target building refer to the same building based on the first and second actual geographic coordinates, and determining whether the gray level of the building in the first and second grayscale images changes from low to high temperature, and determining whether to output an alarm signal regarding a suspected fire in the building based on the determination result, further includes: If it is determined that the first target building and the second target building do not refer to the same building, or if the gray level of the building in the first grayscale image and the second grayscale image does not rise from a low temperature to a high temperature, an alarm signal indicating that no fire has occurred in the building is output.

[0040] Specifically, the method further includes: If an alarm signal is output regarding a suspected fire in the building, the centroid coordinates of the second target search box are calculated based on the second actual geographic coordinates corresponding to the four vertices of the second target search box, and an alarm signal regarding a suspected fire in the building corresponding to the centroid coordinates is output.

[0041] Specifically, the calculation of the centroid coordinates includes: Based on the mean and standard deviation of the second infrared thermal imaging image, a piecewise linear transformation is performed on the grayscale value of the second infrared thermal imaging image to obtain the grayscale value of each point in the 8-bit single-channel image of the second infrared thermal imaging image. The centroid coordinates are then calculated based on the grayscale value of each point in the 8-bit single-channel image of the second infrared thermal imaging image.

[0042] The formula for the piecewise linear change is: Where μ and σ are the mean and standard deviation of the gray values ​​of the original image, respectively; x is the gray value of each point in the original image; y is the gray value of each point in the 8-bit single-channel image obtained after linear transformation; and y is the floor function.

[0043] The formula for calculating the centroid location is as follows: Where M and N represent the width and height of the second target search box, respectively; (Mmin, Nmin) and (Xmax, Ymax) represent the coordinates of the top-left and bottom-right corners of the second target search box, respectively; Iij is the grayscale value of a pixel within the rectangular area; i is the row position of the pixel; j is the column position of the pixel; and (Xc, Yc) represents the centroid coordinates. The area of ​​the second target search box is the product of its height and width.

[0044] Understandably, this invention controls a drone to begin flying along a preset route at a first preset time point on the current date. The preset route includes a first preset waypoint. The drone is controlled to fly to the first preset waypoint and uses an infrared thermal imager mounted on the drone to capture a first infrared thermal image of the target area of ​​the production plant at a second preset time point. The invention also controls the drone to begin flying along a preset route at a first preset time point on the next day, again including the first preset waypoint. The drone is controlled to fly to the first preset waypoint and uses the infrared thermal imager mounted on the drone to capture a second infrared thermal image of the target area at the second preset time point. Furthermore, the invention uses the first and second infrared thermal images to... The system determines whether the grayscale level of buildings in a target area increases based on the image, thereby identifying whether the building is suspected of being on fire. This allows for the assessment of potential fires in all production areas along a preset flight path using only an infrared thermal imager mounted on a drone. This significantly simplifies the hardware system and greatly improves the hardware deployment efficiency for building fire monitoring. At higher flight altitudes, it can simultaneously capture images of numerous buildings in the target area of ​​the production plant, enabling simultaneous assessment of potential fires in a large number of target buildings without the need for complex algorithm modeling. This greatly enhances the intelligence, usability, reliability, and fire detection efficiency of the invention, and significantly expands its application scenarios.

[0045] Please see Figure 3 The present invention provides another embodiment, which provides an intelligent building monitoring system based on image processing. The factory area safety monitoring system based on data fusion analysis includes: The acquisition module 100 includes an infrared thermal imager mounted on a drone, used to capture a first infrared thermal image of a target area in the production plant area, and also used to capture a second infrared thermal image of the target area in the production plant area. Control module 200 is used to control the UAV to start flying along a preset route at a first preset time point on the current date, the preset route including a first preset waypoint, control the UAV to fly to the first preset waypoint, and use the infrared thermal imager installed on the UAV to capture a first infrared thermal image of the target area of ​​the production plant at a second preset time point; it is also used to control the UAV to start flying along a preset route at a first preset time point on the next day, the preset route including a first preset waypoint, control the UAV to fly to the first preset waypoint, and use the infrared thermal imager installed on the UAV to capture a second infrared thermal image of the target area at a second preset time point; and it is used to denoise the first and second infrared thermal images using median filtering, preprocess the first and second infrared thermal images respectively to obtain a first preprocessed image and a second preprocessed image, the first preprocessed image including background noise, multiple target buildings and edge areas, and select a quantization threshold to transform the first and second preprocessed images respectively. Given two grayscale images with only two grayscale levels, a first grayscale image (above 150 degrees Celsius) and a second grayscale image (below 150 degrees Celsius), image segmentation is performed on the first grayscale image using connected component analysis to segment out the first target building. A first target search box is then established based on the first target building. Similarly, image segmentation is performed on the second grayscale image using connected component analysis to segment out the second target building. A second target search box is then established based on the second target building. The first and second actual geographic coordinates are calculated based on the pixel coordinates of the four vertices of the first and second target search boxes. Based on these coordinates, it is determined whether the first and second target buildings refer to the same building, and whether the grayscale level of the building in the first and second grayscale images changes from low to high. Based on the results, it is determined whether to output an alarm signal indicating a suspected fire in the building.

[0046] It should be noted that this invention controls the drone to start flying along a preset route at a first preset time point on the current date. The preset route includes a first preset waypoint. The drone is controlled to fly to the first preset waypoint, and an infrared thermal imager mounted on the drone is used to capture a first infrared thermal image of the target area of ​​the production plant at a second preset time point. The invention also controls the drone to start flying along a preset route at a first preset time point on the next day, the preset route including the first preset waypoint. The drone is controlled to fly to the first preset waypoint, and an infrared thermal imager mounted on the drone is used to capture a second infrared thermal image of the target area of ​​the production plant at the second preset time point. Furthermore, based on the first and second infrared thermal images... This invention uses image analysis to determine whether the grayscale level of buildings in a target area of ​​a production plant increases, thereby identifying whether a building is suspected of being on fire. It enables the assessment of potential fires in all production areas along a preset flight path using only an infrared thermal imager deployed on a drone. This significantly simplifies the hardware system and greatly improves the deployment efficiency of building fire monitoring hardware. At higher flight altitudes, it can simultaneously capture images of numerous buildings in the target area of ​​the production plant, enabling simultaneous assessment of potential fires in a large number of target buildings without the need for complex algorithm modeling. This greatly enhances the intelligence, usability, reliability, and fire detection efficiency of the invention, and significantly expands its application scenarios.

[0047] In a preferred embodiment, this application also provides an electronic device, the electronic device comprising: The computer device includes a memory and a processor, wherein the memory stores computer-readable instructions that, when executed by the processor, implement the aforementioned factory safety monitoring method based on data fusion analysis. The computer device can be broadly categorized as a server, terminal, or any other electronic device with the necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, memory, network interface, communication interface, etc., connected via a system bus. The processor of the computer device can be used to provide the necessary computing, processing, and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system, computer programs, etc. The internal memory can provide an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface and communication interface of the computer device can be used to connect and communicate with external devices via a network. When the computer program is executed by the processor, it performs the steps of the method of the present invention.

[0048] This invention can be implemented as a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes the steps of the methods of embodiments of the invention to be performed. In one embodiment, the computer program is distributed across multiple network-coupled computer devices or processors, such that the computer program is stored, accessed, and executed in a distributed manner by one or more computer devices or processors. A single method step / operation, or two or more method steps / operations, may be executed by a single computer device or processor or by two or more computer devices or processors. One or more method steps / operations may be executed by one or more computer devices or processors, and one or more other method steps / operations may be executed by one or more other computer devices or processors. One or more computer devices or processors may execute a single method step / operation, or execute two or more method steps / operations.

[0049] Those skilled in the art will understand that the method steps of this invention can be performed by a computer program instructing related hardware, such as a computer device or processor, to perform the steps of this invention when executed. Depending on the context, any references herein to memory, storage, databases, or other media may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state drive, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0050] Understandably, this invention controls a drone to begin flying along a preset route at a first preset time point on the current date. The preset route includes a first preset waypoint. The drone is controlled to fly to the first preset waypoint and uses an infrared thermal imager mounted on the drone to capture a first infrared thermal image of the target area of ​​the production plant at a second preset time point. The invention also controls the drone to begin flying along a preset route at a first preset time point on the next day, again including the first preset waypoint. The drone is controlled to fly to the first preset waypoint and uses the infrared thermal imager mounted on the drone to capture a second infrared thermal image of the target area at the second preset time point. Furthermore, the invention uses the first and second infrared thermal images to... The system determines whether the grayscale level of buildings in a target area increases based on the image, thereby identifying whether the building is suspected of being on fire. This allows for the assessment of potential fires in all production areas along a preset flight path using only an infrared thermal imager mounted on a drone. This significantly simplifies the hardware system and greatly improves the hardware deployment efficiency for building fire monitoring. At higher flight altitudes, it can simultaneously capture images of numerous buildings in the target area of ​​the production plant, enabling simultaneous assessment of potential fires in a large number of target buildings without the need for complex algorithm modeling. This greatly enhances the intelligence, usability, reliability, and fire detection efficiency of the invention, and significantly expands its application scenarios.

[0051] The technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification, provided that such combination does not contain contradictions.

[0052] The specific embodiments of the present invention described above do not constitute a limitation on the scope of protection of the present invention. Any other corresponding changes and modifications made in accordance with the technical concept of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A factory safety monitoring method based on data fusion analysis, characterized in that, The method includes: S100: Control the drone to start flying along a preset route at a first preset time point on the current date. The preset route includes a first preset waypoint. Control the drone to fly to the first preset waypoint and use the infrared thermal imager set on the drone to take a first infrared thermal image of the target area of ​​the production plant at a second preset time point. S200: Control the drone to start flying along a preset route at the first preset time point of the next day of the current date. The preset route includes a first preset waypoint. Control the drone to fly to the first preset waypoint and use the infrared thermal imager set on the drone to take a second infrared thermal image of the target area of ​​the production plant at the second preset time point. S300: The first and second infrared thermal imaging images are denoised using median filtering. Preprocessing is performed on both images to obtain a first preprocessed image and a second preprocessed image. The first preprocessed image includes background noise, multiple target buildings, and edge regions. A quantization threshold is selected to transform the first and second preprocessed images into two grayscale images with only two grayscale levels, corresponding to temperature values ​​above 150 degrees Celsius and below 150 degrees Celsius, respectively. The first grayscale image is segmented using connected component analysis to identify the first target building. A first target building is then established based on the first target building. The search box performs image segmentation on the second grayscale image using connected component analysis to segment out the second target building. A second target search box is then established based on the second target building. The first actual geographic coordinates corresponding to the four vertices of the first target search box are calculated based on the pixel coordinates of the four vertices of the second target search box. The second actual geographic coordinates are then calculated based on the pixel coordinates of the four vertices of the second target search box. Based on the first and second actual geographic coordinates, it is determined whether the first target building and the second target building refer to the same building. It is also determined whether the grayscale level of the building in the first and second grayscale images has increased from a low temperature to a high temperature. Based on the determination results, it is decided whether to output an alarm signal regarding a suspected fire in the building.

2. The factory safety monitoring method based on data fusion analysis according to claim 1, characterized in that, When capturing the first and second infrared thermal images, the pan-tilt angle of the infrared thermal imager remains unchanged.

3. The factory area safety monitoring method based on data fusion analysis according to claim 1, characterized in that, The connected component is an eight-way connected component.

4. The factory safety monitoring method based on data fusion analysis according to claim 1, characterized in that, The step of determining whether the first target building and the second target building refer to the same building based on the first actual geographic coordinates and the second actual geographic coordinates includes: Calculate the first Euclidean distance between the geographic coordinates of the top left corner vertex of the first target search box and the geographic coordinates of the top left corner vertex of the second target search box, and determine whether the first Euclidean distance is less than or equal to a first preset threshold. Calculate the second Euclidean distance between the geographic coordinates of the top right corner vertex of the first target search box and the geographic coordinates of the top right corner vertex of the second target search box, and determine whether the second Euclidean distance is less than or equal to a first preset threshold. Calculate the third Euclidean distance between the geographic coordinates of the lower left corner vertex of the first target search box and the geographic coordinates of the lower left corner vertex of the second target search box, and determine whether the third Euclidean distance is less than or equal to a first preset threshold. Calculate the fourth Euclidean distance between the geographic coordinates of the lower right corner vertex of the first target search box and the geographic coordinates of the lower right corner vertex of the second target search box, and determine whether the fourth Euclidean distance is less than or equal to a first preset threshold. Based on the above judgment results, determine whether the first target building and the second target building refer to the same building.

5. The factory area safety monitoring method based on data fusion analysis according to claim 4, characterized in that, The step of determining whether the first target building and the second target building refer to the same building based on the above judgment results includes: If the first Euclidean distance, the second Euclidean distance, the third Euclidean distance, and the fourth Euclidean distance are all less than or equal to the first preset threshold, it is determined that the first target building and the second target building refer to the same building.

6. The factory safety monitoring method based on data fusion analysis according to claim 4, characterized in that, The step of determining whether the first target building and the second target building refer to the same building based on the above judgment result also includes: If the first Euclidean distance is greater than or equal to the first preset threshold, or the second Euclidean distance is greater than or equal to the first preset threshold, or the third Euclidean distance is greater than or equal to the first preset threshold, or the fourth Euclidean distance is greater than or equal to the first preset threshold, it is determined that the first target building and the second target building do not refer to the same building.

7. The factory safety monitoring method based on data fusion analysis according to claim 1, characterized in that, The process of determining whether the first target building and the second target building refer to the same building based on the first and second actual geographical coordinates, and determining whether the gray level of the building in the first and second grayscale images changes from low to high temperature, and determining whether to output an alarm signal regarding a suspected fire in the building based on the determination result, includes: If it is determined that the first target building and the second target building refer to the same building, and the gray level of the building in the first grayscale image and the second grayscale image increases from low temperature to high temperature, an alarm signal is output regarding the suspected fire in the building.

8. The factory area safety monitoring method based on data fusion analysis according to claim 1, characterized in that, The step of determining whether the first target building and the second target building refer to the same building based on the first and second actual geographical coordinates, and determining whether the gray level of the building in the first and second grayscale images changes from low to high temperature, and determining whether to output an alarm signal regarding a suspected fire in the building based on the determination result, further includes: If it is determined that the first target building and the second target building do not refer to the same building, or if the gray level of the building in the first grayscale image and the second grayscale image does not rise from a low temperature to a high temperature, an alarm signal indicating that no fire has occurred in the building is output.

9. The factory area safety monitoring method based on data fusion analysis according to claim 7, characterized in that, The method further includes: If an alarm signal is output regarding a suspected fire in the building, the centroid coordinates of the second target search box are calculated based on the second actual geographic coordinates corresponding to the four vertices of the second target search box, and an alarm signal regarding a suspected fire in the building corresponding to the centroid coordinates is output.

10. A factory area safety monitoring system based on data fusion analysis, characterized in that, include: The acquisition module includes an infrared thermal imager mounted on a drone, used to capture a first infrared thermal image of a target area in the production plant area, and also used to capture a second infrared thermal image of the target area in the production plant area. The control module is used to control the UAV to start flying along a preset route at a first preset time point on the current date. The preset route includes a first preset waypoint. The module controls the UAV to fly to the first preset waypoint and use an infrared thermal imager mounted on the UAV to capture a first infrared thermal image of the target area of ​​the production plant at a second preset time point. The module is also used to control the UAV to start flying along a preset route at a first preset time point on the next day. The preset route includes a first preset waypoint. The module controls the UAV to fly to the first preset waypoint and use an infrared thermal imager mounted on the UAV to capture a second infrared thermal image of the target area of ​​the production plant at a second preset time point. The module further uses median filtering to denoise the first and second infrared thermal images, preprocessing them to obtain a first preprocessed image and a second preprocessed image. The first preprocessed image includes background noise, multiple target buildings, and edge regions. A quantization threshold is selected to transform the first and second preprocessed images. The image is replaced with a first grayscale image and a second grayscale image, each with only two grayscale levels. These two grayscale levels correspond to temperature values ​​above 150 degrees Celsius (high temperature) and below 150 degrees Celsius (low temperature), respectively. The first grayscale image is segmented using connected component analysis to identify the first target building. A first target search box is then created based on the first target building. Similarly, the second grayscale image is segmented using connected component analysis to identify the second target building. A second target search box is then created based on the second target building. The first and second actual geographic coordinates are used to calculate the first and second actual geographic coordinates of the four vertices of the first and second target search boxes. Based on these coordinates, it is determined whether the first and second target buildings refer to the same building, and whether the grayscale level of the building in the first and second grayscale images changes from low to high temperature. Based on the results, an alarm signal indicating a suspected fire in the building is output.

Images