Fire monitoring method, system, equipment and medium of Internet of Things monitoring robot

Abstract

The embodiment of the invention discloses a fire monitoring method, system and equipment of an Internet of Things monitoring robot and a medium, the system controls the monitoring robot to inspect a room according to a preset route and collect an infrared image and a visible light image, and the system generates a first image according to the infrared image and generates a second image according to the visible light image. The system extracts a heat source signal area from the first image, marks the heat source signal area as a first area, and generates the first area. The system extracts an object contour curve from the second image, marks the object contour curve as a second area, and generates the second area; the system determines whether the first region coincides with the second region based on a mapping relationship between the first image and the second image. And if the first area does not coincide with the second area, the system generates a fire early warning signal. And the system sends the fire early warning signal to external equipment for reminding. Through combination of infrared and visible light images, whether the heat source is abnormal can be more accurately judged compared with single use of infrared or visible light.

Description

Technical Field

[0001] The present invention relates to the field of fire monitoring technology, and in particular to a fire monitoring method, system, equipment and medium for an Internet of Things monitoring robot. Background Art

[0002] The traditional way of home monitoring is to install the control camera on the indoor wall to facilitate remote viewing of the indoor situation to prevent theft, personal injury and the operation of indoor electrical appliances. Based on the traditional monitoring method, manual viewing is usually used, but due to various reasons, manual viewing cannot be performed for a long time, making it impossible to obtain the indoor situation in time.

[0003] Secondly, traditional monitoring equipment can only monitor one area and cannot gradually screen the entire house. If you want to gradually screen the entire house, you need to set up multiple cameras in each area to monitor the entire house.

[0004] With the development of the Internet of Things, some monitoring robots have emerged that can monitor indoors along preset routes. The monitoring robots can obtain images of different areas of the room along the preset routes for users to view, such as monitoring natural gas leaks in the kitchen.

[0005] Currently, monitoring robots can only monitor natural gas leaks in the kitchen. They use installed sensors to monitor the natural gas content in the kitchen for remote early warning.

[0006] However, in the case of electrical fires, since electrical fires are not limited to one location in the kitchen, when an electrical fire occurs due to a short circuit, the current monitoring robot can only capture images, but cannot analyze the images, making it impossible to accurately analyze the heat source conditions at each location in the image to determine whether a fire has occurred. Since electrical fires occur very quickly, if the monitoring robot is unable to issue an early warning, it will lead to fire accidents, which in turn affect the safety of people and property. Summary of the invention

[0007] Based on this, it is necessary to propose a fire monitoring method, system, equipment and medium for an Internet of Things monitoring robot to solve the above technical problems.

[0008] The present invention provides a fire monitoring method for an Internet of Things monitoring robot, the method comprising:

[0009] Acquire an infrared image of the monitoring robot during the current patrol cycle to generate a first image;

[0010] Acquire the visible light image of the monitoring robot during the current patrol cycle to generate a second image;

[0011] Extracting a heat source signal region from the first image to generate a first region;

[0012] Extracting a closed contour curve of an object in the image from the second image to generate a second area;

[0013] comparing the first region with the second region according to a mapping relationship between the first image and the second image;

[0014] If the first area does not overlap with the second area, generating a fire warning signal;

[0015] The fire warning signal is sent to the outside.

[0016] In at least one embodiment of the present application, the step of comparing the first area with the second area according to the mapping relationship between the first image and the second image further includes:

[0017] If the first area completely overlaps with the second area, a normal signal is generated and the next cycle of inspection is performed.

[0018] In at least one embodiment of the present application, the method further includes:

[0019] Acquire three adjacent frames of the heat source signal in the first image to obtain a heat source comparison diagram;

[0020] Extracting a first heat source region, a second heat source region, and a third heat source region from the heat source comparison map;

[0021] Compare the first heat source region with the second heat source region and the third heat source region respectively to obtain a comparison overlap rate;

[0022] comparing the comparison coincidence rate with a coincidence rate threshold;

[0023] If the comparison coincidence rate is less than the coincidence rate threshold, a confirmed fire warning signal is generated.

[0024] In at least one embodiment of the present application, the method further includes:

[0025] If the comparison coincidence rate is not less than the coincidence rate threshold, the fire warning signal is modified into a normal signal.

[0026] In at least one embodiment of the present application, the method further includes:

[0027] A fire command is generated based on the confirmed fire warning signal and sent to an external APP for reminder and alert.

[0028] In at least one embodiment of the present application, the method further includes:

[0029] Obtain current data at the IoT switch;

[0030] Screening out a maximum value from the current data to obtain a maximum current value;

[0031] Calculating an average value of the current data to obtain an average current value;

[0032] Obtaining a preset current threshold, calculating the sum of the average current value and the preset current threshold, and obtaining a reference current value;

[0033] Comparing the maximum current value with the reference current value;

[0034] If the maximum current value exceeds the reference current value, a short circuit fire warning signal is generated.

[0035] In at least one embodiment of the present application, the method further includes:

[0036] If the maximum current value does not exceed the reference current value, a fire warning signal due to other reasons is generated.

[0037] The present invention provides a fire monitoring system for an Internet of Things monitoring robot, the system comprising:

[0038] An infrared image acquisition module is used to acquire infrared images of the monitoring robot during the patrol cycle;

[0039] A visible light image acquisition module is used to acquire visible light images of the monitoring robot during the inspection cycle;

[0040] A heat source region extraction module, used to extract a heat source signal region in the first image;

[0041] A contour region extraction module, used for extracting a closed contour region in the second image;

[0042] A comparison module compares the first area with the second area to generate a comparison result, wherein the comparison result includes a fire warning signal and a normal signal;

[0043] An early warning signal sending module is used to send a fire early warning signal;

[0044] The system performs the following steps:

[0045] Acquire an infrared image of the monitoring robot during the current patrol cycle to generate a first image;

[0046] Acquire the visible light image of the monitoring robot during the current patrol cycle to generate a second image;

[0047] Extracting a heat source signal region from the first image to generate a first region;

[0048] Extracting a closed contour curve of an object in the image from the second image to generate a second area;

[0049] comparing the first region with the second region according to a mapping relationship between the first image and the second image;

[0050] If the first area does not overlap with the second area, generating a fire warning signal;

[0051] The fire warning signal is sent to the outside.

[0052] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0053] An infrared image acquisition module is used to acquire infrared images of the monitoring robot during the patrol cycle;

[0054] A visible light image acquisition module is used to acquire visible light images of the monitoring robot during the inspection cycle;

[0055] A heat source region extraction module, used to extract a heat source signal region in the first image;

[0056] A contour region extraction module, used for extracting a closed contour region in the second image;

[0057] A comparison module compares the first area with the second area to generate a comparison result, wherein the comparison result includes a fire warning signal and a normal signal;

[0058] An early warning signal sending module is used to send a fire early warning signal;

[0059] The system performs the following steps:

[0060] Acquire an infrared image of the monitoring robot during the current patrol cycle to generate a first image;

[0061] Acquire the visible light image of the monitoring robot during the current patrol cycle to generate a second image;

[0062] Extracting a heat source signal region from the first image to generate a first region;

[0063] Extracting a closed contour curve of an object in the image from the second image to generate a second area;

[0064] comparing the first region with the second region according to a mapping relationship between the first image and the second image;

[0065] If the first area does not overlap with the second area, generating a fire warning signal;

[0066] The fire warning signal is sent to the outside.

[0067] A computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to perform the following steps:

[0068] An infrared image acquisition module is used to acquire infrared images of the monitoring robot during the patrol cycle;

[0069] A visible light image acquisition module is used to acquire visible light images of the monitoring robot during the inspection cycle;

[0070] A heat source region extraction module, used to extract a heat source signal region in the first image;

[0071] A contour region extraction module, used for extracting a closed contour region in the second image;

[0072] A comparison module compares the first area with the second area to generate a comparison result, wherein the comparison result includes a fire warning signal and a normal signal;

[0073] An early warning signal sending module is used to send a fire early warning signal;

[0074] The system performs the following steps:

[0075] Acquire an infrared image of the monitoring robot during the current patrol cycle to generate a first image;

[0076] Acquire the visible light image of the monitoring robot during the current patrol cycle to generate a second image;

[0077] Extracting a heat source signal region from the first image to generate a first region;

[0078] Extracting a closed contour curve of an object in the image from the second image to generate a second area;

[0079] comparing the first region with the second region according to a mapping relationship between the first image and the second image;

[0080] If the first area does not overlap with the second area, generating a fire warning signal;

[0081] The fire warning signal is sent to the outside.

[0082] The fire monitoring method, system, device and medium of the Internet of Things monitoring robot implementing the present invention will have at least the following beneficial effects:

[0083] The present invention proposes a fire monitoring method, system, equipment and medium for an Internet of Things monitoring robot. The system controls the monitoring robot to patrol indoors along a preset route and collect infrared images and visible light images. The system generates a first image based on the infrared image and generates a second image based on the visible light image.

[0084] The system extracts a heat source signal region from the first image and marks it as a first region to generate a first region.

[0085] The system extracts the object contour curve from the second image and marks it as a second region to generate the second region.

[0086] The system determines whether the first area overlaps with the second area based on the mapping relationship between the first image and the second image.

[0087] If the first area does not overlap with the second area, the system generates a fire warning signal.

[0088] The system sends fire warning signals to external devices for reminder.

[0089] The combination of infrared and visible light images can more accurately determine whether the heat source is abnormal than using infrared or visible light alone, avoiding false alarms caused by normally high temperature objects (such as light bulbs and ovens). BRIEF DESCRIPTION OF THE DRAWINGS

[0090] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0091] in:

[0092] Figure 1 A flowchart of a fire monitoring method of an Internet of Things monitoring robot in one embodiment;

[0093] Figure 2 A flowchart of a fire monitoring method of an Internet of Things monitoring robot in another embodiment;

[0094] Figure 3 A flowchart of a fire monitoring method of an Internet of Things monitoring robot in yet another embodiment;

[0095] Figure 4 A structural block diagram of a fire monitoring system of an Internet of Things monitoring robot in one embodiment;

[0096] Figure 5 FIG. 4 is a structural block diagram of a computer device in one embodiment.

[0097] in:

[0098] 100. Fire monitoring system of the Internet of Things monitoring robot; 110. Infrared image acquisition module; 120. Visible light image acquisition module; 130. Heat source area extraction module; 140. Contour area extraction module; 150. Comparison module; 160. Warning signal sending module. DETAILED DESCRIPTION

[0099] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0100] The present invention provides a fire monitoring method for an Internet of Things monitoring robot, the method comprising:

[0101] S101, obtaining an infrared image of the monitoring robot in the current patrol cycle to generate a first image;

[0102] S102, obtaining a visible light image of the monitoring robot during the current patrol cycle, and generating a second image;

[0103] S103, extracting a heat source signal region from the first image to generate a first region;

[0104] S104, extracting a closed contour curve of the object in the image from the second image to generate a second area;

[0105] S105, comparing the first region with the second region according to a mapping relationship between the first image and the second image;

[0106] S106. If the first area does not overlap with the second area, generating a fire warning signal;

[0107] S107: Send the fire warning signal to the outside.

[0108] Please refer to Figure 1 In this embodiment, the system controls the monitoring robot to patrol the room along a preset route, collect infrared images and visible light images, and the system generates a first image based on the infrared image and a second image based on the visible light image.

[0109] The system extracts a heat source signal region from the first image and marks it as a first region to generate a first region.

[0110] The system extracts the object contour curve from the second image and marks it as a second region to generate the second region.

[0111] The system determines whether the first area overlaps with the second area based on the mapping relationship between the first image and the second image.

[0112] If the first area does not overlap with the second area, the system generates a fire warning signal.

[0113] The system sends fire warning signals to external devices for reminder.

[0114] The combination of infrared and visible light images can more accurately determine whether the heat source is abnormal than using infrared or visible light alone, avoiding false alarms caused by normally high temperature objects (such as light bulbs and ovens).

[0115] Compared with traditional fixed cameras or monitoring methods that only target a single area, this method uses monitoring robots to patrol the entire house, covering a wider range.

[0116] Realize rapid detection and early warning to effectively reduce fire risks.

[0117] By comparing the first area with the second area, the influence of normal heat sources and conventional objects is eliminated, significantly reducing the false alarm rate.

[0118] By sending fire warning signals in real time through the Internet of Things, users can remotely understand the indoor situation and take timely measures.

[0119] The system automatically collects and processes image data, eliminating the need for long-term manual monitoring and making up for the shortcomings of traditional monitoring methods.

[0120] It should be noted that the infrared image of the monitoring robot during the current patrol cycle is obtained to generate the first image. The system captures the infrared image through the infrared sensor of the monitoring robot to reflect the heat distribution of the object in the scene. The generated first image can intuitively display the heat source signal. The infrared image is an infrared video image. Each frame of the infrared image is segmented to segment each frame of the infrared frame image to obtain the first image.

[0121] Infrared images can be used to detect potential thermal anomalies, such as hot areas caused by short circuits or electrical fires.

[0122] Obtain the visible light image of the monitoring robot during the current patrol cycle to generate a second image. The system obtains the visible light image through the ordinary camera on the monitoring robot to intuitively record the appearance and layout of the objects in the scene.

[0123] Visible light images contain visual information about the environment, such as the shape, outline, and position of objects.

[0124] The visible light image is a visible light video, and each frame of the visible light image is segmented to obtain a visible light frame image of each frame to obtain a second image.

[0125] The system extracts the area with abnormal temperature in the infrared image (ie, the heat source signal) and defines it as the "first area".

[0126] Filter out possible high-temperature areas and effectively reduce the interference of redundant data on judgment.

[0127] Convert the thermal information of infrared images into a quantifiable area to provide a basis for subsequent comparison.

[0128] The system uses the mapping relationship to compare the heat source area (first area) in the infrared image with the object contour area (second area) in the visible light image.

[0129] Determine whether the heat source coincides with the location of a specific object and filter out abnormal heat sources.

[0130] The mapping relationship ensures the spatial correspondence of the two image data, making the determination of the heat source and specific location more accurate.

[0131] When the heat source signal area (first area) cannot match the object contour area (second area), the system determines that the heat source may be an abnormally high temperature point and generates a fire warning signal.

[0132] Rapidly identify abnormal heat sources and sound alarms to ensure timely warning.

[0133] For invisible fire sources (such as short circuit high temperature areas), early detection is achieved through the non-overlapping characteristics.

[0134] Realize the remote early warning function, so that users can take emergency measures in the first time to avoid the expansion of fire.

[0135] It should be noted that the first region extraction process may be processed by image processing techniques, such as threshold segmentation, region growing, edge detection, etc. In this embodiment, edge detection is used for extraction.

[0136] In the process of extracting the second area, before extracting the second area, it is usually necessary to preprocess the visible light image to improve the accuracy of the subsequent extraction process.

[0137] Convert color images to grayscale images, retain only brightness information, and reduce data complexity. Use Gaussian denoising to remove image noise and retain the clarity of object edges. Then use histogram equalization and gamma correction to enhance the visibility of object contours.

[0138] Edge detection is used for detection, and then contour extraction is performed to extract the second area.

[0139] In at least one embodiment of the present application, the step of comparing the first area with the second area according to the mapping relationship between the first image and the second image further includes:

[0140] S108: If the first area completely overlaps with the second area, a normal signal is generated and the next cycle of inspection is performed.

[0141] Please refer to Figure 1 In this embodiment, the system determines whether the areas of the first region and the second region completely overlap. If they completely overlap, the existence of the heat source (for example, the heat generated by the lamp lighting) is reasonable, thereby avoiding false alarms.

[0142] By determining the overlap between the two, false alarms caused by normal heating conditions (such as light bulbs and heaters) can be eliminated.

[0143] In the case of complete overlap, the heat source is considered to come from a normal object, thus generating a normal signal.

[0144] After confirming that the heat source area (first area) and the object contour area (second area) are completely matched, the system generates a "normal signal".

[0145] The normal signal is a status indicator, indicating that there is no abnormal heat source in the current monitoring area.

[0146] Terminate the current fire warning detection process and mark the monitored area as safe.

[0147] Prepare for the next inspection and optimize monitoring efficiency. Clarify the system judgment logic to ensure that safe heat sources will not falsely trigger fire warnings. Improve system stability and accuracy and reduce interference to users.

[0148] The system automatically moves to the next patrol cycle and performs a new round of image acquisition and comparison in other areas or the same area to ensure full coverage of continuous monitoring.

[0149] By accurately comparing the heat source area with the object contour area, the interference of normal heat sources (such as light bulbs and heating equipment) can be effectively eliminated, significantly reducing the false alarm rate.

[0150] Avoid frequent interruptions to users due to false alarms, and improve the practicality of the system and user experience. After completing the monitoring of the current area, it automatically enters the next patrol cycle to ensure that all indoor areas can be continuously monitored. Compared with the monitoring method of traditional fixed cameras, it has a wider coverage and fewer blind spots.

[0151] The system judges the status based on real-time data to ensure that the current detection results are based on the latest environmental information. The dynamic monitoring feature makes the system more flexible and adapts to the complex heat source distribution and environmental changes in the early stage of a fire.

[0152] By generating normal signals, it avoids sending useless warning information to users and reduces the burden on users to deal with false alarms.

[0153] Users will only receive warnings when abnormal situations actually exist, reducing unnecessary interference.

[0154] The first area: the heat source signal area extracted from the infrared image, reflecting the actual location and range of the heat source.

[0155] The second area: object contour curves extracted from visible light images, indicating the actual distribution and boundaries of objects in the scene.

[0156] Complete overlap: refers to the fact that the heat source area in the infrared image and the object contour area in the visible light image are highly consistent in position and range.

[0157] In at least one embodiment of the present application, the method further includes:

[0158] S201, acquiring three adjacent frames of the heat source signal in the first image to obtain a heat source comparison diagram;

[0159] S202, extracting a first heat source region, a second heat source region, and a third heat source region from the heat source comparison map;

[0160] S203, comparing the first heat source region with the second heat source region and the third heat source region respectively to obtain a comparison overlap rate;

[0161] S204, comparing the comparison coincidence rate with a coincidence rate threshold;

[0162] S205: If the comparison coincidence rate is less than the coincidence rate threshold, a fire warning signal is generated to confirm the fire.

[0163] In at least one embodiment of the present application, the method further includes:

[0164] S206: If the comparison coincidence rate is not less than the coincidence rate threshold, modify the fire warning signal to a normal signal.

[0165] Please refer to Figure 1-Figure 2 In this embodiment, after the system locates the heat source signal of the frame image in the first image, it continuously acquires the infrared frame images in the next three adjacent first images to generate a heat source comparison map.

[0166] Expand static image analysis to dynamic monitoring, increase the accuracy of abnormal heat source detection, and filter out false alarms caused by transient heat sources (such as light reflection) in a short period of time.

[0167] The heat source areas corresponding to three time points (i.e., the first, second, and third heat source areas) are extracted from the heat source comparison diagram to indicate the specific locations and ranges of the heat sources at different time points.

[0168] Extracting continuous heat source area information enables the system to capture the dynamic characteristics of the heat source (such as diffusion, movement).

[0169] It is convenient to judge whether the heat source is normal (such as a fixed heat source) or abnormal (such as a jumping spark).

[0170] The heat source areas at three time points were compared and their overlap was calculated to quantify the dynamic changes of the heat source.

[0171] By calculating the overlap rate, it is possible to determine whether the heat source is stable (high overlap rate) or has abnormal changes (low overlap rate).

[0172] The overlap rate is an important parameter for dynamic heat source analysis and can effectively distinguish normal heat sources from abnormal heat sources.

[0173] A stable heat source (such as a light bulb) will have a higher coincidence rate, while a heat source such as a flickering spark or open flame will cause the coincidence rate to drop significantly.

[0174] The introduction of the overlap rate improves the sensitivity to dynamic anomalies and enhances the accuracy of fire monitoring.

[0175] The system will compare the overlap rate with the preset overlap rate threshold as a criterion for judging the stability of the heat source. The overlap rate threshold can be pre-set according to the heat source characteristics of the actual scene. Determine whether the heat source changes exceed the normal range and judge whether it is a potential fire risk.

[0176] It should be noted that the overlap rate is calculated here by comparing two by two, and then comparing the results with the overlap rate threshold in turn. As long as one of them does not reach the overlap rate threshold, a fire warning signal is generated.

[0177] In the case of a high coincidence rate, it can be confirmed that the heat source is stable (normal heat source).

[0178] In the case of low overlap rate, further analysis can be performed to determine whether it is necessary to issue a fire warning signal.

[0179] When the overlap rate is lower than the set threshold, the system considers the heat source to be an abnormal heat source and generates a fire warning signal. A confirmed fire warning signal indicates that the risk of fire has increased significantly. Rapidly identify abnormal dynamic heat sources and issue an alarm for possible fire situations. Prevent delayed warnings and improve the timeliness of the fire monitoring system.

[0180] When the overlap rate is higher than or equal to the threshold, the system confirms that the heat source is normal and modifies the previously generated fire warning signal to a "normal signal." This improves the judgment accuracy of the system, reduces the interference of false alarms to users, and ensures the reliability and credibility of the warning signal.

[0181] By comparing the overlap rate, dynamic abnormal heat sources (such as fire) and stable heat sources (such as light bulbs) can be effectively distinguished.

[0182] Reducing false alarms caused by normal heat sources in the environment significantly improves the system's warning accuracy.

[0183] Continuous three-frame analysis of dynamic heat sources enables the system to capture the characteristics of the early stages of a fire (such as spark jumping and flame spread).

[0184] The system's sensitivity to rapidly changing heat sources is improved to adapt to scenarios with complex early-stage fire characteristics.

[0185] The system automatically determines and modifies the signal status, eliminating the need for users to frequently deal with false alarms. The entire process of fire warning is automated, reducing user management costs.

[0186] The combination of dynamic analysis and threshold judgment ensures that fire risks can be captured in a timely manner at an early stage, which is particularly suitable for fire scenarios with unstable initial characteristics such as electrical fires.

[0187] By introducing continuous frame analysis and overlap rate judgment, accurate identification of dynamic heat sources is achieved, which can effectively distinguish normal and abnormal heat sources, and improve the sensitivity, accuracy and automation of fire monitoring. At the same time, this method reduces false alarms and reduces the need for user intervention.

[0188] In at least one embodiment of the present application, the method further includes:

[0189] A fire command is generated based on the confirmed fire warning signal and sent to an external APP for reminder and alert.

[0190] In this embodiment, after the system has gone through multiple steps of detection and judgment and confirmed that the fire warning signal is valid, a fire instruction is generated for further notifying the external system.

[0191] The fire command is sent to the external APP through the IoT communication module (such as Wi-Fi, Bluetooth, cellular network).

[0192] External APPs are usually installed on users' smartphones or other terminal devices to receive fire instructions and display relevant information.

[0193] Realize remote alarm so that users can be informed of fire risks in time no matter where they are.

[0194] Provide detailed fire information, such as heat source location, fire ignition time, etc., to assist users in making judgments and decisions.

[0195] External apps remind users of fire risks in a variety of ways, such as pop-up notifications, sound alarms, vibration prompts, and even linking with other smart devices (such as smart door locks and cameras).

[0196] Fire instructions are quickly transmitted to users after confirmation, ensuring that users can be informed and take countermeasures in the early stages of the fire.

[0197] Improve the timeliness of fire warnings and reduce the possibility of fire expansion and spread.

[0198] In at least one embodiment of the present application, the method further includes:

[0199] S301, obtaining current data at the IoT switch;

[0200] S302, selecting a maximum value from the current data to obtain a maximum current value;

[0201] S303, calculating the average value of the current data to obtain an average current value;

[0202] S304, obtaining a preset current threshold, calculating the sum of the average current value and the preset current threshold, and obtaining a reference current value;

[0203] S305, comparing the maximum current value with the reference current value;

[0204] S306: If the maximum current value exceeds the reference current value, a short circuit fire warning signal is generated.

[0205] In at least one embodiment of the present application, the method further includes:

[0206] S307: If the maximum current value does not exceed the reference current value, a fire warning signal due to other reasons is generated.

[0207] Please refer to Figure 1-Figure 3 In this embodiment, the current data is collected from the switch or related sensors in real time through the Internet of Things technology.

[0208] The system acquires continuous current data at the switch, and selects the maximum instantaneous current from the collected current data to evaluate the maximum load condition of the circuit.

[0209] Rapidly locate abnormally high current as the core basis for determining short circuit fire.

[0210] The system calculates the average value of current data to obtain the average current value. The average current value can more stably reflect the working status of the circuit and avoid misjudgment caused by single point abnormality.

[0211] A dynamic reference current value is obtained by adding a preset current threshold value of the circuit (determined by design or experience) to the average current value.

[0212] The maximum current value is compared with the dynamic reference current value to determine whether the current exceeds the normal range.

[0213] When the maximum current value exceeds the reference current value and the system detects an abnormally high current, it generates a short-circuit fire warning signal to indicate a potential short-circuit fire risk.

[0214] Improve the response speed of short circuit fire and ensure that the system can issue an alarm in time before the danger occurs.

[0215] When the maximum current value does not exceed the reference value, the system believes that the current abnormality is not caused by a short circuit, but may be due to other fire causes (such as overload, equipment heating).

[0216] Classify and warn different causes of fire to avoid confusion between short circuit and other causes of fire, facilitate users to make quick judgments and responses, and enhance the accuracy and intelligence of the warning system.

[0217] The introduction of a dynamic reference current value (average current value + preset threshold) enhances the system's adaptability to different circuit operating environments.

[0218] It reduces false positives and false negatives caused by relying solely on fixed thresholds, thus improving the reliability of the system.

[0219] The system can distinguish between short circuits and other causes of fire based on current characteristics, providing more accurate early warning information.

[0220] It helps users to quickly identify the cause of the fire and take targeted measures.

[0221] Real-time screening and analysis of maximum current values ​​enables the system to quickly detect abnormally high currents caused by short circuits.

[0222] The detection sensitivity and response speed of short-circuit fire are improved.

[0223] Through the collection and multi-level analysis of current data, combined with the application of dynamic thresholds, accurate detection and classified warning of short-circuit fires and other fires are achieved. The overall operation process is scientific and efficient, which significantly improves the accuracy, real-time and intelligent level of fire detection, and provides a strong guarantee for indoor electrical safety.

[0224] The present invention provides a fire monitoring system 100 for an Internet of Things monitoring robot, the system comprising:

[0225] The infrared image acquisition module 110 is used to acquire the infrared image of the monitoring robot during the inspection cycle;

[0226] The visible light image acquisition module 120 is used to acquire the visible light image of the monitoring robot during the inspection cycle;

[0227] A heat source region extraction module 130 is used to extract a heat source signal region in the first image;

[0228] A contour region extraction module 140, used to extract a closed contour region in the second image;

[0229] The comparison module 150 compares the first area with the second area to generate a comparison result, wherein the comparison result includes a fire warning signal and a normal signal;

[0230] The warning signal sending module 160 is used to send a fire warning signal;

[0231] The system performs the following steps:

[0232] Acquire an infrared image of the monitoring robot during the current patrol cycle to generate a first image;

[0233] Acquire the visible light image of the monitoring robot during the current patrol cycle to generate a second image;

[0234] Extracting a heat source signal region from the first image to generate a first region;

[0235] Extracting a closed contour curve of an object in the image from the second image to generate a second area;

[0236] comparing the first region with the second region according to a mapping relationship between the first image and the second image;

[0237] If the first area does not overlap with the second area, generating a fire warning signal;

[0238] The fire warning signal is sent to the outside.

[0239] Please refer to Figure 1-Figure 4In this embodiment, the fire monitoring system 100 of the Internet of Things monitoring robot controls the monitoring robot to patrol the room along a preset route, and collects infrared images and visible light images through the infrared image acquisition module 110 and the visible light image acquisition module 120. The fire monitoring system 100 of the Internet of Things monitoring robot generates a first image based on the infrared image, and the fire monitoring system 100 of the Internet of Things monitoring robot generates a second image based on the visible light image.

[0240] The fire monitoring system 100 of the IoT monitoring robot extracts a heat source signal area from the first image through the heat source area extraction module 130, marks it as the first area, and generates the first area.

[0241] The fire monitoring system 100 of the Internet of Things monitoring robot extracts the object contour curve from the second image through the contour area extraction module 140, marks it as the second area, and generates the second area.

[0242] The fire monitoring system 100 of the Internet of Things monitoring robot determines whether the first area overlaps with the second area based on the mapping relationship between the first image and the second image through the comparison module 150.

[0243] If the first area does not overlap with the second area, the system generates a fire warning signal.

[0244] The fire monitoring system 100 of the IoT monitoring robot sends a fire warning signal to an external device for reminder via the warning signal sending module 160 .

[0245] The combination of infrared and visible light images can more accurately determine whether the heat source is abnormal than using infrared or visible light alone, avoiding false alarms caused by normally high temperature objects (such as light bulbs and ovens).

[0246] Compared with traditional fixed cameras or monitoring methods that only target a single area, this method uses monitoring robots to patrol the entire house, covering a wider range.

[0247] Realize rapid detection and early warning to effectively reduce fire risks.

[0248] By comparing the first area with the second area, the influence of normal heat sources and conventional objects is eliminated, significantly reducing the false alarm rate.

[0249] By sending fire warning signals in real time through the Internet of Things, users can remotely understand the indoor situation and take timely measures.

[0250] The system automatically collects and processes image data, eliminating the need for long-term manual monitoring and making up for the shortcomings of traditional monitoring methods.

[0251] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0252] Acquire an infrared image of the monitoring robot during the current patrol cycle to generate a first image;

[0253] Acquire the visible light image of the monitoring robot during the current patrol cycle to generate a second image;

[0254] Extracting a heat source signal region from the first image to generate a first region;

[0255] Extracting a closed contour curve of an object in the image from the second image to generate a second area;

[0256] comparing the first region with the second region according to a mapping relationship between the first image and the second image;

[0257] If the first area does not overlap with the second area, generating a fire warning signal;

[0258] The fire warning signal is sent to the outside.

[0259] In this embodiment, the fire monitoring system 100 of the Internet of Things monitoring robot controls the monitoring robot to patrol the room along a preset route, and collects infrared images and visible light images through the infrared image acquisition module 110 and the visible light image acquisition module 120. The fire monitoring system 100 of the Internet of Things monitoring robot generates a first image based on the infrared image, and the fire monitoring system 100 of the Internet of Things monitoring robot generates a second image based on the visible light image.

[0260] The fire monitoring system 100 of the IoT monitoring robot extracts a heat source signal area from the first image through the heat source area extraction module 130, marks it as the first area, and generates the first area.

[0261] The fire monitoring system 100 of the Internet of Things monitoring robot extracts the object contour curve from the second image through the contour area extraction module 140, marks it as the second area, and generates the second area.

[0262] The fire monitoring system 100 of the Internet of Things monitoring robot determines whether the first area overlaps with the second area based on the mapping relationship between the first image and the second image through the comparison module 150.

[0263] If the first area does not overlap with the second area, the system generates a fire warning signal.

[0264] The fire monitoring system 100 of the IoT monitoring robot sends a fire warning signal to an external device for reminder via the warning signal sending module 160 .

[0265] The combination of infrared and visible light images can more accurately determine whether the heat source is abnormal than using infrared or visible light alone, avoiding false alarms caused by normally high temperature objects (such as light bulbs and ovens).

[0266] Compared with traditional fixed cameras or monitoring methods that only target a single area, this method uses monitoring robots to patrol the entire house, covering a wider range.

[0267] Realize rapid detection and early warning to effectively reduce fire risks.

[0268] By comparing the first area with the second area, the influence of normal heat sources and conventional objects is eliminated, significantly reducing the false alarm rate.

[0269] By sending fire warning signals in real time through the Internet of Things, users can remotely understand the indoor situation and take timely measures.

[0270] The system automatically collects and processes image data, eliminating the need for long-term manual monitoring and making up for the shortcomings of traditional monitoring methods.

[0271] Figure 5 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a terminal or a server. Figure 5 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor may implement the fire monitoring method of the Internet of Things monitoring robot. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor may implement the fire monitoring method of the Internet of Things monitoring robot. Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0272] In one embodiment, a computer-readable storage medium is provided, storing a computer program, wherein when the computer program is executed by a processor, the processor performs the following steps:

[0273] Acquire an infrared image of the monitoring robot during the current patrol cycle to generate a first image;

[0274] Acquire the visible light image of the monitoring robot during the current patrol cycle to generate a second image;

[0275] Extracting a heat source signal region from the first image to generate a first region;

[0276] Extracting a closed contour curve of an object in the image from the second image to generate a second area;

[0277] comparing the first region with the second region according to a mapping relationship between the first image and the second image;

[0278] If the first area does not overlap with the second area, generating a fire warning signal;

[0279] The fire warning signal is sent to the outside.

[0280] In this embodiment, the fire monitoring system 100 of the Internet of Things monitoring robot controls the monitoring robot to patrol the room along a preset route, and collects infrared images and visible light images through the infrared image acquisition module 110 and the visible light image acquisition module 120. The fire monitoring system 100 of the Internet of Things monitoring robot generates a first image based on the infrared image, and the fire monitoring system 100 of the Internet of Things monitoring robot generates a second image based on the visible light image.

[0281] The fire monitoring system 100 of the IoT monitoring robot extracts a heat source signal area from the first image through the heat source area extraction module 130, marks it as the first area, and generates the first area.

[0282] The fire monitoring system 100 of the Internet of Things monitoring robot extracts the object contour curve from the second image through the contour area extraction module 140, marks it as the second area, and generates the second area.

[0283] The fire monitoring system 100 of the Internet of Things monitoring robot determines whether the first area overlaps with the second area based on the mapping relationship between the first image and the second image through the comparison module 150.

[0284] If the first area does not overlap with the second area, the system generates a fire warning signal.

[0285] The fire monitoring system 100 of the IoT monitoring robot sends a fire warning signal to an external device for reminder via the warning signal sending module 160 .

[0286] The combination of infrared and visible light images can more accurately determine whether the heat source is abnormal than using infrared or visible light alone, avoiding false alarms caused by normally high temperature objects (such as light bulbs and ovens).

[0287] Compared with traditional fixed cameras or monitoring methods that only target a single area, this method uses monitoring robots to patrol the entire house, covering a wider range.

[0288] Realize rapid detection and early warning to effectively reduce fire risks.

[0289] By comparing the first area with the second area, the influence of normal heat sources and conventional objects is eliminated, significantly reducing the false alarm rate.

[0290] By sending fire warning signals in real time through the Internet of Things, users can remotely understand the indoor situation and take timely measures.

[0291] The system automatically collects and processes image data, eliminating the need for long-term manual monitoring and making up for the shortcomings of traditional monitoring methods.

[0292] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0293] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0294] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A fire monitoring method for an Internet of Things monitoring robot, characterized in that: The method comprises: Acquire an infrared image of the monitoring robot during the current patrol cycle to generate a first image; Acquire the visible light image of the monitoring robot during the current patrol cycle to generate a second image; Extracting a heat source signal region from the first image to generate a first region; Extracting a closed contour curve of an object in the image from the second image to generate a second area; comparing the first region with the second region according to a mapping relationship between the first image and the second image; If the first area does not overlap with the second area, generating a fire warning signal; The fire warning signal is sent to the outside.

2. The fire monitoring method of the Internet of Things monitoring robot according to claim 1, characterized in that: The step of comparing the first area with the second area according to the mapping relationship between the first image and the second image further includes: If the first area completely overlaps with the second area, a normal signal is generated and the next cycle of inspection is performed.

3. The fire monitoring method of the Internet of Things monitoring robot according to claim 1, characterized in that: The method further comprises: Acquire three adjacent frames of the heat source signal in the first image to obtain a heat source comparison diagram; Extracting a first heat source region, a second heat source region, and a third heat source region from the heat source comparison map; Compare the first heat source region with the second heat source region and the third heat source region respectively to obtain a comparison overlap rate; comparing the comparison coincidence rate with a coincidence rate threshold; If the comparison coincidence rate is less than the coincidence rate threshold, a confirmed fire warning signal is generated.

4. The fire monitoring method of the Internet of Things monitoring robot according to claim 3 is characterized in that: The method further comprises: If the comparison coincidence rate is not less than the coincidence rate threshold, the fire warning signal is modified into a normal signal.

5. The fire monitoring method of the Internet of Things monitoring robot according to claim 3, characterized in that: The method further comprises: A fire command is generated based on the confirmed fire warning signal and sent to an external APP for reminder and alert.

6. The fire monitoring method of the Internet of Things monitoring robot according to claim 3, characterized in that: The method further comprises: Obtain current data at the IoT switch; Screening out a maximum value from the current data to obtain a maximum current value; Calculating an average value of the current data to obtain an average current value; Obtaining a preset current threshold, calculating the sum of the average current value and the preset current threshold, and obtaining a reference current value; Comparing the maximum current value with the reference current value; If the maximum current value exceeds the reference current value, a short circuit fire warning signal is generated.

7. The fire monitoring method of the Internet of Things monitoring robot according to claim 6, characterized in that: The method further comprises: If the maximum current value does not exceed the reference current value, a fire warning signal due to other reasons is generated.

8. A fire monitoring system for an Internet of Things monitoring robot, characterized in that: The system comprises: An infrared image acquisition module is used to acquire infrared images of the monitoring robot during the patrol cycle; A visible light image acquisition module is used to acquire visible light images of the monitoring robot during the inspection cycle; A heat source region extraction module, used to extract a heat source signal region in the first image; A contour region extraction module, used for extracting a closed contour region in the second image; A comparison module compares the first area with the second area to generate a comparison result, wherein the comparison result includes a fire warning signal and a normal signal; The early warning signal sending module is used to send fire early warning signals.

9. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 7.

Images