Device, method and equipment for detecting cable forest fire caused by lightning stroke

Abstract

The invention discloses a device, a method and equipment for detecting a cable forest fire caused by lightning stroke, and belongs to the technical field of electric power facilities. The device comprises a feature recognition module which is used for obtaining a cable image between cable racks through at least two cameras and recognizing whether a forest fire triggering feature exists in the cable image or not; the feature verification module is used for verifying the forest fire triggering features in the cable images of the cameras to obtain the confidence coefficient of the forest fire triggering features; and the forest fire early warning module is used for generating forest fire early warning information under the condition that the existence of the forest fire triggering features is identified and the confidence exceeds a preset confidence threshold. According to the technical scheme, the forest fire triggering factors can be detected in time by identifying whether the forest fire triggering features exist in the cable image, and the false alarm rate of forest fire early warning can be reduced by determining the confidence coefficient of the forest fire triggering features, so that accurate and effective forest fire early warning information is fed back to workers in time, and the forest fire is prevented from being caused.

Description

Technical Field

[0001] The present application belongs to the technical field of electric power facilities, and specifically relates to a device, method and equipment for detecting cable mountain fires caused by lightning strikes. Background Art

[0002] Cable lines responsible for long-distance power transmission usually cross areas with complex terrain such as grasslands, mountains and hills. Due to the wide coverage area, often spanning tens or even hundreds of kilometers, it is difficult to take strict and comprehensive lightning protection measures for the entire cable line. This makes such cable lines more vulnerable to lightning strikes.

[0003] Lightning strikes can cause the current inside the cable to increase instantly, which may cause the cable to overload or short-circuit, and then generate electric sparks or local high temperatures, causing surrounding trees and weeds to catch fire. However, these mountainous areas and grasslands are often sparsely populated, and once a fire occurs, it is difficult for people to discover and extinguish it in time, which often results in serious losses.

[0004] Therefore, how to automatically detect whether there are wildfire triggering factors in the cable and issue wildfire warnings in a timely manner based on the wildfire triggering factors is an issue that people in this field urgently need to solve. Summary of the invention

[0005] The embodiments of the present application provide a device, method and equipment for detecting cable wildfires caused by lightning strikes, the purpose of which is to promptly feed back accurate and effective wildfire warning information to staff to avoid causing wildfires.

[0006] In a first aspect, an embodiment of the present application provides a device for detecting cable fires caused by lightning strikes, the device comprising:

[0007] A feature recognition module, used to obtain cable images between cable racks through at least two cameras, and identify whether there is a wildfire trigger feature in the cable image; wherein the feature type of the wildfire trigger feature includes at least one of a spark feature, a flame feature, a smoke feature, and a cable jitter feature;

[0008] A feature verification module is used to verify the wildfire triggering features in the cable images of each camera to obtain the confidence level of the wildfire triggering features;

[0009] The wildfire warning module is used to generate wildfire warning information when it is identified that there are wildfire triggering features and the confidence level exceeds a preset confidence threshold.

[0010] In a second aspect, an embodiment of the present application provides a method for detecting cable fires caused by lightning strikes, the method comprising:

[0011] The feature recognition module uses at least two cameras to obtain cable images between cable racks, and identifies whether there is a wildfire trigger feature in the cable image; wherein the feature type of the wildfire trigger feature includes at least one of a spark feature, a flame feature, a smoke feature, and a cable jitter feature;

[0012] Verify the wildfire triggering features in the cable images of each camera through a feature verification module to obtain the confidence level of the wildfire triggering features;

[0013] The wildfire warning module generates wildfire warning information when it is identified that there is a wildfire trigger feature and the confidence level exceeds a preset confidence threshold.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0016] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.

[0017] In an embodiment of the present application, a feature recognition module is used to obtain cable images between cable racks through at least two cameras, and to identify whether there are wildfire trigger features in the cable images; wherein the feature types of the wildfire trigger features include at least one of spark features, flame features, smoke features, and cable jitter features; a feature verification module is used to verify the wildfire trigger features in the cable images of each camera to obtain the confidence of the wildfire trigger features; a wildfire warning module is used to generate wildfire warning information when it is identified that there are wildfire trigger features and the confidence exceeds a preset confidence threshold. The above-mentioned cable wildfire detection device caused by lightning strikes can detect wildfire trigger factors in a timely manner by identifying whether there are wildfire trigger features in the cable images, and can reduce the false alarm rate of wildfire warnings by determining the confidence of the wildfire trigger features, thereby feeding back accurate and effective wildfire warning information to the staff in a timely manner to avoid causing wildfires. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a structural schematic diagram of a cable mountain fire detection device caused by lightning strike provided in Example 1 of the present application;

[0019] Figure 2 It is a structural schematic diagram of a cable mountain fire detection device caused by lightning strike provided in Example 2 of the present application;

[0020] Figure 3 It is a structural schematic diagram of a cable mountain fire detection device caused by lightning strike provided in Example 3 of the present application;

[0021] Figure 4 It is a flow chart of a method for detecting cable mountain fire caused by lightning strike provided in Embodiment 4 of the present application;

[0022] Figure 5 It is a schematic diagram of the structure of an electronic device provided in Example 5 of the present application. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only the part related to the present application but not all the contents are shown in the accompanying drawings. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of each operation can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0025] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0026] In the following, in conjunction with the accompanying drawings, the cable fire detection device, method and equipment caused by lightning strike provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0027] Embodiment 1

[0028] Figure 1 Schematic diagram of the structure of the cable fire detection device caused by lightning strike provided in the first embodiment of the present application. Figure 1 As shown, the device comprises:

[0029] The feature recognition module 110 is used to obtain the cable image between the cable racks through at least two cameras, and identify whether there is a wildfire trigger feature in the cable image; wherein the feature type of the wildfire trigger feature includes at least one of a spark feature, a flame feature, a smoke feature, and a cable jitter feature;

[0030] A feature verification module 120 is used to verify the wildfire triggering features in the cable images of each camera to obtain the confidence of the wildfire triggering features;

[0031] The wildfire warning module 130 is used to generate wildfire warning information when it is identified that there is a wildfire trigger feature and the confidence level exceeds a preset confidence threshold.

[0032] This application is applicable to scenarios where cables are laid in sparsely populated areas such as mountainous areas or grasslands. Specifically, the identification and verification of wildfire triggering features and the generation of wildfire warning information can be performed by smart terminal devices. Based on the received wildfire warning information, the staff can take corresponding risk avoidance measures for the cable locations with wildfire triggering features to avoid the occurrence of wildfires.

[0033] Based on the above usage scenarios, it can be understood that the executor of the present application can be a smart terminal device, such as a desktop computer, a laptop computer, a mobile phone, a tablet computer, and interactive multimedia, etc., and no excessive limitations are made here.

[0034] The feature recognition module 110 is used to obtain cable images between cable racks through at least two cameras, and identify whether there are wildfire triggering features in the cable images; wherein the feature types of the wildfire triggering features include at least one of spark features, flame features, smoke features and cable jitter features.

[0035] A cable is a device that can be used for communication or power transmission. A cable rack is a device for supporting and fixing cables. A cable image may refer to image data including cables between cable racks.

[0036] A camera is a device used to convert visual information in three-dimensional space into electronic signals. The basic process of a camera collecting cable images includes: the optical sensor behind the camera lens converts the light entering through the lens into an electrical signal; the photosensitive element in the optical sensor detects the intensity and color of the light and converts it into a voltage signal; the analog-to-digital converter converts the continuously changing analog voltage signal into a digital form for further processing and storage; the image processor processes and enhances the digital signal, which may include color correction, contrast adjustment, and noise reduction to improve image quality and clarity; the camera compresses the cable image to reduce the space and bandwidth required for storage and transmission; the processed and compressed cable image is output to the processor of the smart terminal device through an interface.

[0037] Wildfire triggering features may be image object features that may trigger wildfires, and their feature types may include spark features, flame features, smoke features, and cable shaking features. Specifically, spark features may refer to small flames or luminous particles generated during combustion, chemical reactions, or physical collisions; flame features may refer to a collection of materials with a certain geometric shape that is luminous and caused by heat; smoke features may refer to a translucent gaseous substance formed by tiny solid particles or liquid droplets suspended in the air; and cable shaking features may refer to a regular back-and-forth vibration or tremor of the cable.

[0038] By using image recognition technology on cable images, it is possible to identify whether there are wildfire triggering features in the cable images. Image recognition technology is a core technology in the field of computer vision that can automatically analyze and understand the content in digital images or videos. Image recognition technology can learn wildfire triggering features from a large number of annotated images including wildfire triggering features through machine learning algorithms and build models, and then use the model to classify, detect, and identify new input images.

[0039] In this technical solution, optionally, the device further includes:

[0040] Lightning strike identification module, used to obtain sound data in the cable laying area;

[0041] Accordingly, the feature recognition module is specifically used for:

[0042] When the volume of the sound data exceeds a preset volume threshold, the cable image between the cable racks is acquired by at least two cameras, and it is identified whether there is a wildfire triggering feature in the cable image.

[0043] The cable laying area can be a pre-set spatial area surrounding the cable. The maximum splash distance of Mars can be determined based on the position and height of the cable, and the setting can be based on the maximum splash distance.

[0044] Sound data may refer to sampled and digitized sound signals. By using an acoustic sensor, sound data of the cable laying area can be obtained. Among them, the acoustic sensor is an electronic device used to sense and convert sound signals.

[0045] The volume may be a physical quantity describing the size of a sound. The preset volume threshold may be a preset lower limit of the volume of sound data indicating that a lightning strike may occur in a cable laying area. The volume of the sound data may be determined according to the waveform amplitude of the sound data.

[0046] The advantage of this arrangement of the present invention is that, by obtaining and identifying images of cables between cable racks through a camera when the sound data in the cable laying area exceeds a preset volume threshold, the power consumption and cost of the present invention can be minimized on the basis of being able to detect lightning strikes in a timely manner.

[0047] The feature verification module 120 is used to verify the wildfire triggering features in the cable images of each camera to obtain the confidence level of the wildfire triggering features.

[0048] The confidence level of a wildfire trigger feature can be the degree of certainty about the real existence of the wildfire trigger feature. The confidence level of a wildfire trigger feature can be determined by verifying whether the wildfire trigger features in the cable images of each camera are the same wildfire trigger features, and determining a first confidence level of the wildfire trigger feature based on the verification result, determining a second confidence level of the wildfire trigger feature based on the feature type of the wildfire trigger feature and the degree of association between the pre-set feature types, and finally determining the confidence level of the wildfire trigger feature based on the first confidence level and the second confidence level.

[0049] The wildfire warning module 130 is used to generate wildfire warning information when it is identified that there is a wildfire trigger feature and the confidence level exceeds a preset confidence threshold.

[0050] The preset confidence threshold may be a preset lower limit of confidence indicating that the wildfire trigger feature can be believed to be real. In view of the severity and urgency of the wildfire situation, the preset confidence threshold may be appropriately lowered to improve the detection sensitivity and response speed of the scheme and reduce the losses caused by the wildfire.

[0051] Wildfire warning information can be used to warn personnel that wildfire triggering features generated by lightning strikes may trigger wildfires and need to be dealt with in a timely manner. The method for generating wildfire warning information can be to determine the first-order level of wildfire warning according to the feature type of wildfire triggering features, determine the second-order level of wildfire warning according to the feature parameters of wildfire triggering features, and generate wildfire warning information according to the first-order level, the second-order level and the wildfire triggering features.

[0052] In the example of the present application, the feature recognition module is used to obtain the cable image between the cable racks through at least two cameras, and to identify whether there is a wildfire trigger feature in the cable image; wherein the feature type of the wildfire trigger feature includes at least one of a spark feature, a flame feature, a smoke feature, and a cable jitter feature; the feature verification module is used to verify the wildfire trigger feature in the cable image of each camera to obtain the confidence of the wildfire trigger feature; the wildfire warning module is used to generate wildfire warning information when it is identified that there is a wildfire trigger feature and the confidence exceeds a preset confidence threshold. This technical solution can detect wildfire trigger factors in a timely manner by identifying whether there is a wildfire trigger feature in the cable image, and can reduce the false alarm rate of the wildfire warning by determining the confidence of the wildfire trigger feature, thereby feeding back accurate and effective wildfire warning information to the staff in a timely manner to avoid causing wildfires.

[0053] Embodiment 2

[0054] Figure 2 It is a structural schematic diagram of the cable wildfire detection device caused by lightning strike provided in Example 2 of the present application. This solution has made better improvements on the basis of the above-mentioned embodiments, and the specific improvements are as follows: the feature verification module includes: a first confidence determination unit, which is used to verify whether the wildfire triggering features in the cable images of each camera are the same wildfire triggering features, and determine the first confidence of the wildfire triggering features according to the verification results; a second confidence determination unit, which is used to determine the second confidence of the wildfire triggering features according to the feature type of the wildfire triggering features and the degree of association between the pre-set feature types; a confidence determination unit, which is used to determine the confidence of the wildfire triggering features according to the first confidence and the second confidence.

[0055] like Figure 2 As shown, the device comprises:

[0056] The feature recognition module 210 is used to obtain the cable image between the cable racks through at least two cameras, and identify whether there is a wildfire trigger feature in the cable image; wherein the feature type of the wildfire trigger feature includes at least one of a spark feature, a flame feature, a smoke feature, and a cable jitter feature;

[0057] A feature verification module 220 is used to verify the wildfire triggering features in the cable images of each camera to obtain the confidence of the wildfire triggering features;

[0058] The wildfire warning module 230 is used to generate wildfire warning information when it is identified that there is a wildfire trigger feature and the confidence level exceeds a preset confidence threshold.

[0059] Wherein, the feature verification module 220 includes:

[0060] A first confidence determination unit 2201 is used to verify whether the wildfire triggering features in the cable images of each camera are the same wildfire triggering features, and determine a first confidence of the wildfire triggering features according to the verification result;

[0061] A second confidence determination unit 2202, configured to determine a second confidence level of the wildfire triggering feature according to a feature type of the wildfire triggering feature and a pre-set degree of association between the feature types;

[0062] The confidence determination unit 2203 is used to determine the confidence of the wildfire triggering feature according to the first confidence and the second confidence.

[0063] The first confidence level may be a confidence level obtained by individually evaluating the wildfire triggering feature. The first confidence level of the wildfire triggering feature may be determined by obtaining the acquisition time of the cable image of each camera, determining the cable position information of the wildfire triggering feature in the cable image of each camera, determining whether the wildfire triggering features in the cable images of each camera are the same wildfire features based on the acquisition time and the cable position information, and determining the first confidence level of the wildfire triggering feature based on the verification result.

[0064] In this technical solution, optionally, the first confidence determination unit is specifically used to:

[0065] Get the acquisition time of the cable image of each camera;

[0066] Determine cable location information of wildfire triggering features in the cable images of each camera;

[0067] Determining whether the wildfire triggering features in the cable images of each camera are the same wildfire triggering features according to the acquisition time and the cable position information;

[0068] A first confidence level of the wildfire triggering feature is determined according to the verification result.

[0069] The acquisition time may refer to the timestamp when the cable image is generated. Modern surveillance cameras generally have a built-in real-time clock, which can automatically record the precise time of each image acquisition. That is, the camera automatically records the acquisition time when acquiring the cable image, and transmits the cable image and the acquisition time to the smart terminal device.

[0070] The cable position information of the wildfire trigger feature may refer to the position of the wildfire trigger feature on the cable in the real three-dimensional space. The cable position information of the wildfire trigger feature may be determined according to the wildfire trigger feature and the position information and size information of the cable in the cable image and the internal and external parameters of the camera.

[0071] For each cable image with the same acquisition time, if there are wildfire trigger features of the same feature type, they can be determined to be the same wildfire trigger features, and their first confidence level can be the inverse of the variance of each cable position information. For example, if the cable position information of the wildfire trigger feature in each cable image is the same, its variance is 0, and its first confidence level can be determined to be 100%.

[0072] Optionally, for the verification of the two ongoing wildfire triggering features, namely, flame features and smoke features, it is not required that the acquisition time of each cable image be the same.

[0073] Optionally, for the verification of the two instantaneous wildfire triggering features, namely, Mars features and cable jitter features, it may only be required that the minimum acquisition time difference between the cable images with Mars features or cable jitter features is less than a preset duration, and the first confidence level may be the ratio of the number of cable images with Mars features or cable jitter features to the total number of cable images.

[0074] The advantage of this arrangement of the present scheme is that by determining the first confidence of the wildfire trigger feature based on the acquisition time of each cable image and the cable position information of the wildfire trigger feature, the authenticity of the wildfire trigger feature can be independently evaluated, thereby improving the accuracy of wildfire trigger detection.

[0075] The second confidence level may be a confidence level obtained by performing an associated evaluation on the wildfire triggering feature.

[0076] The degree of correlation between each feature type may refer to the possibility of the wildfire triggering features of each feature type coexisting with each other, and may be pre-set according to the physical and chemical properties of the wildfire triggering features of each feature type. For example, the degree of correlation between the flame feature and the smoke feature is 80%, the degree of correlation between the spark feature and the cable shaking feature is 50%, the degree of correlation between the smoke feature and the cable shaking feature is 30%, and the degree of correlation between the other two feature types is 20%.

[0077] The second confidence level of a wildfire trigger feature can be determined by determining the correlation level between the wildfire trigger feature and other wildfire trigger features according to the feature type of the wildfire trigger feature and the correlation level between the pre-set feature types, adding the correlation level with other existing wildfire trigger features, and subtracting the correlation level with other non-existent wildfire trigger features to obtain the second confidence level of the wildfire trigger feature. If the calculated second confidence level is less than 0, the second confidence level is determined to be 0, and if the calculated second confidence level is greater than 100%, the second confidence level is determined to be 100%.

[0078] The confidence level of the wildfire triggering feature can be determined by performing a weighted average calculation on the first confidence level and the second confidence level according to a preset weight to obtain the confidence level of the wildfire triggering feature. The weight of the first confidence level can be 0.8, and the weight of the second confidence level can be 0.2.

[0079] Here is a sample code for determining the confidence level of a wildfire trigger feature:

[0080]

[0081] Calculating the first confidence of wildfire triggering features

[0082] parameter:

[0083] cam_image_times (list of datetime) - the acquisition time of each camera cable image

[0084] feature_locations (list of tuples) - Cable location information of wildfire trigger features in the cable images of each camera

[0085] return:

[0086]

[0087]

[0088] Calculating the second confidence level of wildfire triggering characteristics

[0089] parameter:

[0090] feature_types (tuple) – the types of wildfire trigger features

[0091] existing_features (list of tuple) – The types of other wildfire triggering features that have been detected. Returns:

[0092]

[0093] Calculate the overall confidence of wildfire triggering characteristics

[0094] parameter:

[0095] first_confidence(float) - the first confidence of the wildfire trigger feature second_confidence(float) - the second confidence of the wildfire trigger feature Return:

[0096]

[0097]

[0098] The advantage of this arrangement of the present scheme is that a first confidence level is obtained by verifying whether the wildfire triggering features in the cable images of each camera are the same features, a second confidence level is obtained according to the degree of association between the feature types, and finally the confidence level of the wildfire triggering features is determined according to the first confidence level and the second confidence level. The confidence level of the wildfire triggering features can be evaluated independently and in association, thereby effectively reducing the false alarm rate of wildfire warning information.

[0099] Embodiment 3

[0100] Figure 3 It is a structural diagram of the cable wildfire detection device caused by lightning strike provided in Example 3 of the present application. This solution has made better improvements on the basis of the above embodiments, and the specific improvements are as follows: the wildfire warning module includes: a first-order level determination unit, which is used to determine the first-order level of the wildfire warning according to the characteristic type of the wildfire triggering feature; a second-order level determination unit, which is used to determine the second-order level of the wildfire warning according to the characteristic parameters of the wildfire triggering feature; and a warning information generation unit, which is used to generate wildfire warning information according to the first-order level, the second-order level and the wildfire triggering feature.

[0101] like Figure 3 As shown, the device comprises:

[0102] The feature recognition module 310 is used to obtain the cable image between the cable racks through at least two cameras, and identify whether there is a wildfire trigger feature in the cable image; wherein the feature type of the wildfire trigger feature includes at least one of a spark feature, a flame feature, a smoke feature, and a cable jitter feature;

[0103] A feature verification module 320 is used to verify the wildfire triggering features in the cable images of each camera to obtain the confidence of the wildfire triggering features;

[0104] The wildfire warning module 330 is used to generate wildfire warning information when it is identified that there is a wildfire trigger feature and the confidence level exceeds a preset confidence threshold.

[0105] The mountain fire warning module 330 includes:

[0106] A first-order level determination unit 3301 is used to determine the first-order level of the wildfire warning according to the feature type of the wildfire trigger feature;

[0107] A second-order level determination unit 3302, configured to determine the second-order level of the wildfire warning according to the characteristic parameters of the wildfire triggering characteristic;

[0108] The warning information generating unit 3303 is used to generate wildfire warning information according to the first-order level, the second-order level and the wildfire triggering characteristics.

[0109] The first-order level can be a preliminary recognition level for the degree of wildfire triggering crisis. The first-order level of wildfire warning can be determined as follows: if the feature type of the wildfire triggering feature is a flame feature, the first-order level of the wildfire warning is determined as Level I; if the feature type of the wildfire triggering feature is a Mars feature, the first-order level of the wildfire warning is determined as Level II; if the feature type of the wildfire triggering feature is a smoke feature or a cable shaking feature, the first-order level of the wildfire warning is determined as Level III. When there are multiple feature types of wildfire triggering features, the highest first-order level in each feature type is selected as the first-order level of this wildfire warning.

[0110] The second-order level can be the recognition level for the specific development trend of the wildfire trigger. Accordingly, the characteristic parameters of the wildfire trigger feature can be the parameters used to evaluate the specific development trend of the wildfire trigger feature; accordingly, the second-order level of the wildfire warning can be determined by the number characteristic parameters of the Mars feature, the area characteristic parameters of the flame feature, the color characteristic parameters of the smoke feature, and the amplitude characteristic parameters of the cable jitter feature.

[0111] In the technical solution, optionally, the second-order level determination unit is specifically used to:

[0112] Determining a second-order level of wildfire warning according to the quantitative characteristic parameters of the Mars characteristics;

[0113] or,

[0114] Determining the second-order level of forest fire warning according to the area characteristic parameter of the flame characteristic;

[0115] or,

[0116] Determining a second-order level of a wildfire warning according to the color characteristic parameters of the smoke characteristics;

[0117] or,

[0118] The second-order level of wildfire warning is determined based on the amplitude characteristic parameters of the cable jitter characteristics.

[0119] The quantitative characteristic parameter of the Mars feature may refer to the total number of Mars present in a cable image. The method of determining the second-order level of the wildfire warning according to the quantitative characteristic parameter of the Mars feature may be to determine the second-order level of the wildfire warning according to the quantitative characteristic parameter and the correlation between the pre-set total number of Mars and the second-order level. It can be understood that the correlation between the total number of Mars and the second-order level should be that the more the total number of Mars, the higher the second-order level. For example, if the total number of Mars is 1-49, the second-order level is level III; if the total number of Mars is 50-100, the second-order level is level II; if the total number of Mars is greater than 100, the second-order level is level I.

[0120] The area characteristic parameter of the flame feature may refer to the geometric area of ​​the flame feature in a cable image. The method of determining the second-order level of the wildfire warning according to the area characteristic parameter of the flame feature may be to determine the second-order level of the wildfire warning according to the area characteristic parameter and the correlation between the pre-set flame area and the second-order level. It can be understood that the correlation between the flame area and the second-order level should be that the larger the flame area, the higher the second-order level. For example, if the flame area is 1-10 square meters, the second-order level is level III; if the flame area is 11-50 square meters, the second-order level is level II; if the flame area is greater than 50 square meters, the second-order level is level I.

[0121] The color characteristic parameter of the smoke feature may refer to the gray value of the smoke feature in a cable image, which may indicate the smoke concentration. The method of determining the second-order level of the wildfire warning according to the color characteristic parameter of the smoke feature may be to determine the second-order level of the wildfire warning according to the color characteristic parameter and the association between the pre-set smoke color and the second-order level. It is understandable that the association between the smoke color and the second-order level should be that the darker the smoke color, the higher the second-order level. For example, if the smoke color is 0-100 (light gray), the second-order level is level III; if the smoke color is 101-200 (medium gray), the second-order level is level II; if the smoke color is 201-255 (dark gray), the second-order level is level I.

[0122] The amplitude characteristic parameter of the cable jitter feature may refer to the maximum displacement distance of the cable in the cable image. The method of determining the second-order level of the wildfire warning according to the amplitude characteristic parameter of the cable jitter feature may be to determine the second-order level of the wildfire warning according to the amplitude characteristic parameter and the correlation between the pre-set displacement amplitude and the second-order level. It can be understood that the correlation between the displacement amplitude and the second-order level should be that the larger the displacement amplitude, the higher the second-order level. For example, if the displacement amplitude is 0-10 cm, the second-order level is level III; if the displacement amplitude is 11-30 cm, the second-order level is level II; if the flame area is greater than 30 cm, the second-order level is level I.

[0123] The following is a sample code for determining the second-order level of wildfire warning based on the characteristic parameters of the wildfire trigger feature:

[0124]

[0125]

[0126]

[0127] The benefit of this arrangement of the present invention is that by determining the second-order level of the wildfire warning according to the characteristic parameters corresponding to the characteristic type of the wildfire triggering characteristic, the notification priority of the wildfire warning information can be determined in a more multi-dimensional manner.

[0128] The method of generating wildfire warning information according to the first-order level, the second-order level and the wildfire triggering characteristics can be adopted to determine the notification priority of the wildfire warning information according to the first-order level and the second-order level, and generate wildfire warning information according to the wildfire triggering characteristics, the notification priority and the preset notification method associated with the notification priority.

[0129] In this technical solution, optionally, the warning information generating unit is specifically used to:

[0130] Determining the notification priority of the wildfire warning information according to the first-order level and the second-order level;

[0131] Wildfire warning information is generated according to the wildfire triggering characteristics, the notification priority, and a preset notification method associated with the notification priority.

[0132] The notification priority of the wildfire warning information may refer to the order in which the wildfire warning information is sent to the staff. The notification priority of the wildfire warning information may be determined by obtaining the number of wildfire warning information that needs to be generated within a preset period, prioritizing each first-order level and second-order level according to the number, and determining the notification priority to which the current first-order level and second-order level belong.

[0133] The preset notification method associated with the notification priority may refer to the medium and means for sending wildfire warning information to the staff associated with the notification priority. For example, if the notification priority is level I, the staff phone is dialed and the wildfire warning information is broadcasted on the phone; if the notification priority is level II, the wildfire warning information is broadcasted through the intercom channel; if the notification priority is level III, a text message is sent to the staff, and the content of the text message includes the wildfire warning information.

[0134] The benefit of this arrangement of the present scheme is that by determining the notification priority of wildfire warning information and the preset notification method associated with the notification priority according to the first-order level and the second-order level, appropriate notification methods can be adopted for wildfire triggering characteristics of different levels, thereby improving the notification efficiency of wildfire warning information and ensuring that staff can receive wildfire warning information in a timely manner.

[0135] The benefit of this arrangement of the present scheme is that by determining the first-order level of the wildfire warning according to the characteristic type of the wildfire triggering characteristic, and determining the second-order level of the wildfire warning according to the characteristic parameters of the wildfire triggering characteristic, and finally generating wildfire warning information according to the first-order level and the second-order level, the current wildfire triggering risk can be assessed more comprehensively and accurately, and targeted warning information can be issued in a timely manner.

[0136] Embodiment 4

[0137] Figure 4 1 is a flow chart of a method for detecting cable fires caused by lightning strikes provided in Example 4 of the present application. Figure 4 As shown, the specific steps include:

[0138] S401, using a feature recognition module to obtain a cable image between cable racks through at least two cameras, and identifying whether there is a wildfire trigger feature in the cable image; wherein the feature type of the wildfire trigger feature includes at least one of a spark feature, a flame feature, a smoke feature, and a cable jitter feature;

[0139] S402, verifying the wildfire triggering features in the cable images of each camera through a feature verification module to obtain the confidence of the wildfire triggering features;

[0140] S403: Generate wildfire warning information by the wildfire warning module when it is identified that there is a wildfire trigger feature and the confidence level exceeds a preset confidence threshold.

[0141] In an embodiment of the present application, a feature recognition module is used to obtain cable images between cable racks through at least two cameras, and identify whether there are wildfire trigger features in the cable images; wherein the feature types of the wildfire trigger features include at least one of spark features, flame features, smoke features, and cable jitter features; the wildfire trigger features in the cable images of each camera are verified by a feature verification module to obtain the confidence of the wildfire trigger features; and a wildfire warning module generates wildfire warning information when it is identified that there are wildfire trigger features and the confidence exceeds a preset confidence threshold. The above-mentioned cable wildfire detection method caused by lightning strikes can detect wildfire trigger factors in a timely manner by identifying whether there are wildfire trigger features in the cable images, and can reduce the false alarm rate of wildfire warnings by determining the confidence of wildfire trigger features, thereby feeding back accurate and effective wildfire warning information to the staff in a timely manner to avoid causing wildfires.

[0142] The cable fire detection method caused by lightning strike provided in the embodiment of the present application corresponds to the cable fire detection device caused by lightning strike provided in the above embodiment, and has the same functional modules and beneficial effects. To avoid repetition, they will not be described here.

[0143] Embodiment 5

[0144] like Figure 5 As shown, an embodiment of the present application also provides an electronic device 500, including a processor 501, a memory 502, and a program or instruction stored in the memory 502 and executable on the processor 501. When the program or instruction is executed by the processor 501, each process of the embodiment of the cable mountain fire detection device caused by lightning strike is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0145] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0146] Embodiment 6

[0147] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned embodiment of the cable forest fire detection device caused by lightning strike is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0148] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0149] Embodiment 7

[0150] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned embodiment of the cable forest fire detection device caused by lightning strikes, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0151] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0152] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0153] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0154] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0155] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. A cable fire detection device caused by lightning, characterized in that: The device comprises: A feature recognition module, used to obtain cable images between cable racks through at least two cameras, and identify whether there is a wildfire trigger feature in the cable image; wherein the feature type of the wildfire trigger feature includes at least one of a spark feature, a flame feature, a smoke feature, and a cable jitter feature; A feature verification module is used to verify the wildfire triggering features in the cable images of each camera to obtain the confidence level of the wildfire triggering features; The wildfire warning module is used to generate wildfire warning information when it is identified that there are wildfire triggering features and the confidence level exceeds a preset confidence threshold.

2. The cable fire detection device caused by lightning strike according to claim 1, characterized in that: The device also includes: Lightning strike identification module, used to obtain sound data in the cable laying area; Accordingly, the feature recognition module is specifically used for: When the volume of the sound data exceeds a preset volume threshold, the cable image between the cable racks is acquired by at least two cameras, and it is identified whether there is a wildfire triggering feature in the cable image.

3. The cable fire detection device caused by lightning strike according to claim 1, characterized in that: The feature verification module comprises: A first confidence determination unit, used to verify whether the wildfire triggering features in the cable images of each camera are the same wildfire triggering features, and determine a first confidence of the wildfire triggering features according to the verification result; A second confidence determination unit, configured to determine a second confidence level of the wildfire triggering feature according to a feature type of the wildfire triggering feature and a pre-set degree of association between the feature types; A confidence determination unit is used to determine the confidence of the wildfire triggering feature according to the first confidence and the second confidence.

4. The cable fire detection device caused by lightning strike according to claim 3 is characterized in that: The first confidence determination unit is specifically configured to: Get the acquisition time of the cable image of each camera; Determine cable location information of wildfire triggering features in the cable images of each camera; Determining whether the wildfire triggering features in the cable images of each camera are the same wildfire triggering features according to the acquisition time and the cable position information; A first confidence level of the wildfire triggering feature is determined according to the verification result.

5. The cable fire detection device caused by lightning strike according to claim 1, characterized in that: The mountain fire warning module comprises: A first-order level determination unit, used to determine the first-order level of the wildfire warning according to the feature type of the wildfire trigger feature; A second-order level determination unit, used to determine the second-order level of the wildfire warning according to the characteristic parameters of the wildfire triggering characteristics; The warning information generating unit is used to generate wildfire warning information according to the first-order level, the second-order level and the wildfire triggering characteristics.

6. The cable fire detection device caused by lightning strike according to claim 5, characterized in that: The second-order level determination unit is specifically used to: Determining a second-order level of wildfire warning according to the quantitative characteristic parameters of the Mars characteristics; or, Determining the second-order level of forest fire warning according to the area characteristic parameter of the flame characteristic; or, Determining a second-order level of a wildfire warning according to the color characteristic parameters of the smoke characteristics; or, The second-order level of wildfire warning is determined based on the amplitude characteristic parameters of the cable jitter characteristics.

7. The cable fire detection device caused by lightning strike according to claim 5, characterized in that: The warning information generating unit is specifically used for: Determining the notification priority of the wildfire warning information according to the first-order level and the second-order level; Wildfire warning information is generated according to the wildfire triggering characteristics, the notification priority, and a preset notification method associated with the notification priority.

8. A method for detecting cable fires caused by lightning, characterized in that: The method comprises: The feature recognition module uses at least two cameras to obtain cable images between cable racks, and identifies whether there is a wildfire trigger feature in the cable image; wherein the feature type of the wildfire trigger feature includes at least one of a spark feature, a flame feature, a smoke feature, and a cable jitter feature; Verify the wildfire triggering features in the cable images of each camera through a feature verification module to obtain the confidence level of the wildfire triggering features; The wildfire warning module generates wildfire warning information when it is identified that there is a wildfire trigger feature and the confidence level exceeds a preset confidence threshold.

9. The method for detecting cable fire caused by lightning strike according to claim 8, characterized in that: The method further comprises: Acquire sound data of the cable laying area through the lightning strike identification module; Accordingly, the feature recognition module acquires the cable image between the cable racks through at least two cameras, and identifies whether there is a wildfire triggering feature in the cable image, including: When the sound data exceeds a preset volume threshold, at least two cameras are used to obtain images of cables between cable racks, and it is identified whether there are wildfire triggering features in the cable images.

10. An electronic device, characterized in that: The method comprises a processor, a memory and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method for detecting cable mountain fire caused by lightning strike as described in any one of claims 8 to 9.

Images