Power transmission corridor forest fire tripping risk assessment method based on binocular camera and point cloud
By combining binocular cameras and lidar, three-dimensional depth maps and point cloud data are generated, registered and corrected, and inputted to the risk assessment model, solving the problem of low risk assessment accuracy caused by monocular cameras and scanning equipment, and realizing the High accuracy and real-time monitoring of wildfire tripping risks in transmission corridors.
Patent Information
- Application Number
- CN202411160587.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-22
- Publication Date
- 2024-12-13
AI Technical Summary
In the prior art, monocular depth cameras have high depth errors in complex environments, making it difficult to provide accurate three-dimensional information, resulting in low accuracy of wildfire tripping risk assessment in transmission corridors, and low frequency of point cloud data acquisition, making it impossible to monitor the environment in real time. Changes, no timely warnings are provided.
The binocular camera is combined with lidar, and the 3D image data of fire point and the transmission corridor monitoring data are collected through the binocular camera, and the three-dimensional depth map of fire point is generated, and the three-dimensional point cloud data is obtained through lidar, using registration algorithms and environmental feature correction. , input to the pretrained risk assessment model to obtain wildfire trip risk assessment results.
The accuracy of wildfire tripping risk assessment in the transmission corridor has been improved, real-time monitoring and timely early warning of wildfire risks has been achieved, and the problem of low risk assessment accuracy caused by monocular cameras and scanning equipment has been solved.
Smart Images
Figure CN119130133A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a method for assessing the risk of mountain fire tripping in a power transmission corridor based on a binocular camera and point cloud. Background Art
[0002] With the continuous development of the power system, the safe operation of transmission lines has become an important guarantee for the stability of power supply. The management and maintenance of transmission corridors, especially the monitoring and prevention of natural disasters such as wildfires, has become an important part of the operation of the power system.
[0003] In the process of realizing the present invention, the inventors found that the prior art has the following defects: At present, in traditional monitoring technology, monocular depth cameras have been widely used due to their low cost and easy deployment. However, monocular depth cameras have the problem of high depth error, which limits their application in complex environments. Especially in wildfire monitoring and risk assessment of transmission corridors, monocular cameras are difficult to provide accurate three-dimensional information, which affects the accuracy of risk assessment. In addition, due to the cost and operational complexity of scanning equipment, the frequency of acquiring point cloud data is low. This low-frequency data update makes it impossible to monitor changes in transmission corridors in real time, especially in the face of sudden disasters such as wildfires, and it is impossible to provide timely warnings and risk assessments. Summary of the invention
[0004] The present invention provides a method for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and a point cloud, so as to improve the risk assessment of wildfire tripping in a power transmission corridor based on a binocular camera and a point cloud.
[0005] According to one aspect of the present invention, a method for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and point cloud is provided, which includes:
[0006] The three-dimensional image data of the fire point corresponding to the current transmission corridor and the transmission corridor monitoring data are collected in real time by using a binocular camera, and the three-dimensional image data of the fire point is processed to generate a three-dimensional depth map of the fire point;
[0007] Scan the current transmission corridor through LiDAR to obtain the current three-dimensional point cloud data;
[0008] The three-dimensional depth map of the fire point and the current three-dimensional point cloud data are calibrated and registered by a pre-built registration algorithm to determine the distance and position of the current fire point;
[0009] Acquire current surrounding environment characteristic information, and correct the current fire point distance and position by a pre-calibrated surrounding environment characteristic processing method to obtain a current corrected fire point distance and position;
[0010] The acquired current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position are input into a pre-trained risk assessment model to obtain a wildfire tripping risk assessment result corresponding to the current transmission corridor.
[0011] According to another aspect of the present invention, a device for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and point cloud is provided, which includes:
[0012] A fire point three-dimensional depth map generation module is used to collect the corresponding fire point three-dimensional image data and transmission corridor monitoring data under the current transmission corridor in real time through a binocular camera, and perform data processing on the fire point three-dimensional image data to generate a fire point three-dimensional depth map;
[0013] The current three-dimensional point cloud data determination module is used to scan the current transmission corridor through a laser radar to obtain the current three-dimensional point cloud data;
[0014] A current fire point distance and position determination module is used to perform registration and calibration processing on the fire point three-dimensional depth map and the current three-dimensional point cloud data through a pre-built registration algorithm to determine the current fire point distance and position;
[0015] A current corrected fire point distance and position determination module is used to obtain current surrounding environment feature information, and correct the current fire point distance and position through a pre-calibrated surrounding environment feature processing method to obtain the current corrected fire point distance and position;
[0016] The wildfire tripping risk assessment result determination module is used to input the acquired current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position into a pre-trained risk assessment model to obtain the wildfire tripping risk assessment result corresponding to the current transmission corridor.
[0017] According to another aspect of the present invention, there is provided an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and a point cloud as described in any embodiment of the present invention is implemented.
[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and a point cloud as described in any embodiment of the present invention when executed.
[0019] The technical solution of the embodiment of the present invention uses a binocular camera to collect the three-dimensional image data of the fire point and the transmission corridor monitoring data corresponding to the current transmission corridor in real time, and processes the three-dimensional image data of the fire point to generate a three-dimensional depth map of the fire point; scans the current transmission corridor through a laser radar to obtain the current three-dimensional point cloud data; performs registration and calibration processing on the three-dimensional depth map of the fire point and the current three-dimensional point cloud data through a pre-constructed registration algorithm to determine the distance and position of the current fire point; obtains the current surrounding environment feature information, and corrects the current fire point distance and position through a pre-calibrated surrounding environment feature processing method to obtain the current corrected fire point distance and position; inputs the obtained current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position into a pre-trained risk assessment model to obtain a wildfire tripping risk assessment result corresponding to the current transmission corridor. The problem of low risk assessment accuracy caused by monocular depth cameras and scanning equipment is solved, and the accuracy of wildfire tripping risk assessment in transmission corridors is improved. It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.
[0021] Figure 1 It is a flow chart of a method for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and point cloud according to the first embodiment of the present invention;
[0022] Figure 2 It is a structural schematic diagram of a device for assessing the risk of mountain fire tripping in a power transmission corridor based on a binocular camera and point cloud according to Embodiment 2 of the present invention;
[0023] Figure 3 It is a structural schematic diagram of an electronic device provided according to Embodiment 3 of the present invention. DETAILED DESCRIPTION
[0024] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.
[0025] It should be noted that the terms "target", "current", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0026] Embodiment 1
[0027] Figure 1 A flow chart of a method for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and a point cloud is provided in Example 1 of the present invention. This embodiment is applicable to situations where risk assessment is performed on wildfire tripping in a power transmission corridor. The method can be performed by a device for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and a point cloud. The device for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and a point cloud can be implemented in the form of hardware and / or software.
[0028] Correspondingly, such as Figure 1 As shown, the method includes:
[0029] S110, using a binocular camera to collect the three-dimensional image data of the fire point corresponding to the current transmission corridor and the transmission corridor monitoring data in real time, and performing data processing on the three-dimensional image data of the fire point to generate a three-dimensional depth map of the fire point.
[0030] The three-dimensional image data of the fire point may be the three-dimensional image data collected by a binocular camera for describing the fire point. The three-dimensional depth map of the fire point may be a three-dimensional depth map describing the fire point, and the depth map may be generated by the three-dimensional image data of the fire point.
[0031] Optionally, the data processing of the fire point three-dimensional image data to generate the fire point three-dimensional depth map includes: performing data preprocessing on the fire point three-dimensional image data to obtain an initial fire point three-dimensional depth map; and denoising the initial fire point three-dimensional depth map by a set image processing algorithm to generate the fire point three-dimensional depth map.
[0032] In this embodiment, after preprocessing the three-dimensional image data of the fire point, an initial three-dimensional depth map of the fire point can be obtained. There may be a problem of environmental noise in the initial three-dimensional depth map of the fire point. Therefore, the initial three-dimensional depth map of the fire point can be processed to remove the environmental noise through a pre-set image processing algorithm, and then the three-dimensional depth map of the fire point can be obtained.
[0033] S120. Scan the current transmission corridor by using a laser radar to obtain current three-dimensional point cloud data.
[0034] Among them, the current three-dimensional point cloud data can be generated by scanning the current transmission corridor through a laser radar according to a preset period to generate high-precision three-dimensional point cloud data.
[0035] In addition, the current three-dimensional point cloud data may also be stored in a pre-set server database.
[0036] S130, performing registration and calibration processing on the three-dimensional depth map of the fire point and the current three-dimensional point cloud data through a pre-constructed registration algorithm to determine the distance and position of the current fire point.
[0037] The registration algorithm may be an algorithm for performing registration processing on the three-dimensional depth map of the fire point and the current three-dimensional point cloud data. Specifically, the registration algorithm may be an ICP (Iterative Closest Point) algorithm, which is not specifically limited here.
[0038] Specifically, the three-dimensional depth map of the fire point and the current three-dimensional point cloud data are registered and calibrated by a pre-constructed registration algorithm to determine the current fire point distance and position, including: the three-dimensional depth map of the fire point and the current three-dimensional point cloud data are registered by a pre-constructed registration algorithm to obtain the current fire point registration distance and position; according to the three-dimensional depth map of the fire point and the current three-dimensional point cloud data, the current alignment calibration parameter T is calculated by a pre-constructed rigid transformation model; wherein the formula corresponding to the rigid transformation model is Where R is the preset rotation matrix; t is the pre-acquired translation vector; p i is the point in the three-dimensional depth map of the fire point, q i is the point of the current 3D point cloud data, p i and q iThe three-dimensional depth map of the fire point and the corresponding point pair in the current three-dimensional point cloud data; according to the current alignment and calibration parameters, the current fire point registration distance and position are aligned and calibrated to obtain the current fire point distance and position.
[0039] Among them, the current alignment calibration parameter can be the size of the alignment parameter that needs to be offset between the three-dimensional depth map of the fire point and the current three-dimensional point cloud data.
[0040] In this embodiment, after obtaining the current fire point registration distance and position, it is necessary to use the formula corresponding to the rigid transformation model (for example, the rigid transformation model can be the least squares method) To calculate the current alignment calibration parameters, and then perform alignment and calibration processing on the three-dimensional depth map of the fire point and the current three-dimensional point cloud data, the current fire point distance and position can be further calculated.
[0041] For example, assuming qi is (x1, y1, z1), in the three-dimensional depth map of the fire point, the point pair corresponding to the current three-dimensional point cloud data qi is pi, assuming pi is (x2, y2, z2). We can further substitute pi and qi into the formula In the algorithm, the current alignment calibration parameters are calculated, and then the current fire point distance and position can be obtained.
[0042] S140, obtaining current surrounding environment characteristic information, and correcting the current fire point distance and position by a pre-calibrated surrounding environment characteristic processing method to obtain a current corrected fire point distance and position.
[0043] Optionally, the current surrounding environment characteristic information includes surrounding building characteristic information and surrounding pond characteristic information; the current surrounding environment characteristic information is obtained, and the current fire point distance and position are corrected by a pre-calibrated surrounding environment characteristic processing method to obtain the current corrected fire point distance and position, including: obtaining surrounding building characteristic information and surrounding pond characteristic information; according to the surrounding building characteristic information and the surrounding pond characteristic information, the current fire point distance and position are corrected by a pre-calibrated surrounding environment characteristic processing method to obtain the current corrected fire point distance and position.
[0044] In this embodiment, characteristic information of surrounding buildings and surrounding ponds can be obtained to further correct the current fire point distance and position based on the characteristic information of surrounding buildings and surrounding ponds. The corrected current corrected fire point distance and position can be obtained, and the surrounding relevant geographical and meteorological characteristics can also be obtained.
[0045] S150, input the acquired current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position into a pre-trained risk assessment model to obtain a wildfire tripping risk assessment result corresponding to the current transmission corridor.
[0046] Optionally, the current terrain feature environmental change information includes slope and aspect parameters, combustible load, vegetation type parameters, and wind speed, temperature, and humidity parameters; the acquired current terrain feature environmental change information, the transmission corridor monitoring data, and the current corrected fire point distance and position are input into a pre-trained risk assessment model to obtain a wildfire tripping risk assessment result corresponding to the current transmission corridor, including: wherein the current transmission corridor slope and aspect description information is obtained from the point cloud data obtained by the lidar, the combustible load and vegetation type description information is obtained from the collected remote sensing data, and the wind speed, temperature, and humidity description information is obtained from the sensor collected data acquisition; the slope and aspect parameters, the combustible load, the vegetation type parameters, the wind speed, temperature and humidity parameters, the transmission corridor monitoring data and the current corrected fire point distance and position are input into a pre-trained risk assessment model to calculate the phase-to-ground breakdown voltage and the phase-to-phase breakdown voltage; according to the phase-to-ground breakdown voltage and the phase-to-phase breakdown voltage, the phase-to-ground risk assessment coefficient, the phase-to-phase risk assessment coefficient, the phase-to-ground risk level and the phase-to-phase risk level are obtained; according to the phase-to-ground risk assessment coefficient, the phase-to-phase risk assessment coefficient, the phase-to-ground risk level and the phase-to-phase risk level, the wildfire tripping risk assessment result corresponding to the current transmission corridor is obtained.
[0047] The current terrain feature environment change information may include: the current transmission corridor slope and aspect description information corresponding to the current three-dimensional point cloud data, the combustible load and vegetation type description information corresponding to the collected remote sensing data, and the wind speed, temperature and humidity description information corresponding to the data collected by the sensor.
[0048] Specifically, the current slope and aspect description information of the transmission corridor may include height difference and horizontal distance. The slope may be further calculated using a triangular mesh algorithm. In detail, the formula To calculate the slope θ, Δh represents the height difference; Δd represents the horizontal distance. The slope and aspect parameters of the current transmission corridor can be obtained by processing the slope and aspect description information of the current transmission corridor.
[0049] Furthermore, the fuel load and vegetation type description information can be processed to obtain the fuel load and vegetation type parameters.
[0050] In addition, the sensor may be a sensor installed in a meteorological station or on a line, and the wind speed, temperature and humidity description information may be collected through the sensor, and then the wind speed, temperature and humidity parameters may be obtained through a surrounding environment feature processing method.
[0051] In detail, the vegetation type description information in the current terrain feature environment change information includes: vegetation type correction coefficient and vegetation density correction coefficient; the current transmission corridor slope and slope description information includes altitude correction coefficient; combustible load includes smoke particle correction coefficient; wind speed, temperature and humidity parameters include flame temperature correction coefficient; the transmission corridor monitoring data includes: flame height, flame continuous zone height, wire to tree crown distance, standard flame continuous zone unit length mountain fire tolerance strength, standard flame non-continuous zone unit length mountain fire tolerance strength, standard air gap unit length tolerance strength and gap distance between wires; through the formula The current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position are input into the pre-trained risk assessment model to calculate the phase-to-ground breakdown voltage U G ; Among them, H F Indicates flame height; H f Indicates the height of the flame continuous zone; d l-t Indicates the distance between the conductor and the tree crown; E f Indicates the wildfire tolerance intensity per unit length of the standard flame continuous area; E x Indicates the wildfire tolerance intensity per unit length of the standard flame discontinuity zone; E s Indicates the withstand strength per unit length of the standard air gap; C k Indicates vegetation type correction coefficient; C d Represents vegetation density correction coefficient; C a Indicates the altitude correction factor; C p Indicates the smoke particle correction factor; C t Represents the flame temperature correction factor; through the formula The current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position are input into the pre-trained risk assessment model to calculate the phase-to-phase breakdown voltage U P ; where d p Indicates the gap distance between wires.
[0052] In this embodiment, multiple independent variable parameters can be acquired in advance, which may include current terrain feature environmental change information and transmission corridor monitoring data. Specifically, they may include vegetation type correction coefficient, vegetation density correction coefficient, altitude correction coefficient, smoke particle correction coefficient, flame temperature correction coefficient, flame height, flame continuous zone height, conductor to tree crown distance, standard flame continuous zone unit length wildfire tolerance intensity, standard flame discontinuous zone unit length wildfire tolerance intensity, standard air gap unit length tolerance intensity and gap distance between conductors.
[0053] Furthermore, we can put them into the formula and formula In the calculation, the phase-to-ground breakdown voltage and the phase-to-phase breakdown voltage are obtained respectively.
[0054] Correspondingly, the corresponding phase-to-ground risk assessment coefficient, phase-to-phase risk assessment coefficient, phase-to-ground risk level, and phase-to-phase risk level can be calculated by using the calculated phase-to-ground breakdown voltage and phase-to-phase breakdown voltage. Furthermore, the wildfire tripping risk assessment result corresponding to the current transmission corridor can be obtained based on the phase-to-ground risk assessment coefficient, phase-to-phase risk assessment coefficient, phase-to-ground risk level, and phase-to-phase risk level.
[0055] Optionally, after inputting the current terrain feature environmental change information, the transmission corridor monitoring data and the current corrected fire point distance and position into a pre-trained risk assessment model to obtain a wildfire tripping risk assessment result corresponding to the current transmission corridor, it also includes: feeding back the obtained wildfire tripping risk assessment result to a user; wherein the wildfire tripping risk assessment result includes a wildfire tripping risk assessment level, wildfire tripping risk warning information and wildfire tripping emergency measures recommendation information.
[0056] In this embodiment, the wildfire tripping risk assessment level, wildfire tripping risk warning information and wildfire tripping emergency measures recommendation information corresponding to the wildfire tripping risk assessment results can be fed back to the user, and the user can respond to the wildfire tripping in the current transmission corridor based on the feedback information.
[0057] The technical solution of the embodiment of the present invention uses a binocular camera to collect the three-dimensional image data of the fire point and the transmission corridor monitoring data corresponding to the current transmission corridor in real time, and processes the three-dimensional image data of the fire point to generate a three-dimensional depth map of the fire point; scans the current transmission corridor through a laser radar to obtain the current three-dimensional point cloud data; performs registration and calibration processing on the three-dimensional depth map of the fire point and the current three-dimensional point cloud data through a pre-constructed registration algorithm to determine the distance and position of the current fire point; obtains the current surrounding environment feature information, and corrects the current fire point distance and position through a pre-calibrated surrounding environment feature processing method to obtain the current corrected fire point distance and position; inputs the obtained current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position into a pre-trained risk assessment model to obtain a wildfire tripping risk assessment result corresponding to the current transmission corridor. The problem of low risk assessment accuracy caused by monocular depth cameras and scanning equipment is solved, and the accuracy of wildfire tripping risk assessment in transmission corridors is improved.
[0058] Embodiment 2
[0059] Figure 2 A schematic diagram of the structure of a transmission corridor wildfire tripping risk assessment device based on binocular camera and point cloud provided in the second embodiment of the present invention. The transmission corridor wildfire tripping risk assessment device based on binocular camera and point cloud provided in this embodiment can be implemented by software and / or hardware, and can be configured in a terminal device or server to implement a transmission corridor wildfire tripping risk assessment method based on binocular camera and point cloud in the embodiment of the present invention. Figure 2 As shown, the device includes: a fire point three-dimensional depth map generation module 210, a current three-dimensional point cloud data determination module 220, a current fire point distance and position determination module 230, a current corrected fire point distance and position determination module 240 and a wildfire tripping risk assessment result determination module 250.
[0060] The fire point three-dimensional depth map generation module 210 is used to collect the corresponding fire point three-dimensional image data and transmission corridor monitoring data under the current transmission corridor in real time through a binocular camera, and perform data processing on the fire point three-dimensional image data to generate a fire point three-dimensional depth map;
[0061] The current three-dimensional point cloud data determination module 220 is used to scan the current transmission corridor through a laser radar to obtain the current three-dimensional point cloud data;
[0062] The current fire point distance and position determination module 230 is used to perform registration and calibration processing on the fire point three-dimensional depth map and the current three-dimensional point cloud data through a pre-built registration algorithm to determine the current fire point distance and position;
[0063] The current corrected fire point distance and position determination module 240 is used to obtain the current surrounding environment feature information, and correct the current fire point distance and position through a pre-calibrated surrounding environment feature processing method to obtain the current corrected fire point distance and position;
[0064] The wildfire tripping risk assessment result determination module 250 is used to input the acquired current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position into a pre-trained risk assessment model to obtain a wildfire tripping risk assessment result corresponding to the current transmission corridor.
[0065] The technical solution of the embodiment of the present invention uses a binocular camera to collect the three-dimensional image data of the fire point and the transmission corridor monitoring data corresponding to the current transmission corridor in real time, and processes the three-dimensional image data of the fire point to generate a three-dimensional depth map of the fire point; scans the current transmission corridor through a laser radar to obtain the current three-dimensional point cloud data; performs registration and calibration processing on the three-dimensional depth map of the fire point and the current three-dimensional point cloud data through a pre-constructed registration algorithm to determine the distance and position of the current fire point; obtains the current surrounding environment feature information, and corrects the current fire point distance and position through a pre-calibrated surrounding environment feature processing method to obtain the current corrected fire point distance and position; inputs the obtained current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position into a pre-trained risk assessment model to obtain a mountain fire tripping risk assessment result corresponding to the current transmission corridor. The problem of low risk assessment accuracy caused by monocular depth cameras and scanning equipment is solved, and the accuracy of mountain fire tripping risk assessment of transmission corridors based on binocular cameras and point clouds is improved.
[0066] On the basis of the above embodiments, it also includes a wildfire tripping risk assessment result feedback module, which can be specifically used for: after the acquired current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position are input into the pre-trained risk assessment model, and the wildfire tripping risk assessment result corresponding to the current transmission corridor is obtained, the obtained wildfire tripping risk assessment result is fed back to the user; wherein, the wildfire tripping risk assessment result includes the wildfire tripping risk assessment level, wildfire tripping risk warning information and wildfire tripping emergency measures recommendation information.
[0067] Based on the above embodiments, the fire point three-dimensional depth map generation module 210 can be specifically used to: perform data preprocessing on the fire point three-dimensional image data to obtain an initial fire point three-dimensional depth map; perform denoising on the initial fire point three-dimensional depth map through a set image processing algorithm to generate the fire point three-dimensional depth map.
[0068] On the basis of the above embodiments, the current fire point distance and position determination module 230 can be specifically used to: perform registration processing on the fire point three-dimensional depth map and the current three-dimensional point cloud data through a pre-constructed registration algorithm to obtain the current fire point registration distance and position; calculate the current alignment calibration parameter T based on the fire point three-dimensional depth map and the current three-dimensional point cloud data through a pre-constructed rigid transformation model; wherein the formula corresponding to the rigid transformation model is Where R is the preset rotation matrix; t is the pre-acquired translation vector; p i is the point in the three-dimensional depth map of the fire point, q i is the point of the current 3D point cloud data, p i and q i The three-dimensional depth map of the fire point and the corresponding point pair in the current three-dimensional point cloud data; according to the current alignment and calibration parameters, the current fire point registration distance and position are aligned and calibrated to obtain the current fire point distance and position.
[0069] Based on the above embodiments, the current surrounding environment characteristic information includes surrounding building characteristic information and surrounding pond characteristic information.
[0070] Based on the above embodiments, the current corrected fire point distance and position determination module 240 can be specifically used to: obtain surrounding building characteristic information and surrounding pond characteristic information; according to the surrounding building characteristic information and the surrounding pond characteristic information, through a pre-calibrated surrounding environment characteristic processing method, correct the current fire point distance and position to obtain the current corrected fire point distance and position.
[0071] On the basis of the above embodiments, the current terrain feature environment change information includes slope and aspect parameters, combustible load, vegetation type parameters, and wind speed, temperature, and humidity parameters.
[0072] On the basis of the above embodiments, the wildfire tripping risk assessment result determination module 250 can be specifically used for: wherein, the current transmission corridor slope and aspect description information is obtained from the point cloud data obtained by the lidar, the combustible load and vegetation type description information is obtained from the collected remote sensing data, and the wind speed, temperature and humidity description information is obtained from the data collected by the sensor; the slope and aspect parameters, the combustible load, the vegetation type parameters, the wind speed, temperature and humidity parameters, the transmission corridor monitoring data and the current corrected fire point distance and position are input into a pre-trained risk assessment model to calculate the phase-to-ground breakdown voltage and the phase-to-phase breakdown voltage; according to the phase-to-ground breakdown voltage and the phase-to-phase breakdown voltage, the phase-to-ground risk assessment coefficient, the phase-to-phase risk assessment coefficient, the phase-to-ground risk level and the phase-to-phase risk level are obtained; according to the phase-to-ground risk assessment coefficient, the phase-to-phase risk assessment coefficient, the phase-to-ground risk level and the phase-to-phase risk level, the wildfire tripping risk assessment result corresponding to the current transmission corridor is obtained.
[0073] On the basis of the above embodiments, the vegetation type description information in the current terrain feature environment change information includes: vegetation type correction coefficient and vegetation density correction coefficient; the current transmission corridor slope and aspect description information includes altitude correction coefficient; combustible load includes smoke particle correction coefficient; wind speed, temperature and humidity parameters include flame temperature correction coefficient; the transmission corridor monitoring data includes: flame height, flame continuous zone height, conductor to tree crown distance, mountain fire tolerance strength per unit length of standard flame continuous zone, mountain fire tolerance strength per unit length of standard flame discontinuous zone, tolerance strength per unit length of standard air gap and gap distance between conductors.
[0074] On the basis of the above embodiments, the mountain fire tripping risk assessment result determination module 250 can also be specifically used to, through the formula The current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position are input into the pre-trained risk assessment model to calculate the phase-to-ground breakdown voltage U G ; Among them, H F Indicates flame height; H f Indicates the height of the flame continuous zone; d l-t Indicates the distance between the conductor and the tree crown; E f Indicates the wildfire tolerance intensity per unit length of the standard flame continuous area; E x Indicates the wildfire tolerance intensity per unit length of the standard flame discontinuity zone; E s Indicates the withstand strength per unit length of the standard air gap; C k Indicates vegetation type correction coefficient; C d Represents vegetation density correction coefficient; C a Indicates the altitude correction factor; C pIndicates the smoke particle correction factor; C t Represents the flame temperature correction factor; through the formula The current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position are input into the pre-trained risk assessment model to calculate the phase-to-phase breakdown voltage U P ; where d p Indicates the gap distance between wires.
[0075] The wildfire tripping risk assessment device for power transmission corridors based on binocular cameras and point clouds provided in an embodiment of the present invention can execute the wildfire tripping risk assessment method for power transmission corridors based on binocular cameras and point clouds provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.
[0076] Embodiment 3
[0077] Figure 3 A schematic diagram of the structure of an electronic device 10 that can be used to implement the third embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0078] like Figure 3 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0079] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0080] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a wildfire tripping risk assessment method for a power transmission corridor based on a binocular camera and a point cloud.
[0081] In some embodiments, the method for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and a point cloud can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and a point cloud described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the method for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and a point cloud in any other appropriate manner (for example, by means of firmware).
[0082] The method includes: using a binocular camera to collect the three-dimensional image data of the fire point and the transmission corridor monitoring data corresponding to the current transmission corridor in real time, and performing data processing on the three-dimensional image data of the fire point to generate a three-dimensional depth map of the fire point; scanning the current transmission corridor by a laser radar to obtain current three-dimensional point cloud data; using a pre-constructed registration algorithm to perform registration and calibration processing on the three-dimensional depth map of the fire point and the current three-dimensional point cloud data to determine the current fire point distance and position; obtaining current surrounding environment feature information, and correcting the current fire point distance and position by a pre-calibrated surrounding environment feature processing method to obtain the current corrected fire point distance and position; inputting the obtained current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position into a pre-trained risk assessment model to obtain a wildfire tripping risk assessment result corresponding to the current transmission corridor.
[0083] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0084] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0085] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0086] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0087] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0088] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0089] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0090] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
[0091] Embodiment 4
[0092] Embodiment 4 of the present invention also provides a computer-readable storage medium, wherein the computer-readable instructions are used to execute a method for assessing the risk of wildfire tripping of a power transmission corridor based on a binocular camera and a point cloud when executed by a computer processor, the method comprising: using a binocular camera to collect three-dimensional image data of the fire point and the transmission corridor monitoring data corresponding to the current transmission corridor in real time, and performing data processing on the three-dimensional image data of the fire point to generate a three-dimensional depth map of the fire point; scanning the current transmission corridor by a laser radar to obtain current three-dimensional point cloud data; performing registration and calibration processing on the three-dimensional depth map of the fire point and the current three-dimensional point cloud data through a pre-constructed registration algorithm to determine the distance and position of the current fire point; obtaining current surrounding environment feature information, and correcting the current fire point distance and position through a pre-calibrated surrounding environment feature processing method to obtain the current corrected fire point distance and position; inputting the obtained current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position into a pre-trained risk assessment model to obtain a wildfire tripping risk assessment result corresponding to the current transmission corridor.
[0093] Of course, the computer-readable storage medium provided in an embodiment of the present invention, whose computer executable instructions are not limited to the method operations described above, can also execute the relevant operations in the wildfire tripping risk assessment method for the power transmission corridor based on binocular camera and point cloud provided in any embodiment of the present invention.
[0094] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (FLASH), a hard disk or an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0095] It is worth noting that in the above-mentioned embodiment of the wildfire tripping risk assessment device for the power transmission corridor based on binocular camera and point cloud, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.
[0096] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for assessing the risk of wildfire tripping in power transmission corridors based on binocular cameras and point clouds, characterized in that: include: The three-dimensional image data of the fire point corresponding to the current transmission corridor and the transmission corridor monitoring data are collected in real time by using a binocular camera, and the three-dimensional image data of the fire point is processed to generate a three-dimensional depth map of the fire point; Scan the current transmission corridor through LiDAR to obtain the current three-dimensional point cloud data; The three-dimensional depth map of the fire point and the current three-dimensional point cloud data are calibrated and registered by a pre-built registration algorithm to determine the distance and position of the current fire point; Acquire current surrounding environment characteristic information, and correct the current fire point distance and position by a pre-calibrated surrounding environment characteristic processing method to obtain a current corrected fire point distance and position; The acquired current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position are input into a pre-trained risk assessment model to obtain a wildfire tripping risk assessment result corresponding to the current transmission corridor.
2. The method according to claim 1, characterized in that After the acquired current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position are input into the pre-trained risk assessment model to obtain the mountain fire tripping risk assessment result corresponding to the current transmission corridor, the method further includes: Feedback the obtained wildfire tripping risk assessment result to the user; Among them, the wildfire tripping risk assessment results include the wildfire tripping risk assessment level, wildfire tripping risk warning information and wildfire tripping emergency measures recommendation information.
3. The method according to claim 2, characterized in that The step of processing the three-dimensional image data of the fire point to generate a three-dimensional depth map of the fire point includes: Performing data preprocessing on the three-dimensional image data of the fire point to obtain an initial three-dimensional depth map of the fire point; The initial fire point three-dimensional depth map is denoised by a set image processing algorithm to generate the fire point three-dimensional depth map.
4. The method according to claim 3, characterized in that The pre-built registration algorithm is used to perform registration and calibration processing on the three-dimensional depth map of the fire point and the current three-dimensional point cloud data to determine the distance and position of the current fire point, including: The three-dimensional depth map of the fire point and the current three-dimensional point cloud data are registered by a pre-built registration algorithm to obtain the registration distance and position of the current fire point; According to the three-dimensional depth map of the fire point and the current three-dimensional point cloud data, a current alignment calibration parameter T is calculated by a pre-constructed rigid transformation model; Among them, the formula corresponding to the rigid transformation model is Where R is the preset rotation matrix; t is the pre-acquired translation vector; p i is the point in the three-dimensional depth map of the fire point, q i is the point of the current 3D point cloud data, p i and q i The corresponding point pairs in the three-dimensional depth map of the fire point and the current three-dimensional point cloud data; According to the current alignment calibration parameters, the current fire point registration distance and position are aligned and calibrated to obtain the current fire point distance and position.
5. The method according to claim 4, characterized in that The current surrounding environment characteristic information includes surrounding building characteristic information and surrounding pond characteristic information; The obtaining of the current surrounding environment characteristic information and correcting the current fire point distance and position by a pre-calibrated surrounding environment characteristic processing method to obtain the current corrected fire point distance and position includes: Obtaining characteristic information of surrounding buildings and surrounding ponds; According to the characteristic information of the surrounding buildings and the characteristic information of the surrounding ponds, the current fire point distance and position are corrected by a pre-calibrated surrounding environment characteristic processing method to obtain the current corrected fire point distance and position.
6. The method according to claim 5, characterized in that The current terrain feature environment change information includes slope and aspect parameters, combustible load, vegetation type parameters, and wind speed, temperature, and humidity parameters; The acquired current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position are input into the pre-trained risk assessment model to obtain the mountain fire tripping risk assessment result corresponding to the current transmission corridor. include: Among them, the current transmission corridor slope and slope description information is obtained from the point cloud data obtained by the lidar, the combustible load and vegetation type description information is obtained from the collected remote sensing data, and the wind speed, temperature and humidity description information is obtained from the data collected by the sensor; The slope and aspect parameters, the combustible load, the vegetation type parameters, the wind speed, temperature and humidity parameters, the transmission corridor monitoring data and the current corrected fire point distance and position are input into a pre-trained risk assessment model to calculate the phase-to-ground breakdown voltage and the phase-to-phase breakdown voltage; According to the phase-to-ground breakdown voltage and the phase-to-phase breakdown voltage, a phase-to-ground risk assessment coefficient, an inter-phase risk assessment coefficient, a phase-to-ground risk level, and an inter-phase risk level are obtained; Based on the phase-to-ground risk assessment coefficient, the phase-to-phase risk assessment coefficient, the phase-to-ground risk level and the phase-to-phase risk level, the wildfire tripping risk assessment result corresponding to the current transmission corridor is obtained.
7. The method according to claim 6, characterized in that The vegetation type description information in the current terrain feature environment change information includes: vegetation type correction coefficient and vegetation density correction coefficient; the current transmission corridor slope and slope description information includes altitude correction coefficient; combustible load includes smoke particle correction coefficient; wind speed, temperature and humidity parameters include flame temperature correction coefficient; The transmission corridor monitoring data include: flame height, flame continuous zone height, conductor to tree crown distance, wildfire tolerance strength per unit length of standard flame continuous zone, wildfire tolerance strength per unit length of standard flame discontinuous zone, tolerance strength per unit length of standard air gap and gap distance between conductors; By formula The current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position are input into the pre-trained risk assessment model to calculate the phase-to-ground breakdown voltage U G ; Among them, H F Indicates flame height; H f Indicates the height of the flame continuous zone; d l-t Indicates the distance between the conductor and the tree crown; E f Indicates the wildfire tolerance intensity per unit length of the standard flame continuous area; E x Indicates the wildfire tolerance intensity per unit length of the standard flame discontinuity zone; E s Indicates the withstand strength per unit length of the standard air gap; C k Indicates vegetation type correction coefficient; C d Represents vegetation density correction coefficient; C a Indicates the altitude correction factor; C p Indicates the smoke particle correction factor; C t Indicates the flame temperature correction factor; By formula The current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position are input into the pre-trained risk assessment model to calculate the phase-to-phase breakdown voltage U P ; Among them, d p Indicates the gap distance between wires.
8. A device for assessing the risk of mountain fire tripping in a power transmission corridor based on a binocular camera and point cloud, characterized in that: include: A fire point three-dimensional depth map generation module is used to collect the corresponding fire point three-dimensional image data and transmission corridor monitoring data under the current transmission corridor in real time through a binocular camera, and perform data processing on the fire point three-dimensional image data to generate a fire point three-dimensional depth map; The current three-dimensional point cloud data determination module is used to scan the current transmission corridor through a laser radar to obtain the current three-dimensional point cloud data; A current fire point distance and position determination module is used to perform registration and calibration processing on the fire point three-dimensional depth map and the current three-dimensional point cloud data through a pre-built registration algorithm to determine the current fire point distance and position; A current corrected fire point distance and position determination module is used to obtain current surrounding environment feature information, and correct the current fire point distance and position through a pre-calibrated surrounding environment feature processing method to obtain the current corrected fire point distance and position; The wildfire tripping risk assessment result determination module is used to input the acquired current terrain feature environment change information, the transmission corridor monitoring data and the current corrected fire point distance and position into a pre-trained risk assessment model to obtain the wildfire tripping risk assessment result corresponding to the current transmission corridor.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the method for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and a point cloud as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a method for assessing the risk of wildfire tripping in a power transmission corridor based on a binocular camera and a point cloud as described in any one of claims 1 to 7 when executed.