WO2024119705A1 - 针对消防炮的射流落点检测及灭火控制的方法和装置 - Google Patents

针对消防炮的射流落点检测及灭火控制的方法和装置 Download PDF

Info

Publication number
WO2024119705A1
WO2024119705A1 PCT/CN2023/092046 CN2023092046W WO2024119705A1 WO 2024119705 A1 WO2024119705 A1 WO 2024119705A1 CN 2023092046 W CN2023092046 W CN 2023092046W WO 2024119705 A1 WO2024119705 A1 WO 2024119705A1
Authority
WO
WIPO (PCT)
Prior art keywords
fire
jet
point
monitor
fire monitor
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2023/092046
Other languages
English (en)
French (fr)
Inventor
付玲
孙浠汉
范卿
熊忆
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zoomlion Heavy Industry Science and Technology Co Ltd
Original Assignee
Zoomlion Heavy Industry Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zoomlion Heavy Industry Science and Technology Co Ltd filed Critical Zoomlion Heavy Industry Science and Technology Co Ltd
Publication of WO2024119705A1 publication Critical patent/WO2024119705A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A62—LIFE-SAVING; FIRE-FIGHTING
    • A62C—FIRE-FIGHTING
    • A62C19/00—Hand fire-extinguishers in which the extinguishing substance is expelled by an explosion; Exploding containers thrown into the fire
    • A—HUMAN NECESSITIES
    • A62—LIFE-SAVING; FIRE-FIGHTING
    • A62C—FIRE-FIGHTING
    • A62C31/00—Delivery of fire-extinguishing material
    • A62C31/02—Nozzles specially adapted for fire-extinguishing
    • A62C31/03—Nozzles specially adapted for fire-extinguishing adjustable, e.g. from spray to jet or vice versa
    • A—HUMAN NECESSITIES
    • A62—LIFE-SAVING; FIRE-FIGHTING
    • A62C—FIRE-FIGHTING
    • A62C37/00—Control of fire-fighting equipment
    • A—HUMAN NECESSITIES
    • A62—LIFE-SAVING; FIRE-FIGHTING
    • A62C—FIRE-FIGHTING
    • A62C37/00—Control of fire-fighting equipment
    • A62C37/50—Testing or indicating devices for determining the state of readiness of the equipment
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
    • Y02A40/28—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture specially adapted for farming

Definitions

  • the embodiments of the present application relate to the field of fire-fighting equipment, and specifically, to a method and device for jet landing point detection and fire extinguishing control for a fire-fighting cannon.
  • the jet trajectory of the fire monitor is easily affected by external factors such as outdoor wind or machine equipment operation errors, resulting in a deviation between the jet landing point of the fire monitor and the target fire point, making it difficult to accurately detect the jet landing point, so that the fire-fighting effect of the fire monitor in actual application is often not ideal.
  • the purpose of the embodiments of the present application is to provide a method and device for jet landing point detection and fire extinguishing control for a fire monitor, so as to solve the problem that the flow trajectory of the fire monitor is easily affected by external factors.
  • an embodiment of the present application provides a method for detecting the jet landing point of a fire monitor, including: obtaining point cloud data of a three-dimensional target fire point area when the fire monitor is in an unactivated state, and obtaining jet trajectory image data when the fire monitor is in an activated state and the jet trajectory is stable; extracting a jet area from the jet trajectory image data; performing curve fitting on the jet area to obtain a jet trajectory curve; determining the intersection of the jet trajectory curve and the end of the jet area as the jet landing point; and extracting the three-dimensional spatial position information of the jet landing point from the point cloud data of the three-dimensional target fire point area.
  • extracting the jet region from the jet trajectory image data comprises: performing transmittance feature extraction on the jet trajectory image data based on a preset rule to extract a transmittance feature image as the first jet candidate region; performing motion feature extraction on the jet trajectory image data to extract a jet motion region. as a second jet candidate region; and performing similarity feature matching on the first jet candidate region and the second jet candidate region to extract the jet region.
  • An embodiment of the present application also provides a fire extinguishing control method for a fire cannon, including: obtaining the current fire point position; using any of the above-mentioned jet landing point detection methods to obtain the jet landing point position corresponding to the fire extinguishing of the fire cannon based on the initial posture parameters of the fire cannon; and correcting the fire cannon posture when the position deviation between the fire point position and the jet landing point position is greater than or equal to a preset deviation.
  • the obtaining of the current fire point position includes: obtaining visible light image data, infrared image data and three-dimensional fire point area point cloud data for the current fire point; extracting a first flame candidate area and a second flame candidate area from the visible light image data and the infrared image data, respectively; fusing the first flame candidate area and the second flame candidate area to extract an intersection area as a fire point area; and extracting the three-dimensional spatial position information of the fire point area from the three-dimensional target fire point area point cloud data.
  • the method further includes: obtaining a fire cannon jet model showing the correlation between the fire point position, the fire cannon position and the fire cannon initial posture parameters, wherein the fire cannon jet model is configured to output fire cannon posture parameters so that the muzzle direction of the fire cannon is aligned with the fire point direction and the fire cannon jet area can cover the fire point area; and in the fire cannon coordinate system, based on the current fire point position, obtaining the fire cannon initial posture parameters through the fire cannon jet model, wherein the fire cannon initial posture parameters are used to control the posture of the fire cannon.
  • the initial posture parameters of the fire cannon include the direction of the fire cannon muzzle, the elevation angle of the fire cannon, the horizontal angle of the fire cannon and/or the water pressure at the muzzle of the fire cannon, and the fire cannon jet model is configured as follows: based on the direction vector of the fire point position relative to the fire cannon, the elevation angle of the fire cannon and the horizontal angle of the fire cannon are output so that the muzzle direction of the fire cannon is aligned with the direction of the fire point; and in the fire cannon coordinate system and when the muzzle direction of the fire cannon is aligned with the direction of the fire point, based on the spatial position of the fire point position relative to the fire cannon, the elevation angle of the fire cannon and the water pressure at the muzzle of the fire cannon are output so that the jet area of the fire cannon covers the fire point area.
  • the correction of the fire cannon posture includes: determining the horizontal deflection angle that needs to be adjusted for the fire cannon and the landing point position deviation distance that needs to be compensated according to the three-dimensional spatial position coordinates of the fire point, the jet landing point and the fire cannon; determining the expected target fire point position of the fire cannon according to the determined landing point position deviation distance, and based on the expected target fire point position, obtaining the fire cannon optimized posture parameters through the fire cannon jet model; and obtaining the jet landing point optimized position corresponding to the fire cannon extinguishing the fire based on the fire cannon optimized posture parameters. If the position deviation between the expected target fire point position and the jet landing point optimized position is less than the preset deviation, the correction is completed, otherwise repeat the above steps until the corresponding position deviation is less than the preset deviation.
  • the following formula is used to calculate the horizontal deflection angle ⁇ of the fire monitor that needs to be corrected:
  • ( XF , YF , ZF ), ( XW , YW , ZW ) and ( XM , YM , ZM ) are the three-dimensional spatial position coordinates of the fire point, jet landing point and fire monitor respectively.
  • An embodiment of the present application also provides a jet landing point detection device for a fire monitor, comprising: a memory storing a program that can be run on a processor; and the processor, which is configured to implement any of the above-mentioned jet landing point detection methods when executing the program.
  • the embodiment of the present application also provides a fire extinguishing control device for a fire cannon, comprising: a data processing unit and a fire cannon control unit.
  • the data processing unit comprises: a fire point detection module, used to obtain the current fire point position; a fire cannon attitude solution module, used to determine the fire cannon initial attitude parameters based on the fire point position; a jet landing point detection module, configured as any of the above jet landing point detection devices, used to obtain the jet landing point position corresponding to the fire cannon extinguishing the fire based on the fire cannon initial attitude parameters.
  • the fire cannon control unit is configured to: correct the fire cannon attitude when the position deviation between the fire point position and the jet landing point position is greater than or equal to the preset deviation.
  • the fire extinguishing control device also includes a data acquisition unit, and the data acquisition unit includes a visible light image acquisition device, an infrared image acquisition device and a laser radar adapted for installation on the fire monitor, for respectively collecting visible light image data, infrared image data and three-dimensional fire point area point cloud data for the current fire point.
  • the data acquisition unit includes a visible light image acquisition device, an infrared image acquisition device and a laser radar adapted for installation on the fire monitor, for respectively collecting visible light image data, infrared image data and three-dimensional fire point area point cloud data for the current fire point.
  • the present application also provides a machine-readable storage medium.
  • the medium stores instructions for causing the machine to execute any of the above-mentioned jet landing point detection methods or any of the above-mentioned fire extinguishing control methods.
  • the embodiment of the present application combines the three-dimensional target fire point area point cloud data and the jet trajectory image data to achieve accurate landing point detection and positioning, which in turn helps to further guide the adjustment of the fire cannon posture, reduce the deviation between the jet landing point position and the target fire point position, and improve the fire extinguishing effect.
  • FIG1 is a schematic flow chart of a method for detecting a jet landing point of a fire monitor according to an embodiment of the present application
  • FIG2 is a schematic diagram of a process of extracting a jet region from jet trajectory image data in an embodiment of the present application
  • FIG3 is a flow chart of a fire extinguishing control method of a fire monitor according to an embodiment of the present application
  • FIG4 is a schematic diagram of a flow chart of obtaining a fire point position in an embodiment of the present application.
  • FIG5 is a schematic diagram of a process for determining the initial posture parameters of a fire monitor based on the position of a fire point in an embodiment of the present application
  • FIG6 is a plan view of an exemplary jet trajectory according to an embodiment of the present application.
  • FIG7 is a schematic diagram of a process for calibrating the posture of a fire monitor in an embodiment of the present application.
  • FIG8 is a schematic diagram of the spatial position relationship between the fire monitor, the jet landing point and the fire point in the embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of a fire extinguishing control device of a fire monitor according to an embodiment of the present application.
  • Point cloud The embodiments of the present application mainly refer to the laser radar point cloud, which is a set of data points representing a 3D shape or object in space obtained by scanning with a three-dimensional laser radar device. Each point contains three-dimensional coordinate information, namely, three elements of x, y, and z, denoted as (x, y, z).
  • mapping relationship between the 3D spatial coordinates in the point cloud and the 2D pixel coordinates in the image The mapping between the 2D pixel coordinate point (x F , y F ) and the 3D spatial position (X F , Y F , Z F ) in the radar point cloud is realized through the camera internal and external parameters obtained by camera calibration, the relationship between the camera and the ground coordinate system and projection, and the relationship between the pixel and the plane.
  • the mapping relationship can be described as the following formula (1):
  • K is the intrinsic parameter matrix of the camera
  • R is the rotation matrix of the camera pose
  • t is the translation vector
  • controllable factors ⁇ such as equipment deflection angle error
  • uncontrollable factors ⁇ include external wind force, etc., which cannot be well statistically analyzed.
  • the first embodiment of the present application provides a method for detecting the jet landing point of a fire monitor, which is used to improve the accuracy of the landing point detection in various complex fire environments.
  • FIG1 is a flow chart of the method for detecting the jet landing point of a fire monitor in the embodiment of the present application. As shown in FIG1 , the method for detecting the jet landing point may include the following steps S110-S150:
  • Step S110 obtaining the three-dimensional target fire point area point cloud data when the fire monitor is in an unactivated state, and obtaining the jet trajectory image data when the fire monitor is in an activated state and the jet trajectory is stable.
  • the fire monitor sprays water
  • a jet suitable for the fire monitor installation For example, before the fire monitor sprays water, use a jet suitable for the fire monitor installation.
  • the optical radar collects point cloud data of the three-dimensional target fire point area, and starts the fire monitor.
  • the jet trajectory image data is collected through the visible light image acquisition device adapted to the fire monitor installation.
  • the visible light image acquisition device is, for example, a visible light camera.
  • Step S120 extracting a jet area from the jet trajectory image data.
  • Step S121 extracting transmittance features from the jet trajectory image data based on preset rules to extract a transmittance feature image as a first jet candidate region.
  • the transmittance feature image is extracted using the evaluation rule shown in the following formula (2), and then the transmittance feature image is classified using the evaluation rule shown in the following formula (3) to generate the first jet candidate area C 1 of the fire monitor. f(x,y) ⁇ 12 (3)
  • ⁇ r, g, b ⁇ represents the RGB channels of the jet trajectory image
  • J c (x, y) is the pixel value of the RGB channel of the image at (x, y)
  • f(x, y) represents the pixel grayscale value of the transmittance feature image at (x, y)
  • A is the coefficient
  • ⁇ 12 is the threshold.
  • Step S122 extracting motion features from the jet trajectory image data to extract a motion region as a second jet candidate region.
  • step S122 is intended to evaluate motion features, using a background subtraction method based on a mixed Gaussian model and the difference between previous and next frame images to classify the background area and foreground area in the image, and extract the motion area of the jet as the second jet candidate area C 2 of the fire monitor.
  • Step S123 performing similarity feature matching on the first jet candidate region and the second jet candidate region to extract the jet region.
  • the absolute difference matching method is applied to the extracted first jet candidate area C1 and the second jet candidate area C2 , and similarity feature matching is performed using the evaluation rule shown in the following formula (4) to obtain the jet area C of the fire monitor.
  • D(a,b)
  • D(a,b) represents the similarity
  • a(x,y) and b(x,y) correspond to the candidate regions respectively.
  • the pixel value of C1 image and C2 image at (x,y), ⁇ 13 is the threshold.
  • Step S130 performing curve fitting on the jet region to obtain a jet trajectory curve.
  • ⁇ represents the fitted jet trajectory curve
  • n represents the number of pixels in the jet feature area
  • ⁇ is the data deviation.
  • Step S140 determining the intersection of the jet trajectory curve and the end of the jet area as the jet landing point.
  • the intersection point ( xw , yw ) of the jet trajectory curve ⁇ and the end of the trajectory area C is selected as the jet landing point.
  • Step S150 extracting the three-dimensional spatial position information of the jet landing point from the three-dimensional target fire point area point cloud data.
  • the extracted jet landing point is mapped to the three-dimensional space based on the laser radar point cloud data, where the mapping method of the two-dimensional pixel coordinates to the three-dimensional space coordinates is as described in the above formula (1), so that the three-dimensional coordinates of the location of the landing point can be found.
  • the location coordinate information of the point can be fed back to the fire monitor control system to assist the fire monitor control system in completing the landing point positioning and subsequent fire extinguishing control.
  • Example 1 of the present application combines the three-dimensional target fire point area point cloud data and the jet trajectory image data to achieve accurate landing point detection and positioning, which helps to guide the adjustment of the fire monitor posture, reduce the deviation between the jet landing point position and the target fire point position, and improve the fire extinguishing effect.
  • Embodiment 2 of the present application provides a fire extinguishing control method for a fire monitor, as shown in FIG3 , which may include the following steps S310-S330:
  • Step S310 obtaining the current fire point position.
  • step S310 the main idea is: first, find the characteristics of the fire point in the visible light image and the infrared image, evaluate according to the color feature information and motion characteristics of the fire point, find the flame area separately and perform feature matching to obtain the fire point detection result; then, use the lidar to collect the point cloud data of the fire point area, combine the fire point detection result with the three-dimensional information of the point cloud, obtain the three-dimensional spatial information of the fire point, and complete the positioning of the fire point.
  • step S310 may include the following steps S311-S314:
  • Step S311 obtaining visible light image data, infrared image data and three-dimensional fire point area point cloud data for the current fire point.
  • the visible light image acquisition device infrared image acquisition device and laser radar adapted to the fire monitor installation
  • visible light image data infrared image data
  • three-dimensional fire point area point cloud data are collected for the current fire point.
  • the visible light image acquisition device and the infrared image acquisition device are respectively, for example, a visible light camera and an infrared camera, or both can be realized by a visible light/infrared dual-spectrum camera. It is easy to know that this multi-sensor fusion data detection method has redundancy characteristics and can adapt to more scenarios.
  • Step S312 extracting a first flame candidate region and a second flame candidate region from the visible light image data and the infrared image data respectively.
  • the visible light image is converted into a grayscale image, all pixels of the image are traversed, and the first flame candidate region F 1 is extracted using the evaluation rule shown in the following formula (6).
  • f(x,y) represents the grayscale value of the pixel in the image at (x,y)
  • ⁇ 1 is the threshold
  • ⁇ 1 is set according to the grayscale value sorting distribution of the grayscale image.
  • the second flame candidate region F 2 is extracted using the evaluation rules shown in the following equations (7) and (8) based on color space features and the evaluation rule shown in the following equation ( 9 ) based on adjacent frame motion difference features.
  • f R (x, y), f G (x, y), and f B (x, y) represent the image at (x, y) in R, G, and B.
  • fH (x,y), fS (x,y), and fI (x,y) represent the pixel values of the H, S, and I color channels of the image at (x,y).
  • ft (x,y) and ft-1 (x,y) represent the pixel values of the current and previous frames at (x,y), respectively.
  • ⁇ 2 , ⁇ 3 , ⁇ 4 , ⁇ 5 , ⁇ 6 , ⁇ 7 , ⁇ 8 , ⁇ 9 , and ⁇ 10 are thresholds.
  • Step S313 merge the first flame candidate region and the second flame candidate region to extract an intersection region as a fire point region.
  • the first flame candidate region is extracted from the visible light image data, so it can be recorded as a visible light feature region
  • the second flame candidate region is extracted from the infrared image data, so it can be recorded as an infrared feature region.
  • the representation of the visible light feature region and the infrared feature region is the pixel value in the image (for example, the pixel value of the feature region is set to 255, and the pixel value of other regions is set to 0), and the regional fusion is to take the intersection area of the pixel value of the visible light feature map and the infrared feature map as 255.
  • the intersection area is the fire point area to be extracted in the embodiment of the present application.
  • Step S314 extracting the three-dimensional spatial position information of the fire point area from the three-dimensional target fire point area point cloud data.
  • the three-dimensional spatial position information of the centroid coordinates of the fire point area is mainly extracted, and the three-dimensional spatial position information of the entire fire point area is determined based on this.
  • n represents the number of pixels in the flame region F
  • f( xi , yi ) represents the pixel value at the i-th pixel point ( xi , yi ) in the flame region.
  • the centroid coordinates (x F , y F ) of the fire point area F are converted into three-dimensional spatial position information in the three-dimensional target fire point area point cloud data, that is, the current fire point position is obtained.
  • Step S320 using the jet landing point detection method of the first embodiment, obtains the jet landing point position corresponding to the fire extinguishing of the fire monitor based on the initial posture parameters of the fire monitor.
  • step S320 after obtaining the current fire point position, preferably, the fire monitor posture parameters are first determined, wherein the fire monitor initial posture parameters are used to control the posture of the fire monitor.
  • the main idea of determining the fire cannon attitude parameters in step S320 is: after completing the fire point detection and positioning, first convert the fire point position coordinates into the fire cannon coordinate system, obtain the direction vector of the fire point relative to the fire cannon, and adjust the fire cannon pitch angle and horizontal angle according to the direction vector, so that the center direction of the fire cannon muzzle is aligned with the direction of the fire point; then, according to the spatial position of the target fire point relative to the fire cannon, the fire cannon attitude solution is completed through the fire cannon jet model.
  • step S320 may include:
  • Step S321 obtaining a fire monitor jet model showing the correlation between the fire point position, the fire monitor position and the fire monitor initial posture parameters.
  • the fire monitor jet model may be pre-constructed and stored in a storage medium, for example, and then the fire monitor jet model may be directly obtained from the storage medium for application.
  • the fire cannon jet model is configured to output the fire cannon attitude parameters so that the direction of the fire cannon muzzle is aligned with the direction of the fire point and the fire cannon jet area can cover the fire point area.
  • the fire cannon jet model is configured to: based on the direction vector of the fire point position relative to the fire cannon, output the fire cannon pitch angle and the fire cannon horizontal angle so that the direction of the fire cannon muzzle is aligned with the direction of the fire point; and in the fire cannon coordinate system and when the direction of the fire cannon muzzle is aligned with the direction of the fire point, based on the spatial position of the fire point position relative to the fire cannon, output the fire cannon pitch angle and the fire cannon muzzle water pressure so that the fire cannon jet area covers the fire point area.
  • the plane coordinate positions of the fire monitor and the fire point are defined as (0, Y M ) and (X F , Y F ) respectively, ⁇ is the angle between the fire monitor muzzle and the horizontal direction when the fire monitor muzzle is aimed at the fire point, and ⁇ is the angle between the fire monitor jet direction and the horizontal direction (recorded as the fire monitor horizontal angle or jet angle).
  • ⁇ is the angle between the fire monitor muzzle and the horizontal direction when the fire monitor muzzle is aimed at the fire point
  • ⁇ is the angle between the fire monitor jet direction and the horizontal direction (recorded as the fire monitor horizontal angle or jet angle).
  • ⁇ is the flow coefficient
  • P is the muzzle water pressure
  • p is the fluid density
  • jet model of the embodiment of the present application is initially constructed as follows:
  • m is the jet weight
  • k is the air resistance coefficient
  • g is the acceleration due to gravity
  • the muzzle water pressure P is first set according to the fire point distance to control the initial jet velocity v 0 so that the jet trajectory can be greater than the fire point distance, that is, the initial jet velocity v 0 should also be defined as follows:
  • the fire point area cannot be reached at the maximum water pressure, it means that the distance to the fire point exceeds the fire extinguishing distance and the fire cannot be extinguished.
  • the fire monitor jet model of the embodiment of the present application is constructed. It should be noted that the fire monitor attitude parameters output by the fire monitor jet model can be the initial attitude parameters of the fire monitor or the optimized attitude parameters of the fire monitor described below, depending on different application scenarios.
  • Step S322 in the fire monitor coordinate system, based on the current fire point position, the fire monitor initial posture parameters are obtained through the fire monitor jet model.
  • Step S330 when the position deviation between the fire point position and the jet landing point position is greater than or equal to a preset deviation, calibrate the fire monitor posture.
  • this step S330 is equivalent to a secondary adjustment of the fire monitor. This is because, when the fire monitor performs jetting based on the initial posture parameters of step S320, it may be affected by the environment and other factors, which may cause a landing point deviation, thereby affecting the fire extinguishing effect, so step S330 is required to further fine-tune the posture of the fire monitor based on the landing point position obtained in step S320.
  • the factors affecting the landing point deviation include controllable factors ⁇ and uncontrollable factors ⁇ .
  • the controllable factor ⁇ such as the deflection angle error of the equipment, can be manually corrected, and the uncontrollable factor ⁇ includes external wind force, etc., which cannot be well statistically analyzed. Therefore, based on the gradual adjustment of steps S320 and S330, the landing point of the fire monitor jet can be controlled to gradually approach the fire point, and precise fire extinguishing can be achieved on the basis of ensuring the accuracy of landing point detection and the fire extinguishing control rate.
  • step S330 may include the following steps S331-S333:
  • Step S331 according to the three-dimensional spatial position coordinates of the fire point, the jet landing point and the fire monitor, determine the horizontal deflection angle that needs to be adjusted for the fire monitor and the landing point position deviation distance that needs to be compensated.
  • ⁇ 0 is the preset deviation, which is a constant.
  • the embodiment of the present application directly calculates the horizontal deflection angle ⁇ according to formula (18) based on the coordinate positions of the fire point and the jet landing point on the horizontal plane (ignoring the height, that is, the influence of the Z axis).
  • Step S332 determining the expected target fire point position of the fire monitor according to the determined landing point position deviation distance, and obtaining the fire monitor optimized posture parameters through the fire monitor jet model based on the expected target fire point position.
  • Step S333 obtain the optimized position of the jet landing point corresponding to the fire extinguishing by the fire monitor based on the optimized posture parameters of the fire monitor. If the position deviation between the expected target fire point position and the optimized position of the jet landing point is less than the preset deviation, the correction is completed, otherwise repeat the above steps until the corresponding position deviation is less than the preset deviation.
  • the method of embodiment 1 is used to re-determine the jet landing point based on the new target fire point (X aimF , Y aimF ), and recalculate the position deviation ⁇ between the landing point and the fire point. If ⁇ 0 , it means that the jet landing point accurately covers the fire point, otherwise the deviation is recalculated and the fire monitor posture is adjusted.
  • the second embodiment of the present application implements the fire point positioning solution of multi-sensor fusion and the high-precision landing point positioning solution of the first embodiment, and further repeatedly corrects the posture of the fire monitor based on the deviation between the landing point and the fire point, realizes the self-adjustment of the posture of the fire monitor, and thus improves the fire extinguishing effect.
  • the entire fire extinguishing control process of the second embodiment of the present application realizes the fully automatic fire extinguishing operation without manual intervention, improves the intelligence level of the fire monitor, and can meet the current digital construction requirements.
  • Embodiment 3 of the present application provides a jet landing point detection device for a fire monitor, comprising: a memory storing a program that can be run on a processor; and the processor, The device is configured to implement the jet landing point detection method of the first embodiment when executing the program.
  • the jet point detection device can be implemented by using a conventional controller with computing and data transmission capabilities, such as a controller that comes with a fire monitor.
  • the jet point detection device can be installed as a controller on fire fighting equipment such as fire trucks, and can also be installed in factories, warehouses and other scenes, and has wide practicality.
  • the processor includes a kernel, which retrieves the corresponding program unit from the memory.
  • a kernel which retrieves the corresponding program unit from the memory.
  • One or more kernels can be provided, and the drop point detection involved in the embodiment of the present application can be implemented by adjusting kernel parameters.
  • the memory may include a non-permanent memory in a computer-readable medium, a random access memory (RAM) and/or a non-volatile memory, such as a read-only memory (ROM) or a flash RAM.
  • the memory may include at least one memory chip.
  • a fourth embodiment of the present application provides a fire extinguishing control device for a fire monitor, which may include the following data processing unit 100 and a fire monitor control unit 200 .
  • the data processing unit 100 includes: a fire point detection module 110, which is used to obtain the current fire point position; a fire cannon posture solution module 120, which is used to determine the initial posture parameters of the fire cannon based on the fire point position; and a jet landing point detection module 130, which is configured as the jet landing point detection device described in Example 4, and is used to obtain the jet landing point position corresponding to the fire cannon extinguishing the fire based on the initial posture parameters of the fire cannon.
  • a fire point detection module 110 which is used to obtain the current fire point position
  • a fire cannon posture solution module 120 which is used to determine the initial posture parameters of the fire cannon based on the fire point position
  • a jet landing point detection module 130 which is configured as the jet landing point detection device described in Example 4, and is used to obtain the jet landing point position corresponding to the fire cannon extinguishing the fire based on the initial posture parameters of the fire cannon.
  • the fire monitor control unit 200 is configured to correct the fire monitor posture when the position deviation between the fire point position and the jet landing point position is greater than or equal to the preset deviation. Further, according to the specific control amount, the fire monitor control unit may include a fire monitor elevation angle control module, a fire monitor horizontal angle control module, and a fire monitor muzzle water pressure control module.
  • the fire extinguishing control device of the fire monitor may further include: a data acquisition unit 300.
  • the data acquisition unit 300 includes a visible light image acquisition device, an infrared image acquisition device and a laser radar adapted to be installed on the fire monitor, and is used to Visible light image data, infrared image data and three-dimensional fire point area point cloud data are collected for the current fire point.
  • the fire extinguishing control device can be configured as a controller including multiple functional modules or integrated into a fire cannon control system, which makes it easy to implement in practice. It can be built on fire-fighting equipment such as fire trucks, and can also be installed as part of a fire cannon control system (especially a remote system) in factories, warehouses and other scenarios, and has wide practicality.
  • Another embodiment of the present application also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable the machine to execute the jet landing point detection method or fire extinguishing control method described in the above embodiment.
  • the machine is, for example, a controller configured separately or a controller that comes with a fire monitor.
  • the machine-readable storage medium includes but is not limited to phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (Flash Memory) or other memory technology, read-only compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, tape disk storage or other magnetic storage devices and other media that can store program codes.
  • PRAM phase change memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • RAM random access memory
  • ROM read-only memory
  • EEPROM electrically erasable programmable read-only memory
  • flash Memory Flash Memory
  • CD-ROM compact disc read-only memory
  • DVD digital versatile disc
  • the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
  • a computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device that implements the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.
  • These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and/or one or more boxes in the block diagram.
  • a computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory.
  • processors CPU
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and/or non-volatile memory in the form of read-only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information.
  • Information can be computer readable instructions, data structures, program modules or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.
  • computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

Landscapes

  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Fire-Extinguishing By Fire Departments, And Fire-Extinguishing Equipment And Control Thereof (AREA)

Abstract

本申请涉及消防设备领域，公开了一种针对消防炮的射流落点检测及灭火控制的方法和装置。所述方法包括：获取消防炮处于未开启状态的情况下的三维目标火点区域点云数据，以及获取消防炮处于开启状态且射流轨迹稳定的情况下的射流轨迹图像数据；从所述射流轨迹图像数据中提取出射流区域；对所述射流区域进行曲线拟合以得到射流轨迹曲线；确定所述射流轨迹曲线与所述射流区域的末端的交点为射流落点；以及从所述三维目标火点区域点云数据中提取所述射流落点的三维空间位置信息。本申请结合三维目标火点区域点云数据和射流轨迹图像数据实现了精确的落点检测与定位。

Description

针对消防炮的射流落点检测及灭火控制的方法和装置
相关申请的交叉引用
本申请要求2022年12月05日提交的中国专利申请202211552557.7的权益，该申请的内容通过引用被合并于本文。
技术领域
本申请实施例涉及消防设备领域，具体地，涉及一种针对消防炮的射流落点检测及灭火控制的方法和装置。
背景技术
对于现有的消防炮，在用于复杂灭火场景时，消防炮的射流轨迹易受室外风力或机器设备操作误差等外界因素影响，导致消防炮的射流落点位置与目标火点位置存在偏差，难以精确检测射流落点，从而使得消防炮在实际应用中的灭火效果往往不够理想。
发明内容
本申请实施例的目的是提供一种针对消防炮的射流落点检测及灭火控制的方法及装置，用于解决消防炮流轨迹易受外界因素影响的问题。
为了实现上述目的，本申请实施例提供一种消防炮的射流落点检测方法，包括：获取消防炮处于未开启状态的情况下的三维目标火点区域点云数据，以及获取消防炮处于开启状态且射流轨迹稳定的情况下的射流轨迹图像数据；从所述射流轨迹图像数据中提取出射流区域；对所述射流区域进行曲线拟合以得到射流轨迹曲线；确定所述射流轨迹曲线与所述射流区域的末端的交点为射流落点；以及从所述三维目标火点区域点云数据中提取所述射流落点的三维空间位置信息。
优选地，在一种可能的实现方式中，所述从所述射流轨迹图像数据中提取出射流区域包括：基于预设规则对所述射流轨迹图像数据进行透射率特征提取，以提取出透射率特征图像作为第一射流候选区域；对所述射流轨迹图像数据进行运动特征提取，以提取出射流运动区域 作为第二射流候选区域；以及对所述第一射流候选区域和所述第二射流候选区域进行相似度特征匹配，以提取出射流区域。
本申请实施例还提供了一种消防炮的灭火控制方法，包括：获取当前的火点位置；采用上述任意的射流落点检测方法，获取所述消防炮基于消防炮初始姿态参数进行灭火对应的射流落点位置；以及在所述火点位置与所述射流落点位置的位置偏差量大于或等于预设偏差的情况下，校正消防炮姿态。
优选地，在一种可能的实现方式中，所述获取当前的火点位置包括：获取针对当前火点的可见光图像数据、红外图像数据和三维火点区域点云数据；分别从所述可见光图像数据和所述红外图像数据中提取出第一火焰候选区域和第二火焰候选区域；对所述第一火焰候选区域和所述第二火焰候选区域进行融合，以提取出交集区域来作为火点区域；以及从所述三维目标火点区域点云数据中提取所述火点区域的三维空间位置信息。
优选地，在一种可能的实现方式中，所述获取当前的火点位置之后，所述方法还包括：获取示出火点位置、消防炮位置及消防炮初始姿态参数之间的关联关系的消防炮射流模型，其中所述消防炮射流模型被配置为输出的消防炮姿态参数使得所述消防炮炮口方向对准火点方向以及使得消防炮射流区域能够覆盖火点区域；以及在消防炮坐标系下，基于当前的火点位置，通过所述消防炮射流模型获取消防炮初始姿态参数，其中所述消防炮初始姿态参数用于控制所述消防炮的姿态。
优选地，在一种可能的实现方式中，所述消防炮初始姿态参数包括消防炮炮口方向、消防炮俯仰角度、消防炮水平角度和/或消防炮炮口水压，并且所述消防炮射流模型被配置为：基于火点位置相对于消防炮的方向向量，输出所述消防炮俯仰角度和所述消防炮水平角度，以使得所述消防炮炮口方向对准火点方向；以及在消防炮坐标系下及在消防炮炮口方向对准火点方向的情况下，基于火点位置相对于消防炮的空间位置，输出所述消防炮俯仰角度和所述消防炮炮口水压，以使得消防炮射流区域覆盖火点区域。
优选地，在一种可能的实现方式中，所述校正消防炮姿态包括：根据火点、射流落点与消防炮的三维空间位置坐标，确定消防炮需要调整的水平偏转角度以及需要补偿的落点位置偏差距离；根据所确定的落点位置偏差距离，确定消防炮的预期目标火点位置，并基于所述预期目标火点位置，通过所述消防炮射流模型获取消防炮优化姿态参数；以及获取所述消防炮基于所述消防炮优化姿态参数进行灭火对应的射流落点优化位置，若所述预期目标火点位置和所述射流落点优化位置的位置偏差量小于所述预设偏差，则校正完成，否则重复上述步骤直到相应的位置偏差量小于所述预设偏差。
优选地，在一种可能的实现方式中，采用下式计算消防炮需要被校正的水平偏转角度δ：
式中，(XF,YF,ZF)、(XW,YW,ZW)、(XM,YM,ZM)分别为火点、射流落点与消防炮的三维空间位置坐标。
本申请实施例还提供了一种消防炮的射流落点检测装置，包括：存储器，其存储有能够在处理器上运行的程序；以及所述处理器，其被配置为执行所述程序时实现上述任意的射流落点检测方法。
本申请实施例还提供了一种消防炮的灭火控制装置，包括：数据处理单元和消防炮控制单元。所述数据处理单元包括：火点检测模块，用于获取当前的火点位置获取当前的火点位置；消防炮姿态解算模块，用于基于所述火点位置确定消防炮初始姿态参数；射流落点检测模块，被配置为上述任意的射流落点检测装置，用于获取所述消防炮基于所述消防炮初始姿态参数进行灭火对应的射流落点位置。所述消防炮控制单元被配置为：在所述火点位置与所述射流落点位置的位置偏差量大于或等于预设偏差的情况下，校正消防炮姿态。
优选地，在一种可能的实现方式中，所述灭火控制装置还包括数据采集单元，且该数据采集单元包括适配于所述消防炮安装的可见光图像采集装置、红外图像采集装置以及激光雷达，用于针对当前火点分别采集可见光图像数据、红外图像数据和三维火点区域点云数据。
本申请实施例还提供了一种机器可读存储介质，该机器可读存储 介质上存储有指令，该指令用于使得机器执行上述任意的射流落点检测方法或者上述任意的灭火控制方法。
通过上述技术方案，本申请实施例结合三维目标火点区域点云数据和射流轨迹图像数据实现了精确的落点检测与定位，进而有助于进一步引导对消防炮姿态的调整，减少射流落点位置与目标火点位置的偏差，提升了灭火效果。
本申请实施例的其它特征和优点将在随后的具体实施方式部分予以详细说明。
附图说明
附图是用来提供对本申请实施例的进一步理解，并且构成说明书的一部分，与下面的具体实施方式一起用于解释本申请实施例，但并不构成对本申请实施例的限制。在附图中：
图1是本申请实施例的消防炮的射流落点检测方法的流程示意图；
图2是本申请实施例中从射流轨迹图像数据中提取出射流区域的流程示意图；
图3是本申请实施例的消防炮的灭火控制方法的流程示意图；
图4是本申请实施例中获取火点位置的流程示意图；
图5是本申请实施例中基于火点位置确定消防炮初始姿态参数的流程示意图；
图6是本申请实施例的示例射流轨迹平面视图；
图7是本申请实施例中校正消防炮姿态的流程示意图；
图8是本申请实施例中关于消防炮、射流落点和火点的空间位置关系的示意图；以及
图9是本申请实施例消防炮的灭火控制装置的结构示意图。
具体实施方式
以下结合附图对本申请实施例的具体实施方式进行详细说明。应当理解的是，此处所描述的具体实施方式仅用于说明和解释本申请实施例，并不用于限制本申请实施例。
在此，先对本申请实施例所涉及的部分术语进行介绍，以便于理解本申请实施例：
1、点云：本申请实施例主要是指激光雷达点云，其是由三维激光雷达设备扫描得到的在空间中代表3D形状或对象的数据点集合，每一个点都包含了三维坐标信息，即x、y、z三个元素，记为(x,y,z)。
2、点云中的三维空间坐标与图像中的二维像素坐标之间的映射关系：通过相机标定所获得的相机内外参数、相机与地面坐标系及投影的关系、像素与平面的关系，实现二维像素坐标点(xF,yF)与雷达点云中的三维空间位置(XF,YF,ZF)之间的映射。映射关系可以描述为如下的式(1)：
式中，K为相机的内参矩阵，R为相机位姿的旋转矩阵，t为平移向量。
实施例一
目前，在消防炮应用于复杂火场环境，例如室外恶劣火场环境时，可能存在多种因素干扰射流，造成射流落点偏差，进而影响灭火效果。其中，落点偏差的影响因素包括可控因素ρ和不可控因素σ：可控因素ρ如设备偏转角度误差，能够人为修正；不可控因素σ包括外界风力等，无法进行较好的统计分析。
据此，本申请实施例一提供了一种消防炮的射流落点检测方法，用以提升在各种复杂火场环境下的落点检测精度。图1是本申请实施例的消防炮的射流落点检测方法的流程示意图。如图1所示，所述射流落点检测方法可以包括以下的步骤S110-S150：
步骤S110，获取消防炮处于未开启状态的情况下的三维目标火点区域点云数据，以及获取消防炮处于开启状态且射流轨迹稳定的情况下的射流轨迹图像数据。
举例而言，在消防炮未喷射水流前，使用适配于消防炮安装的激 光雷达采集三维目标火点区域点云数据，并启动消防炮，待射流轨迹稳定之后，再通过适配于消防炮安装的可见光图像采集装置，采集射流轨迹图像数据。其中，可见光图像采集装置例如是可见光相机。
步骤S120，从所述射流轨迹图像数据中提取出射流区域。
如图2所示，在优选的实施例中，该步骤S120例如包括以下步骤S121-S123：
步骤S121，基于预设规则对所述射流轨迹图像数据进行透射率特征提取，以提取出透射率特征图像作为第一射流候选区域。
在示例中，针对可见光相机采集的射流轨迹图像数据，遍历图像中所有像素，再基于暗原色先验理论，利用如下的式(2)示出的评估规则提取透射率特征图像，再利用如下的式(3)示出的评估规则对透射率特征图像进行分类，生成消防炮的第一射流候选区域C1。

f(x,y)<ε12      (3)
式中，{r,g,b}表示射流轨迹图像的RGB三个通道，Jc(x,y)是图像在(x,y)处RGB通道的像素值，f(x,y)表示透射率特征图像在(x,y)处的像素灰度值，A为系数，ε12为阈值。
步骤S122，对所述射流轨迹图像数据进行运动特征提取，以提取出运动区域作为第二射流候选区域。
承接上面的示例，该步骤S122旨在进行运动特征评估，利用基于混合高斯模型的背景减除法及前后帧图像差异，对图像中背景区域与前景区域分类，提取射流的运动区域以作为消防炮的第二射流候选区域C2。
步骤S123，对所述第一射流候选区域和所述第二射流候选区域进行相似度特征匹配，以提取出射流区域。
承接上面的示例，对提取的第一射流候选区域C1和第二射流候选区域C2应用绝对差匹配法，利用如下的式(4)示出的评估规则进行相似度特征匹配，获取消防炮的射流区域C。
D(a,b)＝|a(x,y)-b(x,y)|>ε13     (4)
式中，D(a,b)表示相似度，a(x,y)与b(x,y)分别对应候选区域 C1图像与C2图像在(x,y)处的像素值，ε13为阈值。
步骤S130，对所述射流区域进行曲线拟合以得到射流轨迹曲线。
优选地，针对步骤S130，采用基于最小二乘法的曲线拟合方法来处理所述射流区域的所有像素点，以得到射流轨迹0曲线。承接上面的示例，针对所提取的射流区域C，索引所有像素点，通过基于最小二乘法的曲线拟合方法获取消防炮射流轨迹曲线，曲线查找方式如下：
式中，τ代表所拟合的射流轨迹曲线，n表示射流特征区域像素点个数，δ为数据偏差和，当δ的值最小时，便能确定所查找的射流轨迹曲线τ。
步骤S140，确定所述射流轨迹曲线与所述射流区域的末端的交点为射流落点。
承接上面的示例，选取射流轨迹曲线τ与轨迹区域C末端的交点(xw,yw)作为射流落点。
步骤S150，从所述三维目标火点区域点云数据中提取所述射流落点的三维空间位置信息。
举例而言，将所提取的射流落点映射到基于激光雷达点云数据的三维空间中，其中二维像素坐标到三维空间坐标的映射方式如上述式(1)所述，从而可查找出落点的位置三维坐标。另外，可向消防炮控制系统反馈该点的位置坐标信息，以辅助消防炮控制系统完成落点定位及后续的灭火控制。
本申请实施例一针对外界因素对消防炮射流状态存在干扰的情况，结合三维目标火点区域点云数据和射流轨迹图像数据实现了精确的落点检测与定位，进而有助于引导对消防炮姿态的调整，减少射流落点位置与目标火点位置的偏差，提升了灭火效果。
实施例二
本申请实施例二提供一种消防炮的灭火控制方法，如图3所示，可以包括以下步骤S310-S330：
步骤S310，获取当前的火点位置。
针对该步骤S310，主要思路是：首先，查找火点在可见光图像和红外图像中的特征，根据火点的颜色特征信息和运动特征等进行评估，分别查找火焰区域并进行特征匹配，获取火点检测结果；然后，使用激光雷达采集火点区域点云数据，将火点检测结果与点云三维信息结合，获取火点的三维空间信息，完成火点的定位。
基于该主要思路，如图4所示，在优选的实施例中，针对该步骤S310可以包括以下的步骤S311-S314：
步骤S311，获取针对当前火点的可见光图像数据、红外图像数据和三维火点区域点云数据。
举例而言，通过适配于所述消防炮安装的可见光图像采集装置、红外图像采集装置以及激光雷达，针对当前火点分别采集可见光图像数据、红外图像数据和三维火点区域点云数据。其中，可见光图像采集装置、红外图像采集装置分别例如是可见光相机和红外相机，或者两者可以通过可见光/红外双光谱相机实现。易知，这种多传感器融合的数据检测方式，具有冗余特性，能够适应更多场景。
步骤S312，分别从所述可见光图像数据和所述红外图像数据中提取出第一火焰候选区域和第二火焰候选区域。
在示例中，针对所采集的可见光图像数据，将可见光图像转换为灰度图像，遍历图像所有像素，利用如下的式(6)所示出的评估规则提取第一火焰候选区域F1。
f(x,y)>ε1       (6)
其中，f(x,y)表示图像在(x,y)处的像素灰度值，ε1为阈值，且ε1根据灰度图像灰度值排序分布来设定。
针对所采集的红外图像数据，遍历所有像素，利用基于颜色空间特征的如下式(7)、式(8)示出的评估规则以及基于相邻帧运动差异特征的如下式(9)示出的评估规则，提取第二火焰候选区域F2。
fR(x,y)>fG(x,y)>fB(x,y)且fR(x,y)>ε2     (7)
ε4>fH(x,y)>ε5且ε6>fS(x,y)>ε7且ε8>fI(x,y)>ε9    (8)
|ft(x,y)-ft-1(x,y)|>ε10      (9)
其中，fR(x,y)、fG(x,y)、fB(x,y)表示图像在(x,y)处在R、G、B 颜色通道的像素值，fH(x,y)、fS(x,y)、fI(x,y)表示图像在(x,y)处在H、S、I颜色通道的像素值，ft(x,y)与ft-1(x,y)分别表示当前帧和前一帧图像在(x,y)处的像素值，ε2、ε3、ε4、ε5、ε6、ε7、ε8、ε9、ε10为阈值。
步骤S313，对所述第一火焰候选区域和所述第二火焰候选区域进行融合，以提取出交集区域来作为火点区域。
举例而言，第一火焰候选区域是从所述可见光图像数据提取的，故而可记为可见光特征区域，第二火焰候选区域是从所述红外图像数据中提取，故而可记为红外特征区域。可见光特征区域和红外特征区域的表象则是图像中像素值(例如特征区域像素值设为255，其他区域像素值设置为0)，而区域融合则是据此取可见光特征图和红外特征图的像素值为255的交集区域。该交集区域就是本申请实施例所要提取的火点区域。
步骤S314，从所述三维目标火点区域点云数据中提取所述火点区域的三维空间位置信息。
特别地，主要是提取火点区域的重心坐标的三维空间位置信息，据此确定为整个火点区域的三维空间位置信息。
承接上面的示例，采用如下的式(10)和式(11)计算火点区域F的重心坐标(xF,yF)：

其中，n代表火焰区域F内的像素个数，f(xi,yi)表示在火焰区域中第i个像素点(xi,yi)处的像素值。
然后，根据上述式(1)所示的映射关系，将火点区域F的重心坐标(xF,yF)转换为三维目标火点区域点云数据中的三维空间位置信息，即得到了当前的火点位置。
步骤S320，采用实施例一的射流落点检测方法，获取所述消防炮基于消防炮初始姿态参数进行灭火对应的射流落点位置。
针对该步骤S320，优选在获取当前火点位置之后，先确定消防炮姿态参数，其中该消防炮初始姿态参数用于控制所述消防炮的姿态。
在示例中，该步骤S320确定消防炮姿态参数的主要思路是：当完成火点检测定位后，首先将火点位置坐标转换到消防炮坐标系中，获取火点相对于消防炮的方向向量，并根据方向向量调整消防炮俯仰角度与水平角度，使消防炮炮口中心方向对准火点方向；然后，再根据目标火点相对于消防炮的空间位置，通过消防炮射流模型完成消防炮姿态解算。
基于该思路，如图5所示，在优选的实施例中，该步骤S320可以包括：
步骤S321，获取示出火点位置、消防炮位置及消防炮初始姿态参数之间的关联关系的消防炮射流模型。
其中，可以预先构建并且例如在存储介质中存储所述消防炮射流模型，而后则直接从存储介质中获取该消防炮射流模型以进行应用。
其中，所述消防炮射流模型被配置为输出的消防炮姿态参数使得所述消防炮炮口方向对准火点方向以及使得消防炮射流区域能够覆盖火点区域。据此，更为优选地，所述消防炮射流模型被配置为：基于火点位置相对于消防炮的方向向量，输出所述消防炮俯仰角度和所述消防炮水平角度，以使得所述消防炮炮口方向对准火点方向；以及在消防炮坐标系下及在消防炮炮口方向对准火点方向的情况下，基于火点位置相对于消防炮的空间位置，输出所述消防炮俯仰角度和所述消防炮炮口水压，以使得消防炮射流区域覆盖火点区域。
在示例中，参考图6示出的射流轨迹平面视图，定义消防炮与火点平面坐标位置分别为(0,YM)与(XF,YF)，β为消防炮炮口瞄准火点时与水平方向夹角，α为消防炮射流方向与水平方向夹角(记为消防炮水平角度或射流角度)。设定炮口水流速度为v0，则消防炮射流模型的约束条件可设置为：
式中，μ为流量系数，P为炮口水压，p为流体密度。
基于此，本申请实施例的射流模型初步构建为：
式中，m为射流重量，k为空气阻力系数，g为重力加速度。
进一步考虑射流过程中空气对射流轨迹的阻力(与射流速度成正比)，代入初始数据(0,YM)，获取射流角度与射流轨迹的关系模型公式如下：
在该示例中，因为α＝45°时，射流轨迹能达到最大距离，首先根据火点距离设定炮口水压P进而控制初始射流速度v0，使得射流轨迹能够大于火点距离，即初始射流速度v0还应被限定如下:
进一步地，若最大水压时仍无法达到火点区域，则说明火点距离超过灭火距离，无法进行灭火，若此时设定水压下的射流距离大于火点距离，α存在两个解(α＝45°时的解和α<45°时的解)，基于选择较小的解的考虑，可选择α<45°时的解，使得射流轨迹更加清晰，避免射流落点区域水流扩散程度过大，影响后续落点检测结果。
因此，针对上述射流模型，消防炮俯仰角度为：
θ＝α+β       (16)
如此，基于式(12)-式(16)，构建了本申请实施例的消防炮射流模型。需说明的是，消防炮射流模型所输出的消防炮姿态参数根据不同的应用情形，可以是消防炮初始姿态参数，也可以是下文的消防炮优化姿态参数。
步骤S322，在消防炮坐标系下，基于当前的火点位置，通过所述消防炮射流模型获取消防炮初始姿态参数。
在此，该消防炮初始姿态参数用于控制所述消防炮的姿态。承接上面的示例，构建的消防炮射流模型能够输出消防炮炮口方向、消防炮俯仰角度、消防炮水平角度和/或消防炮炮口水压等参数以用于消防炮调节，而这些参数可以提供给消防炮控制系统，以供其发布相应的控制指令来使得消防炮对准火点开始喷射水流。
步骤S330，在所述火点位置与所述射流落点位置的位置偏差量大于或等于预设偏差的情况下，校正消防炮姿态。
需说明的是，相对于步骤S320，该步骤S330相当于对消防炮进行了二次调节。这是因为，消防炮基于步骤S320的初始姿态参数进行射流时，受到环境等影响可能会造成落点偏差，进而影响灭火效果，从而需要步骤S330来基于步骤S320得到的落点位置对消防炮姿态进行进一步的精细调节。其中，如下落点偏差的影响因素包括可控因素ρ和不可控因素σ，可控因素ρ如设备偏转角度误差，能够人为修正，不可控因素σ包括外界风力等，无法进行较好的统计分析。因此，基于步骤S320和步骤S330的逐步调节，可以控制消防炮射流落点逐步逼近火点，在保证落点检测精度和灭火控制速率的基础上，实现精准灭火。
如图7所示，针对该步骤S330，可以包括以下的步骤S331-S333：
步骤S331，根据火点、射流落点与消防炮的三维空间位置坐标，确定消防炮需要调整的水平偏转角度以及需要补偿的落点位置偏差距离。
承接上面的示例，进一步参考图8示出的消防炮、射流落点和火点的空间位置关系，设(XF,YF,ZF)、(XW,YW,ZW)、(XM,YM,ZM)分别为火点、射流落点与消防炮的三维空间位置坐标。此时，此时射流落点与火点的位置偏差ω可通过下式计算：
若此时若ω<ω0，则代表射流落点精确覆盖火点，否则将开始射流落点引导补偿操作以计算需要调整的水平偏转角度以及需要补偿的落点位置偏差距离，ω0为预设偏差，其为常数。
在示例中，采用下面的式(18)计算消防炮需要被校正的水平偏转角度δ：
在此，例如受到侧面风力的影响，使得采用初始姿态参数所得到的射流落点与火点存在水平偏差，而本申请实施例根据火点与射流落点在水平平面上的坐标位置(忽略高度，即Z轴的影响)，直接根据式(18)计算水平偏转角度δ。
进一步地，采用下面的式(19)计算消防炮需要进行补偿的落点位置偏差距离
步骤S332，根据所确定的落点位置偏差距离，确定消防炮的预期目标火点位置，并基于所述预期目标火点位置，通过所述消防炮射流模型获取消防炮优化姿态参数。
承接上面的示例，根据落点位置偏差距离获取新的目标火点(XaimF,YaimF)代入到式(12)-式(16)示出的消防炮射流模型中，获得新的消防炮俯仰角度变化量θnew，其中XaimF为原始预设目标位置与需补偿的位置偏差之和，XaimF与YaimF计算公式如下：

YaimF＝ZF       (21)
步骤S333，获取所述消防炮基于所述消防炮优化姿态参数进行灭火对应的射流落点优化位置，若所述预期目标火点位置和所述射流落点优化位置的位置偏差量小于预设偏差，则校正完成，否则重复上述步骤直到相应的位置偏差量小于预设偏差。
承接上面的示例，通过实施例一的方法来基于新的目标火点(XaimF,YaimF)重新确定射流落点，并重新计算落点与火点的位置偏差ω，若ω<ω0，则代表射流落点精确覆盖火点，否则重新计算偏差量并调整消防炮姿态。
本申请实施例二实现了多传感器融合的火点定位方案以及实施例一的高精度落点定位方案，进一步基于落点和火点的偏差反复校正消防炮姿态，实现消防炮姿态自调整，进而提升灭火效果。并且，本申请实施例二的整个灭火控制过程无需人工介入而实现了全自动灭火操作，提升了消防炮的智能化水平，能满足当前的数字化施工要求。
实施例三
本申请实施例三提供了一种消防炮的射流落点检测装置，包括：存储器，其存储有能够在处理器上运行的程序；以及所述处理器，其 被配置为执行所述程序时实现实施例一的射流落点检测方法。
其中，所述射流落点检测装置可以利用常规的具有计算能力和数据传输能力的控制器来实现，例如消防炮自带的控制器。如此，该射流落点检测装置作为控制器，既能搭建在消防车等消防装置上，也能安装在工厂、仓库等场景内，实用性较广。
其中，处理器中包含内核，由内核去存储器中调取相应的程序单元。内核可以设置一个或以上，通过调整内核参数来实现本申请实施例涉及的落点检测。
其中，存储器可以包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。另外，存储器可以包括至少一个存储芯片。
该实施例三的消防炮的射流落点检测装置的更多实施细节及效果可参考实施例一，在此则不再进行赘述。
实施例四
如图9所示，本申请实施例四提供了一种消防炮的灭火控制装置，可以包括以下的数据处理单元100和消防炮控制单元200。
其中，数据处理单元100包括：火点检测模块110，用于获取当前的火点位置获取当前的火点位置；消防炮姿态解算模块120，用于基于所述火点位置确定消防炮初始姿态参数；以及射流落点检测模块130，被配置为实施例四所述的射流落点检测装置，用于获取所述消防炮基于所述消防炮初始姿态参数进行灭火对应的射流落点位置。
其中，消防炮控制单元200被配置为：在所述火点位置与所述射流落点位置的位置偏差量大于或等于预设偏差的情况下，校正消防炮姿态。进一步地，根据具体的控制量，所述消防炮控制单元可以包括消防炮俯仰角度控制模块、消防炮水平角度控制模块和消防炮炮口水压控制模块等。
在优选地的实施例中，消防炮的灭火控制装置还可以包括：数据采集单元300。其中，所述数据采集单元300包括适配于所述消防炮安装的可见光图像采集装置、红外图像采集装置以及激光雷达，用于 针对当前火点分别采集可见光图像数据、红外图像数据和三维火点区域点云数据。
进一步地，该灭火控制装置可被配置为包括多个功能模块的控制器或者集成到消防炮控制系统中，从而在实践中易于实现，既能搭建在消防车等消防装置上，也能作为消防炮控制系统(特别是远程系统)的部分安装在工厂、仓库等场景内，实用性较广。
该实施例四的消防炮的灭火控制装置的更多实施细节及效果可参考实施例二，在此则不再进行赘述。
本申请另一实施例还提供一种机器可读存储介质，该机器可读存储介质上存储有指令，该指令用于使得机器执行上述实施例所述的射流落点检测方法或者灭火控制方法。其中，所述机器例如是单独配置成的控制器或者消防炮自带的控制器。另外，所述机器可读存储介质包括但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体(Flash Memory)或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁盘存储或其他磁性存储设备等各种可以存储程序代码的介质。
其中，关于该实施例的机器可读存储介质的更多实施细节及效果，可参考前述相应方法的实施例，在此则不再进行赘述。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到 通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。存储器是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括……”限定的要素，并不排除在包括要素的过程、方法、商品或者设备中还存在另外的相同要素。
以上仅为本申请的实施例而已，并不用于限制本申请。对于本领域技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本申请的权利要求范围之内。
另外需要说明的是，在上述具体实施方式中所描述的各个具体技术特征，在不矛盾的情况下，可以通过任何合适的方式进行组合，例如交换部分步骤的执行顺序。为了避免不必要的重复，本申请实施例对各种可能的组合方式不再另行说明。
此外，本申请实施例的各种不同的实施方式之间也可以进行任意组合，只要其不违背本申请实施例的思想，其同样应当视为本申请实施例所公开的内容。

Claims (13)

  1. 一种消防炮的射流落点检测方法，包括：
    获取消防炮处于未开启状态的情况下的三维目标火点区域点云数据，以及获取消防炮处于开启状态且射流轨迹稳定的情况下的射流轨迹图像数据；
    从所述射流轨迹图像数据中提取出射流区域；
    对所述射流区域进行曲线拟合以得到射流轨迹曲线；
    确定所述射流轨迹曲线与所述射流区域的末端的交点为射流落点；以及
    从所述三维目标火点区域点云数据中提取所述射流落点的三维空间位置信息。
  2. 根据权利要求1所述的射流落点检测方法，其中，所述从所述射流轨迹图像数据中提取出射流区域包括：
    基于预设规则对所述射流轨迹图像数据进行透射率特征提取，以提取出透射率特征图像作为第一射流候选区域；
    对所述射流轨迹图像数据进行运动特征提取，以提取出射流运动区域作为第二射流候选区域；以及
    对所述第一射流候选区域和所述第二射流候选区域进行相似度特征匹配，以提取出射流区域。
  3. 一种消防炮的灭火控制方法，包括：
    获取当前的火点位置；
    采用权利要求1或2所述的射流落点检测方法，获取所述消防炮基于消防炮初始姿态参数进行灭火对应的射流落点位置；以及
    在所述火点位置与所述射流落点位置的位置偏差量大于或等于预设偏差的情况下，校正消防炮姿态。
  4. 根据权利要求3所述的灭火控制方法，其中，所述获取当前的火点位置包括：
    获取针对当前火点的可见光图像数据、红外图像数据和三维火点区域点云数据；
    分别从所述可见光图像数据和所述红外图像数据中提取出第一火焰候选区域和第二火焰候选区域；
    对所述第一火焰候选区域和所述第二火焰候选区域进行融合，以提取出交集区域来作为火点区域；以及
    从所述三维目标火点区域点云数据中提取所述火点区域的三维空间位置信息。
  5. 根据权利要求3所述的灭火控制方法，其中，所述获取当前的火点位置之后，所述方法还包括：
    获取示出火点位置、消防炮位置及消防炮初始姿态参数之间的关联关系的消防炮射流模型，其中所述消防炮射流模型被配置为输出消防炮姿态参数以使得所述消防炮炮口方向对准火点方向以及使得消防炮射流区域能够覆盖火点区域；以及
    在消防炮坐标系下，基于当前的火点位置，通过所述消防炮射流模型获取消防炮初始姿态参数，其中所述消防炮初始姿态参数用于控制所述消防炮的姿态。
  6. 根据权利要求5所述的灭火控制方法，其中，所述消防炮初始姿态参数包括消防炮炮口方向、消防炮俯仰角度、消防炮水平角度和/或消防炮炮口水压，并且所述消防炮射流模型被配置为：
    基于火点位置相对于消防炮的方向向量，输出所述消防炮俯仰角度和所述消防炮水平角度，以使得所述消防炮炮口方向对准火点方向；以及
    在消防炮坐标系下及在消防炮炮口方向对准火点方向的情况下，基于火点位置相对于消防炮的空间位置，输出所述消防炮俯仰角度和所述消防炮炮口水压，以使得消防炮射流区域覆盖火点区域。
  7. 根据权利要求5所述的灭火控制方法，其中，所述校正消防炮姿态包括：
    根据火点、射流落点与消防炮的三维空间位置坐标，确定消防炮需要调整的水平偏转角度以及需要补偿的落点位置偏差距离；
    根据所确定的落点位置偏差距离，确定消防炮的预期目标火点位置，并基于所述预期目标火点位置，通过所述消防炮射流模型获取消防炮优化姿态参数；以及
    获取所述消防炮基于所述消防炮优化姿态参数进行灭火对应的射流落点优化位置，若所述预期目标火点位置和所述射流落点优化位置的位置偏差量小于所述预设偏差，则校正完成，否则重复上述步骤直到相应的位置偏差量小于所述预设偏差。
  8. 根据权利要求7所述的灭火控制方法，，采用下式计算消防炮需要被校正的水平偏转角度δ：
    式中，(XF,YF,ZF)、(XW,YW,ZW)、(XM,YM,ZM)分别为火点、射流落点与消防炮的三维空间位置坐标。
  9. 一种消防炮的射流落点检测装置，包括：
    存储器，其存储有能够在处理器上运行的程序；以及
    所述处理器，其被配置为执行所述程序时实现权利要求1或2所述的射流落点检测方法。
  10. 一种消防炮的灭火控制装置，包括：
    数据处理单元，包括：
    火点检测模块，用于获取当前的火点位置获取当前的火点位置；
    消防炮姿态解算模块，用于基于所述火点位置确定消防炮初始姿态参数；
    射流落点检测模块，被配置为采用权利要求9所述的射流落点检测装置，用于获取所述消防炮基于所述消防炮初始姿态参数进行灭火对应的射流落点位置；
    消防炮控制单元，被配置为：
    在所述火点位置与所述射流落点位置的位置偏差量大于或等于预设偏差的情况下，校正消防炮姿态。
  11. 根据权利要求10所述的灭火控制装置，还包括数据采集单元，且该数据采集单元包括适配于所述消防炮安装的可见光图像采集装置、红外图像采集装置以及激光雷达，用于针对当前火点分别采集可见光图像数据、红外图像数据和三维火点区域点云数据。
  12. 一种消防炮的灭火控制装置，包括：
    存储器，其存储有能够在处理器上运行的程序；以及
    所述处理器，其被配置为执行所述程序时实现权利要求3至8中任意一项所述的灭火控制方法。
  13. 一种机器可读存储介质，该机器可读存储介质上存储有指令，该指令用于使得机器执行权利要求1或2所述的射流落点检测方法或者权利要求3至8中任意一项所述的灭火控制方法。
PCT/CN2023/092046 2022-12-05 2023-05-04 针对消防炮的射流落点检测及灭火控制的方法和装置 Ceased WO2024119705A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211552557.7 2022-12-05
CN202211552557.7A CN116020075B (zh) 2022-12-05 2022-12-05 针对消防炮的射流落点检测及灭火控制的方法和装置

Publications (1)

Publication Number Publication Date
WO2024119705A1 true WO2024119705A1 (zh) 2024-06-13

Family

ID=86074992

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/092046 Ceased WO2024119705A1 (zh) 2022-12-05 2023-05-04 针对消防炮的射流落点检测及灭火控制的方法和装置

Country Status (2)

Country Link
CN (1) CN116020075B (zh)
WO (1) WO2024119705A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120305621A (zh) * 2025-06-16 2025-07-15 上海为源物联科技有限公司 一种基于智能控制的消火取水调度方法

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116020075B (zh) * 2022-12-05 2025-10-03 中联重科股份有限公司 针对消防炮的射流落点检测及灭火控制的方法和装置
CN116382356B (zh) * 2023-05-10 2025-12-23 长沙万为机器人有限公司 一种基于火源定位识别的水炮俯仰控制方法
CN116603199B (zh) * 2023-06-26 2025-03-11 中联重科股份有限公司 消防炮的射流落点检测方法、装置、控制系统及介质
CN117547775A (zh) * 2023-11-16 2024-02-13 国网安徽省电力有限公司电力科学研究院 一种消防水喷射路径和落水点检测方法及消防系统
CN117771595B (zh) * 2024-02-27 2024-05-28 中国矿业大学 一种基于多模式视觉系统的举高消防灭火方法及系统
CN119440038B (zh) * 2024-10-25 2025-06-06 南京理工大学 灭火弹飞行参数的确定方法、系统、电子设备及存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109303995A (zh) * 2018-09-12 2019-02-05 东南大学 基于火源定位识别的消防机器人消防炮控制方法
RU2749587C1 (ru) * 2020-05-23 2021-06-15 Борис Юрьевич Гайворонский Способ дистанционного автоматизированного тушения пожаров и огнетушащий элемент для его осуществления
CN113877124A (zh) * 2021-11-15 2022-01-04 应急管理部天津消防研究所 一种消防炮射流落点智能控制系统
CN114307016A (zh) * 2021-11-22 2022-04-12 中国矿业大学 一种基于无人机视觉辅助消防炮灭火系统及控制方法
CN114534146A (zh) * 2021-11-25 2022-05-27 北京南瑞怡和环保科技有限公司 基于移动式电力消防灭火机器人火焰自动寻地的控制方法与系统
CN115035027A (zh) * 2022-04-29 2022-09-09 大连海事大学 一种基于荧光特性的消防闭环控制方法及系统
CN116020075A (zh) * 2022-12-05 2023-04-28 中联重科股份有限公司 针对消防炮的射流落点检测及灭火控制的方法和装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101574567B (zh) * 2009-06-08 2011-08-31 南京航空航天大学 基于计算机视觉技术的火灾智能探测、扑灭方法及系统
RU94864U1 (ru) * 2010-02-16 2010-06-10 Общество с ограниченной ответственностью "Авиаинформатика" Автоматическая система пожаротушения

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109303995A (zh) * 2018-09-12 2019-02-05 东南大学 基于火源定位识别的消防机器人消防炮控制方法
RU2749587C1 (ru) * 2020-05-23 2021-06-15 Борис Юрьевич Гайворонский Способ дистанционного автоматизированного тушения пожаров и огнетушащий элемент для его осуществления
CN113877124A (zh) * 2021-11-15 2022-01-04 应急管理部天津消防研究所 一种消防炮射流落点智能控制系统
CN114307016A (zh) * 2021-11-22 2022-04-12 中国矿业大学 一种基于无人机视觉辅助消防炮灭火系统及控制方法
CN114534146A (zh) * 2021-11-25 2022-05-27 北京南瑞怡和环保科技有限公司 基于移动式电力消防灭火机器人火焰自动寻地的控制方法与系统
CN115035027A (zh) * 2022-04-29 2022-09-09 大连海事大学 一种基于荧光特性的消防闭环控制方法及系统
CN116020075A (zh) * 2022-12-05 2023-04-28 中联重科股份有限公司 针对消防炮的射流落点检测及灭火控制的方法和装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120305621A (zh) * 2025-06-16 2025-07-15 上海为源物联科技有限公司 一种基于智能控制的消火取水调度方法
CN120305621B (zh) * 2025-06-16 2025-08-19 上海为源物联科技有限公司 一种基于智能控制的消火取水调度方法

Also Published As

Publication number Publication date
CN116020075A (zh) 2023-04-28
CN116020075B (zh) 2025-10-03

Similar Documents

Publication Publication Date Title
WO2024119705A1 (zh) 针对消防炮的射流落点检测及灭火控制的方法和装置
CN113327296B (zh) 基于深度加权的激光雷达与相机在线联合标定方法
Wang et al. SOIC: Semantic online initialization and calibration for LiDAR and camera
CN109931939B (zh) 车辆的定位方法、装置、设备及计算机可读存储介质
Bachrach et al. Estimation, planning, and mapping for autonomous flight using an RGB-D camera in GPS-denied environments
CN107148639B (zh) 确定跟踪目标的位置信息的方法及装置、跟踪装置及系统
CN120143870B (zh) 自适应控制的无人机飞行轨迹校正方法及系统
CN113050116A (zh) 机器人定位方法、装置、机器人和可读存储介质
US20190172215A1 (en) System and method for obstacle avoidance
CN113870343A (zh) 相对位姿标定方法、装置、计算机设备和存储介质
CN114332158A (zh) 一种基于相机和激光雷达融合的3d实时多目标跟踪方法
CN103822615A (zh) 一种多控制点自动提取与聚合的无人机地面目标实时定位方法
CN115371673A (zh) 一种未知环境中基于Bundle Adjustment的双目相机目标定位方法
CN111508025A (zh) 三维位置估计装置以及程序
CN113345012A (zh) 单目测距方法、目标的物理参数测量方法、装置及无人机
CN114419259A (zh) 一种基于物理模型成像仿真的视觉定位方法及系统
Sun et al. Automatic targetless calibration for LiDAR and camera based on instance segmentation
CN114266821A (zh) 在线定位方法、装置、终端设备及存储介质
CN115950435A (zh) 无人机巡检影像的实时定位方法
CN119937621A (zh) 一种针对复杂动态环境的飞行器目标锁定追踪方法及系统
KR20010055957A (ko) 증강현실 기반의 3차원 트래커와 컴퓨터 비젼을 이용한영상 정합 방법
CN121475158B (zh) 飞行器的定位方法、装置、飞行器、介质及程序产品
CN121028120B (zh) 基于激光成像雷达的无人机对接锥套目标检测与定位方法
CN112598736A (zh) 一种基于地图构建的视觉定位方法及装置
US20230104937A1 (en) Absolute scale depth calculation device, absolute scale depth calculation method, and computer program product

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23899299

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 23899299

Country of ref document: EP

Kind code of ref document: A1