Fire monitor jet landing point detection method, device, control system and medium

Abstract

The embodiments of the present invention provide a method, device, control system and medium for detecting the jet landing point of a fire monitor, which belongs to the field of fire fighting equipment. The method includes: obtaining a jet area point cloud and determining at least two mapping planes; for each mapping plane, projecting the jet area point cloud into a corresponding two-dimensional jet area projection image, and performing trajectory fitting to obtain a corresponding jet trajectory curve, and then obtaining the intersection position of the jet trajectory curve and the fire point plane constructed based on the fire point position; and fusing the intersection positions obtained based on different mapping planes to obtain the jet landing point position. The embodiments of the present invention use the fire point position and the jet area point cloud to determine the jet landing point, and no longer rely on the ground area point cloud, and can be applied to fire fighting scenarios of non-ground fire points such as high-rise buildings.

Description

Technical Field

[0001] The present invention relates to the field of fire-fighting equipment, and in particular to a method, a device, a control system and a medium for detecting the jet landing point of a fire-fighting cannon. Background Art

[0002] At present, in order to reduce the safety hazards of firefighters at the fire scene and improve the efficiency of firefighting work as well as the level of automation and intelligence, the research on intelligent control of fire cannons has become a hot topic in the industry. Among them, jet landing point detection is an important part of the research on intelligent control of fire cannons. However, when the existing jet landing point detection algorithm is used for firefighting operations in outdoor scenes, the jet landing point detection algorithm used has a good detection effect on the jet landing point in the ground area, but it relies on the point cloud of the ground area. When it comes to firefighting scenarios for non-ground fire points such as high-rise buildings, it does not have the functions of jet landing point positioning and fire extinguishing effect recognition.

[0003] Therefore, it is urgent to propose a fire cannon jet landing point detection solution that can be applied to more fire extinguishing scenarios. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method, device, control system and medium for detecting the jet landing point of a fire monitor, so as to at least partially solve the above-mentioned technical problems.

[0005] In order to achieve the above-mentioned purpose, an embodiment of the present invention provides a method for detecting the jet landing point of a fire monitor, comprising: obtaining a jet area point cloud, and determining at least two mapping planes for projecting the jet area point cloud into a two-dimensional jet area projection image; for each mapping plane, projecting the jet area point cloud into a corresponding two-dimensional jet area projection image, performing trajectory fitting on the projected two-dimensional jet area projection image to obtain a corresponding jet trajectory curve, and then obtaining the intersection position of the obtained jet trajectory curve and a fire point plane constructed based on the fire point position; and fusing the intersection positions obtained based on different mapping planes to obtain the jet landing point position.

[0006] Optionally, the obtaining of the jet area point cloud comprises: collecting point cloud data Cloud1 before the jet is turned on and point cloud data Cloud2 after the jet is turned on respectively by a laser radar installed on the fire monitor; extracting a differential point cloud Cloud1 from the point cloud data Cloud1 before the jet is turned on and the point cloud data Cloud2 after the jet is turned on dis ; and the extracted differential point cloud Cloud dis Perform point cloud segmentation based on region growing to obtain the jet area point cloud Cloud w .

[0007] Optionally, the at least two mapping planes include the following two planes perpendicular to the ground area and perpendicular to each other: a jet farthest end mapping plane for describing the farthest distance that the jet area can reach; and a jet vertical cross-sectional plane for describing the jet lateral offset.

[0008] Optionally, the farthest plane of the jet is determined as follows:

[0009] 0=A1x+B1y+C1z

[0010] In the formula, A1, B1, and C1 are based on the location of the fire point. The normal vector L1(0,0,1) of the ground plane and the coordinates of the closest point in the jet area (x min ,y min ,z min ) are coefficients determined by the jet, and x, y, and z represent the three-dimensional coordinates of the point on the farthest plane of the jet.

[0011] Among them, the coefficients A1, B1, and C1 are determined based on the following formula:

[0012] The vertical cross-sectional plane of the jet that is perpendicular to both the ground area and the plane of the most distal end of the jet determined is determined as follows:

[0013] 0=A2x+B2y+C2z

[0014] Where A2, B2, and C2 are based on the normal vector L1 (0, 0, 1) of the plane of the ground area and the normal vector L of the farthest plane of the jet. plane1 (A1,B1,C1) is determined, and Established.

[0015] Optionally, for the farthest plane of the jet, the steps of projection, trajectory fitting and intersection determination include: projecting the jet area point cloud to the farthest plane of the jet to obtain a jet area point cloud plane projection, projecting the jet area point cloud plane projection into a two-dimensional image to form the two-dimensional jet area projection image; performing curve fitting on the upper contour of the jet area point cloud plane projection image to obtain a corresponding jet trajectory curve; and obtaining the intersection position of the jet trajectory curve and the fire point plane.

[0016] Optionally, for the jet vertical cross-sectional plane, the steps of projection, trajectory fitting and intersection determination include: projecting the jet area point cloud to the jet vertical cross-sectional plane to obtain a jet area point cloud plane projection, projecting the jet area point cloud plane projection into a two-dimensional image to form the two-dimensional jet area projection image; performing curve fitting on the outer trajectory contour of the jet area point cloud plane projection image to obtain an outer jet trajectory curve and an inner jet trajectory curve; and respectively obtaining the intersection positions of the outer jet trajectory curve and the inner jet trajectory curve with the fire point plane.

[0017] Optionally, for the jet vertical cross-sectional plane, before projecting the jet area point cloud onto the jet vertical cross-sectional plane, it also includes: using a jet trajectory curve based on the jet farthest end mapping plane fitting and a preset point cloud removal rule to remove the offset point cloud for the jet vertical cross-sectional plane in the jet area point cloud.

[0018] Optionally, the curve fitting of the outer trajectory contour of the jet area point cloud plane projection image includes: indexing all pixel points in the jet area point cloud plane projection image, and using a minimum circumscribed rectangle fitting algorithm to fit the jet trajectory area based on the indexed pixel points to obtain a fitted rectangular area; determining the inner and outer offsets of the jet trajectory based on the rectangular area; determining the outer trajectory contour according to the offset direction of the jet trajectory, and curve fitting the outer trajectory contour to obtain an outer jet trajectory curve; and determining the inner jet trajectory curve based on the obtained outer jet trajectory curve and the offset.

[0019] Optionally, projecting the jet area point cloud plane into a two-dimensional image to form the two-dimensional jet area projection image includes: using a preset rotation matrix to rotate the current mapping plane and the jet area point cloud plane projection on it to a target plane to perform position correction on the jet area point cloud plane projection; and projecting the jet area point cloud plane after position correction into the two-dimensional image to form the two-dimensional jet area projection image.

[0020] Optionally, the fusion processing of the intersection positions obtained based on different mapping planes includes: for the first intersection position coordinate (x τ1 ,y i ) and the second intersection position coordinates (x τ2 ,y2 i ), The jet landing point position (P water .x,P water .y,P water .z):

[0021]

[0022] Among them, ∈4 and ∈5 are correction constants, k is the scaling constant for the farthest mapping plane of the jet, k2 is the scaling constant for the vertical cross-sectional plane of the jet, and h rows is the distance compensation constant for the farthest mapping plane of the jet, h2 rows is the distance compensation constant for the vertical cross-sectional plane of the jet, represents the lateral offset of the jet determined based on the vertical cross-sectional plane of the jet, h cols is the distance compensation constant.

[0023] Optionally, the jet landing point detection method further includes: converting the obtained jet landing point position into position coordinates in the same coordinate system as the fire point position to determine the position deviation between the jet landing point position and the fire point position.

[0024] An embodiment of the present invention 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.

[0025] An embodiment of the present invention also provides a fire cannon control system, comprising: a laser radar, used to scan the jet of the fire cannon to obtain three-dimensional jet point cloud data; and any of the above-mentioned jet landing point detection devices, used to determine the jet landing point position based on the three-dimensional jet point cloud data obtained by the laser radar.

[0026] An embodiment of the present invention further provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable a machine to execute any of the above-mentioned jet landing point detection methods.

[0027] Through the above technical scheme, the embodiment of the present invention uses the fire point position and the jet area point cloud to determine the jet landing point, and no longer relies on the ground area point cloud. Therefore, even in the face of fire extinguishing scenarios of non-ground fire points such as high-rise buildings, the jet landing point can be accurately located.

[0028] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0030] Figure 11 is a flow chart of a method for detecting a jet landing point of a fire monitor according to an embodiment of the present invention;

[0031] Figure 2 It is a schematic diagram of a flow chart of detecting the jet drop point of a fire monitor in an example of an embodiment of the present invention;

[0032] Figure 3 is a schematic diagram of a process for obtaining a point cloud of a jet region in a preferred embodiment of the present invention;

[0033] Figure 4 is a schematic diagram of the intersection position of the jet trajectory and the fire point plane straight line determined based on the jet farthest end mapping plane in an example of an embodiment of the present invention, wherein the granular area represents the jet point cloud;

[0034] Figure 5 is a schematic diagram of the intersection position of the jet trajectory and the fire point plane straight line determined based on the jet vertical cross-sectional plane in an example of an embodiment of the present invention, wherein the granular area represents the jet point cloud; and

[0035] Figure 6 is a schematic diagram of plane correction shown in an example of an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0037] Here, some terms involved in the embodiments of the present invention are first introduced to facilitate understanding of the embodiments of the present invention:

[0038] 1. Point cloud: The embodiment of the present invention mainly refers to the laser radar point cloud, which is a set of data points representing 3D shapes or objects in space obtained by scanning with a 3D laser radar device. Each point contains 3D coordinate information, namely, three elements of x, y, and z, recorded as (x, y, z). The 3D coordinate information is based on the laser radar coordinate system. In the laser radar coordinate system, facing the direction of the laser radar, the positive half axis of the X axis is forward, the positive half axis of the Z axis is upward, and the positive half axis of the Y axis is right.

[0039] 2. Point cloud segmentation: It refers to the division of point clouds according to spatial, geometric and other feature points, so that the point clouds in the same division have similar features.

[0040] 3. Region growing algorithm: Conventional point cloud segmentation algorithm refers to the process of aggregating sub-regions into larger regions according to pre-defined evaluation rules. In the embodiment of the present invention, the basic idea is to start from a set of growing points (a growing point is a small region) and merge adjacent regions with similar properties to the growing point.

[0041] 4. Mapping plane: refers to the plane used to map the LiDAR 3D point cloud to a 2D image, where the initial position of the LiDAR is recorded as Z0 (0,0,0), which is the origin of the LiDAR coordinate system.

[0042] 5. Offset point cloud: refers to the point cloud information of splashing and falling of water near the jet that affects the search of the jet trajectory.

[0043] Figure 1 FIG. 1 is a flow chart of a method for detecting the jet point of a fire monitor according to an embodiment of the present invention. Figure 1 As shown, the jet landing point detection method may include the following steps S100-S300:

[0044] Step S100: acquiring a jet region point cloud, and determining at least two mapping planes for projecting the jet region point cloud into a two-dimensional jet region projection image.

[0045] Step S200, for each mapping plane, execute: projecting the jet area point cloud into a corresponding two-dimensional jet area projection image; performing trajectory fitting on the projected two-dimensional jet area projection image to obtain a corresponding jet trajectory curve; obtaining the intersection position of the obtained jet trajectory curve and the fire point plane constructed based on the fire point position.

[0046] Step S300, performing fusion processing on the intersection positions obtained based on different mapping planes to obtain the jet landing point position.

[0047] Through the above steps S100-S300, the embodiment of the present invention uses the fire point position and the jet area point cloud to determine the jet landing point, and no longer relies on the ground area point cloud, so that even in the face of fire extinguishing scenarios of non-ground fire points such as high-rise buildings, the jet landing point can be accurately located.

[0048] In a preferred embodiment, the jet landing point detection method may further include:

[0049] Step S400, converting the obtained jet landing point position into position coordinates in the same coordinate system as the fire point position to determine the position deviation between the jet landing point position and the fire point position.

[0050] Based on this, the embodiments of the present invention can evaluate the fire extinguishing effect by the position deviation between the jet landing point and the fire point, or can use the position deviation as a basis for guiding the adjustment of fire cannon parameters (posture, pressure, etc.) to improve the fire extinguishing effect of the fire cannon.

[0051] The following is a detailed description of the above steps S100-S400 based on the example of a fire monitor with a laser radar installed. In this example, the laser radar is installed on the side of the fire monitor, and there is a certain distance between the laser radar and the fire monitor installation position to prevent the diffusion of water mist from affecting the laser radar field of view, resulting in the inability to find the jet landing point. Specifically, Figure 2 FIG. 1 is a flow chart of detecting the jet drop point of a fire monitor in an example of an embodiment of the present invention. Figure 2 As shown, the implementation of the jet landing point detection involved in this example includes the following parts.

[0052] 1. Acquisition of the point cloud of the jet area and the location of the fire point. For steps S1-S5, this belongs to the data collection stage.

[0053] More specifically, in the example, Figure 3 As shown, the following steps S110-S130 are preferably used to obtain the jet area point cloud Cloud w :

[0054] Step S110, collecting point cloud data Cloud1 before the jet is turned on and point cloud data Cloud2 after the jet is turned on respectively through the laser radar installed on the fire monitor.

[0055] It should be noted that the primary task of jet point detection is to eliminate the interference of other objects in the point cloud data on the detection results and segment the point cloud of the jet area. Therefore, in order to ensure the segmentation effect, this example proposes a solution based on frame changes, that is, first obtain Cloud1 (before the jet is turned on) and Cloud2 (after the jet is turned on), and then further obtain the differential point cloud.

[0056] It should also be noted that the frame change scheme is based on the situation that the laser radar position is fixed before and after the fire cannon jet is turned on. If there is a small change in the laser radar posture, you can first perform point cloud registration on Cloud1 and Cloud2 before performing subsequent operations.

[0057] Step S120, extracting a differential point cloud Cloud from the point cloud data Cloud1 before the jet is turned on and the point cloud data Cloud2 after the jet is turned on dis .

[0058] It should be noted that in order to further ensure the extraction effect, the point cloud can also be preprocessed before performing the differential point cloud extraction. For example, the preprocessing steps include downsampling, filtering, plane correction and other steps. Among them, the downsampling step is to reduce the point cloud density and improve the algorithm operation speed. The purpose of the filtering step is: 1) Consider the distance of the fire cannon jet, remove the remote point cloud information, and reduce the amount of calculation data; 2) remove the interference of sparse and discrete point cloud data. The purpose of the plane correction step is to ensure that the horizontal plane of the lidar coordinate system is parallel to the horizontal plane of the real world coordinate system by determining the plane normal vector L1 (0,0,1) of the ground area, so as to better fit the fire cannon jet trajectory in the future, thereby reducing the difficulty of subsequent algorithm processing.

[0059] Returning to step S120, it is preferred to use a Kd-Tree difference algorithm to generate a difference point cloud. The algorithm can be described as follows:

[0060] 1) Taking the point cloud sequence of Cloud1 as the reference sequence, the point cloud coordinates corresponding to the sequence number i1 in Cloud1 In Cloud2, index the point cloud coordinates in sequence according to the sequence number to obtain the coordinates of the point cloud The closest point cloud coordinates Where i2 represents the sequence number of the point cloud sequence of Cloud2;

[0061] 2) If the point cloud coordinates and point cloud coordinates If the distance is less than a preset value, the point cloud sequence i2 is saved to a specified set, which is denoted as DP, for example;

[0062] 3) Complete the indexing of all point cloud sequences in Cloud1 in sequence; and

[0063] 4) Extract all point cloud sequences in Cloud2 that are not in the specified set DP as differential point clouds Cloud dis .

[0064] Step S130: extract the differential point cloud Cloud dis Perform point cloud segmentation based on region growing to obtain the jet area point cloud Cloud w .

[0065] For example, using the region growing method to dis Complete the segmentation of the objects in the target area and find the nearest distance point (x min ,y min ,z min ) and the farthest point (x max ,ymax ,z max ), and retain the category point cloud that meets the requirements according to the evaluation rule corresponding to formula (1), and use this as the jet area point cloud Cloud w .

[0066]

[0067] Among them, ∈x min ,∈y min ,∈z min It is a constant value related to the installation location of the laser radar and fire monitor.

[0068] In this example, the fire point position in the laser radar coordinate system is recorded as P fire , which is not required to be a real fire point. For example, in the fire cannon test experiment, a fire point position can be roughly selected according to the jet trajectory to continue the jet landing position detection. It should be noted that in order to reduce the processing difficulty of the subsequent algorithm, the fire point position P fire Preprocessing is also required, such as using a plane correction matrix to transform the coordinates and obtain the fire point position after coordinate correction. The corresponding fire point position coordinates are recorded as The following examples are based on this fire location conduct.

[0069] Second, the determination of the mapping plane and the fire point plane belongs to the plane determination stage. Figure 2 As shown, the determination of the mapping plane corresponds to step S61A and step S61B, involving two mapping planes described below; the determination of the fire point plane corresponds to step S66A and step S67B respectively for different mapping planes.

[0070] In an example, at least two mapping planes used to project the jet region point cloud into a two-dimensional jet region projection image include the following two planes that are perpendicular to the ground region and perpendicular to each other:

[0071] 1) A jet farthest end mapping plane used to describe the farthest distance that the jet area can reach; and

[0072] 2) The vertical cross-sectional plane of the jet used to describe the lateral deflection of the jet.

[0073] The fire point location was determined in the first part for the mapping plane at the farthest end of the jet and the plane normal vector L1(0,0,1) of the ground area, by combining the closest point in the jet area (x min ,y min ,z min), the jet farthest end mapping plane Plane1 can be determined according to the evaluation rule shown in the following formula (2) (i.e., the rule of determining the plane according to two direction vectors): 0 = A1x + B1y + C1z.

[0074]

[0075] The jet farthest end mapping plane Plane1 can effectively evaluate the farthest distance that the jet area can reach.

[0076] For the vertical cross-sectional plane of the jet, according to the determined farthest end of the jet mapping plane normal vector L plane1 (A1, B1, C1) and the ground area plane normal vector L1 (0, 0, 1) can be used to determine the jet vertical cross-sectional plane Plane2 that is perpendicular to the above two planes at the same time using the evaluation rule shown in the following formula (3): 0 = A2x + B2y + C2z.

[0077]

[0078] The jet vertical cross-sectional plane Plane2 can effectively evaluate the lateral deviation of the water flow in the jet area.

[0079] Furthermore, the fire point plane can be constructed arbitrarily according to the fire point location. In one example, for example, the fire point location is located indoors on a certain floor. A fire point plane parallel to the ground area can be constructed, and because the normal vector of the corrected ground area plane is L1(0,0,1), the fire point plane equation can be recorded as Plane3: In other examples, for example, when an external wall is on fire, the fire point is located on a vertical plane, and a fire point plane perpendicular to the ground area can also be constructed. The embodiment of the present invention is described below using the above-mentioned fire point plane Plane3 as an example.

[0080] 3. Point cloud projection, trajectory fitting and intersection point determination, which correspond to steps S62A-S68A and steps S62B-S69B for different mapping planes.

[0081] (1) The farthest projection plane of the jet.

[0082] In the example, for the farthest plane of the jet, the steps of projection, trajectory fitting and intersection determination include: projecting the jet area point cloud to the farthest plane of the jet to obtain a jet area point cloud plane projection, projecting the jet area point cloud plane projection into a two-dimensional image to form the two-dimensional jet area projection image; performing curve fitting on the upper contour of the jet area point cloud plane projection image to obtain a corresponding jet trajectory curve; and obtaining the intersection position of the jet trajectory curve and the fire point plane.

[0083] The step of projecting the jet region point cloud plane onto the two-dimensional image to form the two-dimensional jet region projection image preferably includes: using a preset rotation matrix to rotate the current mapping plane and the jet region point cloud plane projection onto the target plane to correct the position of the jet region point cloud plane projection; and projecting the jet region point cloud plane after position correction onto the two-dimensional image to form the two-dimensional jet region projection image. The target plane is, for example, a target plane with y=0.

[0084] For further example, in the specific implementation process, it can be described as the following Step 1-Step 5.

[0085] Step 1: After obtaining the point cloud of the jet area w Based on this, the jet area point cloud is projected by using the ProjectInliers projection filter.

[0086] Step 2, the farthest end mapping plane Plane1: 0 = A1x + B1y + C1z of the jet is transformed to the target plane (the plane where the coordinate axis is located) through the rotation matrix to complete the position correction of the projection plane. At this time, the correction plane selected by the farthest end mapping plane of the jet is plane y = 0. The final corrected point cloud is recorded as

[0087] Step 3: Project the jet area point cloud after plane projection and position correction into a two-dimensional image using the evaluation rule shown in the following formula (4).

[0088]

[0089] Where (X 2d ,Y 2d ) is a point in the two-dimensional image, (X 3d ,Y 3d ,,Z 3d ) is the three-dimensional information of the jet area (at this time Y 3d =0), k is the scaling constant, h rows With h colsis the distance compensation constant, and the point (X 2d ,Y 2d )The pixel value is set to 255 to obtain the projection image of the jet area.

[0090] Step 4, the jet trajectory fitting method can be described as: after obtaining the plane projection image of the point cloud of the jet area, all the pixel points in the plane projection image of the point cloud of the jet area are indexed. At this time, what needs to be calculated is the farthest distance point that the jet area can reach. Therefore, only the contour on the jet area is curve fitted, and the evaluation rule shown in formula (5) of the curve fitting method based on the least squares method is used to perform curve fitting.

[0091]

[0092] Among them, τ1 represents the fitted jet trajectory quadratic curve, (x i ,y i ) represents the pixel point of the contour on the jet area, δ2 is the data deviation and, when the value of δ2 is the smallest, the equation of the jet trajectory curve to be searched can be determined as:

[0093]

[0094] Step 5: Process the fire point location It includes: 1) Similar to Step 1, project the fire point position onto the farthest plane of the jet; 2) Use the rotation matrix and correction plane in Step 2 to perform position correction, and finally obtain the new fire point position as

[0095] Step 6, construct the equation of the ignition point plane straight line: Then, it is combined with the jet trajectory fitting curve equation shown in formula (6): Determine the intersection point and obtain the intersection point coordinates (x τ1 ,y i ),like Figure 4 shown.

[0096] (2) Vertical cross-sectional plane of the jet.

[0097] For the jet vertical cross-sectional plane, the steps of projection, trajectory fitting and intersection point determination include: projecting the jet area point cloud to the jet vertical cross-sectional plane to obtain the jet area point cloud plane projection, projecting the jet area point cloud plane projection into a two-dimensional image to form the two-dimensional jet area projection image; performing curve fitting on the outer trajectory contour of the jet area point cloud plane projection image to obtain an outer jet trajectory curve and an inner jet trajectory curve; and respectively obtaining the intersection positions of the outer jet trajectory curve and the inner jet trajectory curve with the fire point plane.

[0098] When the jet vertical cross-sectional plane is projected, the point cloud information such as splashing and falling of the near-end water flow of the jet will affect the jet trajectory search of the jet vertical cross-sectional plane, so the offset point cloud is first removed. Accordingly, for the jet vertical cross-sectional plane, before projecting the jet area point cloud to the jet vertical cross-sectional plane, it also includes: using the jet trajectory curve based on the jet farthest end mapping plane fitting and the preset point cloud removal rules to remove the offset point cloud for the jet vertical cross-sectional plane in the jet area point cloud. That is, Figure 2 The step of removing the offset point cloud is shown in step S62B.

[0099] In the example, refer to Figure 2 The jet trajectory curve fitted by the jet farthest end plane in step S65A can be used to perform the point cloud removal for the jet vertical cross-sectional plane in step S62B, which can specifically include: traversing (The point cloud of the farthest plane of the jet obtained in Step 2 above is corrected) All point cloud sequences, when the sequence point cloud satisfies the point cloud removal rule shown in the following formula (7), store the point cloud sequence, and finally extract Cloud w The point cloud information of the corresponding sequence in is used as the new point cloud of the jet area

[0100]

[0101] Among them, X i , Y i , R i are all intermediate parameters. and for The x and z coordinate values ​​of the point cloud corresponding to point cloud sequence i, ∈2 is a constant, and other parameters can be found above.

[0102] Among them, the details of the point cloud projection steps on the vertical cross-sectional plane are the same as those of the farthest end mapping plane of the jet, so you can refer to the above Step 1-Step 3, and no further details will be given here.

[0103] It should be noted that, unlike the jet trajectory fitting method on the farthest mapping plane of the jet, the jet trajectory fitting on the vertical cross-sectional plane requires curve fitting of the trajectory contour on the outside (left and right sides) of the jet to constrain the jet area. Unlike the relatively concentrated point cloud of the outer jet trajectory, the point cloud of the inner jet trajectory is unevenly distributed, resulting in poor trajectory fitting effect. Therefore, for the vertical cross-sectional plane, curve fitting of the outer trajectory contour of the plane projection image of the point cloud of the jet area includes: indexing all the pixel points in the plane projection image of the point cloud of the jet area, and using the minimum circumscribed rectangle fitting algorithm to fit the jet trajectory area based on the indexed pixel points to obtain a fitted rectangular area; determining the inner and outer offsets of the jet trajectory based on the rectangular area; determining the outer trajectory contour according to the offset direction of the jet trajectory, and curve fitting the outer trajectory contour to obtain the outer jet trajectory curve; and determining the inner jet trajectory curve based on the obtained outer jet trajectory curve and the offset.

[0104] For example, for the vertical cross-sectional plane of the jet, the inner trajectory curve is obtained according to the outer trajectory and the offset. The specific steps are as follows:

[0105] First, after obtaining the plane projection image of the point cloud of the jet area, all the pixels in the plane projection image of the point cloud of the jet area are indexed, and the minimum circumscribed rectangle fitting algorithm is used to fit the jet trajectory area. This method can obtain the information of the long axis L1, short axis L2, angle θ, etc. of the fitted rectangle, and define the offset using the evaluation rule shown in the following formula (8): size.

[0106]

[0107] Where abs() is the absolute value and ∈3 is the proportional constant.

[0108] Secondly, according to the offset direction of the jet trajectory, the outer trajectory profile is found (if the trajectory is offset to the left, that is, abs(θ) ≥ 45°, the left trajectory profile is taken, otherwise abs(θ) < 45°, the right trajectory profile is taken), and the outer trajectory curve is fitted. The fitting method adopts the evaluation rule shown in the above formula (5), and finally the outer trajectory curve and the inner trajectory curve are obtained as shown in the following formula (9) and formula (10) respectively:

[0109]

[0110]

[0111] After determining the outer trajectory curve and the inner trajectory curve and the above-mentioned new fire point position is After that, the equation of the straight line of the ignition point plane is constructed as (Since the fire point plane is parallel to the ground area plane, y i =y2 i ), find the intersection of the jet trajectory fitting curve equation shown in equation (9) and equation (10), and obtain the intersection position coordinates (x τ2 ,y2 i ), like Figure 5 shown.

[0112] 4. Determine the jet landing point, including Figure 2 The three-dimensional coordinates of the intersection position or the intersection midpoint position are inversely calculated as shown in step S68A and step S69B, and then the fusion steps in step S7 and step S8 are performed.

[0113] Following the above, for the first intersection position coordinate (x τ1 ,y i ) and the second intersection position coordinates (x τ2 ,y2 i ), According to formula (11), the jet landing point position (P water .x,P water .y,P water .z):

[0114]

[0115] Among them, ∈4 and ∈5 are correction constants, k is the scaling constant for the farthest mapping plane of the jet, k2 is the scaling constant for the vertical cross-sectional plane of the jet, and h rows is the distance compensation constant for the farthest mapping plane of the jet, h2 rows It is the distance compensation constant for the vertical cross-sectional plane of the jet.

[0116] 5. Determine the position deviation between the jet landing point and the fire point, corresponding to Figure 2 Step S9.

[0117] like Figure 6 As shown, for example, since the coordinate plane used for correction in the example is x=0, y=0, and the two planes are perpendicular to each other, the correction matrix used by the farthest plane of the jet is consistent with the correction matrix used by the vertical cross-sectional plane. The jet landing point position before correction is obtained according to the inverse matrix of the matrix According to the plane correction matrix in the first part, the jet landing point position in the original lidar coordinate system is obtained. And get the jet landing point position With the fire point position P fireHere, the fire-fighting effect of the fire-fighting cannon can be evaluated based on this position deviation, or the position deviation can be used as a basis for guiding the adjustment of fire-fighting cannon parameters (posture, pressure, etc.) to improve the fire-fighting effect of the fire-fighting cannon. For example, if it is aimed at high-altitude fire-fighting needs, such as high-rise fires, the solution of the embodiment of the present invention can construct a fire point plane (for example, a vertical plane of the fire point) to find the position deviation between the jet landing point and the fire point when the fire-fighting cannon is sprayed at high speed.

[0118] It should be noted that the initial fire point position P in the laser radar coordinate system fire It is not necessarily the actual fire point, but the position deviation calculated here is the actual deviation of the fire monitor jet, so the water pressure and spray angle of the fire monitor can be adjusted based on the position deviation.

[0119] Therefore, the jet landing point detection method of the embodiment of the present invention has at least the following advantages:

[0120] 1) The embodiment of the present invention combines the jet area point cloud and the fire point position to find the jet landing point based on multi-plane mapping and trajectory fitting, and no longer relies on the ground area point cloud. Therefore, in the fire extinguishing scenario of non-ground fire points such as high-rise buildings, it still has the ability to locate the jet landing point and identify the fire extinguishing effect.

[0121] 2) The embodiment of the present invention uses time series difference (i.e., the differential point cloud Cloud obtained based on the point cloud data Cloud1 before the jet is turned on and the point cloud data Cloud2 after the jet is turned on) dis ) and region growing algorithm are used to extract the jet area point cloud from the lidar point cloud, which improves the efficiency and accuracy of subsequent fire cannon jet trajectory search.

[0122] 3) The embodiment of the present invention uses a multi-plane jet trajectory curve fitting method to find the intersection position of the jet trajectory curve and the fire point position plane, find the deviation between the jet landing point and the fire point position, and evaluate the fire extinguishing effect of the fire cannon, thereby effectively solving the interference problem of the jet trajectory change and the end water flow scattering on the landing point detection result, and can identify the fire extinguishing effect of the fire point in the non-ground area, thereby improving the accuracy of the jet landing point detection as well as the anti-interference and environmental adaptability.

[0123] 4) The method of the embodiment of the present invention does not require human intervention and meets the requirements of automatic fire extinguishing operation of intelligent fire monitors.

[0124] An embodiment of the present invention 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.

[0125] The jet landing point detection device can be implemented using a conventional controller with computing and data transmission capabilities, such as a controller that comes with a fire monitor.

[0126] The processor includes a kernel, and the kernel 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 invention can be implemented by adjusting kernel parameters.

[0127] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory may include at least one memory chip.

[0128] The embodiment of the present invention also provides a fire monitor control system, comprising: a laser radar, which is used to scan the jet of the fire monitor to obtain three-dimensional jet point cloud data; and any of the above-mentioned jet landing point detection devices, which is used to determine the jet landing point position according to the three-dimensional jet point cloud data obtained by the laser radar. The fire monitor control system can automatically determine the jet landing point position and evaluate the fire extinguishing effect, which is conducive to achieving more accurate landing point control and is more intelligent.

[0129] The embodiment of the present invention also provides a machine-readable storage medium, on which instructions are stored, and the instructions are used to enable the machine to execute any of the above-mentioned jet landing point detection methods. Among them, the machine is, for example, a controller configured separately or a controller that comes with a fire monitor. In addition, 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.

[0130] Among them, for more implementation details and effects of the machine-readable storage medium, please refer to the embodiments of the aforementioned corresponding methods, which will not be repeated here.

[0131] Those skilled in the art will appreciate that 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 include computer-usable program code.

[0132] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0135] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0136] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0137] 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 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. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0138] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0139] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for detecting the jet landing point of a fire monitor, characterized in that: include: Acquire a jet region point cloud, and determine at least two mapping planes for projecting the jet region point cloud into a two-dimensional jet region projection image; For each mapping plane, perform the following steps regarding projection, trajectory fitting, and intersection point determination: Projecting the jet area point cloud into a corresponding two-dimensional jet area projection image; Performing trajectory fitting on the two-dimensional jet region projection image obtained by projection to obtain a corresponding jet trajectory curve; as well as Obtaining the intersection position of the obtained jet trajectory curve and the fire point plane constructed based on the fire point position; as well as The intersection positions obtained based on different mapping planes are fused to obtain the jet landing point position.

2. The jet landing point detection method according to claim 1, characterized in that: The obtaining of the jet area point cloud comprises: The laser radar installed on the fire monitor collects the point cloud data Cloud1 before the jet is turned on and the point cloud data Cloud2 after the jet is turned on respectively; Extract the differential point cloud Cloud from the point cloud data Cloud1 before the jet is turned on and the point cloud data Cloud2 after the jet is turned on. dis ;as well as The extracted differential point cloud Cloud dis Perform point cloud segmentation based on region growing to obtain the jet area point cloud Cloud w .

3. The jet landing point detection method according to claim 1, characterized in that: The at least two mapping planes include the following two planes that are perpendicular to the ground area and perpendicular to each other: The jet farthest end mapping plane used to describe the farthest distance that the jet area can reach; and A vertical cross-section plane of the jet used to describe the lateral deflection of the jet.

4. The method for detecting the jet landing point according to claim 3, characterized in that: The farthest plane of the jet is determined as follows: 0=A1x+B1y+C1z In the formula, A1, B1, and C1 are based on the location of the fire point. The normal vector L1(0,0,1) of the ground plane and the coordinates of the closest point in the jet area (x min ,y min ,z min ) are coefficients determined by, and x, y, and z represent the three-dimensional coordinates of the point on the farthest plane of the jet; Among them, the coefficients A1, B1, and C1 are determined based on the following formula: The vertical cross-sectional plane of the jet that is perpendicular to both the ground area and the plane of the most distal end of the jet determined is determined as follows: 0=A2x+B2y+C2z Where A2, B2, and C2 are based on the normal vector L1 (0, 0, 1) of the plane of the ground area and the normal vector L of the farthest plane of the jet. plane1 (A1,B1,C1) is determined, and Established.

5. The method for detecting the jet landing point according to claim 3, characterized in that: For the farthest plane of the jet, the steps of performing projection, trajectory fitting and intersection point determination include: Projecting the jet area point cloud to the farthest end plane of the jet to obtain a plane projection of the jet area point cloud, and projecting the plane projection of the jet area point cloud to a two-dimensional image to form the two-dimensional jet area projection image; Performing curve fitting on the upper contour of the plane projection image of the point cloud of the jet region to obtain a corresponding jet trajectory curve; and The intersection position of the jet trajectory curve and the ignition point plane is obtained.

6. The method for detecting the jet landing point according to claim 3, characterized in that: For the jet vertical cross-sectional plane, the steps of performing projection, trajectory fitting and intersection point determination include: Projecting the jet area point cloud onto the jet vertical cross-sectional plane to obtain a plane projection of the jet area point cloud, and projecting the plane projection of the jet area point cloud into a two-dimensional image to form the two-dimensional jet area projection image; Performing curve fitting on the outer trajectory profile of the plane projection image of the point cloud of the jet region to obtain an outer jet trajectory curve and an inner jet trajectory curve; and The intersection positions of the outer jet trajectory curve, the inner jet trajectory curve and the fire point plane are respectively obtained.

7. The jet landing point detection method according to claim 6, characterized in that: With respect to the jet vertical cross-sectional plane, before projecting the jet area point cloud onto the jet vertical cross-sectional plane, the method further includes: The offset point cloud for the vertical cross-sectional plane of the jet in the point cloud of the jet area is removed by using the jet trajectory curve fitted based on the farthest end mapping plane of the jet and a preset point cloud removal rule.

8. The method for detecting the jet landing point according to claim 6, characterized in that: The curve fitting of the outer trajectory contour of the jet area point cloud plane projection image comprises: Indexing all pixel points in the plane projection image of the jet area point cloud, and using a minimum circumscribed rectangle fitting algorithm to fit the jet trajectory area based on the indexed pixel points to obtain a fitted rectangular area; Determining the inner and outer offsets of the jet trajectory based on the rectangular area; Determining an outer trajectory profile according to the offset direction of the jet trajectory, and performing curve fitting on the outer trajectory profile to obtain an outer jet trajectory curve; and The inner jet trajectory curve is determined based on the obtained outer jet trajectory curve and the offset.

9. The jet landing point detection method according to any one of claims 5 to 8, characterized in that: The step of projecting the jet region point cloud plane onto a two-dimensional image to form the two-dimensional jet region projection image comprises: Using a preset rotation matrix, the current mapping plane and the jet area point cloud plane projection on it are rotated to a target plane, so as to perform position correction on the jet area point cloud plane projection; and The position-corrected point cloud of the jet region is plane-projected into a two-dimensional image to form the two-dimensional jet region projection image.

10. The jet landing point detection method according to claim 3, characterized in that: The fusion processing of the intersection positions obtained based on different mapping planes includes: The first intersection position coordinate (x τ1 ,y i ) and the second intersection position coordinates (x τ2 ,y2 i ), The jet landing point position (P water .x,P water .y,P water .z): Among them, ∈4 and ∈5 are correction constants, k is the scaling constant for the farthest mapping plane of the jet, k2 is the scaling constant for the vertical cross-sectional plane of the jet, and h rows is the distance compensation constant for the farthest mapping plane of the jet, h2 rows is the distance compensation constant for the vertical cross-sectional plane of the jet, represents the lateral offset of the jet determined based on the vertical cross-sectional plane of the jet, h cols is the distance compensation constant.

11. The method for detecting the jet landing point according to claim 1, characterized in that: The jet landing point detection method also includes: The obtained jet landing point position is converted into position coordinates in the same coordinate system as the fire point position to determine the position deviation between the jet landing point position and the fire point position.

12. A jet landing point detection device for a fire monitor, characterized in that: include: A memory storing a program that can be executed on the processor; as well as The processor is configured to implement the jet landing point detection method described in any one of claims 1 to 11 when executing the program.

13. A fire monitor control system, characterized in that: include: Laser radar is used to scan the jet of the fire monitor to obtain three-dimensional jet point cloud data; as well as The jet landing point detection device described in claim 12 is used to determine the jet landing point position based on the three-dimensional jet point cloud data obtained by the laser radar.

14. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for enabling a machine to execute the jet landing point detection method described in any one of claims 1 to 11.

Images