Drilling platform personnel positioning method, safety early warning method and personnel positioning device

Abstract

The invention provides a drilling platform personnel positioning method, a safety early warning method and a personnel positioning device. The positioning method comprises the following steps: S1, acquiring a two-dimensional image and three-dimensional point cloud data of a drilling platform acquired by two-dimensional and three-dimensional detection equipment; s2, identifying persons from the two-dimensional image, and carrying out frame selection on each person by using a rectangular frame, the selected area being a person area; s3, projecting the three-dimensional point cloud data into the two-dimensional image, retaining the three-dimensional point cloud data falling into the personnel areas, and forming a point cloud group by the three-dimensional point cloud data in each personnel area; s4, performing clustering processing on each point cloud group, and extracting a cluster with the most points in each point cloud group as a target cluster; and performing data conversion on the target cluster according to the first conversion matrix to obtain intermediate data, and performing data conversion on the intermediate data according to the second conversion matrix to obtain position data of personnel corresponding to the point cloud group to which the target cluster belongs. And the positions of personnel on the drilling platform can be accurately positioned.

Description

Technical Field

[0001] The present invention relates to the technical field of drilling engineering, and in particular to a personnel positioning method, a safety early warning method and a personnel positioning device for a drilling platform. Background Art

[0002] When working on an oil drilling platform, safety always comes first. Workers on the platform must strictly abide by safety regulations and operating procedures, wear necessary protective equipment, and ensure the safety of themselves and others. At present, oil drilling platforms mainly rely on manual work to reduce and prevent accident risks. During the operation, multiple people assist in checking the drilling operation process, and when dangerous conditions are found, they manually inform the operators in the dangerous area to pay attention to safety. This method requires every participant in the drilling operation to be on their toes, but human energy and vision are limited after all, and it is inevitable that they will be careless and have safety issues. Therefore, it is necessary to propose a set of methods to ensure the safety of personnel on the drilling platform to ensure that personnel can detect threats in time and are not harmed.

[0003] Traditional methods that rely on manual supervision and post-event tracing are powerless in the face of high-density and high-intensity operating environments. Factors such as personnel fatigue, blind spots, and complex cross-operation make it difficult for even the most stringent regulations and the most dedicated staff to completely avoid accidental collisions. In this case, even the slightest negligence may lead to serious safety accidents, which not only threatens the lives of workers, but may also have an immeasurable impact on the normal operation of the drilling platform and the surrounding environment.

[0004] Therefore, there is an urgent need for a drilling platform personnel positioning method, a safety warning method and a personnel positioning device. Summary of the invention

[0005] 1. Technical issues to be resolved

[0006] In view of the problems existing in the above technologies, the present invention solves them at least to a certain extent. To this end, the first object of the present invention is to provide a method for locating personnel on a drilling platform, which can accurately locate the position of personnel on the drilling platform.

[0007] The second object of the present invention is to provide a drilling platform personnel safety early warning method, which can prevent potential safety risks according to the location of the personnel on the drilling platform.

[0008] The third object of the present invention is to provide a drilling platform personnel positioning device.

[0009] (II) Technical solution

[0010] In order to achieve the above object, the main technical solutions adopted by the present invention include:

[0011] In a first aspect, the present invention provides a method for locating personnel on a drilling platform, comprising the following steps:

[0012] Step S1, obtaining a two-dimensional image and three-dimensional point cloud data of the drilling platform collected by two-dimensional and three-dimensional detection equipment;

[0013] Step S2: Identify people from the two-dimensional image and select each person with a rectangular frame, and the selected area is the person area;

[0014] Step S3, projecting the 3D point cloud data onto the 2D image, deleting the 3D point cloud data that does not fall into the personnel area, retaining the 3D point cloud data that falls into the personnel area, and forming a point cloud group for each 3D point cloud data in the personnel area;

[0015] Step S4: perform clustering processing on each point cloud group to obtain a cluster corresponding to each point cloud group, and extract the cluster with the largest number of points in each point cloud group as the target cluster; perform data conversion on the target cluster according to the first conversion matrix to obtain intermediate data, and perform data conversion on the intermediate data according to the second conversion matrix to obtain the position data of the person corresponding to the point cloud group to which the target cluster belongs;

[0016] The first conversion matrix is ​​a conversion matrix between three-dimensional point cloud data and two-dimensional image pixels, and the second conversion matrix is ​​a conversion matrix between two-dimensional image pixels and the three-dimensional coordinate system of the actual space of the drilling platform.

[0017] Optionally, the field of view of the two-dimensional and three-dimensional detection equipment includes the wellhead area, the rathole area, the wellhead turntable area, the iron roughneck area and the pipe laying machine area.

[0018] Optionally, the left edge of the rectangular box is parallel to the left edge of the two-dimensional image, the right edge of the rectangular box is parallel to the right edge of the two-dimensional image, the upper edge of the rectangular box is parallel to the upper edge of the two-dimensional image, and the lower edge of the rectangular box is parallel to the lower edge of the two-dimensional image. The area selected by the rectangular box is the minimum area that completely covers the person.

[0019] Optionally, each point cloud group is clustered to obtain a cluster corresponding to each point cloud group, including: traversing each point in the point cloud group as the center point, and calculating the adjacent distance between each point in the point cloud group except the center point and the center point, and classifying the points and the center point whose adjacent distance is less than a preset threshold into the same cluster to obtain a cluster corresponding to each point cloud group.

[0020] Optionally, performing data conversion on the intermediate data according to the second conversion matrix to obtain the position data of the person corresponding to the point cloud group to which the target cluster belongs includes:

[0021]

[0022] Where ri is the i-th pixel point in the intermediate data; si is the i-th spatial point of the person in the actual three-dimensional coordinate system of the drilling platform; ri.x is the x-axis coordinate of ri, ri.y is the y-axis coordinate of ri; si.x is the x-axis coordinate of si, si.y is the y-axis coordinate of si, and si.z is the z-axis coordinate of si; G w is the second conversion matrix; K is the internal parameter matrix of the two-dimensional detection device in the two-dimensional and three-dimensional detection device.

[0023] Optionally, before step S1, the method further includes:

[0024] Step S01, obtaining a two-dimensional image and three-dimensional point cloud data of the drilling platform collected by two-dimensional and three-dimensional detection equipment;

[0025] Step S02, according to the four pixel line segments corresponding to the four sides of the wellhead turntable extracted from the two-dimensional image, calculate the intersection of the straight lines where every two pixel line segments are located, and obtain a set of intersection points;

[0026] Step S03, selecting target intersection points within the range of the two-dimensional image from the intersection point set, the number of target intersection points being 4, and the 4 target intersection points respectively corresponding to the pixel positions of the 4 vertices of the wellhead rotary table in the two-dimensional image;

[0027] Step S04, using the PnP algorithm, according to the spatial positions of the four target intersection points and the four vertices of the wellhead turntable in the actual three-dimensional coordinate system of the drilling platform, calculate the relative transformation relationship matrix between the two to obtain a second transformation matrix.

[0028] Optionally, according to the four pixel line segments corresponding to the four edges of the wellhead turntable extracted from the two-dimensional image, the intersection point of the straight lines where every two pixel line segments are located is calculated, including:

[0029] Determine whether the straight lines containing the two pixel line segments to be calculated have an intersection:

[0030] D=A 1 ×B 2 -A 2 ×B 1

[0031] If D≠0, the straight lines where the two pixel line segments are located intersect, and the coordinates of the intersection point p(x,y) are expressed as:

[0032]

[0033] If D = 0, the lines on which the two pixel line segments are located are parallel or coincident, and there is no intersection;

[0034] Among them, A 1 =p12.y-p11.y; B 1 =p11.x-p12.x; C1 =A 1 ×p11.x+B 1 ×p11.y;A 2 =p22.y-p21.y; B 2 =p21.x-p22.x; C 2 =A 2 ×p21.x+B 2 ×p21.y; p11 and p12 are the two endpoints of the first pixel line segment of the two pixel line segments whose intersection is to be calculated, p11.x is the x-axis coordinate of p11, p11.y is the y-axis coordinate of p11, p12.x is the x-axis coordinate of p12, and p12.y is the y-axis coordinate of p12; p21 and p22 are the two endpoints of the second pixel line segment of the two pixel line segments whose intersection is to be calculated, p21.x is the x-axis coordinate of p21, p21.y is the y-axis coordinate of p21, p22.x is the x-axis coordinate of p22, and p22.y is the y-axis coordinate of p22.

[0035] Optionally, a PnP algorithm is used to calculate the relative transformation relationship matrix between the four target intersection points and the four vertices of the wellhead rotary table in the actual three-dimensional coordinate system of the drilling platform, including:

[0036]

[0037] Wherein, pi is the i-th vertex of the wellhead turntable in the two-dimensional image; qi is the vertex of the wellhead turntable in the three-dimensional coordinate system of the actual space of the drilling platform corresponding to pi; i is any integer from 1 to 4; pi.x is the x-axis coordinate of pi, pi.y is the y-axis coordinate of pi; qi.x is the x-axis coordinate of qi, qi.y is the y-axis coordinate of qi, and qi.z is the z-axis coordinate of qi; G w is the second conversion matrix; K is the internal parameter matrix of the two-dimensional detection device in the two-dimensional and three-dimensional detection device.

[0038] In a second aspect, the present invention provides a method for early warning of personnel safety on a drilling platform, comprising: providing an early warning of personnel safety based on personnel location data obtained by the method as described above, as well as location data and operating status data of various mechanical equipment on the drilling platform.

[0039] In a third aspect, the present invention provides a drilling platform personnel positioning device, comprising:

[0040] An acquisition module, used to acquire two-dimensional images and three-dimensional point cloud data of the drilling platform collected by two-dimensional and three-dimensional detection equipment;

[0041] The recognition module is used to recognize people from the two-dimensional image and select each person with a rectangular frame. The selected area is the person area;

[0042] A data screening module is used to project the 3D point cloud data into a 2D image, delete the 3D point cloud data that does not fall into the personnel area, and retain the 3D point cloud data that falls into the personnel area. The 3D point cloud data in each personnel area forms a point cloud group.

[0043] The clustering module is used to perform clustering processing on each point cloud group, obtain the cluster corresponding to each point cloud group, and extract the cluster with the largest number of points in each point cloud group as the target cluster;

[0044] The data conversion module is used to perform data conversion on the target cluster according to the first conversion matrix to obtain intermediate data, and to perform data conversion on the intermediate data according to the second conversion matrix to obtain the position data of the personnel corresponding to the point cloud group to which the target cluster belongs; wherein the first conversion matrix is ​​the conversion matrix between the three-dimensional point cloud data and the two-dimensional image pixel points, and the second conversion matrix is ​​the conversion matrix between the two-dimensional image pixel points and the three-dimensional coordinate system of the actual space of the drilling platform.

[0045] (III) Beneficial effects

[0046] The beneficial effects of the present invention are:

[0047] The drilling platform personnel positioning method, safety warning method and personnel positioning device provided by the present invention are not only limited to whether the safety measures of the drilling platform personnel themselves are in place, but can also warn of possible personnel safety threats on the drilling platform to avoid accidents. The scheme adopts a method of calibration using the wellhead turntable unique to the drilling platform as a reference object, avoiding the need for additional preparation of calibration tools, reducing the calibration process, and improving work efficiency. At the same time, based on the personnel positioning method combining two-dimensional and three-dimensional data, the accuracy of personnel positioning is high in actual application, and personnel safety warning can be effectively realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The present invention is described with the aid of the following drawings:

[0049] Figure 1 It is a schematic flow chart of a method for spatial calibration based on a wellhead rotary table of a drilling platform according to a specific embodiment of the present invention;

[0050] Figure 2 A schematic diagram of a two-dimensional image collected by a two-dimensional and three-dimensional detection device according to a specific embodiment of the present invention;

[0051] Figure 3 It is a schematic flow chart of a method for locating personnel on a drilling platform according to a specific embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation modes in conjunction with the accompanying drawings.

[0053] Figure 1 A schematic flow chart of a spatial calibration method based on a wellhead rotary table of a drilling platform provided by the present invention.

[0054] like Figure 1 As shown, the spatial calibration method based on the wellhead rotary table of the drilling platform includes the following steps:

[0055] Step S01: Acquire a two-dimensional image and three-dimensional point cloud data of a drilling platform collected by two-dimensional and three-dimensional detection equipment.

[0056] Among them, the field of view of the two-dimensional and three-dimensional detection equipment includes the wellhead area, rathole area, wellhead turntable area, iron roughneck area and pipe rack area. The wellhead area, rathole area, wellhead turntable area, iron roughneck area and pipe rack area are the main areas for personnel activities on the drilling platform. Therefore, the field of view of the two-dimensional and three-dimensional detection equipment provides a data basis for visual positioning and safety warning of personnel on the drilling platform. In addition, the field of view of the two-dimensional and three-dimensional detection equipment includes the wellhead turntable area, and the standard rectangular shape of the wellhead turntable can be used for spatial calibration.

[0057] Furthermore, the two-dimensional and three-dimensional detection equipment is installed at a suitable position on the second floor of the drilling platform derrick or the top of the driller's room. In this way, the two-dimensional and three-dimensional detection equipment can easily observe the wellhead area, rathole area, wellhead rotary area, iron roughneck area and pipe laying machine area.

[0058] Further, the two-dimensional and three-dimensional detection device is a TOF camera. Optionally, the two-dimensional and three-dimensional detection device is an ordinary visible light camera and a laser radar. Optionally, the two-dimensional and three-dimensional detection device is a binocular camera. In this way, the data types collected by the two-dimensional and three-dimensional detection device are two-dimensional images and three-dimensional point cloud data.

[0059] It should be noted that the conversion relationship between the two-dimensional image pixels collected by the two-dimensional and three-dimensional detection equipment and the three-dimensional point cloud data is known, which is the first conversion matrix G c .

[0060] Step S02: According to the four pixel line segments corresponding to the four edges of the wellhead turntable extracted from the two-dimensional image, the intersection points of the straight lines where every two pixel line segments are located are calculated to obtain a set of intersection points.

[0061] In actual scenarios, the vertices of the wellhead turntable in the two-dimensional image collected by the two-dimensional and three-dimensional detection equipment are easily blocked by other equipment and cables. Therefore, the four edges of the wellhead turntable are extracted from the two-dimensional image to calculate the intersection of every two edges to obtain the vertices of the wellhead turntable.

[0062] Among them, the four edges of the wellhead turntable (such as Figure 2 As shown), it can be extracted by human selection or by machine recognition.

[0063] Specifically, according to the four pixel line segments corresponding to the four edges of the wellhead turntable extracted from the two-dimensional image, the intersection point of the straight lines where every two pixel line segments are located is calculated, including:

[0064] The straight line where the two pixel line segments whose intersection is to be calculated are expressed as a system of linear equations:

[0065] A 1 x+B 1 y+C 1 =0

[0066] A 2 x+B 2 y+C 2 =0

[0067] Among them, A 1 =p12.y-p11.y; B 1 =p11.x-p12.x; C 1 =A 1 ×p11.x+B 1 ×p11.y;A 2 =p22.y-p21.y; B 2 =p21.x-p22.x; C 2 =A 2 ×p21.x+B 2 ×p21.y; p11 and p12 are the two endpoints of the first pixel line segment of the two pixel line segments whose intersection is to be calculated, p11.x is the x-axis coordinate of p11, p11.y is the y-axis coordinate of p11, p12.x is the x-axis coordinate of p12, and p12.y is the y-axis coordinate of p12; p21 and p22 are the two endpoints of the second pixel line segment of the two pixel line segments whose intersection is to be calculated, p21.x is the x-axis coordinate of p21, p21.y is the y-axis coordinate of p21, p22.x is the x-axis coordinate of p22, and p22.y is the y-axis coordinate of p22.

[0068] Solve a system of linear equations using Cramer's rule:

[0069] D=A 1 ×B 2 -A 2 ×B 1

[0070] If D≠0, the straight lines where the two pixel line segments are located intersect, and the coordinates of the intersection point p(x,y) are expressed as:

[0071]

[0072] If D=0, the straight lines where the two pixel line segments are located are parallel or coincident and have no intersection.

[0073] Finally, the intersection point set P (p1, p2...pn) (n≤6) is obtained.

[0074] Step S03, select target intersection points within the range of the two-dimensional image from the intersection point set, the number of target intersection points is 4, and the 4 target intersection points correspond to the pixel positions of the 4 vertices of the wellhead turntable in the two-dimensional image respectively.

[0075] Step S04, using the PnP algorithm, according to the spatial positions of the four target intersection points and the four vertices of the wellhead turntable in the actual three-dimensional coordinate system of the drilling platform, calculate the relative transformation relationship matrix between the two to obtain a second transformation matrix.

[0076] The actual three-dimensional coordinate system of the drilling platform takes the center of the wellhead as the origin, the horizontal surface of the drilling platform as the xy axis plane, and the direction of gravity as the z axis.

[0077] Specifically, the PnP algorithm is used to calculate the relative transformation relationship matrix between the four target intersection points and the four vertices of the wellhead rotary table in the actual three-dimensional coordinate system of the drilling platform, including:

[0078]

[0079] Wherein, pi is the i-th vertex of the wellhead turntable in the two-dimensional image; qi is the vertex of the wellhead turntable in the three-dimensional coordinate system of the actual space of the drilling platform corresponding to pi; i is any integer from 1 to 4; pi.x is the x-axis coordinate of pi, pi.y is the y-axis coordinate of pi; qi.x is the x-axis coordinate of qi, qi.y is the y-axis coordinate of qi, and qi.z is the z-axis coordinate of qi; G w is the second conversion matrix; K is the internal parameter matrix of the two-dimensional detection device in the two-dimensional and three-dimensional detection device.

[0080] Figure 3 A schematic flow chart of the drilling platform personnel positioning method provided by the present invention.

[0081] like Figure 3 As shown, the drilling platform personnel positioning method includes the following steps:

[0082] Step S1, obtaining a two-dimensional image and three-dimensional point cloud data of the current drilling platform collected by two-dimensional and three-dimensional detection equipment.

[0083] Step S2: Identify people from the two-dimensional image and select each person with a rectangular frame, and the selected area is the person area.

[0084] The number of people identified is N, and the number of rectangular boxes is also N.

[0085] Preferably, the left edge of the rectangular frame is parallel to the left edge of the two-dimensional image, the right edge of the rectangular frame is parallel to the right edge of the two-dimensional image, the upper edge of the rectangular frame is parallel to the upper edge of the two-dimensional image, the lower edge of the rectangular frame is parallel to the lower edge of the two-dimensional image, and the area selected by the rectangular frame is the minimum area that completely covers the person. In this way, the amount of data obtained about the person area is small, reducing the amount of calculation in the subsequent process.

[0086] Step S3, projecting the three-dimensional point cloud data into the two-dimensional image, deleting the three-dimensional point cloud data that does not fall into the personnel area, retaining the three-dimensional point cloud data that falls into the personnel area, and the three-dimensional point cloud data in each personnel area forms a point cloud group.

[0087] Specifically, the three-dimensional point cloud data is projected into a two-dimensional image according to the first transformation matrix, and finally N point cloud groups are obtained.

[0088] Step S4: perform clustering processing on each point cloud group to obtain the cluster corresponding to each point cloud group, and extract the cluster with the largest number of points in each point cloud group as the target cluster; perform data conversion on the target cluster according to the first transformation matrix to obtain intermediate data, and perform data conversion on the intermediate data according to the second transformation matrix to obtain the location data of the personnel corresponding to the point cloud group to which the target cluster belongs.

[0089] In addition to the points on the target person, there are many interference points in the point cloud group, so each point cloud group is clustered separately.

[0090] Specifically, each point cloud group is clustered to obtain a cluster corresponding to each point cloud group, including: traversing each point in the point cloud group as the center point, and calculating the adjacent distance between each point in the point cloud group except the center point and the center point, and classifying the points and the center point whose adjacent distance is less than a preset threshold into the same cluster to obtain a cluster corresponding to each point cloud group.

[0091] Calculate the adjacent distance between each point in the point cloud group except the center point and the center point. The formula is expressed as:

[0092]

[0093] Among them, i is the i-th point in the point cloud group except the center point; o center is the center point; x i ,y i 、z i Respectively o i The x-axis, y-axis, and z-axis coordinates of center ,y center 、z center Respectively o center The x-axis, y-axis, and z-axis coordinates of .

[0094] Specifically, the intermediate data is converted according to the second conversion matrix to obtain the position data of the person corresponding to the point cloud group to which the target cluster belongs, including:

[0095]

[0096] Where ri is the i-th pixel point in the intermediate data; si is the i-th spatial point of the person in the actual three-dimensional coordinate system of the drilling platform; ri.x is the x-axis coordinate of ri, ri.y is the y-axis coordinate of ri; si.x is the x-axis coordinate of si, si.y is the y-axis coordinate of si, and si.z is the z-axis coordinate of si; G w is the second conversion matrix; K is the internal parameter matrix of the two-dimensional detection device in the two-dimensional and three-dimensional detection device.

[0097] The present invention also provides a drilling platform personnel safety early warning method, comprising: according to the personnel position data obtained by the above method, as well as the position data and operation status data of each mechanical equipment on the drilling platform, early warning of personnel safety is issued.

[0098] In addition, the present invention also provides a drilling platform personnel positioning device, comprising:

[0099] The acquisition module is used to obtain the two-dimensional image and three-dimensional point cloud data of the drilling platform collected by the two-dimensional and three-dimensional detection equipment.

[0100] The recognition module is used to recognize people from the two-dimensional image and select each person with a rectangular frame. The selected area is the person area.

[0101] The data screening module is used to project the three-dimensional point cloud data into a two-dimensional image, delete the three-dimensional point cloud data that does not fall into the personnel area, and retain the three-dimensional point cloud data that falls into the personnel area. The three-dimensional point cloud data in each personnel area forms a point cloud group.

[0102] The clustering module is used to perform clustering processing on each point cloud group, obtain the cluster corresponding to each point cloud group, and extract the cluster with the largest number of points in each point cloud group as the target cluster.

[0103] The data conversion module is used to perform data conversion on the target cluster according to the first conversion matrix to obtain intermediate data, and to perform data conversion on the intermediate data according to the second conversion matrix to obtain the position data of the personnel corresponding to the point cloud group to which the target cluster belongs; wherein the first conversion matrix is ​​the conversion matrix between the three-dimensional point cloud data and the two-dimensional image pixel points, and the second conversion matrix is ​​the conversion matrix between the two-dimensional image pixel points and the three-dimensional coordinate system of the actual space of the drilling platform.

[0104] The specific processing process of each module in the drilling platform personnel positioning device is consistent with the above-mentioned drilling platform personnel positioning method, and will not be repeated here.

[0105] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0106] The present invention 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 invention. 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.

[0107] It should be noted that in the claims, any reference numerals placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In the claims enumerating several means, several of these means may be embodied by the same hardware. The use of the words first, second, third, etc., is for convenience of expression only and does not indicate any order. These words may be understood as part of the component name.

[0108] In addition, it should be noted that, in the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0109] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments after knowing the basic creative concept. Therefore, the claims should be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0110] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include these modifications and variations.

Claims

1. A method for positioning personnel on a drilling platform, characterized in that: The following steps are involved: Step S1, obtaining a two-dimensional image and three-dimensional point cloud data of the drilling platform collected by two-dimensional and three-dimensional detection equipment; Step S2: Identify people from the two-dimensional image and select each person with a rectangular frame, and the selected area is the person area; Step S3, projecting the 3D point cloud data onto the 2D image, deleting the 3D point cloud data that does not fall into the personnel area, retaining the 3D point cloud data that falls into the personnel area, and forming a point cloud group for each 3D point cloud data in the personnel area; Step S4, clustering each point cloud group to obtain the cluster corresponding to each point cloud group, and extracting the cluster with the largest number of points in each point cloud group as the target cluster; Performing data conversion on the target cluster according to the first conversion matrix to obtain intermediate data, and performing data conversion on the intermediate data according to the second conversion matrix to obtain position data of the person corresponding to the point cloud group to which the target cluster belongs; Among them, the first conversion matrix is ​​the conversion matrix between the three-dimensional point cloud data and the two-dimensional image pixels, and the second conversion matrix is ​​the conversion matrix between the two-dimensional image pixels and the three-dimensional coordinate system of the actual space of the drilling platform.

2. The drilling platform personnel positioning method according to claim 1, characterized in that: The field of view of the two-dimensional and three-dimensional detection equipment includes the wellhead area, rathole area, wellhead turntable area, iron roughneck area and pipe laying machine area.

3. The drilling platform personnel positioning method according to claim 1, characterized in that: The left edge of the rectangular box is parallel to the left edge of the two-dimensional image, the right edge of the rectangular box is parallel to the right edge of the two-dimensional image, the upper edge of the rectangular box is parallel to the upper edge of the two-dimensional image, and the lower edge of the rectangular box is parallel to the lower edge of the two-dimensional image. The area selected by the rectangular box is the minimum area that completely covers the person.

4. The drilling platform personnel positioning method according to claim 1, characterized in that: Perform clustering on each point cloud group to obtain the cluster corresponding to each point cloud group, including: Traverse each point in the point cloud group as the center point, and calculate the adjacent distance between each point in the point cloud group except the center point and the center point, and classify the points and the center point whose adjacent distance is less than the preset threshold into the same cluster to obtain the cluster corresponding to each point cloud group.

5. The drilling platform personnel positioning method according to claim 1, characterized in that: The intermediate data is converted according to the second conversion matrix to obtain the position data of the person corresponding to the point cloud group to which the target cluster belongs, including: Among them, ri is the i-th pixel point in the intermediate data; si is the i-th spatial point of the person in the actual three-dimensional coordinate system of the drilling platform; ri.x is the x-axis coordinate of ri, ri.y is the y-axis coordinate of ri; si.x is the x-axis coordinate of si, si.y is the y-axis coordinate of si, si.z is the z-axis coordinate of si; Gw is the second transformation matrix; K is the internal parameter matrix of the two-dimensional detection device in the two-dimensional and three-dimensional detection device.

6. The drilling platform personnel positioning method according to claim 1, characterized in that: Before step S1, the method further includes: Step S01, obtaining a two-dimensional image and three-dimensional point cloud data of the drilling platform collected by two-dimensional and three-dimensional detection equipment; Step S02, according to the four pixel line segments corresponding to the four sides of the wellhead turntable extracted from the two-dimensional image, calculate the intersection of the straight lines where every two pixel line segments are located, and obtain a set of intersection points; Step S03, selecting target intersection points within the range of the two-dimensional image from the intersection point set, the number of target intersection points being 4, and the 4 target intersection points respectively corresponding to the pixel positions of the 4 vertices of the wellhead rotary table in the two-dimensional image; Step S04, using the PnP algorithm, according to the spatial positions of the four target intersection points and the four vertices of the wellhead turntable in the actual three-dimensional coordinate system of the drilling platform, calculate the relative transformation relationship matrix between the two to obtain a second transformation matrix.

7. The drilling platform personnel positioning method according to claim 6, characterized in that: According to the four pixel line segments corresponding to the four sides of the wellhead turntable extracted from the two-dimensional image, the intersection point of the straight line where every two pixel line segments are located is calculated, including: Determine whether the straight lines where the two pixel line segments to be calculated have an intersection: D=A1×B2-A2×B1 If D≠0, the straight lines where the two pixel line segments are located intersect, and the coordinates of the intersection point p(x,y) are expressed as: If D = 0, the lines on which the two pixel line segments lie are parallel or coincident, and there is no intersection; Among them, A1=p12.y-p11.y; B1=p11.x-p12.x; C1=A1×p11.x+B1×p11.y; A2=p22.y-p21.y; B2=p21.x-p22.x; C2=A2×p21.x+B2×p21.y; p11 and p12 are the two endpoints of the first pixel line segment of the two pixel line segments whose intersection is to be calculated, and p11.x is p p11 is the x-axis coordinate of p11, p11.y is the y-axis coordinate of p11, p12.x is the x-axis coordinate of p12, and p12.y is the y-axis coordinate of p12; p21 and p22 are the two endpoints of the second pixel line segment of the two pixel line segments to be calculated for intersection, p21.x is the x-axis coordinate of p21, p21.y is the y-axis coordinate of p21, p22.x is the x-axis coordinate of p22, and p22.y is the y-axis coordinate of p22.

8. The method for locating personnel on a drilling platform according to claim 6, characterized in that: The PnP algorithm is used to calculate the relative transformation relationship matrix between the four target intersection points and the four vertices of the wellhead turntable in the actual three-dimensional coordinate system of the drilling platform, including: Wherein, pi is the i-th vertex of the wellhead turntable in the two-dimensional image; qi is the vertex of the wellhead turntable in the three-dimensional coordinate system of the actual space of the drilling platform corresponding to pi; i is any integer from 1 to 4; pi.x is the x-axis coordinate of pi, pi.y is the y-axis coordinate of pi; qi.x is the x-axis coordinate of qi, qi.y is the y-axis coordinate of qi, and qi.z is the z-axis coordinate of qi; G w is the second conversion matrix; K is the internal parameter matrix of the two-dimensional detection device in the two-dimensional and three-dimensional detection device.

9. A drilling platform personnel safety early warning method, characterized in that: include: According to the personnel position data obtained by the method according to any one of claims 1 to 8, as well as the position data and operation status data of each mechanical equipment on the drilling platform, an early warning of personnel safety is issued.

10. A drilling platform personnel positioning device, characterized in that: include: An acquisition module, used to acquire two-dimensional images and three-dimensional point cloud data of the drilling platform collected by two-dimensional and three-dimensional detection equipment; The recognition module is used to recognize people from the two-dimensional image and select each person with a rectangular frame. The selected area is the person area; A data screening module is used to project the 3D point cloud data into a 2D image, delete the 3D point cloud data that does not fall into the personnel area, and retain the 3D point cloud data that falls into the personnel area. The 3D point cloud data in each personnel area forms a point cloud group. The clustering module is used to perform clustering processing on each point cloud group, obtain the cluster corresponding to each point cloud group, and extract the cluster with the largest number of points in each point cloud group as the target cluster; The data conversion module is used to perform data conversion on the target cluster according to the first conversion matrix to obtain intermediate data, and to perform data conversion on the intermediate data according to the second conversion matrix to obtain the position data of the personnel corresponding to the point cloud group to which the target cluster belongs; wherein the first conversion matrix is ​​the conversion matrix between the three-dimensional point cloud data and the two-dimensional image pixel points, and the second conversion matrix is ​​the conversion matrix between the two-dimensional image pixel points and the three-dimensional coordinate system of the actual space of the drilling platform.

Images