BIM-based model annotation and site-viewing point 3D positioning method and equipment

Abstract

The present invention provides a method and device for model annotation and three-dimensional positioning of real-life viewpoints based on BIM. The present invention obtains a BIM model and video surveillance corresponding to the BIM model, constructs a collision block in the BIM model, and performs image recognition on the video content to obtain a target recognition result; based on the pixel coordinates of the diagonal points of the target recognition result, the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system are solved; based on the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system, the coordinates of the target recognition result in the BIM model coordinate system are calculated. The present invention improves the efficiency and accuracy of target annotation in the BIM model; simplifies the coordinate system conversion between the BIM model and the real-life image; realizes the real-life image and the BIM model. Real-time mapping and three-dimensional positioning are achieved; and the safety management and efficiency of the construction site are improved.

Description

Technical Field

[0001] The present invention relates to the field of building information model (BIM) and monitoring camera technology, and in particular to a BIM-based model annotation and real-time point three-dimensional positioning method. Background Art

[0002] With the development of digital technology, BIM technology has been widely used in the construction field. BIM provides an all-round and refined digital platform by organically linking information from various fields, making the management and monitoring of construction sites more efficient and accurate. However, the establishment and maintenance of BIM models require a lot of data input and updating work, and the problems of delayed information updates and inaccurate data often limit its application. Although BIM technology has shown its advancement in demonstration projects, its high cost and complex operating procedures make large-scale promotion challenging.

[0003] The application of video surveillance systems in construction sites is becoming increasingly popular. Video surveillance systems have the advantages of not needing to build complex models, low cost, and easy large-scale promotion, and can provide real-time on-site image information. However, the data of video surveillance systems is usually unstructured and lacks association with other data sources, making it difficult to trace and analyze problems. Although video surveillance systems have been successfully applied in a large number of projects, their improvement in actual production benefits is limited.

[0004] Although BIM technology and video surveillance systems have their own advantages and disadvantages, the combined application of the two is still relatively rare. Combining the precise modeling capabilities of BIM models with the real-time nature of video surveillance can greatly improve the management level and safety assurance of construction sites. However, how to achieve the precise correspondence between the plane annotations and building blocks in the BIM model and the three-dimensional coordinate system of the camera and panorama has become an urgent problem to be solved. Summary of the invention

[0005] The object of the present invention is to provide a BIM-based model annotation and real-world point three-dimensional positioning method.

[0006] In order to solve the above problems, the present invention provides a BIM-based model annotation and real-time point three-dimensional positioning method, comprising:

[0007] Step 1: Obtain the BIM model and the video surveillance corresponding to the BIM model, build collision blocks in the BIM model, and perform image recognition on the video content to obtain the target recognition result;

[0008] Step 2: Based on the pixel coordinates of the diagonal points of the target recognition result, solve the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system;

[0009] Step 3: Based on the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system, calculate the coordinates of the target recognition result in the BIM model coordinate system.

[0010] Furthermore, in the above method, step 1 comprises:

[0011] Step 1.1: Based on the integrated site model and building model, present the BIM model through the graphics engine;

[0012] Step 1.2: Construct collision blocks with regular geometric shapes in the BIM model, wherein the target recognition results of subsequent video surveillance will be projected onto the collision blocks in the BIM model;

[0013] Step 1.3: Install the camera at a high location on the building site;

[0014] Step 1.4: Obtain the video stream of the construction site through the camera, intercept each frame of monitoring screen of the video stream at a preset frequency, perform image recognition on each frame of monitoring screen to obtain a target recognition result, express the target recognition result with a rectangular frame, and store the pixel coordinates of the diagonal points of the target recognition result.

[0015] Furthermore, in the above method, step 1.4 comprises:

[0016] The video stream is captured at a frequency of one frame per second, and image recognition is performed through Yolo. The target recognition result is expressed by a rectangular box, and the pixel coordinates of the upper left corner and lower right corner of the target recognition result are stored.

[0017] Furthermore, in the above method, step 2 comprises:

[0018] Step 2.1: Define parameters, including: the pixel coordinates of a diagonal point of the target recognition result in the monitoring screen are (u, v), the width of the monitoring screen is canvasWidth, the height is canvasHeight, the horizontal rotation angle pan of the current camera, the vertical rotation angle tilt, the horizontal field of view fov_x, and the vertical field of view fov_y;

[0019] Step 2.2: Based on the parameters, the pixel coordinates (u, v) are converted into the camera internal spherical coordinates (p, t) through coordinate transformation.

[0020] Furthermore, in the above method, step 2.2 comprises:

[0021] Step 2.2.1: In the rectangular coordinate system, O is the origin and the location of the camera, and A is the center point of the monitoring screen. is the camera orientation, rectangle is the monitoring screen of the current camera. The target recognition result is displayed on the monitoring screen of the current camera. points in the equation, based on the parameters and by Obtain The rectangular coordinates of The rectangular coordinates are converted into camera spherical coordinates, that is, the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system are obtained.

[0022] Furthermore, in the above method, step 2.2.1 includes:

[0023] Step 2.2.1.1, the modulus of the OA vector ;

[0024] ;

[0025] ;

[0026] ,Will Convert to unit vector ;

[0027] ;

[0028] ;

[0029] Point Projecting on the xOy plane yields point L, and rotating in the positive direction of the x-axis to The angle is p, In the Oy plane, the positive direction of the y axis rotates to The angle is .

[0030] Furthermore, in the above method, step 3 includes:

[0031] Step 3.1: By calibrating the camera, the coordinates (x, y, z) and the direction vector of the camera in the BIM model coordinate system are obtained when the camera is in the initial state, which are forward, left, and up respectively;

[0032] Step 3.2: According to the horizontal rotation angle p and vertical rotation angle t of the target recognition result in step 2 in the camera spherical coordinate system, rotate the forward and left around up in the right-hand direction by -p to obtain the forward1 and left , then move the up and forward1 around the left Rotate the right hand -t to get the new direction vectors of the camera's front and top. ,superior Obtain the ray of the target recognition result in the BIM model coordinate system ;

[0033] Step 3.3: Solve The intersection point of the collision block in the BIM model is the projection of the target recognition result in the BIM model.

[0034] Furthermore, in the above method, step 3.3 includes:

[0035] Through the HitTest algorithm, solve The intersection point of the collision block in the BIM model is the projection of the target recognition result in the BIM model.

[0036] The present invention also provides a computer-readable storage medium having computer-executable instructions stored thereon, wherein when the computer-executable instructions are executed by a processor, the processor is caused to: adopt any of the methods described above.

[0037] The present invention also provides a computer device, comprising:

[0038] Processor; and

[0039] A memory arranged to store computer executable instructions which, when executed, cause the processor to: adopt any of the methods described above.

[0040] Compared with the prior art, the present invention obtains the BIM model and the video surveillance corresponding to the BIM model, constructs the collision block in the BIM model, and performs image recognition on the video content to obtain the target recognition result;

[0041] Based on the pixel coordinates of the diagonal points of the target recognition result, the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system are solved; based on the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system, the coordinates of the target recognition result in the BIM model coordinate system are calculated. The present invention improves the efficiency and accuracy of target annotation in the BIM model; simplifies the coordinate system conversion between the BIM model and the real-scene image; realizes the real-scene image and the BIM model The real-time mapping and three-dimensional positioning are realized; and the safety management and efficiency of the construction site are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 The present invention is a flowchart of a method for model annotation and three-dimensional positioning of real-world sites based on BIM according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0044] In a typical configuration of the present application, the terminal, the device of the service network and the trusted party all include one or more processors (CPU), input / output interfaces, network interfaces and memories.

[0045] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0046] 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 non-transitory media such as modulated data signals and carrier waves.

[0047] like Figure 1 As shown, the present invention provides a BIM-based model annotation and real-time point three-dimensional positioning method, the method comprising:

[0048] Step 1: Obtain the BIM model and the video surveillance corresponding to the BIM model, build collision blocks in the BIM model, and perform image recognition on the video content to obtain the target recognition result;

[0049] Preferably, step 1 may include:

[0050] Step 1.1: Based on the integrated site model and building model, present the BIM model through the graphics engine;

[0051] Step 1.2: Construct collision blocks with regular geometric shapes in the BIM model, wherein the target recognition results of subsequent video surveillance will be projected onto the collision blocks in the BIM model;

[0052] Specifically, for example, collision blocks are constructed with regular geometric shapes in the BIM model, such as collision blocks of sites, office areas, etc.;

[0053] Step 1.3: Install the camera at a high location on the building site (such as a tower crane);

[0054] Specifically, for example, a camera may be installed on the No. 2 tower crane;

[0055] Step 1.4: Obtain a video stream of the construction site through the camera, intercept each frame of monitoring screen from the video stream at a preset frequency, perform image recognition on each frame of monitoring screen to obtain a target recognition result, express the target recognition result with a rectangular frame, and store the pixel coordinates of the diagonal points of the target recognition result;

[0056] Specifically, for example, you can take a screenshot of the video stream at a frequency of one frame per second, perform image recognition through YOLO, express the target recognition result with a rectangular box, and store the pixel coordinates of the upper left corner and lower right corner of the target recognition result. Take the pixel coordinates of the upper left corner (212,301) as an example to perform the following operations;

[0057] Step 2: Based on the pixel coordinates of the diagonal points of the target recognition result, solve the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system;

[0058] Preferably, step 2 comprises:

[0059] Step 2.1: Define parameters, including: the pixel coordinates of a diagonal point of the target recognition result in the monitoring screen are (u, v), the width of the monitoring screen is canvasWidth, the height is canvasHeight, the horizontal rotation angle pan of the current camera, the vertical rotation angle tilt, the horizontal field of view fov_x, and the vertical field of view fov_y;

[0060] Specifically, for example, parameter definition: the coordinates of the upper left corner pixel of the target recognition result in the picture are (212,301), the picture width canvasWidth=960, the height canvasHeight=576, the horizontal rotation angle pan=40.9°, the vertical rotation angle tilt=46.4°, the horizontal field of view fov_x=51.64°, the vertical field of view fov_y=30.45° of the current camera, and the pixel coordinates (212,301) are converted to the internal spherical coordinates (p, t) of the camera through coordinate transformation;

[0061] Step 2.2: Based on the parameters, the pixel coordinates (u, v) are converted into the camera internal spherical coordinates (p, t) through coordinate transformation.

[0062] Preferably, step 2.2 comprises:

[0063] Step 2.2.1: In the rectangular coordinate system, O is the origin and the location of the camera, and A is the center point of the monitoring screen. is the camera orientation, rectangle is the monitoring screen of the current camera. The target recognition result is displayed on the monitoring screen of the current camera. points in the equation, based on the parameters and by Obtain The rectangular coordinates of The rectangular coordinates are converted into camera spherical coordinates, that is, the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system are obtained.

[0064] Preferably, step 2.2.1 comprises:

[0065] Step 2.2.1.1, the modulus of the OA vector ;

[0066] ;

[0067] ;

[0068] ,Will Convert to unit vector ;

[0069] ;

[0070] ;

[0071] Point Projecting on the xOy plane yields point L, and rotating in the positive direction of the x-axis to The angle is p, In the Oy plane, the positive direction of the y axis rotates to The angle is .

[0072] Specifically, for example, the modulus of the OA vector ;

[0073] ;

[0074] ;

[0075] ;

[0076] ;

[0077] ;

[0078] Point Projecting on the xOy plane yields point L, and rotating in the positive direction of the x-axis to The angle is ,exist In the Oy plane, the positive direction of the y axis rotates to The angle is ;

[0079] Step 3: Based on the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system, the coordinates of the target recognition result in the BIM model coordinate system are calculated;

[0080] Preferably, step 3 comprises:

[0081] Step 3.1: By calibrating the camera, the coordinates (x, y, z) and the direction vector of the camera in the BIM model coordinate system are obtained when the camera is in the initial state, which are forward, left, and up respectively;

[0082] Specifically, for example, by calibrating the camera, we can obtain the coordinates (115.8, 15.8, 60.5) and the direction vector of the camera in the model coordinate system when the camera is in the initial state, which are:

[0083] forward=(0.99969,−0.00349,−0.02444);

[0084] leftleft=(0.00349,0.99879,-0.04884)(0.00349, 0.99879, -0.04884);

[0085] up = (−0.02444, 0.04882, 0.99850);

[0086] Step 3.2: According to the horizontal rotation angle p and vertical rotation angle t of the target recognition result in step 2 in the camera spherical coordinate system, rotate the forward and left around up in the right-hand direction by -p to obtain the forward1 and left , then move the up and forward1 around the left Rotate the right hand -t to get the new direction vectors of the camera's front and top. ,superior Obtain the ray of the target recognition result in the BIM model coordinate system ;

[0087] Specifically, for example,

[0088] ;

[0089] ;

[0090] ;

[0091] Obtain the ray of the recognition result in the model coordinate system .

[0092] Step 3.3: Solve by HitTest algorithm The first intersection point with the collision block in the BIM model is the projection of the target recognition result in the BIM model.

[0093] The present invention also provides a computer-readable storage medium having computer-executable instructions stored thereon, wherein when the computer-executable instructions are executed by a processor, the processor is enabled to: adopt the method described in any of the above embodiments.

[0094] The present invention also provides a computer device, comprising:

[0095] Processor; and

[0096] A memory arranged to store computer executable instructions, which, when executed, cause the processor to: adopt the method described in any one of the above embodiments.

[0097] The detailed contents of the device embodiments of the present invention can be found in the corresponding parts of the method embodiments, which will not be described in detail here.

[0098] In summary, the present invention improves the efficiency and accuracy of target annotation in the BIM model; simplifies the coordinate system conversion between the BIM model and the real-scene image; realizes the real-time mapping and three-dimensional positioning of the real-scene image and the BIM model; and improves the safety management and efficiency of the construction site.

[0099] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0100] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, it can be implemented using an application-specific integrated circuit (ASIC), a general-purpose computer or any other similar hardware device. In one embodiment, the software program of the present invention can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present invention (including related data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and the like. In addition, some steps or functions of the present invention can be implemented using hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.

[0101] In addition, a part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. The program instruction for calling the method of the present invention may be stored in a fixed or removable recording medium, and / or transmitted through a data stream in a broadcast or other signal-bearing medium, and / or stored in a working memory of a computer device that runs according to the program instruction. Here, according to an embodiment of the present invention, a device is included, the device including a memory for storing computer program instructions and a processor for executing program instructions, wherein, when the computer program instruction is executed by the processor, the device is triggered to run the method and / or technical solution based on the aforementioned multiple embodiments of the present invention.

[0102] It is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential features of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive, and the scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is obvious that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim can also be implemented by one unit or device through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

Claims

1. A BIM-based model annotation and site point three-dimensional positioning method, characterized in that: include: Step 1: Obtain the BIM model and the video surveillance corresponding to the BIM model, build collision blocks in the BIM model, and perform image recognition on the video content to obtain the target recognition result; Step 2: Based on the pixel coordinates of the diagonal points of the target recognition result, solve the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system; Step 3: Based on the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system, the coordinates of the target recognition result in the BIM model coordinate system are calculated; Step 2 includes: Step 2.1: Define parameters, including: the pixel coordinates of a diagonal point of the target recognition result in the monitoring screen are (u, v), the width of the monitoring screen is canvasWidth, the height is canvasHeight, the horizontal rotation angle pan of the current camera, the vertical rotation angle tilt, the horizontal field of view fov_x, and the vertical field of view fov_y; Step 2.2: Based on the parameters, the pixel coordinates (u, v) are converted into the camera internal spherical coordinates (p, t) by coordinate transformation; Step 2.2 includes: Step 2.2.1: In the rectangular coordinate system, O is the origin and the location of the camera, and A is the center point of the monitoring screen. is the camera orientation, the rectangle GFG′F′ is the monitoring screen of the current camera, L′ is the point of the target recognition result in the monitoring screen GFG′F′ of the current camera, based on the parameters, and through Obtain the rectangular coordinates of L′, and then convert the rectangular coordinates of L′ into the camera spherical coordinates, that is, obtain the horizontal rotation angle p and the vertical rotation angle t of the target recognition result in the camera spherical coordinate system; Step 2.2.1, including: Step 2.2.1.1, modulus r of OA vector OA =0.5*canvasWidth / tan(fox_x / 2); Will Convert to unit vector Will Convert to unit vector Project point L' on the xOy plane to get point L, and rotate the positive direction of the x-axis to The angle is p, and in the L′Oy plane, the positive direction of the y axis rotates to The angle is θ, t = 90°-θ; Step 3 includes: Step 3.1: By calibrating the camera, the coordinates (x, y, z) and the direction vector of the camera in the BIM model coordinate system are obtained when the camera is in the initial state, which are forward, left, and up respectively; Step 3.2: According to the horizontal rotation angle p and vertical rotation angle t of the target recognition result in the camera spherical coordinate system obtained in step 2, rotate the forward and left around the up by -p in the right-hand direction to obtain the forward1 and left', and then rotate the up and forward1 around the left' by -t in the right hand direction to obtain the new direction vectors of the camera's front and top, respectively. The rays of the target recognition result in the BIM model coordinate system are obtained by forward' and up'. Step 3.3: Solve The intersection point of the collision block in the BIM model is the projection of the target recognition result in the BIM model.

2. The BIM-based model annotation and site point three-dimensional positioning method according to claim 1, characterized in that: Step 1 includes: Step 1.1: Based on the integrated site model and building model, present the BIM model through the graphics engine; Step 1.2: Construct collision blocks with regular geometric shapes in the BIM model, wherein the target recognition results of subsequent video surveillance will be projected onto the collision blocks in the BIM model; Step 1.3: Install the camera at a high location on the building site; Step 1.4: Obtain the video stream of the construction site through the camera, intercept each frame of monitoring screen of the video stream at a preset frequency, perform image recognition on each frame of monitoring screen to obtain a target recognition result, express the target recognition result with a rectangular frame, and store the pixel coordinates of the diagonal points of the target recognition result.

3. The BIM-based model annotation and real-time point three-dimensional positioning method according to claim 2, characterized in that: Step 1.4 includes: The video stream is captured at a frequency of one frame per second, and image recognition is performed through Yolo. The target recognition result is expressed by a rectangular box, and the pixel coordinates of the upper left corner and lower right corner of the target recognition result are stored.

4. The BIM-based model annotation and site point three-dimensional positioning method according to claim 1, characterized in that: Step 3.3 includes: Through the HitTest algorithm, solve The intersection point of the collision block in the BIM model is the projection of the target recognition result in the BIM model.

5. A computer-readable storage medium having computer-executable instructions stored thereon, wherein: When the computer executable instructions are executed by a processor, the processor is caused to: adopt the method according to any one of claims 1 to 4.

6. A computer device, wherein: include: processor; as well as A memory arranged to store computer executable instructions which, when executed, cause the processor to: employ a method as claimed in any one of claims 1 to 4.

Images