Building information model adjusting method and device

Abstract

The embodiment of the invention provides a building information model adjusting method and device.The building information model adjusting method comprises the steps that a virtual picture of a building information model and a corresponding real scene picture are obtained, the virtual picture is obtained based on a virtual camera in the building information model, and the real scene picture is obtained based on the virtual camera in the building information model; the real scene picture is obtained based on a corresponding scene camera in a real scene; performing picture matching on the virtual picture and the real scene picture, and determining an adjustment parameter of the virtual camera; and adjusting the virtual camera in the building information model according to the adjustment parameter of the virtual camera. Thus, the virtual camera in the building information model is automatically adjusted by matching the virtual picture obtained by digital modeling with the real scene picture in the real environment, so that the virtual camera of the building information model is updated in time in the informatization management process, the consistency of digital modeling and the real environment is kept, and the user experience is improved. And the accuracy of the building information model is ensured.

Description

Technical Field

[0001] The embodiments of the present specification relate to the field of computer technology, and more particularly to a method and device for adjusting a building information model. Background Art

[0002] With the rapid development of computer technology, information technology and economy, intelligent building has become one of the mainstream technologies in today's building development. As a tool of architecture, building information modeling (BIM) takes various relevant information data of construction projects as the basis of the model, and simulates the real information of the building through digital information simulation. The building information model has eight characteristics, including information completeness, information relevance, information consistency, visualization, coordination, simulation, optimization and plotting. It can enable project participants such as construction units, design units, construction units, and supervision units to share the same building information model on the same platform, which is conducive to project visualization and refined construction. It is an important tool for realizing refined and informationized management of the construction industry and has been widely used in many fields.

[0003] In the prior art, the placement of each device in the building information model is based on the drawings. In the process of information management, if there is no artificial change to the device in the real scene, the building information model is usually not changed. However, in the long-term operation process, there may be a deviation between the building information model and the real scene, which reduces the accuracy of the building information model. Therefore, a more accurate building information model adjustment solution is urgently needed. Summary of the invention

[0004] In view of this, an embodiment of the present specification provides a method for adjusting a building information model. One or more embodiments of the present specification also relate to an adjustment device for a building information model, a computing device, a computer-readable storage medium, and a computer program product to solve the technical defects existing in the prior art.

[0005] According to a first aspect of an embodiment of this specification, a method for adjusting a building information model is provided, comprising: Acquire a virtual picture of a building information model and a corresponding real scene picture, wherein the virtual picture is obtained based on a virtual camera in the building information model, and the real scene picture is obtained based on a corresponding scene camera in the real scene; Matching the virtual image with the real scene image to determine adjustment parameters of the virtual camera; The virtual camera in the building information model is adjusted according to the adjustment parameters of the virtual camera.

[0006] According to a second aspect of an embodiment of this specification, there is provided a device for adjusting a building information model, comprising: An acquisition module is configured to acquire a virtual image of a building information model and a corresponding real scene image, wherein the virtual image is acquired based on a virtual camera in the building information model, and the real scene image is acquired based on a corresponding scene camera in the real scene; A determination module is configured to match the virtual picture with the real scene picture to determine the adjustment parameters of the virtual camera; The adjustment module is configured to adjust the virtual camera in the building information model according to the adjustment parameters of the virtual camera.

[0007] According to a third aspect of an embodiment of this specification, a computing device is provided, including: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the above-mentioned building information model adjustment method are implemented.

[0008] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned building information model adjustment method are implemented.

[0009] According to a fifth aspect of the embodiments of this specification, a computer program product is provided, including a computer program / instruction, which implements the steps of the above-mentioned building information model adjustment method when executed by a processor.

[0010] One embodiment of the present specification realizes obtaining a virtual image of a building information model and a corresponding real scene image, then matching the virtual image with the real scene image, determining the adjustment parameters of the virtual camera, and adjusting the virtual camera in the building information model according to the adjustment parameters of the virtual camera. In this way, by matching the virtual image obtained by digital modeling with the real scene image in the real environment, the virtual camera in the building information model is automatically adjusted, and the virtual camera of the building information model is updated in time during the information management process, the consistency between the digital modeling and the real environment is maintained, and the accuracy of the building information model is guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 is a flow chart of a method for adjusting a building information model provided by an embodiment of this specification; Figure 2 It is a process flow chart of a method for adjusting a building information model provided by one embodiment of the present specification; Figure 3 It is a structural schematic diagram of a building information model adjustment device provided by an embodiment of the present specification; Figure 4 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0012] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0013] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0014] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0015] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0016] First, the terms involved in one or more embodiments of this specification are explained.

[0017] CCTV (Closed-Circuit Television): is an image communication system that uses video cameras to transmit video signals to a specific location for monitoring and / or recording via a dedicated transmission line (usually a cable, but it may also be a wireless connection). CCTV mainly consists of the following key parts: Camera: responsible for capturing live video images. Cameras in modern CCTV systems include both analog and digital models, and increasingly use high-definition and network / IP cameras; Transmission media: used to transmit the video signals captured by the camera to the control room or other monitoring locations, which can be coaxial cables, optical fibers, network lines or wireless transmission technologies; Recording equipment: traditionally using video tape recorders (VCRs) or digital video recorders (DVRs), modern systems are more likely to use network video recorders (NVRs) or cloud-based storage solutions to record and store video data; Video management software: allows users to control cameras (such as adjusting the viewing angle, focus), view real-time video streams, playback recordings, manage storage and alarms, etc.; Monitor: displays real-time video images or recording playback, which can be a single screen or display multiple video streams through a video wall; Control system: includes keyboard, mouse, remote control or touch screen interface, used to operate and configure the entire CCTV system. CCTV systems are widely used in many fields such as security monitoring, traffic management, retail stores, financial institutions, public areas, industrial sites, schools and homes to enhance security prevention, and can also be used for a variety of non-security purposes such as workflow supervision and customer service improvement.

[0018] Building Information Model (BIM): It is based on various relevant information data of construction projects, manages three-dimensional building models, and simulates the real information of buildings through digital information simulation. It is a process based on intelligent three-dimensional models, used for building design, construction and management. BIM is not only a three-dimensional modeling technology, but also an integrated cooperation platform, covering the information management of the entire life cycle of buildings from conceptual design, construction, operation to demolition. BIM has eight major characteristics, including information completeness, information relevance, information consistency, visualization, coordination, simulation, optimization and plotting. It can enable project participants such as construction units, design units, construction units, and supervision units to share the same building information model on the same platform, which is conducive to project visualization and refined construction. BIM is an important tool for realizing refined and information management in the construction industry.

[0019] Transformation parameter matrix: Usually discussed in fields such as computer graphics, linear algebra, geometry, and machine learning, it is a mathematical tool used to describe linear transformations from one coordinate system to another (such as rotation, scaling, translation, etc.). This matrix contains the information needed to complete a specific transformation.

[0020] RANSAC (Random Sample Consensus): It is an iterative machine learning algorithm that is mainly used to estimate the parameters of mathematical models from a data set containing a large number of outliers, such as the fitting of geometric models such as lines, circles, and planes. The RANSAC algorithm is particularly suitable for applications in computer vision, image processing, robot navigation, and other fields. Its main purpose is to find the data subset that best fits the model assumptions in noisy data.

[0021] Fast Nearest Neighbor Algorithm: usually refers to an efficient search method for finding the nearest neighbor (NN) of a query point in high-dimensional space. In many machine learning and data mining tasks, such as classification, clustering, recommendation systems, etc., nearest neighbor search is a basic and important step. Since the complexity of direct nearest neighbor search in high-dimensional space is very high (especially on large-scale data sets), a series of fast algorithms have been developed to speed up this process.

[0022] In this specification, a method for adjusting a building information model is provided. This specification also relates to an adjustment device for a building information model, a computing device, a computer-readable storage medium, and a computer program product, which are described in detail one by one in the following embodiments.

[0023] See also Figure 1 , Figure 1 A flowchart of a method for adjusting a building information model provided according to an embodiment of the present specification is shown, which specifically includes the following steps 102-106.

[0024] Step 102: Acquire a virtual image of the building information model and a corresponding real scene image, wherein the virtual image is obtained based on a virtual camera in the building information model, and the real scene image is obtained based on a corresponding scene camera in the real scene.

[0025] The embodiments of this specification are applied to an information management platform, in which a corresponding building information model is constructed based on drawings corresponding to real scenes, and the building information model is managed and maintained. The building information model corresponds to the real scene and simulates the real information of the building in the real scene through digital information simulation.

[0026] It should be noted that a scene camera is set in the real scene to capture the real scene image of the real scene in order to monitor the real scene; a corresponding virtual camera is set at the corresponding position of the building information model to capture the corresponding virtual image. The position, angle and other parameters of the virtual camera and the scene camera should be consistent, so as to ensure the consistency between the digital modeling and the real environment.

[0027] Specifically, the information management platform can read the virtual images taken by the virtual camera in the building information model, and obtain the corresponding CCTV images as the corresponding real scene images, wherein the CCTV images are video images of the real scene captured by the CCTV system and transmitted through the network.

[0028] In actual implementation, in the process of realizing information management of the construction industry, the scene camera in the real scene may have problems such as misalignment and loss of motion due to long-term motion zoom, resulting in inconsistency between digital modeling and the real environment. Therefore, the embodiment of this specification provides a method for adjusting a building information model, which can obtain a virtual picture of the building information model and a corresponding real scene picture. Subsequently, by matching the virtual picture and the real scene picture, the virtual camera in the building information model can be automatically adjusted to ensure that the digital modeling is consistent with the real environment.

[0029] Step 104: Match the virtual image with the real scene image to determine the adjustment parameters of the virtual camera.

[0030] Among them, the adjustment parameters of the virtual camera can indicate the adjustment method of the virtual camera. After adjustment according to the adjustment parameters of the virtual camera, the virtual picture taken by the virtual camera can overlap with the real scene picture.

[0031] It should be noted that the virtual picture is the picture taken by the virtual camera in the building information model, and the real scene picture is the real picture taken by the real scene camera at the corresponding position in the real scene. Since the building information model and the real scene are corresponding, the pictures taken by the virtual camera and the scene camera at the corresponding positions should be consistent. If the two pictures are inconsistent, it means that the parameters of the virtual camera in the building information model are inconsistent with those of the real scene camera in the real scene. According to the difference between the two pictures, the adjustment parameters of the virtual camera can be determined, thereby realizing automatic adjustment of the virtual camera in the building information model.

[0032] In an optional implementation of this embodiment, matching the virtual image with the real scene image to determine the adjustment parameters of the virtual camera includes: Extracting virtual feature points in a virtual picture, and extracting scene feature points in a real scene picture; Matching virtual feature points with scene feature points to determine pixel transformation information between the virtual image and the real scene image; According to the pixel transformation information, the adjustment parameters of the virtual camera are determined.

[0033] Among them, virtual feature points are feature points related to the structure extracted from the virtual picture, and scene feature points are feature points related to the structure extracted from the real scene picture, such as feature points on columns, door frames, and tracks.

[0034] In one possible implementation method, edge recognition can be used to identify objects related to the structure in the image, such as pillars, door frames, tracks, etc., and the edge points of the identified objects can be used as the feature points. In another possible implementation method, corner point recognition can be used to identify feature points related to the structure. A corner point refers to a point where two edges in the image intersect. For the same scene, even if the viewing angle changes, the corner point usually has a stable property, so the corner point can be used to extract feature points related to the structure.

[0035] In actual implementation, image recognition models or image recognition algorithms can be used to extract virtual feature points and scene feature points, such as SIFT (Scale-Invariant Feature Transform), ORB (OrientedFAST and Rotated BRIEF), CNN features (Convolutional Neural Network Features), etc.

[0036] For example, a virtual picture is obtained based on the current parameters of the virtual camera, virtual feature points are extracted from the virtual picture, and the coordinate information B1, B2, ..., Bi of each virtual feature point is recorded; the current CCTV picture is obtained as the real scene picture, the scene feature points of the real scene picture are extracted, and the coordinate information C1, C2, ..., Cj of each scene feature point is recorded.

[0037] It should be noted that after matching and obtaining pixel transformation information, the adjustment parameters of the virtual camera can be determined according to the pixel transformation information. The pixel transformation information is used to indicate the difference in pixels between the two images, and the adjustment parameters of the corresponding virtual camera can be calculated according to the difference in pixels. That is, after adjusting the virtual camera in the building information model according to the adjustment parameters of the virtual camera, the captured virtual image can completely overlap with the real scene image.

[0038] In actual implementation, the pixel transformation information can be a transformation parameter matrix. Specifically, the RANSAC algorithm can be used to match and calculate the virtual feature points and the scene feature points to obtain a transformation parameter matrix, which can be a 4x4 matrix, which is often used to describe geometric transformations occurring in three-dimensional space, including rotation, scaling, translation, and projection operations, including a 3x3 unit matrix and a row or column representing a translation vector. The 3x3 unit matrix is ​​used to indicate linear transformations, such as rotation and scaling, and an additional row or column is related to the translation transformation.

[0039] In the 3x3 identity matrix, the first row is used to affect the X component of the object after scaling and translation in the X-axis direction, the second row is used to affect the Y component of the object after scaling and translation in the Y-axis direction, and the third row is used to affect the Z component of the object after scaling and translation in the Z-axis direction. The 3x3 identity matrix can be further decomposed into rotation and scaling, where rotation can be achieved through a specific rotation matrix (such as a rotation matrix around the X, Y, and Z axes), and scaling is achieved by placing scaling factors on the diagonal. Each element in a row or column indicating a translation transformation represents the amount of translation of the object in the X-axis direction, the Y-axis direction, and the Z-axis direction, respectively.

[0040] By using a 4x4 transformation parameter matrix and combining its elements, we can fully describe the transformation in three-dimensional space, including shape deformation (rotation, scaling) and position movement (translation). Based on this transformation parameter matrix, we can determine the adjustment parameters of the virtual camera, such as rotation angle, translation position, etc.

[0041] Of course, in actual implementation, the pixel transformation information can be not only the above-mentioned transformation parameter matrix, but also pixel difference, structural similarity index, image gradient / texture difference and other parameters that can describe the difference in pixels between two images, and the embodiments of this specification do not limit this.

[0042] In the embodiments of the present specification, virtual feature points in a virtual picture can be extracted, and scene feature points in a real scene picture can be extracted, and then the virtual feature points and the scene feature points can be matched to determine pixel transformation information of the virtual picture and the real scene picture. The pixel transformation information can indicate the pixel difference between the two pictures. Based on the pixel transformation information, the adjustment parameters of the virtual camera can be determined. Based on the feature point comparison, the pixel difference between the digital modeling and the corresponding picture of the real environment can be determined, and the adjustment parameters of the virtual camera can be determined simply and quickly.

[0043] In an optional implementation of this embodiment, matching the virtual feature points with the scene feature points to determine the pixel transformation information of the virtual picture and the real scene picture includes: According to the positional relationship of the virtual feature points, the corresponding feature points are matched in the scene feature points to obtain the matched virtual feature points and the matched scene feature points; According to the matching virtual feature points and the matching scene feature points, the pixel transformation information of the virtual picture and the real scene picture is determined.

[0044] It should be noted that virtual feature points are structural points obtained by feature recognition of virtual images, while scene feature points are structural points obtained by feature point recognition of real scene images. Therefore, the obtained virtual feature points and scene feature points do not correspond to each other, and feature point comparison cannot be achieved to determine the distinguishing information.

[0045] In actual implementation, a fast nearest neighbor algorithm can be used to match virtual feature points and scene feature points to obtain one-to-one matching virtual feature points and matching scene feature points, and then feature point matching and comparison are performed based on the one-to-one matching virtual feature points and matching scene feature points to determine the pixel transformation information of the virtual image and the real scene image.

[0046] As an example, the Randomized kd Tree Algorithm, the Priority Search K-Means Tree Algorithm, the Hierarchical Clustering Tree and other algorithms can be used to search and match the virtual feature points B1, B2, …, Bi and the scene feature points C1, C2, …, Cj to obtain matching virtual feature points B1, B2, …, Bk and matching scene feature points C1, C2, …, Ck, and the matching virtual feature points and the matching scene feature points correspond one to one, that is, B1 and C1, B2 and C2, …, Bk and Ck are corresponding feature points.

[0047] In the embodiments of the present specification, the corresponding feature points can be matched in the scene feature points according to the positional relationship of the virtual feature points to obtain one-to-one matched virtual feature points and matched scene feature points, and then the feature points can be matched to determine the pixel transformation information of the virtual picture and the real scene picture, thereby ensuring that the determined pixel transformation information can accurately reflect the difference in feature points between the two pictures, thereby improving the accuracy of the determined pixel transformation information.

[0048] In an optional implementation of this embodiment, according to the positional relationship of the virtual feature points, the corresponding feature points are matched in the scene feature points to obtain the matched virtual feature points and the matched scene feature points, including: According to the positional relationship of the first feature point, matching the corresponding second feature point in the scene feature point, wherein the first feature point is any virtual feature point; If the corresponding second feature point is matched, the first feature point is used as the matching virtual feature point, the second feature point is used as the matching scene feature point, and the corresponding relationship between the first feature point and the second feature point is stored; if the corresponding second feature point is not matched, the first feature point is deleted; When the virtual feature points are matched, the remaining unmatched feature points in the scene feature points are deleted.

[0049] In actual implementation, any virtual feature point can be used as the first feature point. Based on the positional relationship of the first feature point, the corresponding second feature point can be matched in the scene feature point. If the corresponding second feature point is matched, it means that the first feature point and the second feature point correspond to each other, and the next virtual feature point can be matched. If the corresponding second feature point is not matched, it means that there is no feature point corresponding to the first feature point in the scene feature point, and the first feature point may be a noise point irrelevant to the structure. At this time, the first feature point can be deleted, and the next virtual feature point can be matched until the matching of each virtual feature point is completed. At this time, the matched virtual feature points obtained all have corresponding feature points in the scene feature points.

[0050] In addition, the feature points in the scene feature points that are not matched with the virtual feature points may be noise points irrelevant to the structure, so the remaining unmatched feature points in the scene feature points can be deleted, and at this time, one-to-one matching virtual feature points and matching scene feature points can be obtained.

[0051] For example, for virtual feature point B1, it is assumed that it is adjacent to virtual feature points B2 and B3. According to the positional relationship of virtual feature points B1, B2, and B3, search and match are performed in scene feature points C1, C2, ..., and Cj. Assuming that the positional relationship of C1 is similar to that of B1, it can be determined that virtual feature point B1 corresponds to scene feature point C1. Assuming that no feature points with similar positions are searched out in scene feature points C1, C2, ..., and Cj, virtual feature point B1 is deleted. In addition, assuming that virtual feature points B1, B2, ..., and Bi are matched to obtain matching virtual feature points B1, B2, ..., and Bk, which correspond one-to-one with matching scene feature points C1, C2, ..., and Ck, the remaining feature points in scene feature points C1, C2, ..., and Cj are deleted.

[0052] In the embodiments of the present specification, virtual feature points that cannot be matched in scene feature points are screened out, and scene feature points that cannot be matched in virtual feature points are screened out. Through two-way cross-checking, noise information of non-structural points in virtual feature points and scene feature points is screened out, and one-to-one matching virtual feature points and matching scene feature points are obtained to facilitate subsequent feature point matching and determine pixel transformation information, thereby ensuring the correspondence between feature points of the virtual picture and the real scene picture, thereby improving matching accuracy and matching efficiency.

[0053] In an optional implementation of this embodiment, if the corresponding second feature point is matched, the first feature point is used as a matching virtual feature point and the second feature point is used as a matching scene feature point, including: If the corresponding second feature point is matched, the similarity between the first feature point and the second feature point is determined; When the similarity is greater than the similarity threshold, the first feature point is used as a matching virtual feature point and the second feature point is used as a matching scene feature point; When the similarity is less than or equal to the similarity threshold, the first feature point is deleted.

[0054] The similarity threshold is a pre-configured value used to determine the degree of similarity. For example, the similarity threshold can be configured as 0.7, 0.8, etc.

[0055] It should be noted that even if the second feature point corresponding to the first feature point is matched, there may still be a situation where the similarity between the first feature point and the second feature point is not high, that is, non-corresponding feature points may be matched incorrectly. Therefore, in actual implementation, the similarity between the first feature point and the second feature point can be further determined. If the similarity is greater than the similarity threshold, it means that the first feature point and the second feature point are corresponding feature points, and the first feature point is used as the matching virtual feature point and the second feature point is used as the matching scene feature point; if the similarity is less than or equal to the similarity threshold, it means that the first feature point and the second feature point are not very similar, and may be a noise point irrelevant to the structure and incorrectly matched. In this case, the first feature point is deleted.

[0056] In the embodiments of the present specification, by setting a similarity threshold, it is possible to further determine whether the first feature point and the second feature point match based on the relationship between the similarity between the first feature point and the second feature point and the similarity threshold, thereby avoiding erroneous matching of noise points irrelevant to the structure and improving the accuracy of feature point matching.

[0057] In an optional implementation of this embodiment, matching the virtual feature points with the scene feature points to determine the pixel transformation information of the virtual picture and the real scene picture includes: Sampling the virtual feature points and the scene feature points multiple times, removing redundant feature points from the virtual feature points and the scene feature points, and obtaining updated virtual feature points and updated scene feature points; The updated virtual feature points and the updated scene feature points are matched to determine the pixel transformation information of the virtual picture and the real scene picture.

[0058] It should be noted that, in addition to the above implementation method of directly matching the virtual feature points with the scene feature points based on the position relationship, it is also possible to first perform a redundancy removal operation on the scene feature points.

[0059] In actual implementation, since users often move around in real scenes, the scene feature points extracted from the real scene screen may include many redundant feature points that are irrelevant to the structure. However, since the virtual feature points are feature points extracted from the virtual screen based on the building information model, they will not include redundant information such as users. Therefore, in specific implementation, the virtual feature points and scene feature points can be sampled multiple times, and the redundant feature points in the virtual feature points and scene feature points can be removed to obtain updated virtual feature points and updated scene feature points, and then the updated virtual feature points and updated scene feature points are matched to determine the pixel transformation information of the virtual screen and the real scene screen.

[0060] Specifically, according to the positional relationship of the updated virtual feature points, the corresponding feature points can be matched in the updated scene feature points to obtain matched virtual feature points and matched scene feature points, and then the pixel transformation information of the virtual picture and the real scene picture can be determined based on the matched virtual feature points and matched scene feature points.

[0061] In the embodiments of the present specification, redundant feature points in virtual feature points and scene feature points may be removed before subsequent feature point matching is performed, thereby reducing the amount of data for feature point matching and improving matching efficiency and accuracy.

[0062] In an optional implementation of this embodiment, multiple sampling of virtual feature points and scene feature points is performed to remove redundant feature points in the virtual feature points and scene feature points to obtain updated virtual feature points and updated scene feature points, including: The virtual feature points and the scene feature points are sampled multiple times respectively to obtain multiple groups of reference virtual feature points and multiple groups of reference scene feature points; respectively determining difference information between a plurality of groups of reference virtual feature points and a plurality of groups of reference scene feature points; According to the difference information and the number of feature points, one group is determined from the multiple groups of reference virtual feature points as the updated virtual feature points, and one group is determined from the multiple groups of reference scene feature points as the updated scene feature points.

[0063] The difference information is a parameter that can represent the difference value of the feature points, such as mean square error, root mean square error, mean absolute error, etc.

[0064] In actual implementation, the virtual feature points and scene feature points can be sampled multiple times to obtain multiple groups of reference virtual feature points and multiple groups of reference scene feature points. Then, a group of reference virtual feature points and a group of reference scene feature points are fitted to calculate the difference information, and the pair with the smallest difference information and the largest number of feature points is selected as the updated virtual feature points and updated scene feature points.

[0065] Continuing with the above example, virtual feature points B1, B2, ..., Bi are extracted from the virtual picture, and scene feature points C1, C2, ..., Cj are extracted from the real scene picture. Using the constraint conditions of minimum mean square error and the largest number of feature points, the updated virtual feature points B1, B2, ..., Bn are obtained, and the updated scene feature points C1, C2, ..., Cm are updated.

[0066] In the embodiments of the present specification, virtual feature points and scene feature points may be sampled multiple times, and redundancy removal operations may be performed based on difference information and the number of feature points to improve the robustness of the feature points and ensure the accuracy of subsequent feature point matching.

[0067] Step 106: Adjust the virtual camera in the building information model according to the adjustment parameters of the virtual camera.

[0068] It should be noted that the adjustment parameters of the virtual camera can indicate the adjustment method of the virtual camera, so the virtual camera in the building information model can be controlled to adjust according to the adjustment parameters, so that the virtual picture taken by the adjusted virtual camera can overlap with the real scene picture.

[0069] In an optional implementation of this embodiment, the adjustment parameters of the virtual camera include a rotation angle and a translation size; and adjusting the virtual camera in the building information model according to the adjustment parameters of the virtual camera includes: Adjust the current angle and current position of the virtual camera in the building information model according to the rotation angle and translation size.

[0070] The adjustment parameters of the virtual camera include a rotation angle and a translation size. The rotation angle refers to the angle at which the virtual camera needs to rotate in order to match the angle of the scene camera. The translation size refers to the size of the translation required to match the position of the virtual camera with that of the scene camera.

[0071] In actual implementation, the virtual camera in the building information model can be controlled to rotate from the current angle to the rotation angle, and move the translation size at the current position to complete the adjustment of the virtual camera in the building information model.

[0072] For example, assuming that the adjustment parameters of the virtual camera include rotating 15° in the P direction and translating L distance in the M direction, the virtual camera in the building information model can be controlled to rotate 15° in the P direction from the current angle and translate L distance in the M direction from the current angle.

[0073] In the embodiments of the present specification, the current angle and current position of the virtual camera in the building information model can be adjusted according to the determined rotation angle and translation size, so that the virtual image captured by the adjusted virtual camera can completely overlap with the real scene image, thereby ensuring the consistency between the digital modeling and the real environment.

[0074] Of course, in actual implementation, the adjustment parameters of the virtual camera may include other parameters that can be calculated based on picture matching, such as zoom ratio, etc., in addition to the above-mentioned rotation angle and translation size, and the embodiments of this specification do not limit this.

[0075] In an optional implementation of this embodiment, adjusting the virtual camera in the building information model according to the adjustment parameters of the virtual camera includes: Determine the deviation amplitude of the virtual camera according to the adjustment parameters of the virtual camera; If the deviation amplitude is less than the deviation threshold, the virtual camera in the building information model is adjusted according to the adjustment parameters of the virtual camera; If the deviation amplitude is greater than or equal to the deviation threshold, an abnormal prompt is issued, wherein the abnormal prompt is used to instruct the scene camera in the real scene to be repaired.

[0076] The deviation threshold is a pre-configured value used to determine the degree of deviation between the virtual camera in the building information model and the scene camera in the real scene.

[0077] In actual implementation, the deviation amplitude of the virtual camera can be determined according to the adjustment parameters of the virtual camera. If the deviation amplitude is less than the deviation threshold, it means that the scene camera in the real scene has only changed slightly. At this time, the virtual camera in the building information model can be adjusted according to the adjustment parameters of the virtual camera to ensure the consistency between the digital modeling and the real environment; if the deviation amplitude is greater than or equal to the deviation threshold, it means that the scene camera in the real scene has changed to a large extent, and the scene camera in the real scene may have an abnormality or failure. At this time, the virtual camera in the building information model does not need to be adjusted, but an abnormal prompt is given to instruct the scene camera in the real scene to be repaired.

[0078] Specifically, if the adjustment parameter of the virtual camera is a numerical value indicating the deviation, the adjustment parameter can be directly used as the deviation amplitude. For example, if the adjustment parameter includes a difference of 15° to the left, the deviation amplitude is 15°. If the adjustment parameter of the virtual camera is information indicating the adjustment method, the deviation amplitude is determined based on the adjustment method. For example, if the adjustment parameter includes a rotation of 15° in the P direction, it can be indicated that the deviation amplitude is 15°.

[0079] It should be noted that whether to adjust the virtual camera in the building information model can be determined based on the deviation amplitude and deviation threshold of the virtual camera. For slight deviations, the virtual camera in the building information model is adjusted to keep it consistent with the real environment. When the difference is too large, a prompt is given to adjust the scene camera in the real scene to avoid scene camera failure, which may lead to incorrect adjustment of the building information model.

[0080] By using the adjustment method of the building information model provided in the embodiment of this specification, the deviation amplitude of the virtual camera and the scene camera is determined by matching the virtual picture obtained by digital modeling and the real scene picture in the real environment. In the case of a small deviation, the virtual camera in the building information model is automatically adjusted to achieve timely updating of the virtual camera of the building information model in the information management process, maintain the consistency of digital modeling and the real environment, and thus ensure the accuracy of the building information model; in the case of a large deviation, prompts are given in time to repair the scene camera in the real scene.

[0081] The following combination Figure 2 , taking the application of the building information model adjustment method provided in this specification in the rail transit scenario as an example, the building information model adjustment method is further explained. Figure 2 A flowchart of a processing process of a method for adjusting a building information model provided by an embodiment of the present specification is shown, which specifically includes the following steps.

[0082] A station in rail transit has a corresponding building information model created in the information management platform. A camera is set at position A of the station, which can shoot the real video of the station and transmit it to the information management platform through the network. A virtual camera is set at position A in the building information model, which can shoot the virtual picture of the building information model.

[0083] The information management platform can obtain the virtual images captured by the virtual camera and the real video images of the station. Feature points are extracted from the virtual images to obtain virtual feature points, and feature points are extracted from the real video images to obtain scene feature points.

[0084] The virtual feature points and the scene feature points are sampled multiple times respectively, and redundancy removal is performed on the virtual feature points and the scene feature points to obtain updated virtual feature points and updated scene feature points.

[0085] According to the positional relationship of the updated virtual feature points, the corresponding feature points are matched in the updated scene feature points to obtain the matched virtual feature points and the matched scene feature points.

[0086] According to the matching virtual feature points and the matching scene feature points, the transformation parameter matrix of the virtual picture and the real scene picture is determined.

[0087] According to the transformation parameter matrix, the deviation amplitude of the virtual camera relative to the camera is determined, and according to the deviation amplitude, the angle and position of the virtual camera in the building information model are adjusted, or an abnormal prompt is given to prompt maintenance of the camera installed at position A of the station.

[0088] By applying the method for adjusting the building information model provided in the embodiments of this specification, the deviation between the virtual camera and the station camera is determined by matching the virtual picture obtained by digital modeling and the real video picture of the station. According to the deviation, it is determined whether to automatically adjust the virtual camera in the building information model or to issue an abnormal prompt, so as to realize the timely update of the virtual camera of the building information model in the process of information management, maintain the consistency between the digital modeling and the real environment, and thus ensure the accuracy of the building information model.

[0089] Corresponding to the above method embodiment, this specification also provides an embodiment of a device for adjusting a building information model. Figure 3 FIG. 1 is a schematic diagram showing a structure of a device for adjusting a building information model provided by an embodiment of the present specification. Figure 3 As shown, the device comprises: An acquisition module 302 is configured to acquire a virtual image of a building information model and a corresponding real scene image, wherein the virtual image is acquired based on a virtual camera in the building information model, and the real scene image is acquired based on a corresponding scene camera in the real scene; The determination module 304 is configured to match the virtual image with the real scene image and determine the adjustment parameters of the virtual camera; The adjustment module 306 is configured to adjust the virtual camera in the building information model according to the adjustment parameters of the virtual camera.

[0090] Optionally, the determination module 304 is further configured: Extracting virtual feature points in a virtual picture, and extracting scene feature points in a real scene picture; Matching virtual feature points with scene feature points to determine pixel transformation information between the virtual image and the real scene image; According to the pixel transformation information, the adjustment parameters of the virtual camera are determined.

[0091] Optionally, the determination module 304 is further configured: According to the positional relationship of the virtual feature points, the corresponding feature points are matched in the scene feature points to obtain the matched virtual feature points and the matched scene feature points; According to the matching virtual feature points and the matching scene feature points, the pixel transformation information of the virtual picture and the real scene picture is determined.

[0092] Optionally, the determination module 304 is further configured: According to the positional relationship of the first feature point, matching the corresponding second feature point in the scene feature point, wherein the first feature point is any virtual feature point; If the corresponding second feature point is matched, the first feature point is used as the matching virtual feature point, the second feature point is used as the matching scene feature point, and the corresponding relationship between the first feature point and the second feature point is stored; if the corresponding second feature point is not matched, the first feature point is deleted; When the virtual feature points are matched, the remaining unmatched feature points in the scene feature points are deleted.

[0093] Optionally, the determination module 304 is further configured: If the corresponding second feature point is matched, the similarity between the first feature point and the second feature point is determined; When the similarity is greater than the similarity threshold, the first feature point is used as a matching virtual feature point and the second feature point is used as a matching scene feature point; When the similarity is less than or equal to the similarity threshold, the first feature point is deleted.

[0094] Optionally, the determination module 304 is further configured: Sampling the virtual feature points and the scene feature points multiple times, removing redundant feature points from the virtual feature points and the scene feature points, and obtaining updated virtual feature points and updated scene feature points; The updated virtual feature points and the updated scene feature points are matched to determine the pixel transformation information of the virtual picture and the real scene picture.

[0095] Optionally, the determination module 304 is further configured: The virtual feature points and the scene feature points are sampled multiple times respectively to obtain multiple groups of reference virtual feature points and multiple groups of reference scene feature points; respectively determining difference information between a plurality of groups of reference virtual feature points and a plurality of groups of reference scene feature points; According to the difference information and the number of feature points, one group is determined from the multiple groups of reference virtual feature points as the updated virtual feature points, and one group is determined from the multiple groups of reference scene feature points as the updated scene feature points.

[0096] Optionally, the adjustment parameters of the virtual camera include a rotation angle and a translation size; the adjustment module 306 is further configured to: Adjust the current angle and current position of the virtual camera in the building information model according to the rotation angle and translation size.

[0097] Optionally, the adjustment module 306 is further configured to: Determine the deviation amplitude of the virtual camera according to the adjustment parameters of the virtual camera; If the deviation amplitude is less than the deviation threshold, the virtual camera in the building information model is adjusted according to the adjustment parameters of the virtual camera; If the deviation amplitude is greater than or equal to the deviation threshold, an abnormal prompt is issued, wherein the abnormal prompt is used to instruct the scene camera in the real scene to be repaired.

[0098] The adjustment device of the building information model provided by the embodiment of the present specification includes an acquisition module, a determination module, and an adjustment module. Through the interaction and cooperation of the three modules, the virtual picture obtained by digital modeling and the real scene picture in the real environment are matched, and the deviation amplitude of the virtual camera and the scene camera is automatically adjusted in the case of a small deviation, so that the virtual camera of the building information model is updated in time during the information management process, the consistency between the digital modeling and the real environment is maintained, and the accuracy of the building information model is guaranteed; in the case of a large deviation, prompts are given in time to repair the scene camera in the real scene.

[0099] The above is a schematic scheme of a building information model adjustment device of this embodiment. It should be noted that the technical scheme of the building information model adjustment device and the technical scheme of the building information model adjustment method described above belong to the same concept, and the details of the technical scheme of the building information model adjustment device that are not described in detail can all be referred to the description of the technical scheme of the building information model adjustment method described above.

[0100] Figure 4 The block diagram of a computing device according to an embodiment of the present specification is shown. The components of the computing device 400 include but are not limited to a memory 410 and a processor 420. The processor 420 is connected to the memory 410 via a bus 430, and the database 450 is used to store data.

[0101] The computing device 400 also includes an access device 440 that enables the computing device 400 to communicate via one or more networks 460. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 440 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0102] In one embodiment of the present specification, the above components of the computing device 400 and Figure 4 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 4 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0103] The computing device 400 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 400 may also be a mobile or stationary server.

[0104] The processor 420 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned building information model adjustment method.

[0105] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned method for adjusting the building information model belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned method for adjusting the building information model.

[0106] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned building information model adjustment method.

[0107] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned method for adjusting the building information model belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned method for adjusting the building information model.

[0108] An embodiment of the present specification further provides a computer program product, including a computer program / instruction, which implements the steps of the above-mentioned building information model adjustment method when executed by a processor.

[0109] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above-mentioned method for adjusting the building information model belong to the same concept, and the details not described in detail in the technical scheme of the computer program can be referred to the description of the technical scheme of the above-mentioned method for adjusting the building information model.

[0110] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0111] Computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. Computer readable media may include: any entity or device capable of carrying computer program codes, recording media, USB flash drives, mobile hard disks, magnetic disks, optical disks, computer memories, read-only memories (ROM), random access memories (RAM), electric carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the contents of computer readable media may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0112] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0113] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0114] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A method for adjusting a building information model, characterized in that: include: Acquire a virtual picture of a building information model and a corresponding real scene picture, wherein the virtual picture is obtained based on a virtual camera in the building information model, and the real scene picture is obtained based on a corresponding scene camera in the real scene; Matching the virtual image with the real scene image to determine adjustment parameters of the virtual camera; The virtual camera in the building information model is adjusted according to the adjustment parameters of the virtual camera.

2. The method according to claim 1, characterized in that The performing picture matching on the virtual picture and the real scene picture to determine the adjustment parameters of the virtual camera includes: Extracting virtual feature points in the virtual picture, and extracting scene feature points in the real scene picture; Matching the virtual feature points with the scene feature points to determine pixel transformation information of the virtual picture and the real scene picture; According to the pixel transformation information, adjustment parameters of the virtual camera are determined.

3. The method according to claim 2, characterized in that The matching of the virtual feature points with the scene feature points to determine pixel transformation information of the virtual picture and the real scene picture includes: According to the positional relationship of the virtual feature points, corresponding feature points are matched in the scene feature points to obtain matched virtual feature points and matched scene feature points; Pixel transformation information of the virtual picture and the real scene picture is determined according to the matched virtual feature points and the matched scene feature points.

4. The method according to claim 3, characterized in that The step of matching corresponding feature points in the scene feature points according to the positional relationship of the virtual feature points to obtain matching virtual feature points and matching scene feature points includes: According to the positional relationship of the first feature point, matching the corresponding second feature point in the scene feature point, wherein the first feature point is any of the virtual feature points; If the corresponding second feature point is matched, the first feature point is used as a matching virtual feature point, the second feature point is used as a matching scene feature point, and the corresponding relationship between the first feature point and the second feature point is stored; if the corresponding second feature point is not matched, the first feature point is deleted; When the virtual feature points are matched, the remaining unmatched feature points in the scene feature points are deleted.

5. The method according to claim 4, characterized in that If the corresponding second feature point is matched, the first feature point is used as a matching virtual feature point and the second feature point is used as a matching scene feature point, including: If a corresponding second feature point is matched, determining the similarity between the first feature point and the second feature point; When the similarity is greater than a similarity threshold, taking the first feature point as a matching virtual feature point and taking the second feature point as a matching scene feature point; When the similarity is less than or equal to a similarity threshold, the first feature point is deleted.

6. The method according to claim 2, characterized in that The matching of the virtual feature points with the scene feature points to determine pixel transformation information of the virtual picture and the real scene picture includes: Sampling the virtual feature points and the scene feature points multiple times, removing redundant feature points from the virtual feature points and the scene feature points, and obtaining updated virtual feature points and updated scene feature points; The updated virtual feature points and the updated scene feature points are matched to determine pixel transformation information of the virtual picture and the real scene picture.

7. The method according to claim 6, characterized in that The step of sampling the virtual feature points and the scene feature points for multiple times, removing redundant feature points from the virtual feature points and the scene feature points, and obtaining updated virtual feature points and updated scene feature points includes: Sampling the virtual feature points and the scene feature points multiple times respectively to obtain multiple groups of reference virtual feature points and multiple groups of reference scene feature points; respectively determining difference information between the multiple groups of reference virtual feature points and the multiple groups of reference scene feature points; According to the difference information and the number of feature points, one group is determined from the multiple groups of reference virtual feature points as the updated virtual feature points, and one group is determined from the multiple groups of reference scene feature points as the updated scene feature points.

8. The method according to any one of claims 1 to 7, characterized in that: The adjustment parameters of the virtual camera include a rotation angle and a translation size; and adjusting the virtual camera in the building information model according to the adjustment parameters of the virtual camera includes: According to the rotation angle and the translation size, the current angle and the current position of the virtual camera in the building information model are adjusted.

9. The method according to any one of claims 1 to 7, characterized in that: The step of adjusting the virtual camera in the building information model according to the adjustment parameters of the virtual camera includes: Determining a deviation amplitude of the virtual camera according to an adjustment parameter of the virtual camera; If the deviation amplitude is less than the deviation threshold, adjusting the virtual camera in the building information model according to the adjustment parameters of the virtual camera; If the deviation amplitude is greater than or equal to the deviation threshold, an abnormal prompt is issued, wherein the abnormal prompt is used to instruct the scene camera in the real scene to be repaired.

10. A device for adjusting a building information model, characterized in that: include: An acquisition module is configured to acquire a virtual image of a building information model and a corresponding real scene image, wherein the virtual image is acquired based on a virtual camera in the building information model, and the real scene image is acquired based on a corresponding scene camera in the real scene; A determination module is configured to match the virtual picture with the real scene picture to determine the adjustment parameters of the virtual camera; The adjustment module is configured to adjust the virtual camera in the building information model according to the adjustment parameters of the virtual camera.

11. A computing device, characterized in that: include: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the method for adjusting the building information model described in any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, implement the steps of the method for adjusting the building information model described in any one of claims 1 to 9.

13. A computer program product, characterized in that The invention comprises a computer program / instruction, which, when executed by a processor, implements the steps of the method for adjusting the building information model according to any one of claims 1 to 9.

Images