WO2020228326A1

WO2020228326A1 - Visual three-dimensional scanning modeling method, system and device, and storage medium

Info

Publication number: WO2020228326A1
Application number: PCT/CN2019/126980
Authority: WO
Inventors: 李新福
Original assignee: 广东康云科技有限公司
Priority date: 2019-05-14
Filing date: 2019-12-20
Publication date: 2020-11-19
Also published as: CN110322544A

Abstract

A visual three-dimensional scanning modeling method, system and device, and a storage medium. The visual three-dimensional scanning modeling method comprises: acquiring three-dimensional scanning data of a scene, and also carrying out edge computing processing on the three-dimensional scanning data to obtain a three-dimensional model (S110); and displaying or storing the three-dimensional model and the generation process of the three-dimensional model in real time (S120). According to the method, a scanning device itself can achieve computing while scanning, thereby shortening the time consumed for generating all three-dimensional models, and the requirements of real-time visual monitoring and quick acquisition of intelligent analysis results of the three-dimensional models can be met.

Description

A visual three-dimensional scanning modeling method, system, equipment and storage medium

Technical field

The invention relates to the technical field of digital modeling, in particular to a visual three-dimensional scanning modeling method, system, equipment and storage medium.

Background technique

Digital modeling technology, especially 3D scanning modeling technology, has been gradually applied in many industries, such as cultural relics restoration, accident reproduction, and reverse engineering. Three-dimensional scanning modeling technology usually refers to obtaining the shape data of an object through a scanning device, and modeling the obtained data information to form an overall three-dimensional data file.

However, the current 3D scanning modeling technology generally has the problem of low modeling efficiency. For example, using laser scanning to acquire as many as one billion data points in more than 50 locations of a building and model it will take several years. Long. In addition, after the three-dimensional digital model is generated, further identification and judgment are often required. In some occasions where it is necessary to obtain relevant information of the 3D digital model as soon as possible (for example, in the case of an emergency, the emergency department needs to know the information of the surrounding environment as soon as possible in order to act quickly), the current 3D scanning modeling technology cannot realize real-time visualization. Seriously restrict the progress of follow-up work.

Summary of the invention

In order to solve the above technical problems, the embodiments of the present application provide a method, system, equipment and storage medium for visualized 3D scanning modeling, which improves the efficiency of 3D scanning modeling and can realize real-time visualized monitoring.

In the first aspect, an embodiment of the present application provides a visualized 3D scanning modeling method, including the following steps:

Acquire 3D scan data of the scene, and simultaneously perform edge calculation processing on the 3D scan data to obtain a 3D model;

The three-dimensional model and the generation process of the three-dimensional model are displayed or stored in real time.

Further, the visualization 3D scanning modeling method also includes:

Obtain point cloud data and perform point cloud segmentation processing on the point cloud data to obtain a point cloud;

Using artificial intelligence algorithms to perform intelligent analysis and processing on point clouds, intelligent analysis and processing includes identifying the type and quantity of objects, and analyzing and judging the relationship between different objects.

Further, the visualized 3D scanning modeling method further includes: displaying or storing the results of point cloud segmentation processing and intelligent analysis processing in real time.

Further, the visualized 3D scanning modeling method further includes: sending the 3D model, the generation process of the 3D model, the result of the point cloud segmentation processing, and the result of the intelligent analysis processing to the server in real time.

Further, analyzing and judging the relationship between different objects further includes: analyzing and judging whether the distance between the boundaries of different objects reaches a preset threshold.

Further, the step of acquiring three-dimensional scan data of the scene and simultaneously performing edge calculation processing on the three-dimensional scan data to obtain a three-dimensional model further includes:

Performing a first processing operation on the three-dimensional scan data, the first processing operation including denoising processing, UV optimization processing, and anti-aliasing processing;

Perform a second processing operation on the 3D scan data to obtain the original 3D model data. The second processing operation includes sharpening processing, image denoising processing, saturation optimization processing, image HDR optimization processing, coloring processing, and model repair processing And rendering optimization processing, the second processing operation adopts artificial intelligence algorithm for image processing;

The original three-dimensional model data is compressed to obtain compressed three-dimensional model data.

Further, the step of acquiring the three-dimensional scan data of the scene and simultaneously performing edge calculation processing on the three-dimensional scan data to obtain a three-dimensional model is specifically:

Acquire three-dimensional scan data of the scene through a scanning device, the scanning device including an aerial scanning device, a human body scanning device, an object scanning device, an indoor scanning device, and an outdoor scanning device, the scanning device is equipped with a graphics processor;

The graphics processor of the scanning device uses an artificial intelligence algorithm to perform edge calculation processing on the three-dimensional scan data to obtain a three-dimensional model.

In the second aspect, an embodiment of the present application provides a visualized 3D scanning modeling system, including:

The three-dimensional modeling module is used to obtain three-dimensional scan data of the scene, and simultaneously perform edge calculation processing on the three-dimensional scan data to obtain a three-dimensional model;

The visualization module is used to display or store the three-dimensional model and the generation process of the three-dimensional model in real time.

In a third aspect, an embodiment of the present application provides a visualized 3D scanning modeling device, including:

At least one processor;

At least one memory for storing at least one program;

The at least one program is executed by the at least one processor, so that the at least one processor implements the visual three-dimensional scanning modeling method according to any of the foregoing technical solutions.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium in which instructions executable by a processor are stored, and the instructions executable by the processor are used to implement any of the foregoing technical solutions when executed by the processor The described visualization three-dimensional scanning modeling method.

The beneficial effects of the embodiments of the present application include at least the following: edge computing processing enables the scanning device itself to build a three-dimensional model by scanning and computing, thereby reducing the time-consuming generation of all three-dimensional models and improving the efficiency of three-dimensional scanning modeling . In addition, displaying or storing the 3D model and the generation process of the 3D model in real time can meet the needs of real-time visual monitoring and obtaining the intelligent analysis results of the 3D model as soon as possible.

Description of the drawings

Fig. 1 is a flowchart of a method for visualized 3D scanning modeling in an embodiment of the application;

2 is a flowchart of another method for visualized 3D scanning modeling in an embodiment of the application;

FIG. 3 is a flowchart of yet another method for visualized 3D scanning modeling in an embodiment of the application;

4 is a flowchart of yet another method for visualized 3D scanning modeling in an embodiment of the application;

FIG. 5 is a specific flowchart of the three-dimensional modeling process in an embodiment of the application;

Fig. 6 is a structural block diagram of a visualized 3D scanning modeling system in an embodiment of the application.

Detailed ways

In the following, the concept, specific structure and technical effects of the present invention will be clearly and completely described in conjunction with the embodiments and the drawings, so as to fully understand the objectives, solutions and effects of the present invention.

It should be noted that, unless otherwise specified, when a feature is called "fixed" or "connected" to another feature, it can be directly fixed and connected to another feature, or indirectly fixed or connected to another feature. One feature. In addition, the top, bottom, left, right and other descriptions used in the present disclosure are only relative to the mutual positional relationship of the components of the present disclosure in the drawings. The singular forms of "a", "said" and "the" used in the present disclosure are also intended to include plural forms, unless the context clearly indicates other meanings. In addition, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art. The terms used in this specification are only for describing specific embodiments, not for limiting the present invention. The term "and/or" as used herein includes any combination of one or more related listed items.

It should be understood that, although the terms first, second, third, etc. may be used in this disclosure to describe various elements, these elements should not be limited to these terms. These terms are only used to distinguish elements of the same type from each other. For example, without departing from the scope of the present disclosure, the first element may also be referred to as the second element, and similarly, the second element may also be referred to as the first element. The use of any and all examples or exemplary language ("such as", "such as", etc.) provided herein is only intended to better illustrate the embodiments of the present invention, and unless otherwise required, will not impose limitations on the scope of the present invention .

The embodiments of the present application mainly relate to scanning equipment, servers, and user-side display devices.

Among them, the scanning device is used to scan scenes such as industrial parks or indoors, and is especially suitable for areas where the conventional method of scanning and modeling takes a long time due to the large area. The scanned objects in the scene include stationary objects and moving objects. The scanning device may be an aerial scanning device, an indoor scanning device, or an outdoor scanning device. The scanning device is configured with a graphics processor, a display device, and a storage device. Scanning equipment is also used for 3D model generation, point cloud segmentation processing, and intelligent analysis processing.

The server is used to receive the results of the 3D model, the results of the point cloud segmentation processing, and the intelligent analysis processing results, etc., and send them to the user-side display device.

The user-side display device is used to display the three-dimensional model of the scene and the result of intelligent recognition. The display device can use any of AR display devices, VR display devices, mobile terminals, tablet computers, PC computers, air screens, LED displays, LCD displays, OLED displays, and dot matrix displays.

In the first aspect, referring to FIG. 1, an embodiment of the present application provides a visualized 3D scanning modeling method. The visual 3D scanning modeling method includes the following steps:

S110: Acquire three-dimensional scan data of the scene, and simultaneously perform edge calculation processing on the three-dimensional scan data to obtain a three-dimensional model;

S120, displaying or storing the three-dimensional model and the process of generating the three-dimensional model in real time.

Edge Computing (Edge Computing) refers to performing local calculation and analysis on the side close to the data source near the terminal device. The difference is cloud computing, which makes it possible to store and process data through a remote server network (also known as the "cloud") or perform other computing tasks in addition to its own physical hardware. Edge computing reduces the transmission of data back and forth between the clouds, making the storage and processing of data closer to the terminal, so the real-time computing is higher.

Specifically, the scanning device scans the scene. The scene is, for example, the interior and surrounding environment of a building, a park, a block, a mountain forest or even a large outdoor area. The scanning device itself obtains the generated 3D scan data of a part of the scene, and the edge calculation processing can obtain a corresponding part of the 3D model. As the 3D data of the scene is completely scanned, all 3D models of the scene are also generated.

Edge computing processing does not have to wait for all scan data to be uploaded to the server, and the server performs three-dimensional modeling. On the contrary, the edge calculation processing enables the scanning device itself to participate in the calculation processing of the 3D modeling, and realizes the calculation while scanning, thereby shortening the time-consuming generation of all 3D models and improving the efficiency of 3D scanning modeling. In addition, real-time display or storage of the 3D model and the generation process of the 3D model realizes real-time visual observation and monitoring, so that you can perform subsequent intelligent analysis and processing based on the 3D model without waiting for the generation of all 3D models, so as to obtain the 3D digital model as soon as possible. Related information needs.

In some alternative embodiments, the scanning device uses edge computing to process a part of the three-dimensional scan data (for example, about 75% of the three-dimensional scan data) to obtain a part of the three-dimensional model, and the server analyzes the other part of the received The three-dimensional scan data (for example, approximately 25% of the three-dimensional scan data) is subjected to arithmetic processing to obtain another part of the three-dimensional model. Integrate the three-dimensional models of the above two parts to obtain a complete three-dimensional model. The scanning device and the server cooperate to complete the entire 3D scanning modeling work, which can combine the respective advantages of edge computing and cloud computing.

In some other embodiments, referring to FIG. 2, the visual 3D scanning modeling method further includes the following steps:

S130: Obtain point cloud data and perform point cloud segmentation processing on the point cloud data to obtain a point cloud;

S140, using an artificial intelligence algorithm to perform intelligent analysis and processing on the point cloud. The intelligent analysis processing includes identifying the type and quantity of objects, and analyzing and judging the relationship between different objects.

Specifically, in this embodiment, the point cloud of an object in the scene is segmented according to the relationship between the points in the point cloud data and the neighboring points. Based on this relationship, the points that meet the division criteria are divided into the same type of point cloud. For example, a point whose distance to a certain point is within a preset threshold can be included in the point cloud to which the point belongs. Optionally, the classification criteria may also be attributes such as color or size.

In this embodiment, according to the input samples and tags, artificial intelligence algorithms are used to train the point cloud recognition model; the point cloud of the object in the scene is input into the point cloud recognition model to identify the type of the point cloud of the object in the scene; The number of point clouds of the type object, thereby determining the number of objects. The input sample is the point cloud data of a predetermined object, or the point cloud data of a newly generated object after training and recognition. Through continuous self-learning and updating, the accuracy and accuracy of the recognition model can be improved. The tag is used to identify the type of point cloud data in the sample, and the point cloud data in the input sample and the corresponding type are known.

Intelligent analysis processing not only recognizes the type and quantity of objects, but also analyzes the positional relationship and size relationship between the objects. After the 3D model is generated, point cloud segmentation and intelligent analysis processing are performed, so that the entire 3D model generation process will not take too much time due to point cloud segmentation and intelligent analysis processing, thereby improving the efficiency of 3D scanning modeling . At the same time, point cloud segmentation processing and intelligent analysis processing facilitate the use of three-dimensional models to read relevant information and make judgments, such as locating the location of a target, or whether the branches and leaves of trees have touched high-voltage power lines.

In some other embodiments, referring to FIG. 3, the visual 3D scanning modeling method further includes the following steps:

S150, displaying or storing the result of point cloud segmentation processing and the result of intelligent analysis processing in real time.

Specifically, the scanning device itself or other non-server equipment (wired or wirelessly connected to the scanning device) is provided with a display device or a storage device. The display device can choose any of AR display equipment, VR display equipment, mobile terminal screens, tablet computer screens, PC computer screens, air screens, LED displays, LCD displays, OLED displays, and dot matrix displays. ; Or, store the results of the point cloud segmentation processing and the results of the intelligent analysis processing in the scanning device itself or other non-server-side devices, and leave them for reading analysis by the reading device.

Display or store the results of point cloud segmentation processing and intelligent analysis processing in real time, so that the point cloud segmentation processing and intelligent analysis processing are also visualized in real time. Display or store the results of intelligent analysis processing in real time, without waiting for the completion of all intelligent analysis processing of the entire scene. Even for the intelligent analysis and processing of a specific object, there is no need to wait for the completion of all intelligent analysis and processing of the object, and follow-up actions can be carried out after obtaining the required relevant information. For example, if a suspect hides in a certain location in a certain mountain forest, after the aerial scanning equipment scans and generates a three-dimensional model of the mountain forest, the aerial scanning equipment also displays or stores the results of intelligent analysis and processing in real time. After the suspect’s hiding location can be determined based on the results of real-time intelligent analysis and processing, there is no need to wait for the intelligent analysis and processing of other areas in the mountain forest to be completed, and a message notification can be sent to remind relevant personnel.

In other embodiments, referring to FIG. 4, the visual 3D scanning modeling method further includes the following steps:

S160: Send the three-dimensional model, the generation process of the three-dimensional model, the result of the point cloud segmentation processing, and the result of the intelligent analysis processing to the server in real time.

Specifically, the scanning device or other non-server device is connected to the server through a wired connection or a wireless connection, so as to transmit the 3D model, the generation process of the 3D model, the result of the point cloud segmentation processing, and the intelligence to the server. Analysis and processing results.

The results of point cloud segmentation processing and intelligent analysis processing are sent to the server in real time, and the above results can be sent to the mobile terminal or PC computer terminal again through the server, so that the user can view and analyze the above results.

In other embodiments,

Analyze and judge the relationship between different objects, including the following steps:

S1401: Analyze and determine whether the distance between the boundaries of different objects reaches a preset threshold.

Specifically, the boundaries of pixels of different objects are analyzed to determine whether the distance between the boundaries is smaller than a preset threshold. For example, analyze whether the pixel boundary between a certain tree and its neighboring poles is less than a preset threshold of 0.5 meters. If it is less than this value, it means that the branches and leaves of the tree are too close to the telephone poles, and relevant personnel should be notified to trim the branches and leaves.

By judging the distance between the boundaries of different objects, the positional relationship between different objects can be confirmed, so as to provide a comprehensive judgment for the monitoring and early warning of the entire scene (for example, an industrial park).

In other embodiments, referring to FIG. 5, the step of acquiring three-dimensional scan data of the scene and simultaneously performing edge calculation processing on the three-dimensional scan data to obtain a three-dimensional model further includes:

S1101: Perform a first processing operation on the three-dimensional scan data, where the first processing operation includes denoising processing, UV optimization processing, and anti-aliasing processing;

S1102. Perform a second processing operation on the three-dimensional scan data to obtain original three-dimensional model data. The second processing operation includes sharpening processing, picture denoising processing, saturation optimization processing, picture HDR optimization processing, coloring processing, and model Repair processing and rendering optimization processing, the second processing operation adopts artificial intelligence algorithm for image processing;

S1103: Compress the original three-dimensional model data to obtain compressed three-dimensional model data.

Specifically, the artificial intelligence algorithm includes a deep learning algorithm, and the deep learning algorithm uses a generative confrontation network model;

The core of Generative Adversarial Nets is adversarial. There are two networks competing with each other, one is responsible for generating samples (Generator), and the other is responsible for discriminating samples (Discriminator).

3D scanning modeling adopts artificial intelligence algorithms, which can further improve the efficiency of 3D modeling on the basis of edge computing processing. In other words, edge computing enables scanning equipment to also participate in the calculation processing of 3D modeling, thereby improving the efficiency of 3D modeling; artificial intelligence algorithms implement machine learning through training models, abandoning manual 3D modeling processing methods, and can achieve faster calculations Speed, thereby improving the efficiency of 3D modeling.

In other embodiments, the type of data sent to the server includes at least one of the following types: audio data, video data, image data, and text data.

Specifically, the results of the point cloud segmentation processing and the intelligent analysis processing are sent to the server in the form of audio data, video data, picture data, and text data, and the server sends the above data to the user's AR display device, VR display device, Any of mobile terminal screens, tablet computer screens, PC computer screens, air screens, LED displays, LCD displays, OLED displays, and dot matrix displays.

Use one of the above data types to send the results of point cloud segmentation processing and intelligent analysis processing to the server, so that the results of point cloud segmentation processing and intelligent analysis processing sent by the server to the user are more vivid, intuitive, and richer. Further enhance the effect of real-time monitoring.

In some other embodiments, the step of acquiring three-dimensional scan data of the scene and simultaneously performing edge calculation processing on the three-dimensional scan data to obtain a three-dimensional model is specifically:

Graphics Processing Unit (GPU), also known as display core, visual processor or display chip, is a kind of specialized in personal computers, workstations, game consoles or some mobile devices (such as tablet computers, smart phones, etc.) On the microprocessor that realizes the image operation. With a graphics processor, the CPU can be freed from graphics processing tasks and perform more system tasks, thereby greatly improving the overall performance of the computer.

Specifically, the scanning device has a built-in graphics processor, and the graphics processor performs edge calculation processing on the three-dimensional scan data in real time to obtain a three-dimensional model. For example, an aerial scanning device has a built-in graphics processor, and the graphics processor is embedded with artificial intelligence algorithms, so that the aerial scanning device itself can perform 3D modeling calculation processing based on artificial intelligence algorithms, and the entire 3D modeling work is more efficient.

The graphics processor is embedded in the scanning device, so that the scanning device performs calculation while scanning, which greatly improves the efficiency of 3D scanning modeling. The graphics processor can process graphics and image data very fast, which provides a powerful guarantee for the real-time performance of visualized 3D scanning modeling. The graphics processor is embedded with artificial intelligence algorithms, which greatly accelerates the calculation and processing speed of 3D scanning modeling.

In the second aspect, referring to FIG. 6, an embodiment of the present application also provides a visualized 3D scanning modeling system, including:

The three-dimensional modeling module 10 is used to obtain three-dimensional scan data of the scene, and simultaneously perform edge calculation processing on the three-dimensional scan data to obtain a three-dimensional model;

The visualization module 20 is used to display or store the three-dimensional model and the generation process of the three-dimensional model in real time.

The contents in the foregoing method embodiments are all applicable to the corresponding system embodiments. Therefore, the specific functions implemented by this system embodiment are the same as the foregoing method embodiments, and the beneficial effects achieved are also the same as the foregoing method embodiments.

It can be understood that corresponding to any of the foregoing method embodiments, there are corresponding system embodiments, which are not repeated here.

In a third aspect, an embodiment of the present application also provides a visualized 3D scanning modeling device, including:

At least one processor;

At least one memory for storing at least one program;

The contents in the foregoing method embodiments are all applicable to the corresponding device embodiments. Therefore, the specific functions implemented by this device embodiment are the same as the foregoing method embodiments, and the beneficial effects achieved are also the same as the foregoing method embodiments.

In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium, in which instructions executable by a processor are stored, and the instructions executable by the processor are used to implement any of the foregoing technologies when executed by the processor. The visual 3D scanning modeling method described in the scheme.

The contents in the foregoing method embodiments are all applicable to the corresponding storage medium embodiments, so the specific functions implemented by this storage medium embodiment are the same as the foregoing method embodiments, and the beneficial effects achieved are also the same as the foregoing method embodiments.

Taking the 3D scanning modeling of a certain area on both sides of the highway as an example, the specific implementation steps of the technical solution of this application are as follows:

Step 1: The aerial scanning equipment scans the area to obtain the 3D scanning data of the area. At the same time, the graphics processor of the aerial scanning equipment performs edge calculation on the 3D scanning data to obtain a 3D model;

Step 2: Obtain point cloud data and perform point cloud segmentation processing on the point cloud data to obtain point clouds, such as the point cloud of trees and the point cloud of telephone poles;

Step 3: Use artificial intelligence algorithms to perform intelligent analysis and processing on the point cloud. The intelligent analysis processing includes identifying the type and number of objects (such as the number of trees and the number of telephone poles), and analyzing and judging whether the distance between the boundaries of different objects has reached A preset threshold (for example, is the distance between the boundaries of the tree image and the pixel of the telephone pole image less than 0.5 meters).

Step 4: The display device of the aerial scanning equipment displays the results of point cloud segmentation processing and intelligent analysis processing in real time. At the same time, the aerial scanning equipment also has a storage device that can store the results of point cloud segmentation processing and intelligent analysis processing in real time the result of.

Step 5: Send the result of the point cloud segmentation processing and the result of the intelligent analysis processing to the server in real time. The sending form includes video form, audio form, picture form and text form. The server sends the results of intelligent analysis and processing (for example, trees and telephone poles have been completely in contact, and there may be potential accidents) in the form of video, picture, voice prompt or short message to the user's mobile phone or computer.

It can be understood by those skilled in the art that the above steps can be changed in order or processed in parallel as needed in actual operation. The above steps are repeated until the three-dimensional modeling and intelligent analysis of the entire outdoor park are completed.

It should be recognized that the embodiments of the present application can be realized or implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The method can be implemented in a computer program using standard programming techniques-including a non-transitory computer readable storage medium configured with a computer program, where the storage medium so configured allows the computer to operate in a specific and predefined manner-according to the specific The methods and drawings described in the examples. Each program can be implemented in a high-level process or object-oriented programming language to communicate with the computer system. However, if necessary, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.

In addition, the operations of the processes described herein may be performed in any suitable order, unless otherwise indicated herein or otherwise clearly contradictory to the context. The processes (or variants and/or combinations thereof) described herein can be executed under the control of one or more computer systems configured with executable instructions, and can be used as code (for example, , Executable instructions, one or more computer programs, or one or more applications), implemented by hardware or a combination thereof. The computer program includes a plurality of instructions executable by one or more processors.

Further, the method can be implemented in any type of computing platform that is operatively connected to a suitable computing platform, including but not limited to personal computers, mini computers, main frames, workstations, networks or distributed computing environments, standalone or integrated Computer platform, or communication with charged particle tools or other imaging devices, etc. Aspects of the application can be implemented by machine-readable codes stored on non-transitory storage media or devices, whether removable or integrated into computing platforms, such as hard disks, optical reading and/or writing storage media, RAM, ROM, etc., so that they can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the processes described herein. In addition, the machine-readable code, or part thereof, can be transmitted through a wired or wireless network. When such a medium includes instructions or programs that implement the steps described above in combination with a microprocessor or other data processor, the invention described herein includes these and other different types of non-transitory computer-readable storage media. When programming according to the methods and techniques described in this application, this application also includes the computer itself.

A computer program can be applied to input data to perform the functions described herein, thereby converting the input data to generate output data that is stored in non-volatile memory. The output information can also be applied to one or more output devices such as displays. In a preferred embodiment of the present application, the converted data represents physical and tangible objects, including specific visual depictions of physical and tangible objects generated on the display.

The above are only preferred embodiments of this application. This application is not limited to the above implementations, as long as it achieves the technical effects of this application by the same means, everything done within the spirit and principle of this application Any modifications, equivalent replacements, improvements, etc. of, shall be included in the scope of protection of this application. Within the protection scope of this application, its technical solutions and/or implementations can have various modifications and changes.

Claims

A visual three-dimensional scanning modeling method, which is characterized in that it comprises the following steps:

Acquire 3D scan data of the scene, and simultaneously perform edge calculation processing on the 3D scan data to obtain a 3D model;

The three-dimensional model and the generation process of the three-dimensional model are displayed or stored in real time.
The visual 3D scanning modeling method according to claim 1, wherein the visual 3D scanning modeling method further comprises:

Acquiring point cloud data and performing point cloud segmentation processing on the point cloud data to obtain a point cloud;

An artificial intelligence algorithm is used to perform intelligent analysis and processing on the point cloud. The intelligent analysis and processing includes identifying the type and quantity of objects, and analyzing and judging the relationship between different objects.
The visualized 3D scanning modeling method according to claim 2, further comprising: displaying or storing the result of the point cloud segmentation processing and the result of the intelligent analysis processing in real time.
The visualized 3D scanning modeling method according to claim 3, further comprising: sending the 3D model, the generation process of the 3D model, the result of the point cloud segmentation processing, and the Intelligent analysis and processing results.
The visual three-dimensional scanning modeling method according to claim 3 or 4, wherein the analyzing and judging the relationship between different objects further comprises: analyzing and judging whether the distance between the boundaries of different objects reaches a preset threshold.
The visualized 3D scanning modeling method according to claim 1, wherein the step of obtaining 3D scanning data of the scene and performing edge calculation processing on the 3D scanning data at the same time to obtain a 3D model further comprises:

Performing a first processing operation on the three-dimensional scan data, the first processing operation including denoising processing, UV optimization processing, and anti-aliasing processing;

Perform a second processing operation on the 3D scan data to obtain the original 3D model data. The second processing operation includes sharpening processing, image denoising processing, saturation optimization processing, image HDR optimization processing, coloring processing, and model repair processing And rendering optimization processing, the second processing operation adopts artificial intelligence algorithm for image processing;

The original three-dimensional model data is compressed to obtain compressed three-dimensional model data.
The visualized 3D scanning modeling method according to claim 6, wherein the step of obtaining 3D scanning data of the scene and performing edge calculation processing on the 3D scanning data at the same time to obtain a 3D model is specifically:

Acquire three-dimensional scan data of the scene through a scanning device, the scanning device including an aerial scanning device, a human body scanning device, an object scanning device, an indoor scanning device, and an outdoor scanning device, the scanning device is equipped with a graphics processor;

The graphics processor of the scanning device uses an artificial intelligence algorithm to perform edge calculation processing on the three-dimensional scan data to obtain a three-dimensional model.
A visualized 3D scanning modeling system, which is characterized in that it includes:

The three-dimensional modeling module is used to obtain three-dimensional scan data of the scene, and simultaneously perform edge calculation processing on the three-dimensional scan data to obtain a three-dimensional model;

The visualization module is used to display or store the three-dimensional model and the generation process of the three-dimensional model in real time.
A visualized 3D scanning modeling device, which is characterized in that it includes:

At least one processor;

At least one memory for storing at least one program;

The at least one program is executed by the at least one processor, so that the at least one processor implements the visual three-dimensional scanning modeling method according to any one of claims 1-7.
A computer-readable storage medium, wherein instructions executable by a processor are stored, wherein the instructions executable by the processor are used to implement the instructions as described in any one of claims 1-7 when executed by the processor. The described visualization 3D scanning modeling method.