WO2020215858A1 - 基于虚拟环境的物体构建方法、装置、计算机设备及可读存储介质 - Google Patents

基于虚拟环境的物体构建方法、装置、计算机设备及可读存储介质 Download PDF

Info

Publication number
WO2020215858A1
WO2020215858A1 PCT/CN2020/074910 CN2020074910W WO2020215858A1 WO 2020215858 A1 WO2020215858 A1 WO 2020215858A1 CN 2020074910 W CN2020074910 W CN 2020074910W WO 2020215858 A1 WO2020215858 A1 WO 2020215858A1
Authority
WO
WIPO (PCT)
Prior art keywords
point cloud
collected
frames
images
voxel
Prior art date
Application number
PCT/CN2020/074910
Other languages
English (en)
French (fr)
Inventor
沈超
Original Assignee
腾讯科技（深圳）有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Priority to EP20794587.4A priority Critical patent/EP3960261A4/en
Publication of WO2020215858A1 publication Critical patent/WO2020215858A1/zh
Priority to US17/345,366 priority patent/US12059615B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/60—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor
    • A63F13/63—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor by the player, e.g. authoring using a level editor
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/50—Controlling the output signals based on the game progress
    • A63F13/52—Controlling the output signals based on the game progress involving aspects of the displayed game scene
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F13/00—Video games, i.e. games using an electronically generated display having two or more dimensions
    • A63F13/60—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor
    • A63F13/65—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor automatically by game devices or servers from real world data, e.g. measurement in live racing competition
    • A63F13/655—Generating or modifying game content before or while executing the game program, e.g. authoring tools specially adapted for game development or game-integrated level editor automatically by game devices or servers from real world data, e.g. measurement in live racing competition by importing photos, e.g. of the player
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating 3D models or images for computer graphics
    • G06T19/20—Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/55—Depth or shape recovery from multiple images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/55—Depth or shape recovery from multiple images
    • G06T7/564—Depth or shape recovery from multiple images from contours
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
    • A63F2300/60—Methods for processing data by generating or executing the game program
    • A63F2300/6009—Methods for processing data by generating or executing the game program for importing or creating game content, e.g. authoring tools during game development, adapting content to different platforms, use of a scripting language to create content
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63F—CARD, BOARD, OR ROULETTE GAMES; INDOOR GAMES USING SMALL MOVING PLAYING BODIES; VIDEO GAMES; GAMES NOT OTHERWISE PROVIDED FOR
    • A63F2300/00—Features of games using an electronically generated display having two or more dimensions, e.g. on a television screen, showing representations related to the game
    • A63F2300/60—Methods for processing data by generating or executing the game program
    • A63F2300/69—Involving elements of the real world in the game world, e.g. measurement in live races, real video
    • A63F2300/695—Imported photos, e.g. of the player
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2200/00—Indexing scheme for image data processing or generation, in general
    • G06T2200/24—Indexing scheme for image data processing or generation, in general involving graphical user interfaces [GUIs]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30244—Camera pose
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2210/00—Indexing scheme for image generation or computer graphics
    • G06T2210/12—Bounding box
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2210/00—Indexing scheme for image generation or computer graphics
    • G06T2210/56—Particle system, point based geometry or rendering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
    • G06T2219/20—Indexing scheme for editing of 3D models
    • G06T2219/2008—Assembling, disassembling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
    • G06T2219/20—Indexing scheme for editing of 3D models
    • G06T2219/2012—Colour editing, changing, or manipulating; Use of colour codes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
    • G06T2219/20—Indexing scheme for editing of 3D models
    • G06T2219/2024—Style variation

Definitions

  • the embodiments of the present application relate to the field of virtual environments, and in particular, to a method, device, computer equipment, and readable storage medium for building objects based on a virtual environment.
  • Sandbox game is a game mode in which players use the voxel blocks provided in the game to create original objects and interact with the created original objects.
  • the voxel blocks provided in the sandbox game can be classified by materials
  • the voxel block can also be a voxel block classified by color, such as: coal voxel block, diamond voxel block, brick voxel block, etc., or red voxel block, green voxel block are provided in the sandbox game , Purple voxel blocks, etc.
  • players use voxel blocks classified by color to build colorful scenes such as decorations and billboards in a sandbox game environment.
  • the player first determines the overall style of the decorative objects to be built, and stacks voxel blocks of different colors at corresponding positions of the style according to the overall style, and obtains the decorative object after stacking.
  • a method, device, computer equipment, and readable storage medium based on a virtual environment are provided.
  • the environment interface includes a screen corresponding to the virtual environment
  • the shooting operation is used to collect three-dimensional information of the object to be collected through the camera to obtain a feature point cloud of the object to be collected, and the feature point cloud is used to determine the style of the target object to be constructed ;
  • An object construction device based on a virtual environment which is applied to a terminal provided with a camera, and includes:
  • a display module for displaying an environment interface, the environment interface including a picture corresponding to the virtual environment
  • the receiving module is configured to receive a shooting operation for collecting three-dimensional information of the object to be collected through the camera to obtain a feature point cloud of the object to be collected, and the feature point cloud is used for the target to be constructed
  • the style of the object is determined
  • the receiving module is further configured to receive a position input operation, where the position input operation is used to determine the display position of the target object in the virtual environment;
  • the display module is further configured to display the target object at the display position in the virtual environment according to the shooting operation and the position input operation, where the target object is formed by a voxel block in the characteristic Filled in the area corresponding to the point cloud.
  • a computer device includes a processor and a memory, the memory stores at least one instruction, at least one program, code set, or instruction set, the at least one instruction, the at least one program, the code
  • the set or instruction set is loaded and executed by the processor to implement the object construction method based on the virtual environment provided in the above embodiment of the present application.
  • a computer-readable storage medium storing at least one instruction, at least one program, code set or instruction set, the at least one instruction, the at least one program, the code set or the instruction set It is loaded and executed by the processor to implement the virtual environment-based object construction method provided in the above-mentioned embodiment of the present application.
  • a computer program product when the computer program product runs on a computer, causes the computer to execute the object construction method based on a virtual environment as provided in the above embodiments of the present application.
  • Fig. 1 is a schematic diagram of a virtual environment and voxel blocks of a sandbox game provided by an exemplary embodiment of the present application;
  • FIG. 2 is a schematic diagram of the overall flow of a method for constructing an object based on a virtual environment provided by an exemplary embodiment of the present application;
  • Fig. 3 is a flowchart of an object construction method based on a virtual environment provided by an exemplary embodiment of the present application
  • FIG. 4 is a schematic diagram of an interface of a method for shooting an object to be collected based on the embodiment shown in FIG. 3;
  • FIG. 5 is a schematic diagram of an interface based on the method for filling a voxel area provided by the embodiment shown in FIG. 3;
  • Fig. 6 is a flowchart of a method for constructing an object based on a virtual environment provided by another exemplary embodiment of the present application;
  • FIG. 7 is a flowchart of a method for filling voxel blocks in an area corresponding to a feature point cloud according to an exemplary embodiment of the present application
  • FIG. 8 is a schematic diagram of a method for determining a voxel area provided based on the embodiment shown in FIG. 7;
  • FIG. 9 is a flowchart of a method for constructing an object based on a virtual environment provided by another exemplary embodiment of the present application.
  • FIG. 10 is a structural block diagram of a terminal provided by an exemplary embodiment of the present application.
  • FIG. 11 is a structural block diagram of an object construction device based on a virtual environment provided by an exemplary embodiment of the present application.
  • FIG. 12 is a structural block diagram of a virtual environment-based object construction device provided by another exemplary embodiment of the present application.
  • FIG. 13 is a structural block diagram of a terminal provided by another exemplary embodiment of the present application.
  • Sandbox game is a game mode in which players use the voxel blocks provided in the game to create original objects and interact with the original objects.
  • the sandbox game is a game application that builds virtual objects in a virtual environment through voxel blocks.
  • sandbox games are highly interactive and have a high degree of freedom. Players can build and stack them in the virtual environment of the game according to their creativity.
  • a main storyline is usually not set in a sandbox game, and the player walks freely in the virtual environment of the game without completing corresponding tasks according to the development of the storyline.
  • Voxel block It is a material block provided in a sandbox game for constructing virtual objects in a virtual environment.
  • the voxel block classification includes classification by material type, classification by color, And through any one of material type classification and color classification, the three situations are schematically illustrated respectively.
  • the sandbox game provides coal voxel blocks, diamond voxel blocks, brick voxel blocks, etc.; 2. Red voxel blocks, green voxel blocks, purple voxel blocks, etc. are provided in sandbox games; 3. Red bricks, green bricks, and purple bricks are provided in sandbox games.
  • voxel blocks classified by material types can be processed into materials for building, furniture and other articles, for example, glass is obtained by smelting sand voxel blocks and used as windows of buildings.
  • objects with rich colors such as decorations and billboards can be constructed using voxel blocks classified by color.
  • the size of the voxel block can be fixed.
  • the size of the voxel block can be determined according to the different material types; for voxel blocks classified by color, any color can be used
  • the voxel blocks of are the same size, and each color corresponds to voxel blocks of multiple sizes, such as small white voxel blocks, medium white voxel blocks, and large white voxel blocks.
  • the shape of the voxel block may be uniform, such as a rectangular parallelepiped, a cube, etc., or multiple styles.
  • the environment interface 100 includes a screen corresponding to a virtual environment. It includes a virtual character 110 and an object 120 built by the player.
  • the object 120 is constructed by voxel blocks in the voxel library.
  • the shapes of some voxel blocks in the voxel library are as shown in the voxel block display area 130.
  • the voxel block display area 130 includes a green square voxel block 131, a brown square voxel block 132, a brown triangular voxel block 133, a black square voxel block 134, and a gray stepped voxel block 135.
  • the plain blocks are displayed in the shape of Lego blocks.
  • the voxel block can be obtained by the player in the virtual environment, or provided by the application itself.
  • the coal voxel block, diamond voxel block, etc. require the player to pass through the virtual environment
  • the common voxel blocks that are mined and classified by color are provided by the game itself.
  • Feature point cloud refers to the contour of the object to be collected in the form of a point cloud, which is generated according to the three-dimensional information of the object to be collected.
  • the feature point cloud is based on the depth obtained after the object to be collected is photographed by a depth camera Information generated.
  • the application scenarios of the virtual environment-based object construction method provided in this application include at least the following application scenarios:
  • the player When constructing a target object in a sandbox game, the player shoots the object to be collected through the camera of the terminal in the sandbox game, and generates a feature point cloud corresponding to the object to be collected according to the three-dimensional information of the object to be collected. And automatically fill the corresponding voxel block in the area corresponding to the feature point cloud according to the feature point cloud, generate a target object corresponding to the object to be collected, and display it at the display position.
  • a sandbox game is used as an example for description.
  • the method can also be applied to any application that provides a virtual environment and voxel blocks, which is not limited in the embodiment of the present application.
  • the environment interface 210 of the sandbox game includes a shooting function control 211.
  • a shooting interface 220 is displayed.
  • the shooting interface 220 includes The screen displayed when the camera is performing image capture, as shown in FIG. 2, the shooting interface 220 includes an object 221 to be collected.
  • the user long presses the shooting control 222 of the shooting interface 220 and holds the terminal to surround the object 221
  • the feature point cloud 230 corresponding to the object to be collected 221 is generated, and the voxel block is filled according to the feature point cloud 230 to generate the target object 240, and the target object 240 is displayed according to the display position of the target object 240 in the virtual environment.
  • the target object 240 is displayed.
  • FIG. 3 is a flowchart of the virtual environment-based object construction method provided by an exemplary embodiment of the present application. It is applied to a terminal provided with a camera as an example for description. As shown in Figure 3, the method includes:
  • Step 301 Display the environment interface.
  • the environment interface includes a screen corresponding to the virtual environment.
  • the method can be applied to a sandbox game, where a virtual environment is provided in the virtual environment, and the virtual environment includes virtual objects, and the player can control the virtual objects to move in the virtual environment, build voxel blocks, etc. .
  • the currently available voxel blocks are also displayed in the environment interface.
  • Step 302 Receive a shooting operation, which is used to collect three-dimensional information of the object to be collected through a camera to obtain a feature point cloud of the object to be collected.
  • the feature point cloud is used to determine the style of the target object to be constructed.
  • the style of the target object includes at least one of the outline, structure, and color composition of the target object, wherein the outline of the target object is used to represent the form of appearance of the target object, and the shape of the target object
  • the structure is used to represent the building structure of the target object, such as a hollow structure, a solid structure, etc.
  • the color composition of the target object is used to represent the color of the voxel block that builds the target object.
  • the shooting operation when receiving the shooting operation, it can be realized by receiving a shooting operation of n frames of images around the object to be collected, where n is a positive integer, wherein the n frames of images include images taken around the object to be collected
  • the n frames of images include images taken in front, left, right, back, and above the object to be collected.
  • the n frames of images can be implemented as n frames of images in a segment of video stream, or can be implemented as n frames of images obtained by shooting at a fixed point around the object to be collected, that is, the n frames of image collection methods include:
  • the image is continuously captured by a camera according to the video shooting operation.
  • the camera surrounds the object to be collected.
  • the user moves the camera clockwise around the object to be collected from the front of the object to be collected. After one rotation, surround above the object to be collected.
  • the camera does not surround below the object to be collected, such as: the object to be collected is placed on the desktop and cannot surround the object to be collected.
  • the unphotographed area corresponding to the target object is realized as a plane, that is, the bottom of the target object is realized as a plane.
  • the designated position may be a position determined according to a prompt of the terminal during the shooting process.
  • a prompt message bar 411 "Please proceed on the front of the object is displayed in the shooting interface 410 "Shooting”, and when the shooting operation is received and the first frame of image 412 is obtained, the prompt message bar 421 "Please shoot on the left side of the object” is displayed in the shooting interface 410, and the second frame of image 422 is obtained after the shooting operation is received.
  • the shooting interface 410 displays the prompt message bar 431 "Please shoot on the right side of the object", when the shooting operation is received and the third frame of image 432 is acquired, the prompt message bar 441 "Please take the object Shooting from the rear", the fourth frame of image 442 is acquired after receiving the shooting operation, where the front, left, right, and rear shooting operations are fixed-point shooting operations around the object. It is worth noting that 4 frames of images are taken as an example in FIG. 4 for illustration. In actual operation, the number of images obtained by the fixed-point shooting operation may be more or less.
  • the method of generating the feature point cloud according to the n frames of images includes any one of the following methods:
  • the camera of the terminal is a depth camera, that is, when the camera is used to take a depth image
  • the image taken by the camera corresponds to depth information.
  • the software development kit (SDK) of the terminal camera supports the feature point cloud computing function
  • the feature point cloud can be directly obtained according to the n frames of images.
  • the three-dimensional reconstruction of the object to be collected is performed through n frames of images to obtain a feature point cloud.
  • three-dimensional reconstruction refers to the process of establishing a mathematical model of a three-dimensional object that conforms to computer expression and processing.
  • the three-dimensional reconstruction process is a process of reconstructing three-dimensional information based on single-view or multi-view images, based on the relationship between the image coordinate system of the camera and the world coordinate system, and using the information of multiple two-dimensional images to reconstruct the three-dimensional information.
  • Generate feature point cloud is a process of reconstructing three-dimensional information based on single-view or multi-view images, based on the relationship between the image coordinate system of the camera and the world coordinate system, and using the information of multiple two-dimensional images to reconstruct the three-dimensional information.
  • Step 303 Receive a position input operation, where the position input operation is used to determine the display position of the target object in the virtual environment.
  • the target object when the position input operation is not received, the target object includes an initial position in the virtual environment, and the actual display position of the target object in the virtual environment is obtained by adjusting the initial position, which is illustrative ,
  • the initial display position of the target object is (a, b, c)
  • the relative adjustment distance of the adjustment operation is (x, y, z)
  • the display position of the target object is (a+x, b+y, c+z).
  • the display size of the target object in the virtual environment is determined, and the display size determination method includes at least one of the following methods:
  • step 302 can be performed first and then step 303, or step 303 can be performed first and then step 302 can be performed, and step 302 and step 303 can be performed simultaneously.
  • the execution order of step 303 is not limited.
  • Step 304 Display the target object at the display position in the virtual environment according to the shooting operation and the position input operation.
  • the target object is obtained by filling the voxel block in the region corresponding to the feature point cloud.
  • filling the voxel block in the area corresponding to the feature point cloud includes at least one of the following methods:
  • the stacked voxel block has no intersection with the pixel points in the feature point cloud, discard the pixel points with the feature point cloud Voxel blocks without intersection;
  • FIG. 5 When stacking the target object corresponding to the feature point cloud 510 layer by layer, first stack the bottom voxel blocks, and the voxel block 521 and the pixel points of the feature point cloud 510 have no intersection. , The voxel block 521 is discarded, and there is an intersection between the voxel block 522 and the pixel points of the feature point cloud 510, so the voxel block 522 is retained.
  • this step 304 may be implemented by the terminal, or the terminal may send n frames of images and the depth information of the image to the server. After the target object is constructed by the server, the construction result of the target object is sent to the terminal for display at the display position.
  • the object to be collected is photographed by the camera of the terminal, and after the three-dimensional information of the object to be collected is collected, the characteristics of the object to be collected are generated according to the three-dimensional information Point cloud, in the virtual environment, the target object is generated by filling the voxel block in the area corresponding to the feature point cloud, and displayed at the display position, which avoids the inability to accurately control the voxel block when the player manually constructs the target object
  • the structure of the object leads to the problem of object construction failure, and the method provided in this embodiment is used to construct the object, which improves the efficiency of object construction and the accuracy of object construction.
  • FIG. 6 is a flowchart of a virtual environment-based object construction method provided by another exemplary embodiment of the present application Take the method applied to a terminal with a camera as an example for description. As shown in Figure 6, the method includes:
  • Step 601 Display the environment interface.
  • the environment interface includes a screen corresponding to the virtual environment.
  • the method can be applied to a sandbox game, where a virtual environment is provided in the virtual environment, and the virtual environment includes virtual objects, and the player can control the virtual objects to move in the virtual environment, build voxel blocks, etc. .
  • the currently available voxel blocks are also displayed in the environment interface.
  • Step 602 Receive a shooting operation of n frames of images around the object to be collected.
  • Step 603 Determine the relative position of the camera when each of the n frames of images is taken.
  • the relative position of the camera is determined according to the positional relationship with the camera when the key frame image is taken.
  • the key frame image is the first image taken by the camera. Frame image.
  • the camera shoots the first frame of image, set the position of the camera at this time, and sense the position change of the terminal during the shooting process according to the Inertial Measurement Unit (IMU) in the terminal, and use the IMU position data
  • IMU Inertial Measurement Unit
  • the relative position of the camera when determining the relative position of the camera, it can also be determined by combining various sensor data in the terminal, such as a gyroscope, a gravity sensor, and the like.
  • the IMU is a device for measuring the three-axis attitude angle (or angular rate) and acceleration of the terminal.
  • an IMU contains three single-axis accelerometers and three single-axis gyroscopes.
  • the accelerometer is used to detect the acceleration signal of the object on each coordinate axis in the three-dimensional coordinate system, and then calculate the displacement vector; and
  • the gyro is used to detect the rotation matrix of the object in the three-dimensional coordinate system.
  • the IMU includes a gyroscope, an accelerometer, and a geomagnetic sensor.
  • the process of determining the relative position of the camera when each frame of image is captured according to the IMU includes: first, the first frame of image captured by the camera is used as a key frame image, and when the camera subsequently captures images, the terminal compares the current image and the key frame image The common feature points are tracked, and the pose changes of the camera in the real world are calculated according to the changes in the feature point positions between the current image and the key frame image, and combined with the measurement data of the IMU, it is determined that the camera is capturing the current image The relative position of the time.
  • the terminal camera shoots around the object A to obtain a first image and a second image, wherein the first image and the second image both include the object A
  • the terminal determines the first image as a key frame image
  • the initial pose parameters can be collected by the IMU.
  • the second image is tracked with respect to the first image by feature points.
  • the pose parameter and the feature point tracking result calculate the pose parameter when the camera takes the second image, thereby determining the target pose parameter when the camera takes the second image, that is, the relative position of the camera when the second image is taken.
  • the target feature point in the second image that matches the initial feature point in the first image is obtained, and according to the initial feature point and the target feature point, Calculate the amount of change in the pose of the camera from the initial posture to the target posture, where the initial posture is the posture when the camera takes the first image, and the target posture is the posture when the camera takes the second image.
  • the terminal performs feature point extraction on the first image to obtain N initial feature points, and performs feature point extraction on the second image to obtain M candidate feature points, and combine the M candidate feature points with N initial feature points Perform matching and determine at least one set of matching feature point pairs.
  • Each set of matching feature point pairs includes an initial feature point and a target feature point, where the initial feature point is the feature point in the first image, and the target feature point is the second The candidate feature point in the image with the highest matching degree with the initial feature point.
  • the terminal calculates the homography matrix homography between the two frames of images according to the initial feature points and the target feature points; decomposes the homography matrix homography to obtain the pose change amount when the camera changes from the initial pose parameters to the target pose parameters R relocalize and T relocalize .
  • the homography matrix describes the mapping relationship between the two planes. If the feature points in the natural scene (real environment) all fall on the same physical plane, the homography matrix can be used for motion estimation.
  • the device decomposes the homography matrix through Random Sample Consensus (RANSAC) algorithm to obtain the rotation matrix R relocalize and the translation vector T relocalize .
  • R Random Sample Consensus
  • R relocalize is the rotation matrix when the camera changes from the initial pose parameters to the target pose parameters
  • T relocalize is the displacement vector when the camera changes from the initial pose parameters to the target pose parameters.
  • the above-mentioned feature point tracking process can use the visual odometer tracking algorithm or the KLT (Kanade-Lucas) optical flow tracking algorithm.
  • the feature point tracking process can also be based on SIFT (Scale-Invariant Feature Transform). Conversion)
  • SIFT Scale-Invariant Feature Transform
  • ORB Oriented FAST and Rotated Brief, fast feature point extraction and description
  • This application does not limit the specific algorithm of feature point tracking, and the feature point tracking process can adopt the feature point method or the direct method.
  • Step 604 Determine the position of the pixel in the three-dimensional space according to the position of the pixel in each of the n frames of images, the depth information corresponding to the pixel, and the relative position of the camera.
  • the depth information corresponding to each frame of image includes the depth information corresponding to the pixels in the frame of image. According to the depth information of the pixel and the position of the pixel in the image, combined with the relative position of the camera, that is The position of the pixel in the three-dimensional space can be obtained.
  • the depth information of the pixel i is d
  • the position coordinates of the pixel i in the image k are (a, b)
  • the relative position coordinates of the pixel i in the camera coordinate system are (a*d , B*d, d)
  • the rotation matrix when the camera shoots the image k is R
  • the translation matrix is t
  • the coordinates of the pixel i in the three-dimensional space are calculated in the following formula 1:
  • L w is used to represent the rotation and translation of the coordinates of the pixel point
  • X is used to represent the coordinate a*d of pixel i in the camera coordinate system
  • Y is used to represent the pixel point i in the camera coordinate system.
  • the coordinates b*d, Z are used to represent the coordinates d of the pixel i in the camera coordinate system
  • X c , Y c and Z c are used to represent the three-dimensional coordinates of the pixel i in the three-dimensional space.
  • each pixel point also corresponds to color information.
  • the depth camera performs one shooting operation to obtain two images, the two images include a color image and a depth image, where the color image includes the color information of each pixel, and the depth image includes the depth of each pixel. information.
  • the depth image shall prevail, and the pixels in the depth image are matched with the pixels in the color image to obtain the color and depth information of each pixel.
  • Step 605 Obtain a feature point cloud according to the position of each pixel in the three-dimensional space.
  • the feature point cloud is obtained according to the position in the three-dimensional space of each pixel in the collected n frames of images, where the pixel points in the n frames of images that overlap can be calculated only once, and when the When the pixel appears again in other images, the recalculation of the pixel is ignored.
  • Step 606 Receive a position input operation, where the position input operation is used to determine the display position of the target object in the virtual environment.
  • the position input operation can be determined by dragging the feature point cloud in the virtual environment, or the target object can be generated for preview after step 605, and the target object can be displayed in the virtual environment. Drag to determine the display position of the target object in the virtual environment.
  • the way of previewing the position of the target object can be by highlighting the position of the target object in the virtual environment, such as: The position of the target object is displayed in black.
  • step 607 the target object is displayed at the display position in the virtual environment according to the shooting operation and the position input operation, and the target object is obtained by filling the voxel block in the region corresponding to the feature point cloud.
  • the voxel block for filling the area corresponding to the feature point cloud can be a voxel block with a uniform color, or the voxel block can be filled according to a preset color rule, or it can be determined according to the color of the object to be collected. Fill the color of the voxel block corresponding to the feature point cloud.
  • the image taken by the camera also corresponds to the color of each pixel.
  • the object to be collected is photographed by the camera of the terminal, and after the three-dimensional information of the object to be collected is collected, the characteristics of the object to be collected are generated according to the three-dimensional information Point cloud, in the virtual environment, the target object is generated by filling the voxel block in the area corresponding to the feature point cloud, and displayed at the display position, which avoids the inability to accurately control the voxel block when the player manually constructs the target object
  • the structure of the object leads to the problem of object construction failure, and the method provided in this embodiment is used to construct the object, which improves the efficiency of object construction and the accuracy of object construction.
  • the image is collected by a depth camera, and the position of the pixel in the three-dimensional space is determined according to the position of the pixel in the image, the depth information of the pixel, and the relative position of the camera, thereby generating a feature point cloud , Improve the efficiency of generating feature point clouds and generating target objects.
  • FIG. 7 is provided by another exemplary embodiment of the present application.
  • Step 701 Receive a three-dimensional slicing operation to obtain a slicing mode corresponding to each dimension.
  • the three-dimensional slicing operation is used to perform three-dimensional slicing of the bounding box corresponding to the feature point cloud according to the slicing mode.
  • the bounding box is the smallest cuboid box surrounding the feature point cloud; or, the bounding box is a cuboid box corresponding to the feature point cloud generated according to the three-dimensional size of the feature point cloud.
  • the slicing manner includes any one of the number of slices corresponding to each dimension and the slice size corresponding to each dimension.
  • the slicing mode is the number of slices corresponding to each dimension
  • average slicing is performed on each dimension according to the number of slices.
  • the three-dimensional slicing refers to slicing the three dimensions of the bounding box in a slicing manner corresponding to each dimension.
  • the execution mode of the 3D slicing operation includes any one of the following modes:
  • the slice number input operation includes an input operation on the number of slices in three dimensions of the feature point cloud, and the bounding box is three-dimensionally sliced according to the slice number according to the slice number input operation;
  • a bounding box 820 corresponding to the feature point cloud 810 is displayed in the virtual environment interface 800.
  • the x-axis direction, the y-axis direction and the z-axis direction in the three-dimensional direction in the virtual environment are such as the coordinate axis 830
  • the slice number setting operation in the slice number input box 840 is received.
  • the slice number setting result is that the x-axis direction is divided into 10 parts, the y-axis direction is divided into 15 parts, and the z-axis direction is divided into 20 parts, the bounding box 820 is three-dimensionally sliced according to the setting result of the number of slices, wherein the bounding box 820 is divided into 10 parts in the x-axis direction, 15 parts in the y-axis direction, and z-axis direction The upper average is divided into 20 parts.
  • the number of slices corresponding to each dimension is used to determine the degree of refinement of the target object generated by the target three-dimensional model. For example, when the number of slices is large, the target object has a higher degree of refinement. The target object and the object to be collected The similarity is also higher; when the number of slices is small, the degree of refinement of the target object is lower, and the similarity between the target object and the object to be collected is lower.
  • Step 702 Determine a voxel area according to the three-dimensional slicing operation, and the voxel area is an area obtained by performing three-dimensional slicing on the bounding box.
  • three-dimensional slicing is performed on the bounding box, that is, a slicing operation is performed in all three dimensions of the bounding box, and the voxel area is obtained according to the slicing operation in the three dimensions, and the voxel area is after three-dimensional slicing The resulting area.
  • the voxel area is used for filling by voxel blocks.
  • Step 703 Fill the voxel area with voxel blocks according to the inclusion relationship between the voxel area and the pixel points in the feature point cloud.
  • the voxel block is filled in the voxel area.
  • the voxel block filling the voxel area is a voxel block of a target color
  • the target color can be determined in any of the following ways:
  • the weighted average color of the pixel is calculated based on the RGB value of the pixel.
  • the color with the highest distribution is determined as the target color.
  • a voxel block whose color is closest to the target color is filled in the voxel area.
  • the preset color table is a color table of all colors of the voxel block provided in the application, and the color difference between the first color and the colors in the preset color table is calculated to determine the difference between the preset color table and the color in the preset color table.
  • the first color has the smallest color difference, and the voxel block of this color is used as the voxel block filling the voxel area.
  • the color distance between the two colors can be calculated by the Euclidean distance calculation method.
  • the greater the color distance the greater the color difference between the two colors.
  • the distance between the two colors C 1 and C 2 can be calculated by the following formula 2 provided by the Euclidean distance calculation method, where C 1 is the above-mentioned first color, and C 2 For the colors in the preset color table:
  • C 1, R represents the red value of the first color C 1
  • C 2 represents the red value of the color C 2
  • C 1 G represents the green value of the first color C 1
  • C 2 G represents the color C 2
  • the green value of C 1,B represents the blue value of the first color C 1
  • C 2,B represents the blue value of the color C 2 .
  • the color difference calculation method can also be calculated by the RGB square method, the CIELab color difference calculation formula (eg: CIELab 76, CIELab 94), and CIEDE 2000.
  • the embodiment of the application calculates the color difference The method is not limited.
  • the object to be collected is photographed by the camera of the terminal, and after the three-dimensional information of the object to be collected is collected, the characteristics of the object to be collected are generated according to the three-dimensional information Point cloud, in the virtual environment, the target object is generated by filling the voxel block in the area corresponding to the feature point cloud, and displayed at the display position, which avoids the inability to accurately control the voxel block when the player manually constructs the target object
  • the structure of the object leads to the problem of object construction failure, and the method provided in this embodiment is used to construct the object, which improves the efficiency of object construction and the accuracy of object construction.
  • a voxel area is obtained by slicing the bounding box corresponding to the feature point cloud, and the voxel area is filled with voxel blocks to determine the segmentation fineness of the target object by slicing , Improve the efficiency of object construction and the accuracy of object construction.
  • Fig. 9 is an overall flowchart of a method for constructing an object based on a virtual environment provided by an exemplary embodiment of the present application. The method is applied to a terminal as an example for description. As shown in Fig. 9, the method includes:
  • step 901 shooting is performed through the terminal camera to obtain depth information and image information.
  • the terminal camera is a depth camera
  • the object to be collected is captured by the camera to obtain depth information and image information of the object to be collected, where the depth information is used to represent the three-dimensional information of the image to be collected, and the image information Used to represent the color information of the image to be collected.
  • Step 902 Generate a feature point cloud according to the depth information and the image information.
  • the position of each pixel in the image in the three-dimensional space is determined according to the depth information and the image information, and the feature point cloud is generated according to the position of each pixel.
  • the specific generation method has been detailed in step 604 above. Description, not repeat them here.
  • Step 903 Perform slicing processing on the bounding box corresponding to the feature point cloud.
  • the slicing process is used to perform three-dimensional slicing of the bounding box corresponding to the feature point cloud to obtain the voxel region.
  • the slicing method of the three-dimensional slice is used to determine the degree of refinement of the target object to be constructed, that is, The similarity between the target object and the object to be collected.
  • Step 904 Perform a voxel inclusion check on the voxel area.
  • the voxel containment check is used to determine whether a voxel block needs to be filled in the voxel region according to the number of pixels contained in the voxel region.
  • the voxel inclusion check is also used to determine the color of the voxel block contained in the voxel area.
  • Step 905 position setting of the target object.
  • the position setting can be determined by dragging the feature point cloud in the virtual environment, or the target object can be generated for preview after the above steps, and by dragging the target object in the virtual environment To determine the display position of the target object in the virtual environment.
  • Step 906 Determine the position of the target object according to the position setting.
  • Step 907 display the target object.
  • the method for constructing objects based on a virtual environment includes importing a target 3D model in the virtual environment and selecting the display position of the target object, and filling in the outline range of the target 3D model in the virtual environment
  • the voxel block generates the target object and displays it at the display position, which avoids the problem that the player cannot accurately control the structure of the voxel block when manually constructing the target object, and the object construction fails, and this embodiment provides The method of construction improves the efficiency of object construction and the accuracy of object construction.
  • FIG. 10 is a structural block diagram of a terminal provided by an exemplary embodiment of the present application. As shown in FIG. 10, the terminal includes: a processor 1010, a display screen 1020, a memory 1030, and a camera 1040;
  • the processor 1010 includes a CPU and a GPU.
  • the CPU is mainly responsible for the calculation tasks of the terminal
  • the GPU is mainly responsible for the display tasks of the terminal. That is, the GPU is responsible for rendering the display content according to the data transmitted by the CPU, and displaying the content through the display screen 1020. To display.
  • a sandbox game application 1032 developed based on the Unity engine 1031 is installed in the terminal, a virtual environment is provided in the sandbox game application 1032, and the virtual object can be in the virtual environment of the sandbox game application 1032
  • the virtual object is built through voxel blocks, and the built virtual object is displayed in the virtual environment through the CPU and GPU.
  • the user can also use the virtual environment-based object construction method provided in the embodiments of this application to collect the depth information and image information of the image to be collected through the camera 1040, and generate a feature point cloud based on the depth information and the image information to fill the voxel block,
  • the target object corresponding to the object to be collected is displayed in the virtual environment of the sandbox game application program 1032.
  • FIG. 11 is a structural block diagram of an object construction device based on a virtual environment provided by an exemplary embodiment of the present application.
  • the device is applied to a terminal provided with a camera as an example for description.
  • the device includes: a display Module 1110 and receiving module 1120;
  • the display module 1110 is configured to display an environment interface, and the environment interface includes a screen corresponding to the virtual environment;
  • the receiving module 1120 is configured to receive a shooting operation for collecting three-dimensional information of the object to be collected through the camera to obtain a feature point cloud of the object to be collected, and the feature point cloud is used for the object to be constructed The style of the target object is determined;
  • the receiving module 1120 is further configured to receive a position input operation, where the position input operation is used to determine the display position of the target object in the virtual environment;
  • the display module 1110 is further configured to display the target object at the display position in the virtual environment according to the shooting operation and the position input operation, and the target object is formed by a voxel block in the display position.
  • the area corresponding to the feature point cloud is filled in.
  • the receiving module 1120 is further configured to receive a shooting operation of n frames of images around the object to be collected, and the n frames of images include images obtained by shooting around the object to be collected Image, n is a positive integer;
  • the device further includes:
  • a generating module 1130 configured to generate the feature point cloud according to the depth information corresponding to each frame of the n frames of images, where the depth information is used to combine the images to represent the three-dimensional information of the object to be collected; Or, performing three-dimensional reconstruction on the object to be collected through the n frames of images to obtain the characteristic point cloud.
  • the generating module 1130 is further configured to determine the relative position of the camera when each frame of the n frames of images is taken, wherein the relative position is based on the The positional relationship when the camera takes the key frame image is determined;
  • the generating module 1130 is further configured to determine the position of the pixel in each frame of the n frames of image, the depth information corresponding to the pixel, and the relative position of the camera. The position of the point in the three-dimensional space is determined;
  • the generating module 1130 is further configured to obtain the feature point cloud according to the position of each pixel point in the three-dimensional space.
  • the receiving module 1120 is further configured to receive a video shooting operation surrounding the object to be collected, and the video stream captured by the video shooting operation includes the n frames of images;
  • the receiving module 1120 is further configured to receive a fixed-point shooting operation around the object to be collected, and the fixed-point shooting operation is used to shoot the n frames of images at a designated position around the object to be collected.
  • the receiving module 1120 is further configured to receive a three-dimensional slicing operation to obtain a slicing mode corresponding to each dimension, and the three-dimensional slicing operation is used to perform a calculation on the feature point cloud according to the slicing mode. 3D slice the corresponding bounding box;
  • the device further includes:
  • the determining module 1140 is configured to determine a voxel area according to the three-dimensional slicing operation, the voxel area is an area obtained by performing the three-dimensional slicing of the bounding box, and the voxel area is used to pass through the volume Filling with plain blocks;
  • the filling module 1150 is configured to fill the voxel block into the voxel area according to the inclusion relationship between the voxel area and the pixel points in the feature point cloud.
  • the receiving module 1120 is further configured to receive a slice number input operation, where the slice number input operation includes an input operation on the number of slices in three dimensions of the feature point cloud; Perform the three-dimensional slice on the bounding box according to the slice number according to the slice number input operation;
  • the receiving module 1120 is further configured to receive a sliding slice operation, and perform the three-dimensional slice on the bounding box according to the sliding slice operation;
  • the number of slices corresponding to each dimension is used to determine the degree of refinement of the feature point cloud to generate the target object.
  • the filling module 1150 is further configured to fill the volume in the voxel area when the number of pixels contained in the voxel area is greater than a preset number. Plain block.
  • the filling module 1150 is further configured to determine the weighted average color of the pixel points contained in the voxel area to obtain a target color, and the color closest to the target color The voxel block is filled in the voxel area;
  • the filling module 1150 is further configured to determine the color with the highest distribution as the target color according to the color distribution of the pixel points contained in the voxel area, and select the volume whose color is closest to the target color.
  • the voxel block is filled in the voxel area.
  • the device for constructing objects based on a virtual environment can import a target three-dimensional model in the virtual environment and select the display position of the target object, and fill in the outline of the target three-dimensional model in the virtual environment.
  • the voxel block generates the target object and displays it at the display position, which avoids the problem that the player cannot accurately control the structure of the voxel block when manually constructing the target object, and the object construction fails, and this embodiment provides The method of construction improves the efficiency of object construction and the accuracy of object construction.
  • the object construction device based on the virtual environment provided in the above embodiments is only illustrated by the division of the above functional modules.
  • the above functions can be allocated by different functional modules according to needs, namely The internal structure of the device is divided into different functional modules to complete all or part of the functions described above.
  • the device for constructing an object based on a virtual environment provided in the above embodiment and the method embodiment of a method for constructing an object based on a virtual environment belong to the same concept. For the specific implementation process, refer to the method embodiment, which will not be repeated here.
  • FIG. 13 shows a structural block diagram of a terminal 1300 provided by an exemplary embodiment of the present invention.
  • the terminal 1300 can be: a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III, moving picture expert compression standard audio layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, moving picture expert compressing standard audio Level 4) Player, laptop or desktop computer.
  • the terminal 1300 may also be called user equipment, portable terminal, laptop terminal, desktop terminal, and other names.
  • the terminal 1300 includes a processor 1301 and a memory 1302.
  • the processor 1301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so on.
  • the processor 1301 may adopt at least one hardware form among DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array, Programmable Logic Array). achieve.
  • the processor 1301 may also include a main processor and a coprocessor.
  • the main processor is a processor used to process data in the wake state, also called a CPU (Central Processing Unit, central processing unit); the coprocessor is A low-power processor used to process data in the standby state.
  • the processor 1301 may be integrated with a GPU (Graphics Processing Unit, image processor), and the GPU is used to render and draw content that needs to be displayed on the display screen.
  • the processor 1301 may further include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.
  • AI Artificial Intelligence
  • the memory 1302 may include one or more computer-readable storage media, which may be non-transitory.
  • the memory 1302 may also include high-speed random access memory and non-volatile memory, such as one or more magnetic disk storage devices and flash memory storage devices.
  • the non-transitory computer-readable storage medium in the memory 1302 is used to store at least one instruction, and the at least one instruction is used to be executed by the processor 1301 to implement the virtual-based The object construction method of the environment.
  • the terminal 1300 may optionally further include: a peripheral device interface 1303 and at least one peripheral device.
  • the processor 1301, the memory 1302, and the peripheral device interface 1303 may be connected by a bus or a signal line.
  • Each peripheral device can be connected to the peripheral device interface 1303 through a bus, a signal line, or a circuit board.
  • the peripheral device includes: at least one of a radio frequency circuit 1304, a touch display screen 1305, a camera 1306, an audio circuit 1307, a positioning component 1308, and a power supply 1309.
  • the peripheral device interface 1303 may be used to connect at least one peripheral device related to I/O (Input/Output) to the processor 1301 and the memory 1302.
  • the processor 1301, the memory 1302, and the peripheral device interface 1303 are integrated on the same chip or circuit board; in some other embodiments, any one of the processor 1301, the memory 1302, and the peripheral device interface 1303 or The two can be implemented on separate chips or circuit boards, which are not limited in this embodiment.
  • the radio frequency circuit 1304 is used to receive and transmit RF (Radio Frequency, radio frequency) signals, also called electromagnetic signals.
  • the radio frequency circuit 1304 communicates with a communication network and other communication devices through electromagnetic signals.
  • the radio frequency circuit 1304 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals.
  • the radio frequency circuit 1304 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and so on.
  • the radio frequency circuit 1304 can communicate with other terminals through at least one wireless communication protocol.
  • the wireless communication protocol includes but is not limited to: World Wide Web, Metropolitan Area Network, Intranet, various generations of mobile communication networks (2G, 3G, 4G, and 5G), wireless local area network and/or WiFi (Wireless Fidelity, wireless fidelity) network.
  • the radio frequency circuit 1304 may also include NFC (Near Field Communication) related circuits, which is not limited in this application.
  • the display screen 1305 is used to display UI (User Interface).
  • the UI can include graphics, text, icons, videos, and any combination thereof.
  • the display screen 1305 also has the ability to collect touch signals on or above the surface of the display screen 1305.
  • the touch signal may be input to the processor 1301 as a control signal for processing.
  • the display screen 1305 may also be used to provide virtual buttons and/or virtual keyboards, also called soft buttons and/or soft keyboards.
  • the display screen 1305 may be one display screen 1305, which is provided with the front panel of the terminal 1300; in other embodiments, there may be at least two display screens 1305, which are respectively arranged on different surfaces of the terminal 1300 or in a folding design; In still other embodiments, the display screen 1305 may be a flexible display screen, which is disposed on the curved surface or the folding surface of the terminal 1300. Furthermore, the display screen 1305 can also be set as a non-rectangular irregular pattern, that is, a special-shaped screen.
  • the display screen 1305 can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode, organic light-emitting diode).
  • the camera assembly 1306 is used to collect images or videos.
  • the camera assembly 1306 includes a front camera and a rear camera.
  • the front camera is set on the front panel of the terminal, and the rear camera is set on the back of the terminal.
  • the camera assembly 1306 may also include a flash.
  • the flash can be a single-color flash or a dual-color flash. Dual color temperature flash refers to a combination of warm light flash and cold light flash, which can be used for light compensation under different color temperatures.
  • the audio circuit 1307 may include a microphone and a speaker.
  • the microphone is used to collect the sound waves of the user and the environment, and convert the sound waves into electrical signals and input them to the processor 1301 for processing, or input to the radio frequency circuit 1304 to realize voice communication.
  • the microphone can also be an array microphone or an omnidirectional acquisition microphone.
  • the speaker is used to convert the electrical signal from the processor 1301 or the radio frequency circuit 1304 into sound waves.
  • the speaker can be a traditional membrane speaker or a piezoelectric ceramic speaker.
  • the speaker When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into human audible sound waves, but also convert the electrical signal into human inaudible sound waves for purposes such as distance measurement.
  • the audio circuit 1307 may also include a headphone jack.
  • the positioning component 1308 is used to locate the current geographic position of the terminal 1300 to implement navigation or LBS (Location Based Service, location-based service).
  • the positioning component 1308 may be a positioning component based on the GPS (Global Positioning System, Global Positioning System) of the United States, the Beidou system of China, or the Galileo system of Russia.
  • the power supply 1309 is used to supply power to various components in the terminal 1300.
  • the power source 1309 may be alternating current, direct current, disposable batteries or rechargeable batteries.
  • the rechargeable battery may be a wired rechargeable battery or a wireless rechargeable battery.
  • a wired rechargeable battery is a battery charged through a wired line
  • a wireless rechargeable battery is a battery charged through a wireless coil.
  • the rechargeable battery can also be used to support fast charging technology.
  • the terminal 1300 further includes one or more sensors 1310.
  • the one or more sensors 1310 include, but are not limited to, an acceleration sensor 1311, a gyroscope sensor 1312, a pressure sensor 1313, a fingerprint sensor 1314, an optical sensor 1315, and a proximity sensor 1316.
  • the acceleration sensor 1311 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the terminal 1300.
  • the acceleration sensor 1311 can be used to detect the components of the gravitational acceleration on three coordinate axes.
  • the processor 1301 may control the touch screen 1305 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 1311.
  • the acceleration sensor 1311 may also be used for the collection of game or user motion data.
  • the gyroscope sensor 1312 can detect the body direction and rotation angle of the terminal 1300, and the gyroscope sensor 1312 can cooperate with the acceleration sensor 1311 to collect the user's 3D actions on the terminal 1300. Based on the data collected by the gyroscope sensor 1312, the processor 1301 can implement the following functions: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.
  • the pressure sensor 1313 may be disposed on the side frame of the terminal 1300 and/or the lower layer of the touch screen 1305.
  • the processor 1301 performs left and right hand recognition or quick operation according to the holding signal collected by the pressure sensor 1313.
  • the processor 1301 controls the operability controls on the UI interface according to the user's pressure operation on the touch display screen 1305.
  • the operability control includes at least one of a button control, a scroll bar control, an icon control, and a menu control.
  • the fingerprint sensor 1314 is used to collect the user's fingerprint.
  • the processor 1301 identifies the user's identity according to the fingerprint collected by the fingerprint sensor 1314, or the fingerprint sensor 1314 identifies the user's identity according to the collected fingerprint. When it is recognized that the user's identity is a trusted identity, the processor 1301 authorizes the user to perform related sensitive operations, including unlocking the screen, viewing encrypted information, downloading software, paying, and changing settings.
  • the fingerprint sensor 1314 may be provided on the front, back or side of the terminal 1300. When a physical button or a manufacturer logo is provided on the terminal 1300, the fingerprint sensor 1314 may be integrated with the physical button or the manufacturer logo.
  • the optical sensor 1315 is used to collect the ambient light intensity.
  • the processor 1301 may control the display brightness of the touch screen 1305 according to the intensity of the ambient light collected by the optical sensor 1315. Specifically, when the ambient light intensity is high, the display brightness of the touch screen 1305 is increased; when the ambient light intensity is low, the display brightness of the touch screen 1305 is decreased.
  • the processor 1301 may also dynamically adjust the shooting parameters of the camera assembly 1306 according to the ambient light intensity collected by the optical sensor 1315.
  • the proximity sensor 1316 also called a distance sensor, is usually arranged on the front panel of the terminal 1300.
  • the proximity sensor 1316 is used to collect the distance between the user and the front of the terminal 1300.
  • the processor 1301 controls the touch screen 1305 to switch from the on-screen state to the off-screen state; when the proximity sensor 1316 detects When the distance between the user and the front of the terminal 1300 gradually increases, the processor 1301 controls the touch display screen 1305 to switch from the on-screen state to the on-screen state.
  • FIG. 13 does not constitute a limitation on the terminal 1300, and may include more or fewer components than shown, or combine certain components, or adopt different component arrangements.
  • the program can be stored in a computer-readable storage medium.
  • the medium may be a computer-readable storage medium included in the memory in the foregoing embodiment; or may be a computer-readable storage medium that exists alone and is not assembled into the terminal.
  • the computer-readable storage medium stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by the processor In order to realize the object construction method based on virtual environment as described in any one of FIG. 3, FIG. 6 and FIG.
  • a computer device in another aspect, includes a processor and a memory.
  • the memory stores at least one instruction, at least one program, code set or instruction set, the at least one instruction, the at least A piece of program, the code set or the instruction set is loaded and executed by the processor to realize the object construction method based on the virtual environment as described in any one of FIG. 3, FIG. 6 and FIG.
  • a computer-readable storage medium stores at least one instruction, at least one program, code set or instruction set, the at least one instruction, the at least one program, the The code set or instruction set is loaded and executed by the processor to implement the virtual environment-based object construction method described in any one of FIGS. 3, 6 and 7.
  • a computer program product is provided.
  • the computer program product runs on a computer
  • the computer executes the object construction method based on a virtual environment as described in any one of FIGS. 3, 6 and 7.
  • Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
  • SRAM static RAM
  • DRAM dynamic RAM
  • SDRAM synchronous DRAM
  • DDRSDRAM double data rate SDRAM
  • ESDRAM enhanced SDRAM
  • SLDRAM synchronous chain Channel
  • memory bus Radbus direct RAM
  • RDRAM direct memory bus dynamic RAM
  • RDRAM memory bus dynamic RAM

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Computer Graphics (AREA)
  • Geometry (AREA)
  • Architecture (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Processing Or Creating Images (AREA)

Abstract

一种基于虚拟环境的物体构建方法、装置及可读存储介质，涉及虚拟环境领域。该方法应用于设置有摄像头的终端中，该方法包括：显示环境界面；接收拍摄操作，对待采集物体的三维信息进行采集，得到待采集物体的特征点云；接收位置输入操作，对目标物体的显示位置进行确定；根据拍摄操作和位置输入操作在虚拟环境中的显示位置处显示目标物体。

Description

基于虚拟环境的物体构建方法、装置、计算机设备及可读存储介质
本申请要求于2019年04月25日提交中国专利局，申请号为2019103404014，发明名称为“基于虚拟环境的物体构建方法、装置及可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及虚拟环境领域，特别涉及一种基于虚拟环境的物体构建方法、装置、计算机设备及可读存储介质。
背景技术
沙盒游戏是一种由玩家利用游戏中提供的体素块制造原创物体，并与制造的原创物体进行互动的游戏模式，可选地，沙盒游戏中提供的体素块可以是通过材料分类的体素块，也可以是通过颜色分类的体素块，如：沙盒游戏中提供煤炭体素块、钻石体素块、砖头体素块等，或提供红色体素块、绿色体素块、紫色体素块等。
通常，玩家采用通过颜色分类的体素块在沙盒游戏环境中搭建装饰物、广告牌等色彩较为丰富的场景。以搭建装饰物为例，玩家首先确定需要搭建的装饰物的整体样式，并根据该整体样式将不同颜色的体素块在该样式的对应位置进行堆积，堆积后得到该装饰物。
发明内容
根据本申请的各种实施例，提供了一种基于虚拟环境的物体构建方法、装置、计算机设备及可读存储介质。
一种基于虚拟环境的物体构建方法，应用于设置有摄像头的终端中，所述方法包括：
显示环境界面，所述环境界面中包括所述虚拟环境对应的画面；
接收拍摄操作，所述拍摄操作用于通过所述摄像头对待采集物体的三维信息进行采集，得到所述待采集物体的特征点云，所述特征点云用于对待构建的目标物体的样式进行确定；
接收位置输入操作，所述位置输入操作用于对所述目标物体在所述虚拟环境中的显示位置进行确定；
根据所述拍摄操作和所述位置输入操作在所述虚拟环境中的所述显示位置处显示所述目标物体，所述目标物体是由体素块在所述特征点云对应的区域内进行填充得到的。
一种基于虚拟环境的物体构建装置，应用于设置有摄像头的终端中，所述装置包括：
显示模块，用于显示环境界面，所述环境界面中包括所述虚拟环境对应的画面；
接收模块，用于接收拍摄操作，所述拍摄操作用于通过所述摄像头对待采集物体的三维信息进行采集，得到所述待采集物体的特征点云，所述特征点云用于对待构建的目标物体的样式进行确定；
所述接收模块，还用于接收位置输入操作，所述位置输入操作用于对所述目标物体在所述虚拟环境中的显示位置进行确定；
所述显示模块，还用于根据所述拍摄操作和所述位置输入操作在所述虚拟环境中的所述显示位置处显示所述目标物体，所述目标物体是由体素块在所述特征点云对应的区域内进行填充得到的。
一种计算机设备，所述计算机设备包括处理器和存储器，所述存储器中存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行以实现如上述本申请实施例中提供的基于虚拟环境的物体构建方法。
一种计算机可读存储介质，所述可读存储介质中存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行以实现如上述本申请实施例中提供的基于虚拟环境的物体构建方法。
一种计算机程序产品，当所述计算机程序产品在计算机上运行时，使得计算机执行如上述本申请实施例中提供的基于虚拟环境的物体构建方法。
本申请的一个或多个实施例的细节在下面的附图和描述中提出。本申请的其它特征和优点将从说明书、附图以及权利要求书变得明显。
附图说明
为了更清楚地说明本申请实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请一个示例性实施例提供的沙盒游戏的虚拟环境以及体素块的示意图；
图2是本本申请一个示例性实施例提供的基于虚拟环境的物体构建方法的整体流程示意图；
图3是本申请一个示例性实施例提供的基于虚拟环境的物体构建方法的流程图；
图4是基于图3示出的实施例提供的待采集物体的拍摄方法的界面示意图；
图5是基于图3示出的实施例提供的体素区域的填充方法的界面示意图；
图6是本申请另一个示例性实施例提供的基于虚拟环境的物体构建方法的流程图；
图7是本申请一个示例性实施例提供的体素块在特征点云对应的区域内进行填充的方法的流程图；
图8是基于图7示出的实施例提供的体素区域的确定方法的示意图；
图9是本申请另一个示例性实施例提供的基于虚拟环境的物体构建方法的流程图；
图10是本申请一个示例性实施例提供的终端的结构框图；
图11是本申请一个示例性实施例提供的基于虚拟环境的物体构建装置的结构框图；
图12是本申请另一个示例性实施例提供的基于虚拟环境的物体构建装置的结构框图；
图13是本申请另一个示例性实施例提供的终端的结构框图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。应当理解，此处所描述的具体实施例仅仅用以解释 本申请，并不用于限定本申请。
首先，对本申请实施例中涉及的名词进行简单介绍：
沙盒游戏：是一种由玩家利用游戏中提供的体素块制造原创物体，并与制造的原创物体进行互动的游戏模式。可选地，该沙盒游戏是一种在虚拟环境中通过体素块对虚拟物体进行搭建的游戏应用程序。通常，沙盒游戏中交互性较强、自由度较高，玩家可以根据创意在游戏的虚拟环境中通过体素块任意进行搭建、堆砌。可选地，沙盒游戏中通常不会设置主线剧情，玩家在游戏的虚拟环境中进行自由走动，而不需要根据剧情的发展完成对应的任务。
体素块：是一种在沙盒游戏中提供的用于在虚拟环境中对虚拟物体进行构建的材料块，可选地，该体素块的分类方式包括通过材料类型分类，通过颜色分类，以及通过材料类型分类和颜色分类中的任意一种，示意性的，对三种情况分别进行举例说明，1、沙盒游戏中提供煤炭体素块、钻石体素块、砖头体素块等；2、沙盒游戏中提供红色体素块、绿色体素块、紫色体素块等；3、沙盒游戏中提供红色砖块、绿色砖块、紫色砖块等。可选地，通过材料类型分类的体素块可以加工为建筑物、家具等用品的制作材料，如：通过熔炼沙子体素块得到玻璃，作为建筑物的窗户。可选地，装饰物、广告牌等色彩较丰富的物体可以采用通过颜色分类的体素块进行构建。可选地，体素块的大小可以是固定的，针对通过材料类型分类的体素块，可以根据材料类型的不同，确定体素块的大小；针对通过颜色分类的体素块，可以任意颜色的体素块的大小相同，且每种颜色对应有多种大小的体素块，如：小型白色体素块，中型白色体素块以及大型白色体素块。可选地，体素块的形状可以是统一的，如：长方体、正方体等，也可以是多种样式的，如图1所示，在环境界面100中包括虚拟环境对应的画面，该虚拟环境中包括虚拟人物110以及玩家搭建的物体120，该物体120是通过体素库中的体素块进行搭建的，其中，体素库中的部分体素块的形状如体素块显示区域130所示，该体素块显示区域130中包括绿色方形体素块131、棕色方形体素块132、棕色三角体素块133、黑色方形体素块134以及灰色阶梯体素块135，其中，上述体素块显示为乐高块的形状。
可选地，该体素块可以是玩家在虚拟环境中获取的，也可以是应用程序中本身提供的，示意性的，煤炭体素块、钻石体素块等需要玩家通过在虚拟环境中通 过开采获得，而由颜色分类的普通体素块是游戏本身提供的。
特征点云：是指根据待采集物体的三维信息生成的以点云形式表达的该待采集物体的轮廓，可选地，该特征点云是根据该待采集物体通过深度相机拍摄后得到的深度信息生成的。
其次，本申请实施例提供的基于虚拟环境的物体构建方法的应用场景进行说明，本申请提供的基于虚拟环境的物体构建方法的应用场景至少包括如下应用场景：
在沙盒游戏中对目标物体进行构建时，玩家在沙盒游戏中通过终端的摄像头对待采集物体进行拍摄，根据拍摄得到的该待采集物体的三维信息生成该待采集物体对应的特征点云，并自动根据特征点云在该特征点云对应的区域内填充对应的体素块，生成与该待采集物体对应的目标物体并显示在显示位置处。
可选地，上述举例中以沙盒游戏为例进行说明，该方法还可以应用于任意提供虚拟环境以及体素块的应用程序中，本申请实施例对此不加以限定。
示意性的，请参考图2，在沙盒游戏的环境界面210中包括拍摄功能控件211，用户在该拍摄功能控件211上进行选择后，显示拍摄界面220，该拍摄界面220中包括通过终端的摄像头进行图像采集时显示的画面，如图2所示，该拍摄界面220中包括待采集物体221，用户在该拍摄界面220的拍摄控件222上进行长按，并持终端围绕该待采集物体221进行连续拍摄后，生成该待采集物体221对应的特征点云230，并根据该特征点云230进行体素块填充，生成目标物体240，根据该目标物体240在虚拟环境中的显示位置对该目标物体240进行显示。
结合上述名词简介以及应用场景，对本申请实施例提供的基于虚拟环境的物体构建方法进行说明，图3是本申请一个示例性实施例提供的基于虚拟环境的物体构建方法的流程图，以该方法应用于设置有摄像头的终端中为例进行说明，如图3所示，该方法包括：
步骤301，显示环境界面。
可选地，该环境界面中包括虚拟环境对应的画面。
可选地，该方法可以应用于沙盒游戏中，该沙盒游戏中提供有虚拟环境，该虚拟环境中包括虚拟对象，玩家可以控制虚拟对象在虚拟环境中进行移动、体素块搭建等操作。可选地，该环境界面中还显示有当前可以使用的体素块。
步骤302，接收拍摄操作，该拍摄操作用于通过摄像头对待采集物体的三维信息进行采集，得到待采集物体的特征点云。
可选地，该特征点云用于对待构建的目标物体的样式进行确定。可选地，该目标物体的样式包括指该目标物体的轮廓、结构、颜色构成中的至少一项，其中，该目标物体的轮廓用于表示该目标物体的外观表现的形式，该目标物体的结构用于表示该目标物体的搭建结构，如：中空结构、实心结构等，该目标物体的颜色构成用于表示搭建该目标物体的体素块的颜色。
可选地，接收该拍摄操作时，可以通过接收在该待采集物体周围对n帧图像的拍摄操作实现，n为正整数，其中，该n帧图像中包括环绕该待采集物体拍摄得到的图像，如，该n帧图像中包括在该待采集物体前方、左侧、右侧、后方以及上方拍摄的图像。可选地，该n帧图像可以实现为一段视频流中的n帧图像，也可以实现为围绕该待采集物体进行定点拍摄得到的n帧图像，即该n帧图像的采集方式包括：
第一，接收围绕该待采集物体的视频拍摄操作，该视频拍摄操作拍摄得到的视频流中包括该n帧图像；
可选地，根据该视频拍摄操作通过摄像头对图像进行连续采集，可选地，该摄像头围绕该待采集物体进行拍摄，如：用户将摄像头从待采集物体的前方顺时针围绕该待采集物体进行旋转一周后，向该待采集物体的上方进行围绕，可选地，当该摄像头未向该待采集物体的下方进行围绕时，如：该待采集物体置于桌面，无法围绕该待采集物体的下方进行拍摄时，则目标物体对应的该未被拍摄处实现为平面，即，该目标物体的底部实现为平面。
第二，接收在待采集物体周围的定点拍摄操作，该定点拍摄操作用于围绕待采集物体在指定位置对n帧图像进行拍摄；
可选地，该指定位置可以是根据终端在拍摄过程中的提示确定的位置，如图4所示，开启拍摄界面410后，在该拍摄界面410中显示提示消息栏411“请在物体正面进行拍摄”，并在接收到拍摄操作并获取第一帧图像412时，在拍摄界面410中显示提示消息栏421“请在物体左侧进行拍摄”，在接收到拍摄操作并 获取第二帧图像422时，在拍摄界面410中显示提示消息栏431“请在物体右侧进行拍摄”，在接收到拍摄操作并获取第三帧图像432时，在拍摄界面410中显示提示消息栏441“请在物体后方进行拍摄”，在接收到拍摄操作后获取第四帧图像442，其中，正面、左侧、右侧以及后方的拍摄操作即为在该物体周围的定点拍摄操作。值得注意的是，图4中以4帧图像为例进行说明，实际操作中，该定点拍摄操作得到的图像的数量可以更多或者更少。
可选地，根据终端的摄像头的拍摄能力，根据该n帧图像生成特征点云的方式包括如下方式中的任意一种：
第一，根据n帧图像中每帧图像对应的深度信息生成特征点云，该深度信息用于结合图像以表示该待采集物体的三维信息；
可选地，当终端的摄像头为深度摄像头，即该摄像头用于对深度图像进行拍摄时，该摄像头拍摄的图像对应有深度信息。可选地，当终端相机的软件开发工具包(Software Development Kit，SDK)支持特征点云计算功能时，根据该n帧图像可以直接得到该特征点云。
第二，通过n帧图像对待采集物体进行三维重建，得到特征点云。
可选地，三维重建是指对三维物体建立符合计算机表达和处理的数学模型的过程。可选地，该三维重建过程是根据单视图或者多视图的图像重建三维信息的过程，根据摄像头的图像坐标系与世界坐标系的关系，并利用多个二维图像的信息重建出三维信息后，生成特征点云。
步骤303，接收位置输入操作，该位置输入操作用于对目标物体在虚拟环境中的显示位置进行确定。
可选地，当未接收到该位置输入操作时，该目标物体在虚拟环境中包括一个初始位置，通过对该初始位置进行调整，得到该目标物体在虚拟环境中的实际显示位置，示意性的，该目标物体的初始显示位置为(a，b，c)，该调整操作的调整相对距离为(x，y，z)，则该目标物体的显示位置为(a+x，b+y，c+z)。
可选地，对该目标物体在虚拟环境中的显示位置进行确定后，确定该目标物体在该虚拟环境中的显示尺寸，该显示尺寸的确定方式包括如下方式中的至少一种：
第一，根据该特征点云的尺寸直接确定该目标物体的显示尺寸；
第二，在虚拟环境中的显示位置处预览该待采集物体，并通过尺寸调整操作 对该待采集物体在该虚拟环境中的显示尺寸进行调整，从而调整生成的目标物体在该虚拟环境中的显示尺寸；
第三，输入该目标物体在目标维度的长度，根据待采集物体的三个维度的比例以及目标维度的长度确定该目标物体的尺寸；其中，该目标物体的目标维度的长度通过该目标物体在目标维度上体素块的数量进行设置。
值得注意的是，上述步骤302和步骤303中，可以先执行步骤302再执行步骤303，也可以先执行步骤303再执行步骤302，还可以同时执行步骤302和步骤303，本实施例对步骤302和步骤303的执行顺序不做限定。
步骤304，根据拍摄操作和位置输入操作在虚拟环境中的显示位置处显示目标物体，该目标物体是由体素块在特征点云对应的区域内进行填充得到的。
可选地，将体素块在特征点云对应的区域内进行填充时，包括如下方式中的至少一种：
第一，确定位于该特征点云对应区域的轮廓上的体素块，并根据位于特征点云对应区域的轮廓上的体素块对轮廓内的体素块进行填充；
第二，沿该特征点云对应的区域直接对该体素块进行逐层堆砌，当堆砌的体素块与该特征点云内的像素点无交集时，舍弃该与特征点云的像素点无交集的体素块；
示意性的，请参考图5，在对特征点云510对应的目标物体进行逐层堆砌时，首先对最底层的体素块进行堆砌，体素块521与特征点云510的像素点无交集，舍弃该体素块521，体素块522与特征点云510的像素点存在交集，故保留该体素块522。
可选地，该步骤304可以由终端实现，也可以由终端将n帧图像以及图像的深度信息发送至服务器，由服务器构建目标物体后将目标物体的构建结果发送至终端在显示位置进行显示。
综上所述，本实施例提供的基于虚拟环境的物体构建方法，通过终端的摄像头对待采集物体进行拍摄，并对待采集物体的三维信息进行采集后，根据该三维信息生成该待采集物体的特征点云，在虚拟环境中通过在特征点云对应的区域内填充体素块生成目标物体，并在该显示位置进行显示，避免了玩家手动对目标物体进行构建时，无法准确把控体素块的结构而导致物体构建失败的问题，且通过本实施例提供的方法进行构建，提高了物体的构建效率，以及物体构建的准确 率。
在一个可选的实施例中，该特征点云的生成过程中需要根据深度信息以及摄像头位置进行确定，图6是本申请另一个示例性实施例提供的基于虚拟环境的物体构建方法的流程图，以该方法应用于设置有摄像头的终端中为例进行说明，如图6所示，该方法包括：
步骤601，显示环境界面。
可选地，该环境界面中包括虚拟环境对应的画面。
可选地，该方法可以应用于沙盒游戏中，该沙盒游戏中提供有虚拟环境，该虚拟环境中包括虚拟对象，玩家可以控制虚拟对象在虚拟环境中进行移动、体素块搭建等操作。可选地，该环境界面中还显示有当前可以使用的体素块。
步骤602，接收在待采集物体周围对n帧图像的拍摄操作。
可选地，该n帧图像的拍摄操作的具体操作过程在上述步骤302中已进行了详细说明，此处不再赘述。
步骤603，确定拍摄n帧图像中每帧图像时摄像头所处的相对位置。
可选地，拍摄每帧图像时，该摄像头所处的相对位置是根据所述与摄像头拍摄关键帧图像时的位置关系确定的，可选地，该关键帧图像为该摄像头所拍摄的第一帧图像。可选地，当摄像头拍摄第一帧图像时，设定此时摄像头的位置，根据终端中的惯性测量单元(Inertial Measurement Unit，IMU)感应终端在拍摄过程中的位置变化，通过IMU位置数据的叠加变换以及当前帧图像与该第一帧图像之间的特征点即可得到摄像头拍摄每帧图像时的相对位置。
可选地，在确定摄像头的相对位置时，还可以结合终端中的多种传感器数据进行确定，如：陀螺仪、重力传感器等。
可选地，IMU是用于测量终端的三轴姿态角(或角速率)以及加速度的装置。可选地，一个IMU包含了三个单轴的加速度计和三个单轴的陀螺，加速度计用于检测物体在三维坐标系中每个坐标轴上的加速度信号，进而计算得到位移向量；而陀螺用于检测物体在三维坐标系中的旋转矩阵。可选地，IMU包括陀螺仪、加速度计和地磁传感器。
可选地，根据IMU确定拍摄每帧图像时摄像头的相对位置的过程包括：首先将该摄像头采集的第一帧图像作为关键帧图像，在摄像头后续采集图像时，终 端对当前图像与关键帧图像之间共同具有的特征点进行追踪，根据当前图像与关键帧图像之间的特征点位置变化计算摄像头在现实世界中的位姿变化，并结合IMU的测量数据，从而确定该摄像头在拍摄当前图像时的相对位置。示意性的，终端摄像头围绕物体A进行拍摄，得到第一图像和第二图像，其中，第一图像和第二图像中都包括该物体A，终端将该第一图像确定为关键帧图像，并记录摄像头拍摄该第一图像时的初始位姿参数，该初始位姿参数可以由IMU进行采集，然后在拍摄第二图像后，将第二图像相对于第一图像进行特征点追踪，根据初始位姿参数和特征点追踪结果计算该摄像头拍摄第二图像时的位姿参数，从而确定摄像头拍摄该第二图像时的目标位姿参数，也即摄像头拍摄第二图像时的相对位置。
可选地，将第二图像相对于第一图像进行特征点追踪后，得到第二图像中与该第一图像中的初始特征点匹配的目标特征点，并根据初始特征点和目标特征点，计算摄像头从初始姿态改变至目标姿态的位姿变化量，其中，初始姿态即为摄像头拍摄第一图像时的姿态，目标姿态为摄像头拍摄第二图像时的姿态。示意性的，终端对第一图像进行特征点提取，得到N个初始特征点，并对第二图像进行特征点提取，得到M个候选特征点，将M个候选特征点与N个初始特征点进行匹配，确定至少一组匹配特征点对，每组匹配特征点对中包括一个初始特征点和一个目标特征点，其中，初始特征点为第一图像中的特征点，目标特征点为第二图像中与初始特征点匹配度最高的候选特征点。终端根据初始特征点和目标特征点计算两帧图像之间的单应性矩阵homography；对单应性矩阵homography进行分解，得到摄像头从初始位姿参数改变至目标位姿参数时的位姿变化量R relocalize和T relocalize。
其中，单应性矩阵描述了两个平面之间的映射关系，若自然场景(现实环境)中的特征点都落在同一物理平面上，则可以通过单应性矩阵进行运动估计。当存在至少四对相匹配的初始特征点和目标特征点时，设备通过随机抽样一致性(Random Sample Consensus，RANSAC)算法对该单应性矩阵进行分解，得到旋转矩阵R relocalize和平移向量T relocalize。
其中，R relocalize是摄像头从初始位姿参数改变至目标位姿参数时的旋转矩阵，T relocalize是摄像头从初始位姿参数改变至目标位姿参数时的位移向量。
可选地，上述特征点追踪过程可以采用视觉里程计的追踪算法或KLT (Kanade-Lucas)光流追踪算法，该特征点追踪过程还可以通过基于SIFT(Scale-Invariant Feature Transform，尺度不变特征转换)算法提取的SIFT特征点描述子或基于ORB(Oriented FAST and Rotated BRIEF，快速特征点提取和描述)算法提取的ORB特征点描述子进行特征点跟踪。本申请对特征点追踪的具体算法不加以限定，特征点追踪过程可以采用特征点法或直接法。
步骤604，根据n帧图像中每帧图像中的像素点的位置、像素点对应的深度信息以及摄像头的相对位置，对像素点在三维空间中的位置进行确定。
可选地，每帧图像对应的深度信息中包括该帧图像中的像素点对应的深度信息，根据该像素点的深度信息，以及像素点在图像中的位置，结合该摄像头的相对位置，即可得到该像素点在三维空间中的位置。
示意性的，像素点i的深度信息为d，该像素点i在图像k中的位置坐标为(a，b)，则该像素点i在相机坐标系中的相对位置坐标为(a*d，b*d，d)，摄像头拍摄该图像k时的旋转矩阵为R，平移矩阵为t，则该像素点i在三维空间中的坐标的计算方式如下公式一所示：
公式一：
Figure PCTCN2020074910-appb-000001
其中，L w用于表示对该像素点坐标的旋转和平移，其中，X用于表示像素点i在相机坐标系中的坐标a*d，Y用于表示像素点i在相机坐标系中的坐标b*d，Z用于表示像素点i在相机坐标系中的坐标d，X c、Y c以及Z c用于表示像素点i在三维空间中的三维坐标。
可选地，每个像素点还对应有颜色信息。可选地，深度摄像头进行一次拍摄操作得到两个图像，该两个图像包括色彩图像和深度图像，其中，色彩图像中包括每个像素点的颜色信息，深度图像中包括每个像素点的深度信息。可选地，深度图像的尺寸小于色彩图像的尺寸，则以深度图像为准，将深度图像中的像素点与色彩图像中的像素点进行匹配，得到每个像素点的颜色以及深度信息。
步骤605，根据每个像素点在三维空间中的位置得到特征点云。
可选地，根据采集的n帧图像中每个像素点在三维空间中的位置得到该特征点云，其中，针对该n帧图像中存在重合情况的像素点可以仅进行一次计算，并当该像素点在其他图像中再次出现时，忽略该像素点的再计算。
步骤606，接收位置输入操作，该位置输入操作用于对目标物体在虚拟环境中的显示位置进行确定。
可选地，该位置输入操作可以通过对特征点云在所述虚拟环境中进行拖动进行确定，也可以在上述步骤605后生成该目标物体进行预览，并通过对该目标物体在虚拟环境中进行拖动从而确定该目标物体在虚拟环境中的显示位置。
可选地，在对目标物体在虚拟环境中进行拖动的过程中，对该目标物体的位置进行预览的方式可以通过将虚拟环境中该目标物体所处的位置进行高亮显示，如：将该目标物体所处的位置进行标黑显示。
步骤607，根据拍摄操作和位置输入操作在虚拟环境中的显示位置处显示目标物体，该目标物体是由体素块在特征点云对应的区域内进行填充得到的。
可选地，对该特征点云对应的区域进行填充的体素块可以是统一颜色的体素块，也可以根据预设颜色规律进行体素块填充，还可以根据待采集物体本身的颜色确定填充该特征点云对应的区域的体素块的颜色。
可选地，当根据待采集物体本身的颜色确定体素块的颜色时，该摄像头拍摄的图像还对应有每个像素点的颜色。
综上所述，本实施例提供的基于虚拟环境的物体构建方法，通过终端的摄像头对待采集物体进行拍摄，并对待采集物体的三维信息进行采集后，根据该三维信息生成该待采集物体的特征点云，在虚拟环境中通过在特征点云对应的区域内填充体素块生成目标物体，并在该显示位置进行显示，避免了玩家手动对目标物体进行构建时，无法准确把控体素块的结构而导致物体构建失败的问题，且通过本实施例提供的方法进行构建，提高了物体的构建效率，以及物体构建的准确率。
本实施例提供的方法，通过深度摄像头对图像进行采集，并根据像素点在图像中的位置，像素点的深度信息以及摄像头的相对位置确定像素点在三维空间中的位置，从而生成特征点云，提高了生成特征点云以及生成目标物体的效率。
在一个可选地实施例中，当生成该特征点云之后，对体素块在该特征点云对应的区域内进行填充的方法进行说明，图7是本申请另一个示例性实施例提供的体素块在该特征点云对应的区域内进行填充的方法的流程图，该方法应用于如图3所示的步骤302之后，或该方法应用于如图6所示的步骤605之后，如 图7所示，该方法包括：
步骤701，接收三维切片操作，得到每个维度对应的切片方式，该三维切片操作用于根据切片方式对特征点云对应的包围盒进行三维切片。
可选地，该包围盒为包围该特征点云的最小长方体盒；或，该包围盒为根据特征点云的三维尺寸生成的与该特征点云对应的长方体盒。
可选地，该切片方式包括每个维度对应的切片数量、每个维度对应的切片大小中的任意一种。其中，当切片方式为每个维度对应的切片数量时，根据该切片数量对每个维度进行平均切片。
可选地，该三维切片是指通过每个维度对应的切片方式对包围盒的三个维度进行切片。
可选地，该三维切片操作的执行方式包括如下方式中的任意一种：
第一，接收切片数量输入操作，该切片数量输入操作包括对特征点云的三个维度的切片数量的输入操作，根据切片数量输入操作对包围盒按照该切片数量进行三维切片；
示意性的，请参考图8，在虚拟环境界面800中显示有特征点云810对应的包围盒820，默认该虚拟环境中三维方向中x轴方向、y轴方向以及z轴方向如坐标轴830所示，接收在切片数量输入框840中的切片数量设置操作，该切片数量设置结果为，x轴方向切分为10个部分，y轴方向切分为15个部分，z轴方向切分为20个部分，根据该切片数量设置结果对包围盒820进行三维切片，其中，对包围盒820在x轴方向上平均分为10份，在y轴方向上平均分为15份，在z轴方向上平均分为20份。
第二，接收滑动切片操作，根据滑动切片操作对包围盒进行三维切片。
可选地，每个维度对应的切片数量用于对目标三维模型生成目标物体的细化程度进行确定，如：切片数量较多时，该目标物体的细化程度越高，目标物体与待采集物体的相似度也越高；切片数量较少时，该目标物体的细化程度越低，目标物体与待采集物体的相似度越低。
步骤702，根据三维切片操作确定体素区域，该体素区域是通过对包围盒进行三维切片后得到的区域。
可选地，对该包围盒进行三维切片，即在该包围盒的三个维度都进行了切片操作，根据该在三个维度上的切片操作得到体素区域，该体素区域是三维切片后 得到的区域。可选地，该体素区域用于通过体素块进行填充。
步骤703，根据体素区域与特征点云中的像素点的包含关系，向体素区域中填充体素块。
可选地，当体素区域中包含的像素点的数量大于预设数量时，向该体素区域中填充体素块。
可选地，填充该体素区域的体素块为目标颜色的体素块，该目标颜色可以通过如下方式中的任意一种方式进行确定：
第一，确定体素区域中包含的像素点的加权平均颜色，得到目标颜色；
可选地，该像素点的加权平均颜色是根据像素点的RGB值进行计算的。
第二，根据体素区域中包含的像素点的颜色分布，确定分布占比最高的颜色作为目标颜色。
可选地，根据该目标颜色，将颜色与该目标颜色最接近的体素块填充于体素区域。
可选地，对体素区域包含的像素点进行遍历，并确定该体素区域对应的第一颜色(即上述目标颜色)，将第一颜色与预设颜色表中的颜色进行色差计算，得到预设颜色表中色差计算结果最小的第二颜色，该第二颜色即为该体素区域中填充的体素块的颜色。可选地，该预设颜色表为应用程序中提供的体素块的所有颜色的颜色表，通过计算第一颜色与预设颜色表中的颜色的色差，确定该预设颜色表中与该第一颜色色差最小的颜色，并将该颜色的体素块作为填充该体素区域的体素块。
可选地，计算第一颜色与预设颜色表中的颜色的色差时，可以通过欧氏距离计算法计算两个颜色之间的颜色距离，颜色距离越大，两个颜色之间的色差越大，反之，两个颜色越接近颜色距离越小。在计算颜色距离时，在RGB控件内，可以通过如下欧氏距离计算法提供的公式二计算得到两个颜色C 1、C 2之间的距离，其中，C 1为上述第一颜色，C 2为预设颜色表中的颜色：
公式二：
Figure PCTCN2020074910-appb-000002
其中，C 1,R表示第一颜色C 1的红色数值，C 2,R表示颜色C 2的红色数值，C 1,G表示第一颜色C 1的绿色数值，C 2,G表示颜色C 2的绿色数值，C 1,B表示第一颜色C 1的蓝色数值，C 2,B表示颜色C 2的蓝色数值。
将第一颜色C 1和预设颜色表中的颜色C 2的RGB值代入上述公式二后，得 到第一颜色C 1和预设颜色表中的颜色C 2的色差。
可选地，计算色差的方式除上述欧氏距离计算法外，还可以通过RGB平方法、CIELab色差计算公式(如：CIELab 76、CIELab 94)、CIEDE 2000进行计算，本申请实施例对色差计算方式不做限定。
综上所述，本实施例提供的基于虚拟环境的物体构建方法，通过终端的摄像头对待采集物体进行拍摄，并对待采集物体的三维信息进行采集后，根据该三维信息生成该待采集物体的特征点云，在虚拟环境中通过在特征点云对应的区域内填充体素块生成目标物体，并在该显示位置进行显示，避免了玩家手动对目标物体进行构建时，无法准确把控体素块的结构而导致物体构建失败的问题，且通过本实施例提供的方法进行构建，提高了物体的构建效率，以及物体构建的准确率。
本实施例提供的方法，通过将特征点云对应的包围盒进行切片处理，得到体素区域，并对该体素区域通过体素块进行填充，以切片方式确定该目标物体的切分细度，提高了物体的构建效率，以及物体构建的准确率。
图9是本申请一个示例性实施例提供的基于虚拟环境的物体构建方法的整体流程图，以该方法应用于终端中为例进行说明，如图9所示，该方法包括：
步骤901，通过终端摄像头进行拍摄，得到深度信息和图像信息。
可选地，该终端摄像头为深度摄像头，通过该摄像头对待采集物体进行拍摄，得到该待采集物体的深度信息和图像信息，其中，深度信息用于表示该待采集图像的三维信息，该图像信息用于表示该待采集图像的颜色信息。
步骤902，根据深度信息和图像信息生成特征点云。
可选地，根据深度信息和图像信息确定图像中每个像素点在三维空间中的位置，并根据每个像素点的位置生成该特征点云，具体生成方式在上述步骤604中已进行了详细说明，此处不再赘述。
步骤903，对特征点云对应的包围盒进行切片处理。
可选地，该切片处理用于对特征点云对应的包围盒进行三维切片得到体素区域，可选地，该三维切片的切片方式用于确定待构建的目标物体的细化程度，也即该目标物体与待采集物体之间的相似度。
步骤904，对体素区域进行体素包含检查。
可选地，该体素包含检查用于根据体素区域中包含的像素点的数量确定该体素区域中是否需要填充体素块。
可选地，该体素包含检查还用于确定该体素区域中包含的体素块的颜色。
步骤905，对目标物体进行位置设置。
可选地，该位置设置可以通过对特征点云在所述虚拟环境中进行拖动进行确定，也可以在上述步骤后生成该目标物体进行预览，并通过对该目标物体在虚拟环境中进行拖动从而确定该目标物体在虚拟环境中的显示位置。
步骤906，根据位置设置确定目标物体的位置。
步骤907，显示该目标物体。
综上所述，本实施例提供的基于虚拟环境的物体构建方法，通过在虚拟环境中导入目标三维模型以及选择该目标物体的显示位置，在虚拟环境中通过在目标三维模型的轮廓范围内填充体素块生成目标物体，并在该显示位置进行显示，避免了玩家手动对目标物体进行构建时，无法准确把控体素块的结构而导致物体构建失败的问题，且通过本实施例提供的方法进行构建，提高了物体的构建效率，以及物体构建的准确率。
应该理解的是，虽然图3、6、7和9的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，图3、6、7和9中的至少一部分步骤可以包括多个子步骤或者多个阶段，这些子步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些子步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤的子步骤或者阶段的至少一部分轮流或者交底地执行。
图10是本申请一个示例性实施例提供的终端的结构框图，如图10所示，该终端包括：处理器1010、显示屏1020、存储器1030以及摄像头1040；
其中，处理器1010包括CPU和GPU，CPU主要负责实现终端的计算任务，GPU主要负责实现终端的显示任务，即GPU负责根据CPU传递的数据对显示内容进行渲染，并通过显示屏1020对显示内容进行显示。
可选地，该终端中安装有基于Unity引擎1031开发的沙盒游戏应用程序 1032，该沙盒游戏应用程序1032中提供有虚拟环境，虚拟对象在该沙盒游戏应用程序1032的虚拟环境中可以通过体素块对虚拟物体进行搭建，并通过CPU以及GPU对搭建的虚拟物体在虚拟环境中进行显示。用户也可以通过本申请实施例中提供的基于虚拟环境的物体构建方法，通过摄像头1040采集待采集图像的深度信息以及图像信息，并根据深度信息和图像信息生成特征点云以填充体素块，在该沙盒游戏应用程序1032的虚拟环境中显示该待采集物体对应的目标物体。
图11是本申请一个示例性实施例提供的基于虚拟环境的物体构建装置的结构框图，以该装置应用于设置有摄像头的终端中为例进行说明，如图11所示，该装置包括：显示模块1110和接收模块1120；
显示模块1110，用于显示环境界面，所述环境界面中包括所述虚拟环境对应的画面；
接收模块1120，用于接收拍摄操作，所述拍摄操作用于通过所述摄像头对待采集物体的三维信息进行采集，得到所述待采集物体的特征点云，所述特征点云用于对待构建的目标物体的样式进行确定；
所述接收模块1120，还用于接收位置输入操作，所述位置输入操作用于对所述目标物体在所述虚拟环境中的显示位置进行确定；
所述显示模块1110，还用于根据所述拍摄操作和所述位置输入操作在所述虚拟环境中的所述显示位置处显示所述目标物体，所述目标物体是由体素块在所述特征点云对应的区域内进行填充得到的。
在一个可选的实施例中，所述接收模块1120，还用于接收在所述待采集物体周围对n帧图像的拍摄操作，所述n帧图像中包括环绕所述待采集物体拍摄得到的图像，n为正整数；
如图12所示，所述装置，还包括：
生成模块1130，用于根据所述n帧图像中每帧图像对应的深度信息生成所述特征点云，所述深度信息用于结合所述图像以表示所述待采集物体的所述三维信息；或，通过所述n帧图像对所述待采集物体进行三维重建，得到所述特征点云。
在一个可选的实施例中，所述生成模块1130，还用于确定拍摄所述n帧图 像中的每帧图像时所述摄像头所处的相对位置，其中，所述相对位置是根据所述摄像头拍摄关键帧图像时的位置关系确定的；
所述生成模块1130，还用于根据所述n帧图像中每帧图像中的像素点的位置、所述像素点对应的所述深度信息以及所述摄像头的所述相对位置，对所述像素点在三维空间中的位置进行确定；
所述生成模块1130，还用于根据每个所述像素点在所述三维空间中的位置得到所述特征点云。
在一个可选的实施例中，所述接收模块1120，还用于接收围绕所述待采集物体的视频拍摄操作，所述视频拍摄操作拍摄得到的视频流中包括所述n帧图像；
或，
所述接收模块1120，还用于接收在所述待采集物体周围的定点拍摄操作，所述定点拍摄操作用于围绕所述待采集物体在指定位置对所述n帧图像进行拍摄。
在一个可选的实施例中，所述接收模块1120，还用于接收三维切片操作，得到每个维度对应的切片方式，所述三维切片操作用于根据所述切片方式对所述特征点云对应的包围盒进行三维切片；
所述装置，还包括：
确定模块1140，用于根据所述三维切片操作确定体素区域，所述体素区域是通过对所述包围盒进行所述三维切片后得到的区域，所述体素区域用于通过所述体素块进行填充；
填充模块1150，用于根据所述体素区域与所述特征点云中的像素点的包含关系，向所述体素区域中填充所述体素块。
在一个可选的实施例中，所述接收模块1120，还用于接收切片数量输入操作，所述切片数量输入操作包括对所述特征点云的三个维度的所述切片数量的输入操作；根据所述切片数量输入操作对所述包围盒按照所述切片数量进行所述三维切片；
或，
所述接收模块1120，还用于接收滑动切片操作，根据所述滑动切片操作对所述包围盒进行所述三维切片；
其中，每个维度对应的所述切片数量用于对所述特征点云生成所述目标物体的细化程度进行确定。
在一个可选的实施例中，所述填充模块1150，还用于当所述体素区域中包含的所述像素点的数量大于预设数量时，向所述体素区域中填充所述体素块。
在一个可选的实施例中，所述填充模块1150，还用于确定所述体素区域中包含的所述像素点的加权平均颜色，得到目标颜色，将颜色与所述目标颜色最接近的所述体素块填充于所述体素区域；
或，
所述填充模块1150，还用于根据所述体素区域中包含的像素点的颜色分布，确定分布占比最高的颜色作为所述目标颜色，将颜色与所述目标颜色最接近的所述体素块填充于所述体素区域。
综上所述，本实施例提供的基于虚拟环境的物体构建装置，通过在虚拟环境中导入目标三维模型以及选择该目标物体的显示位置，在虚拟环境中通过在目标三维模型的轮廓范围内填充体素块生成目标物体，并在该显示位置进行显示，避免了玩家手动对目标物体进行构建时，无法准确把控体素块的结构而导致物体构建失败的问题，且通过本实施例提供的方法进行构建，提高了物体的构建效率，以及物体构建的准确率。
需要说明的是：上述实施例提供的基于虚拟环境的物体构建装置，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将设备的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。另外，上述实施例提供的基于虚拟环境的物体构建装置与基于虚拟环境的物体构建方法的方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。
图13示出了本发明一个示例性实施例提供的终端1300的结构框图。该终端1300可以是：智能手机、平板电脑、MP3播放器(Moving Picture Experts Group Audio Layer III，动态影像专家压缩标准音频层面3)、MP4(Moving Picture Experts Group Audio Layer IV，动态影像专家压缩标准音频层面4)播放器、笔记本电脑或台式电脑。终端1300还可能被称为用户设备、便携式终端、膝上型终端、台 式终端等其他名称。
通常，终端1300包括有：处理器1301和存储器1302。
处理器1301可以包括一个或多个处理核心，比如4核心处理器、8核心处理器等。处理器1301可以采用DSP(Digital Signal Processing，数字信号处理)、FPGA(Field－Programmable Gate Array，现场可编程门阵列)、PLA(Programmable Logic Array，可编程逻辑阵列)中的至少一种硬件形式来实现。处理器1301也可以包括主处理器和协处理器，主处理器是用于对在唤醒状态下的数据进行处理的处理器，也称CPU(Central Processing Unit，中央处理器)；协处理器是用于对在待机状态下的数据进行处理的低功耗处理器。在一些实施例中，处理器1301可以在集成有GPU(Graphics Processing Unit，图像处理器)，GPU用于负责显示屏所需要显示的内容的渲染和绘制。一些实施例中，处理器1301还可以包括AI(Artificial Intelligence，人工智能)处理器，该AI处理器用于处理有关机器学习的计算操作。
存储器1302可以包括一个或多个计算机可读存储介质，该计算机可读存储介质可以是非暂态的。存储器1302还可包括高速随机存取存储器，以及非易失性存储器，比如一个或多个磁盘存储设备、闪存存储设备。在一些实施例中，存储器1302中的非暂态的计算机可读存储介质用于存储至少一个指令，该至少一个指令用于被处理器1301所执行以实现本申请中方法实施例提供的基于虚拟环境的物体构建方法。
在一些实施例中，终端1300还可选包括有：外围设备接口1303和至少一个外围设备。处理器1301、存储器1302和外围设备接口1303之间可以通过总线或信号线相连。各个外围设备可以通过总线、信号线或电路板与外围设备接口1303相连。具体地，外围设备包括：射频电路1304、触摸显示屏1305、摄像头1306、音频电路1307、定位组件1308和电源1309中的至少一种。
外围设备接口1303可被用于将I/O(Input/Output，输入/输出)相关的至少一个外围设备连接到处理器1301和存储器1302。在一些实施例中，处理器1301、存储器1302和外围设备接口1303被集成在同一芯片或电路板上；在一些其他实施例中，处理器1301、存储器1302和外围设备接口1303中的任意一个或两个可以在单独的芯片或电路板上实现，本实施例对此不加以限定。
射频电路1304用于接收和发射RF(Radio Frequency，射频)信号，也称电 磁信号。射频电路1304通过电磁信号与通信网络以及其他通信设备进行通信。射频电路1304将电信号转换为电磁信号进行发送，或者，将接收到的电磁信号转换为电信号。可选地，射频电路1304包括：天线系统、RF收发器、一个或多个放大器、调谐器、振荡器、数字信号处理器、编解码芯片组、用户身份模块卡等等。射频电路1304可以通过至少一种无线通信协议来与其它终端进行通信。该无线通信协议包括但不限于：万维网、城域网、内联网、各代移动通信网络(2G、3G、4G及5G)、无线局域网和/或WiFi(Wireless Fidelity，无线保真)网络。在一些实施例中，射频电路1304还可以包括NFC(Near Field Communication，近距离无线通信)有关的电路，本申请对此不加以限定。
显示屏1305用于显示UI(User Interface，用户界面)。该UI可以包括图形、文本、图标、视频及其它们的任意组合。当显示屏1305是触摸显示屏时，显示屏1305还具有采集在显示屏1305的表面或表面上方的触摸信号的能力。该触摸信号可以作为控制信号输入至处理器1301进行处理。此时，显示屏1305还可以用于提供虚拟按钮和/或虚拟键盘，也称软按钮和/或软键盘。在一些实施例中，显示屏1305可以为一个，设置终端1300的前面板；在另一些实施例中，显示屏1305可以为至少两个，分别设置在终端1300的不同表面或呈折叠设计；在再一些实施例中，显示屏1305可以是柔性显示屏，设置在终端1300的弯曲表面上或折叠面上。甚至，显示屏1305还可以设置成非矩形的不规则图形，也即异形屏。显示屏1305可以采用LCD(Liquid Crystal Display，液晶显示屏)、OLED(Organic Light-Emitting Diode,有机发光二极管)等材质制备。
摄像头组件1306用于采集图像或视频。可选地，摄像头组件1306包括前置摄像头和后置摄像头。通常，前置摄像头设置在终端的前面板，后置摄像头设置在终端的背面。在一些实施例中，后置摄像头为至少两个，分别为主摄像头、景深摄像头、广角摄像头、长焦摄像头中的任意一种，以实现主摄像头和景深摄像头融合实现背景虚化功能、主摄像头和广角摄像头融合实现全景拍摄以及VR(Virtual Reality，虚拟现实)拍摄功能或者其它融合拍摄功能。在一些实施例中，摄像头组件1306还可以包括闪光灯。闪光灯可以是单色温闪光灯，也可以是双色温闪光灯。双色温闪光灯是指暖光闪光灯和冷光闪光灯的组合，可以用于不同色温下的光线补偿。
音频电路1307可以包括麦克风和扬声器。麦克风用于采集用户及环境的声 波，并将声波转换为电信号输入至处理器1301进行处理，或者输入至射频电路1304以实现语音通信。出于立体声采集或降噪的目的，麦克风可以为多个，分别设置在终端1300的不同部位。麦克风还可以是阵列麦克风或全向采集型麦克风。扬声器则用于将来自处理器1301或射频电路1304的电信号转换为声波。扬声器可以是传统的薄膜扬声器，也可以是压电陶瓷扬声器。当扬声器是压电陶瓷扬声器时，不仅可以将电信号转换为人类可听见的声波，也可以将电信号转换为人类听不见的声波以进行测距等用途。在一些实施例中，音频电路1307还可以包括耳机插孔。
定位组件1308用于定位终端1300的当前地理位置，以实现导航或LBS(Location Based Service，基于位置的服务)。定位组件1308可以是基于美国的GPS(Global Positioning System，全球定位系统)、中国的北斗系统或俄罗斯的伽利略系统的定位组件。
电源1309用于为终端1300中的各个组件进行供电。电源1309可以是交流电、直流电、一次性电池或可充电电池。当电源1309包括可充电电池时，该可充电电池可以是有线充电电池或无线充电电池。有线充电电池是通过有线线路充电的电池，无线充电电池是通过无线线圈充电的电池。该可充电电池还可以用于支持快充技术。
在一些实施例中，终端1300还包括有一个或多个传感器1310。该一个或多个传感器1310包括但不限于：加速度传感器1311、陀螺仪传感器1312、压力传感器1313、指纹传感器1314、光学传感器1315以及接近传感器1316。
加速度传感器1311可以检测以终端1300建立的坐标系的三个坐标轴上的加速度大小。比如，加速度传感器1311可以用于检测重力加速度在三个坐标轴上的分量。处理器1301可以根据加速度传感器1311采集的重力加速度信号，控制触摸显示屏1305以横向视图或纵向视图进行用户界面的显示。加速度传感器1311还可以用于游戏或者用户的运动数据的采集。
陀螺仪传感器1312可以检测终端1300的机体方向及转动角度，陀螺仪传感器1312可以与加速度传感器1311协同采集用户对终端1300的3D动作。处理器1301根据陀螺仪传感器1312采集的数据，可以实现如下功能：动作感应(比如根据用户的倾斜操作来改变UI)、拍摄时的图像稳定、游戏控制以及惯性导航。
压力传感器1313可以设置在终端1300的侧边框和/或触摸显示屏1305的下层。当压力传感器1313设置在终端1300的侧边框时，可以检测用户对终端1300的握持信号，由处理器1301根据压力传感器1313采集的握持信号进行左右手识别或快捷操作。当压力传感器1313设置在触摸显示屏1305的下层时，由处理器1301根据用户对触摸显示屏1305的压力操作，实现对UI界面上的可操作性控件进行控制。可操作性控件包括按钮控件、滚动条控件、图标控件、菜单控件中的至少一种。
指纹传感器1314用于采集用户的指纹，由处理器1301根据指纹传感器1314采集到的指纹识别用户的身份，或者，由指纹传感器1314根据采集到的指纹识别用户的身份。在识别出用户的身份为可信身份时，由处理器1301授权该用户执行相关的敏感操作，该敏感操作包括解锁屏幕、查看加密信息、下载软件、支付及更改设置等。指纹传感器1314可以被设置终端1300的正面、背面或侧面。当终端1300上设置有物理按键或厂商Logo时，指纹传感器1314可以与物理按键或厂商Logo集成在一起。
光学传感器1315用于采集环境光强度。在一个实施例中，处理器1301可以根据光学传感器1315采集的环境光强度，控制触摸显示屏1305的显示亮度。具体地，当环境光强度较高时，调高触摸显示屏1305的显示亮度；当环境光强度较低时，调低触摸显示屏1305的显示亮度。在另一个实施例中，处理器1301还可以根据光学传感器1315采集的环境光强度，动态调整摄像头组件1306的拍摄参数。
接近传感器1316，也称距离传感器，通常设置在终端1300的前面板。接近传感器1316用于采集用户与终端1300的正面之间的距离。在一个实施例中，当接近传感器1316检测到用户与终端1300的正面之间的距离逐渐变小时，由处理器1301控制触摸显示屏1305从亮屏状态切换为息屏状态；当接近传感器1316检测到用户与终端1300的正面之间的距离逐渐变大时，由处理器1301控制触摸显示屏1305从息屏状态切换为亮屏状态。
本领域技术人员可以理解，图13中示出的结构并不构成对终端1300的限定，可以包括比图示更多或更少的组件，或者组合某些组件，或者采用不同的组件布置。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，该计算机可读存储介质可以是上述实施例中的存储器中所包含的计算机可读存储介质；也可以是单独存在，未装配入终端中的计算机可读存储介质。该计算机可读存储介质中存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行以实现如图3、图6以及图7任一所述的基于虚拟环境的物体构建方法。
另一方面，提供了一种计算机设备，所述计算机设备包括处理器和存储器，所述存储器中存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行以实现如图3、图6以及图7任一所述的基于虚拟环境的物体构建方法。
另一方面，提供了一种计算机可读存储介质，所述可读存储介质中存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行以实现如图3、图6以及图7任一所述的基于虚拟环境的物体构建方法。
另一方面，提供了一种计算机程序产品，当所述计算机程序产品在计算机上运行时，使得计算机执行如图3、图6以及图7任一所述的基于虚拟环境的物体构建方法。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一非易失性计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、 直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。以上实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对申请专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。

Claims (20)

  1. 一种基于虚拟环境的物体构建方法，其特征在于，应用于设置有摄像头的终端中，所述方法包括：
    显示环境界面，所述环境界面中包括所述虚拟环境对应的画面；
    接收拍摄操作，所述拍摄操作用于通过所述摄像头对待采集物体的三维信息进行采集，得到所述待采集物体的特征点云，所述特征点云用于对待构建的目标物体的样式进行确定；
    接收位置输入操作，所述位置输入操作用于对所述目标物体在所述虚拟环境中的显示位置进行确定；
    根据所述拍摄操作和所述位置输入操作在所述虚拟环境中的所述显示位置处显示所述目标物体，所述目标物体是由体素块在所述特征点云对应的区域内进行填充得到的。
  2. 根据权利要求1所述的方法，其特征在于，所述接收拍摄操作，包括：
    接收在所述待采集物体周围对n帧图像的拍摄操作，所述n帧图像中包括环绕所述待采集物体拍摄得到的图像，n为正整数；
    根据所述n帧图像中每帧图像对应的深度信息生成所述特征点云；或，
    通过所述n帧图像对所述待采集物体进行三维重建，得到所述特征点云。
  3. 根据权利要求2所述的方法，其特征在于，所述根据所述n帧图像中每帧图像对应的深度信息生成所述特征点云，包括：
    确定拍摄所述n帧图像中的每帧图像时所述摄像头所处的相对位置，其中，所述相对位置是根据与所述摄像头拍摄关键帧图像时的位置关系确定的；
    根据所述n帧图像中每帧图像中的像素点的位置、所述像素点对应的所述深度信息以及所述摄像头的所述相对位置，对所述像素点在三维空间中的位置进行确定；
    根据每个所述像素点在所述三维空间中的位置得到所述特征点云。
  4. 根据权利要求2所述的方法，其特征在于，所述接收在所述待采集物体周围对n帧图像的拍摄操作，包括：
    接收围绕所述待采集物体的视频拍摄操作，所述视频拍摄操作拍摄得到的视频流中包括所述n帧图像；或，
    接收在所述待采集物体周围的定点拍摄操作，所述定点拍摄操作用于围绕 所述待采集物体在指定位置对所述n帧图像进行拍摄。
  5. 根据权利要求1至4任一所述的方法，其特征在于，所述体素块在所述特征点云对应的区域内进行填充的方法包括：
    接收三维切片操作，得到每个维度对应的切片方式，所述三维切片操作用于根据所述切片方式对所述特征点云对应的包围盒进行三维切片；
    根据所述三维切片操作确定体素区域，所述体素区域是通过对所述包围盒进行所述三维切片后得到的区域；
    根据所述体素区域与所述特征点云中的像素点的包含关系，向所述体素区域中填充所述体素块。
  6. 根据权利要求5所述的方法，其特征在于，所述接收三维切片操作，包括：
    接收切片数量输入操作，所述切片数量输入操作包括对所述特征点云的三个维度的所述切片数量的输入操作；根据所述切片数量输入操作对所述包围盒按照所述切片数量进行所述三维切片；或，
    接收滑动切片操作，根据所述滑动切片操作对所述包围盒进行所述三维切片；
    其中，每个维度对应的所述切片数量用于对所述特征点云生成所述目标物体的细化程度进行确定。
  7. 根据权利要求5所述的方法，其特征在于，所述根据所述体素区域与所述特征点云中的像素点的包含关系，向所述体素区域中填充所述体素块，包括：
    当所述体素区域中包含的所述像素点的数量大于预设数量时，向所述体素区域中填充所述体素块。
  8. 根据权利要求7所述的方法，其特征在于，所述向所述体素区域中填充所述体素块，包括：
    确定所述体素区域中包含的所述像素点的加权平均颜色，得到目标颜色，将颜色与所述目标颜色最接近的所述体素块填充于所述体素区域；或，
    根据所述体素区域中包含的像素点的颜色分布，确定分布占比最高的颜色作为所述目标颜色，将颜色与所述目标颜色最接近的所述体素块填充于所述体素区域。
  9. 一种基于虚拟环境的物体构建装置，其特征在于，应用于设置有摄像头 的终端中，所述装置包括：
    显示模块，用于显示环境界面，所述环境界面中包括所述虚拟环境对应的画面；
    接收模块，用于接收拍摄操作，所述拍摄操作用于通过所述摄像头对待采集物体的三维信息进行采集，得到所述待采集物体的特征点云，所述特征点云用于对待构建的目标物体的样式进行确定；
    所述接收模块，还用于接收位置输入操作，所述位置输入操作用于对所述目标物体在所述虚拟环境中的显示位置进行确定；
    所述显示模块，还用于根据所述拍摄操作和所述位置输入操作在所述虚拟环境中的所述显示位置处显示所述目标物体，所述目标物体是由体素块在所述特征点云对应的区域内进行填充得到的。
  10. 根据权利要求9所述的装置，其特征在于，所述接收模块，还用于接收在所述待采集物体周围对n帧图像的拍摄操作，所述n帧图像中包括环绕所述待采集物体拍摄得到的图像，n为正整数；
    所述装置，还包括：
    生成模块，用于根据所述n帧图像中每帧图像对应的深度信息生成所述特征点云；或，通过所述n帧图像对所述待采集物体进行三维重建，得到所述特征点云。
  11. 根据权利要求10所述的装置，其特征在于，所述生成模块，还用于确定单元，用于确定拍摄所述n帧图像中的每帧图像时所述摄像头所处的相对位置，其中，所述相对位置是根据所述摄像头拍摄关键帧图像时的位置关系确定的；
    所述生成模块，还用于根据所述n帧图像中每帧图像中的像素点的位置、所述像素点对应的所述深度信息以及所述摄像头的所述相对位置，对所述像素点在三维空间中的位置进行确定；
    所述生成模块，还用于根据每个所述像素点在所述三维空间中的位置得到所述特征点云。
  12. 根据权利要求10所述的装置，其特征在于，所述接收模块，还用于接收围绕所述待采集物体的视频拍摄操作，所述视频拍摄操作拍摄得到的视频流中包括所述n帧图像；或，
    所述接收模块，还用于接收在所述待采集物体周围的定点拍摄操作，所述定 点拍摄操作用于围绕所述待采集物体在指定位置对所述n帧图像进行拍摄。
  13. 根据权利要求9至12任一所述的装置，其特征在于，所述接收模块，还用于接收三维切片操作，得到每个维度对应的切片方式，所述三维切片操作用于根据所述切片方式对所述特征点云对应的包围盒进行三维切片；
    所述装置，还包括：
    确定模块，用于根据所述三维切片操作确定体素区域，所述体素区域是通过对所述包围盒进行所述三维切片后得到的区域，所述体素区域用于通过所述体素块进行填充；
    填充模块，用于根据所述体素区域与所述特征点云中的像素点的包含关系，向所述体素区域中填充所述体素块。
  14. 一种计算机设备，其特征在于，所述计算机设备包括处理器和存储器，所述存储器中存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行时，使得所述处理器执行以下步骤：
    显示环境界面，所述环境界面中包括所述虚拟环境对应的画面；
    接收拍摄操作，所述拍摄操作用于通过所述摄像头对待采集物体的三维信息进行采集，得到所述待采集物体的特征点云，所述特征点云用于对待构建的目标物体的样式进行确定；
    接收位置输入操作，所述位置输入操作用于对所述目标物体在所述虚拟环境中的显示位置进行确定；
    根据所述拍摄操作和所述位置输入操作在所述虚拟环境中的所述显示位置处显示所述目标物体，所述目标物体是由体素块在所述特征点云对应的区域内进行填充得到的。
  15. 如权利要求14所述的计算机设备，其特征在于，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行时，使得所述处理器还执行以下步骤：
    接收在所述待采集物体周围对n帧图像的拍摄操作，所述n帧图像中包括环绕所述待采集物体拍摄得到的图像，n为正整数；
    根据所述n帧图像中每帧图像对应的深度信息生成所述特征点云；或，
    通过所述n帧图像对所述待采集物体进行三维重建，得到所述特征点云。
  16. 如权利要求15所述的计算机设备，其特征在于，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行根据所述n帧图像中每帧图像对应的深度信息生成所述特征点云的步骤时，使得所述处理器具体执行以下步骤：
    确定拍摄所述n帧图像中的每帧图像时所述摄像头所处的相对位置，其中，所述相对位置是根据与所述摄像头拍摄关键帧图像时的位置关系确定的；
    根据所述n帧图像中每帧图像中的像素点的位置、所述像素点对应的所述深度信息以及所述摄像头的所述相对位置，对所述像素点在三维空间中的位置进行确定；
    根据每个所述像素点在所述三维空间中的位置得到所述特征点云。
  17. 如权利要求16所述的计算机设备，其特征在于，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行接收在所述待采集物体周围对n帧图像的拍摄操作的步骤时，使得所述处理器具体执行以下步骤：
    接收围绕所述待采集物体的视频拍摄操作，所述视频拍摄操作拍摄得到的视频流中包括所述n帧图像；或，
    接收在所述待采集物体周围的定点拍摄操作，所述定点拍摄操作用于围绕所述待采集物体在指定位置对所述n帧图像进行拍摄。
  18. 一种计算机可读存储介质，其特征在于，所述可读存储介质中存储有至少一条指令、至少一段程序、代码集或指令集，所述至少一条指令、所述至少一段程序、所述代码集或指令集由处理器加载并执行时，使得所述处理器执行以下步骤：
    显示环境界面，所述环境界面中包括所述虚拟环境对应的画面；
    接收拍摄操作，所述拍摄操作用于通过所述摄像头对待采集物体的三维信息进行采集，得到所述待采集物体的特征点云，所述特征点云用于对待构建的目标物体的样式进行确定；
    接收位置输入操作，所述位置输入操作用于对所述目标物体在所述虚拟环境中的显示位置进行确定；
    根据所述拍摄操作和所述位置输入操作在所述虚拟环境中的所述显示位置处显示所述目标物体，所述目标物体是由体素块在所述特征点云对应的区域内 进行填充得到的。
  19. 如权利要求18所述的存储介质，其特征在于，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行时，使得所述处理器还执行以下步骤：
    接收在所述待采集物体周围对n帧图像的拍摄操作，所述n帧图像中包括环绕所述待采集物体拍摄得到的图像，n为正整数；
    根据所述n帧图像中每帧图像对应的深度信息生成所述特征点云；或，
    通过所述n帧图像对所述待采集物体进行三维重建，得到所述特征点云。
  20. 如权利要求19所述的存储介质，其特征在于，所述至少一条指令、所述至少一段程序、所述代码集或指令集由所述处理器加载并执行根据所述n帧图像中每帧图像对应的深度信息生成所述特征点云的步骤时，使得所述处理器具体执行以下步骤：
    确定拍摄所述n帧图像中的每帧图像时所述摄像头所处的相对位置，其中，所述相对位置是根据与所述摄像头拍摄关键帧图像时的位置关系确定的；
    根据所述n帧图像中每帧图像中的像素点的位置、所述像素点对应的所述深度信息以及所述摄像头的所述相对位置，对所述像素点在三维空间中的位置进行确定；
    根据每个所述像素点在所述三维空间中的位置得到所述特征点云。
PCT/CN2020/074910 2019-04-25 2020-02-12 基于虚拟环境的物体构建方法、装置、计算机设备及可读存储介质 WO2020215858A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP20794587.4A EP3960261A4 (en) 2019-04-25 2020-02-12 OBJECT CONSTRUCTION METHOD AND DEVICE BASED ON VIRTUAL ENVIRONMENT, COMPUTER DEVICE AND READABLE STORAGE MEDIUM
US17/345,366 US12059615B2 (en) 2019-04-25 2021-06-11 Virtual-environment-based object construction method and apparatus, computer device, and computer-readable storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910340401.4 2019-04-25
CN201910340401.4A CN110064200B (zh) 2019-04-25 2019-04-25 基于虚拟环境的物体构建方法、装置及可读存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/345,366 Continuation US12059615B2 (en) 2019-04-25 2021-06-11 Virtual-environment-based object construction method and apparatus, computer device, and computer-readable storage medium

Publications (1)

Publication Number Publication Date
WO2020215858A1 true WO2020215858A1 (zh) 2020-10-29

Family

ID=67369031

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/074910 WO2020215858A1 (zh) 2019-04-25 2020-02-12 基于虚拟环境的物体构建方法、装置、计算机设备及可读存储介质

Country Status (4)

Country Link
US (1) US12059615B2 (zh)
EP (1) EP3960261A4 (zh)
CN (1) CN110064200B (zh)
WO (1) WO2020215858A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4343698A4 (en) * 2021-06-26 2024-09-04 Huawei Tech Co Ltd MODELING METHOD AND ASSOCIATED ELECTRONIC DEVICE AND STORAGE MEDIUM

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110064200B (zh) * 2019-04-25 2022-02-22 腾讯科技（深圳）有限公司 基于虚拟环境的物体构建方法、装置及可读存储介质
CN112308103B (zh) * 2019-08-02 2023-10-20 杭州海康威视数字技术股份有限公司 生成训练样本的方法和装置
CN111429553B (zh) * 2020-04-22 2024-03-29 同济大学建筑设计研究院(集团)有限公司 动画预览方法、装置、计算机设备和存储介质
CN111599223A (zh) * 2020-06-12 2020-08-28 浙江商汤科技开发有限公司 沙盘展示系统及沙盘展示方法
CN112085823B (zh) * 2020-09-01 2024-05-24 上海擎朗智能科技有限公司 一种激光地图的拼接方法、装置、电子设备及存储介质
CN114911550A (zh) * 2021-02-09 2022-08-16 阿里巴巴集团控股有限公司 云应用界面处理系统、方法、装置及设备
CN112947238B (zh) 2021-03-15 2021-11-09 哈尔滨工业大学 一种基于vr技术的工业机器人实时控制系统
DE102023104579A1 (de) * 2022-02-25 2023-08-31 Adobe Inc. Beschneiden zur effizienten dreidimensionalen Digitalwiedergabe
CN114863037B (zh) * 2022-07-06 2022-10-11 杭州像衍科技有限公司 基于单手机的人体三维建模数据采集与重建方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108136257A (zh) * 2015-08-17 2018-06-08 乐高公司 创建虚拟游戏环境的方法和采用该方法的互动游戏系统
WO2018203029A1 (en) * 2017-05-05 2018-11-08 Sony Interactive Entertainment Inc. System and method of 3d print modelling
CN109525831A (zh) * 2017-09-19 2019-03-26 佳能株式会社 提供装置、提供方法和计算机可读存储介质
CN109641150A (zh) * 2016-07-05 2019-04-16 乐高公司 用于创建虚拟对象的方法
CN110064200A (zh) * 2019-04-25 2019-07-30 腾讯科技（深圳）有限公司 基于虚拟环境的物体构建方法、装置及可读存储介质

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10702216B2 (en) * 2010-06-08 2020-07-07 Styku, LLC Method and system for body scanning and display of biometric data
CA2836201C (en) * 2011-11-17 2014-07-29 Techmed 3D Inc. Method and system for forming a virtual model of a human subject
CN103971404B (zh) * 2014-04-14 2017-04-12 浙江工业大学 一种高性价比的3d实景复制装置
US9852543B2 (en) * 2015-03-27 2017-12-26 Snap Inc. Automated three dimensional model generation
WO2017168038A1 (en) * 2016-03-31 2017-10-05 Umbra Software Oy Virtual reality streaming
JP6919864B2 (ja) * 2017-02-17 2021-08-18 エスゼット ディージェイアイ テクノロジー カンパニー リミテッドＳｚ Ｄｊｉ Ｔｅｃｈｎｏｌｏｇｙ Ｃｏ．，Ｌｔｄ ３次元点群の再構成のための方法および装置
CN108694741B (zh) * 2017-04-07 2021-11-12 杭州海康威视数字技术股份有限公司 一种三维重建方法及装置
CN108122275A (zh) * 2017-12-22 2018-06-05 清华大学 基于骨架跟踪的动态实时三维人体重建方法及系统
CN108537876B (zh) * 2018-03-05 2020-10-16 清华-伯克利深圳学院筹备办公室 三维重建方法、装置、设备及存储介质
CN108550181B (zh) * 2018-03-12 2020-07-31 中国科学院自动化研究所 移动设备上在线跟踪与稠密重建方法、系统及设备
CN108596948A (zh) * 2018-03-16 2018-09-28 中国科学院自动化研究所 基于深度相机识别人体头部姿态的方法及装置
CN109003325B (zh) * 2018-06-01 2023-08-04 杭州易现先进科技有限公司 一种三维重建的方法、介质、装置和计算设备
CN109410316B (zh) * 2018-09-21 2023-07-07 达闼机器人股份有限公司 物体的三维重建的方法、跟踪方法、相关装置及存储介质
CN109584362B (zh) * 2018-12-14 2023-03-21 北京市商汤科技开发有限公司 三维模型构建方法及装置、电子设备和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108136257A (zh) * 2015-08-17 2018-06-08 乐高公司 创建虚拟游戏环境的方法和采用该方法的互动游戏系统
CN109641150A (zh) * 2016-07-05 2019-04-16 乐高公司 用于创建虚拟对象的方法
WO2018203029A1 (en) * 2017-05-05 2018-11-08 Sony Interactive Entertainment Inc. System and method of 3d print modelling
CN109525831A (zh) * 2017-09-19 2019-03-26 佳能株式会社 提供装置、提供方法和计算机可读存储介质
CN110064200A (zh) * 2019-04-25 2019-07-30 腾讯科技（深圳）有限公司 基于虚拟环境的物体构建方法、装置及可读存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3960261A4

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP4343698A4 (en) * 2021-06-26 2024-09-04 Huawei Tech Co Ltd MODELING METHOD AND ASSOCIATED ELECTRONIC DEVICE AND STORAGE MEDIUM

Also Published As

Publication number Publication date
EP3960261A1 (en) 2022-03-02
US20210299560A1 (en) 2021-09-30
US12059615B2 (en) 2024-08-13
EP3960261A4 (en) 2022-07-13
CN110064200B (zh) 2022-02-22
CN110064200A (zh) 2019-07-30

Similar Documents

Publication Publication Date Title
WO2020215858A1 (zh) 基于虚拟环境的物体构建方法、装置、计算机设备及可读存储介质
US11158083B2 (en) Position and attitude determining method and apparatus, smart device, and storage medium
US11798190B2 (en) Position and pose determining method, apparatus, smart device, and storage medium
WO2019223468A1 (zh) 相机姿态追踪方法、装置、设备及系统
US11962930B2 (en) Method and apparatus for controlling a plurality of virtual characters, device, and storage medium
CN108682038B (zh) 位姿确定方法、装置及存储介质
CN109308727B (zh) 虚拟形象模型生成方法、装置及存储介质
WO2020207146A1 (zh) 基于虚拟环境的物体构建方法、装置、计算机设备及可读存储介质
CN110427110B (zh) 一种直播方法、装置以及直播服务器
CN110148178B (zh) 相机定位方法、装置、终端及存储介质
CN111701238A (zh) 虚拟画卷的显示方法、装置、设备及存储介质
CN111464749B (zh) 进行图像合成的方法、装置、设备及存储介质
JP2021524957A (ja) 画像処理方法およびその、装置、端末並びにコンピュータプログラム
WO2022052620A1 (zh) 图像生成方法及电子设备
CN111784841A (zh) 重建三维图像的方法、装置、电子设备及介质
CN112308103B (zh) 生成训练样本的方法和装置
CN112257594B (zh) 多媒体数据的显示方法、装置、计算机设备及存储介质
CN109833623B (zh) 基于虚拟环境的物体构建方法、装置及可读存储介质
US20240359095A1 (en) Virtual-environment-based object construction method and apparatus, computer device, and computer-readable storage medium
WO2024108555A1 (zh) 人脸图像生成方法、装置、设备以及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20794587

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020794587

Country of ref document: EP

Effective date: 20211125