WO2019137006A1 - 虚实对象合成方法及装置 - Google Patents

虚实对象合成方法及装置 Download PDF

Info

Publication number
WO2019137006A1
WO2019137006A1 PCT/CN2018/101241 CN2018101241W WO2019137006A1 WO 2019137006 A1 WO2019137006 A1 WO 2019137006A1 CN 2018101241 W CN2018101241 W CN 2018101241W WO 2019137006 A1 WO2019137006 A1 WO 2019137006A1
Authority
WO
WIPO (PCT)
Prior art keywords
depth information
virtual object
virtual
target object
terminal device
Prior art date
Application number
PCT/CN2018/101241
Other languages
English (en)
French (fr)
Inventor
林形省
Original Assignee
北京小米移动软件有限公司
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 北京小米移动软件有限公司 filed Critical 北京小米移动软件有限公司
Priority to RU2018143709A priority Critical patent/RU2715797C1/ru
Priority to JP2018567578A priority patent/JP2020507136A/ja
Priority to KR1020197004558A priority patent/KR102194094B1/ko
Publication of WO2019137006A1 publication Critical patent/WO2019137006A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
    • 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
    • G06T19/006—Mixed reality
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/60—Editing figures and text; Combining figures or text
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/00—3D [Three Dimensional] image rendering
    • G06T15/10—Geometric effects
    • G06T15/20—Perspective computation
    • 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
    • G06T7/70—Determining position or orientation of objects or cameras
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/64—Three-dimensional objects
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
    • H04N21/4728—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for selecting a Region Of Interest [ROI], e.g. for requesting a higher resolution version of a selected region
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging
    • 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

Definitions

  • the present disclosure relates to the field of image processing technologies, and in particular, to a method and apparatus for synthesizing virtual and real objects.
  • AR Augmented Reality
  • AR Augmented Reality
  • the virtual and real object synthesis method in the related art can correctly handle the occlusion relationship of the virtual real object in some cases, but has a large amount of calculation, and is not suitable for the terminal device such as a mobile phone or a tablet computer.
  • the present disclosure provides a virtual and real object synthesis method and apparatus, which can correctly display a virtual object in an image captured by a terminal device in real time.
  • a method for synthesizing a virtual object comprising: acquiring a target object in an image captured by the terminal device; in the depth information fusion mode Obtaining depth information of the target object by using an imaging device of the terminal device, where the depth information fusion mode is used to superimpose a virtual object generated by computer modeling into the image, and depth information of the target object is used for Representing a distance between the target object and the terminal device; acquiring depth information of the virtual object; and superimposing the virtual object into the image based on depth information of the target object and depth information of the virtual object.
  • the superimposing the virtual object into the image based on the depth information of the target object and the depth information of the virtual object includes: if the depth information of the target object is smaller than Depicting the depth information of the virtual object, the portion of the virtual object that is not obscured by the target object is superimposed on the image.
  • the superimposing the virtual object into the image based on the depth information of the target object and the depth information of the virtual object includes: if the depth information of the target object is greater than or Equal to the depth information of the virtual object, the virtual object is superimposed on the image.
  • the camera device of the terminal device includes at least two cameras, and acquiring the depth information of the target object by using the camera device of the terminal device, including: according to the target object and the at least The positional relationship of the two cameras and the distance between the at least two cameras determine depth information of the target object.
  • acquiring the depth information of the virtual object includes: acquiring location information of a location of the virtual object; and determining depth information of the virtual object according to the location information.
  • a virtual object synthesizing device configured to apply to a terminal device, and the device includes: an object acquiring module, configured to acquire a target object in an image captured by the terminal device; An information acquiring module, configured to acquire depth information of the target object by using an imaging device of the terminal device in the depth information fusion mode, where the depth information fusion mode is used to superimpose a virtual object generated by computer modeling to In the image, the depth information of the target object is used to represent the distance between the target object and the terminal device; the second information acquiring module is configured to acquire depth information of the virtual object; and the overlay module is configured to be based on the target object The depth information and the depth information of the virtual object, the virtual object is superimposed into the image.
  • the superimposing module includes: a first superposition sub-module, configured to superimpose the virtual image on the image when depth information of the target object is smaller than depth information of the virtual object The portion of the object that is not obscured by the target object.
  • the superimposing module further includes: a second superposition sub-module, configured to superimpose on the image when the depth information of the target object is greater than or equal to the depth information of the virtual object The virtual object.
  • the first obtaining module includes: a first determining submodule, configured to: according to a positional relationship between the target object and the at least two cameras, and between the at least two cameras The distance determines depth information of the target object.
  • the second obtaining module includes: an acquiring submodule, configured to acquire location information of a location of the virtual object; and a second determining submodule, configured to determine, according to the location information, Describe the depth information of the virtual object.
  • the technical solution provided by the embodiment of the present disclosure may include the following effects: the occlusion relationship of the object of different depth information is different.
  • the terminal device after acquiring the target object, the terminal device is based on the depth information of the target object and the depth information of the virtual object.
  • the virtual object is superimposed on the image captured by the terminal device, and the superimposing manner can be determined according to the comparison result of the depth information when the target object is acquired, instead of directly superimposing or comparing the depth information of all the objects and superimposing, the superposition can be reduced.
  • the amount of calculation in the process can be better applied to the AR application in the terminal device.
  • the embodiment of the present disclosure utilizes the camera device of the terminal device to acquire the depth information of the target object, which is advantageous for the application of the embodiment on the terminal device. Therefore, the virtual object synthesis method and apparatus according to aspects of the present disclosure can correctly display a virtual object in an image captured by the terminal device in real time.
  • FIG. 1 is a flowchart of a method for synthesizing virtual objects according to an exemplary embodiment.
  • FIG. 2 is a flowchart of a method for synthesizing virtual objects according to an exemplary embodiment.
  • FIG. 3 is a block diagram of a virtual real object synthesizing apparatus according to an exemplary embodiment.
  • FIG. 4 is a block diagram of a virtual real object synthesizing apparatus according to an exemplary embodiment.
  • FIG. 5 is a block diagram of a virtual real object synthesizing apparatus according to an exemplary embodiment.
  • FIG. 6 is a block diagram of a virtual real object synthesizing apparatus according to an exemplary embodiment.
  • FIG. 1 is a flowchart of a method for synthesizing a virtual object according to an exemplary embodiment. As shown in FIG. 1 , the method for synthesizing a virtual object is used in a terminal device, such as a mobile phone, a tablet computer, etc. Includes the following steps:
  • step S11 a target object in the image captured by the terminal device is acquired.
  • the image captured by the terminal device may be an image corresponding to the real scene, and the terminal device may capture the image by using the camera device of the camera.
  • the terminal device can capture the image in real time, and the terminal device can also continuously capture multiple images. It can be understood that a plurality of real-time images continuously captured by the terminal device can constitute a video.
  • the target object can be a real object in a real scene, for example, it can be a real person or an object.
  • the target object can be a specific object in the real scene, or it can be a certain type of object in the real scene. For example, there are multiple people in a real scene, and the target object may be one of a plurality of people, or may be all people in a real scene.
  • the target object can be an object that has an occlusion relationship with the virtual object. The present disclosure does not limit the target object.
  • the terminal device can identify and acquire the target object in the image by using an image recognition technology in the related art.
  • the target object can be moved in an image captured by the terminal device, for example, a person can walk around in a real scene.
  • the target image may enter or disappear from the image, such as a person walking into a real scene or leaving a real scene.
  • step S12 in the depth information fusion mode, the depth information of the target object is acquired by the camera device of the terminal device, and the depth information fusion mode is used to superimpose a virtual object generated by computer modeling into the image.
  • the depth information of the target object is used to represent the distance between the target object and the terminal device.
  • AR technology can superimpose virtual objects into real scenes.
  • virtual objects can be used to represent objects generated by computer modeling, such as virtual people, objects, and the like.
  • the virtual object may be a computer-created mathematical model, and the mathematical model may include data representing features such as outlines, textures, and the like of the virtual object, and the data may be extracted based on real objects such as real people, objects, or the like, or may be manually created as needed.
  • Image rendering can be based on this data, and the virtual object has been displayed in the real scene.
  • the terminal device can change the position of the virtual object so that the virtual object moves in the image corresponding to the real scene.
  • the present disclosure does not limit the manner in which virtual objects are generated.
  • the terminal device can generate virtual objects locally, and can also acquire virtual objects from other devices. After the terminal device obtains the virtual object from other devices, the virtual object can be locally adjusted.
  • the terminal device may directly display the virtual object before the captured image when the target object is not acquired.
  • the terminal device can display the virtual object on a layer above the layer in which the image is located. In this way, the terminal device can quickly and conveniently superimpose the virtual object into the real scene.
  • the present disclosure does not limit the operation when the target object is not acquired.
  • the terminal device may initiate the depth information fusion mode when the target object is acquired.
  • the depth information fusion mode can be used to superimpose a virtual object into the image.
  • the depth information fusion mode may determine an occlusion relationship of the virtual object and the target object based on the depth information, and determine a manner of superimposing the virtual object into the image according to the occlusion relationship.
  • the fusion of virtual objects in the terminal device is more realistic.
  • the target object is obtained, the object captured by the terminal device may have an occlusion relationship with the virtual object. In this case, incorrect occlusion may cause poor fusion effect, and some scenarios cannot be implemented, so the terminal device can be started. Deep information fusion mode for more realistic integration.
  • the target object is a person and the virtual object is a stool.
  • the deep information fusion mode can be activated, thereby realizing the scene where the person stands in front of the stool and sits on the stool.
  • the depth information of the target object is used to indicate the distance between the target object and the terminal device.
  • the realistic objective world is a three-dimensional space that becomes a two-dimensional image that loses the third-dimensional depth information after being imaged by the camera.
  • the terminal device can acquire depth information of the target object through the camera device.
  • the camera device of the terminal device includes at least two cameras, and the terminal device may be configured according to a positional relationship between the target object and the at least two cameras, and a distance between the at least two cameras. Determining depth information of the target object.
  • the terminal device can determine the angle between the connection between the target object and the two cameras and the connection between the two cameras, and the distance between the two cameras. Depth information of the target object. The above is only one example of determining the depth information of the target object, and the terminal device may also determine the depth information of the target object according to other manners in the related art.
  • step S13 depth information of the virtual object is acquired.
  • the terminal device can place the virtual model corresponding to the virtual object at different positions of the captured image, and can move the position of the virtual model.
  • the virtual object is not a real object in the image captured by the terminal device, and corresponds to a virtual model.
  • a virtual model can be called a virtual object when it is displayed on an image.
  • the depth information of the virtual object may be fixed.
  • the terminal device can record the correspondence between the virtual model and the depth information in the process of generating the virtual model.
  • the terminal device may obtain the depth information corresponding to the virtual object according to the correspondence between the virtual model and the depth information.
  • the depth information of the virtual object may change as the virtual model moves in the image.
  • the terminal device may record the depth information in the location information of the virtual model in the process of generating the virtual model, and may use the location information of the virtual model as the location information of the virtual object.
  • the terminal device may acquire location information of a location of the virtual object, and determine depth information of the virtual object according to the location information.
  • step S14 the virtual object is superimposed into the image based on the depth information of the target object and the depth information of the virtual object.
  • An object with a large depth information may be occluded by an object having a small depth information, and only a part of an object having a large depth information may be displayed in the captured image of the terminal device.
  • FIG. 2 is a flowchart of a method for synthesizing virtual objects according to an exemplary embodiment. As shown in FIG. 2, step S14 includes the following steps:
  • step S141 it is determined whether the depth information of the target object is smaller than the depth information of the virtual object. If the depth information of the target object is smaller than the depth information of the virtual object, step S142 is performed; otherwise, step S143 is performed.
  • step S142 a portion of the virtual object that is not occluded by the target object is superimposed on the image.
  • a pixel location of each pixel of the target object and a pixel location of each pixel of the virtual object may be acquired.
  • the pixel points of the virtual object may not be drawn at the position.
  • the pixel point of the virtual object can be drawn at the position.
  • the target object is a person
  • the virtual object is a stool
  • the depth information of the person is less than the depth information of the stool.
  • the terminal device may superimpose a portion of the stool that is not obscured by the person on the image. In this way, it is possible to present a scene in which a person stands in front of a stool and sits on a stool.
  • step S143 the virtual object is superimposed on the image.
  • the target object is a person
  • the virtual object is a stool
  • the depth information of the person is greater than or equal to the depth information of the stool.
  • the terminal device can superimpose the stool directly on the image. In this way, it is possible to present a scene in which a person stands behind a stool.
  • the occlusion relationship of the object of the different depth information is different.
  • the terminal device when the target object is acquired, the terminal device superimposes the virtual object on the image captured by the terminal device based on the depth information of the target object and the depth information of the virtual object.
  • the superposition method is determined according to the comparison result of the depth information, instead of directly superimposing or comparing the depth information of all the objects and superimposing, the calculation amount in the superimposition process can be reduced, so that the terminal device can be better applied to the terminal device.
  • the embodiment of the present disclosure utilizes the camera device of the terminal device to acquire the depth information of the target object, which is advantageous for the application of the embodiment on the terminal device. Therefore, according to the virtual object synthesis method of the embodiment, the virtual object can be correctly displayed in the image captured by the terminal device in real time.
  • FIG. 3 is a block diagram of a virtual real object synthesizing apparatus according to an exemplary embodiment.
  • the virtual object synthesizing device 30 is applied to a terminal device, and the device 30 includes an object acquiring module 31, a first information acquiring module 32, a second information acquiring module 33, and a superimposing module 34.
  • the object acquisition module 31 is configured to acquire a target object in an image captured by the terminal device
  • the first information acquiring module 32 is configured to acquire depth information of the target object by using an imaging device of the terminal device in the depth information fusion mode, where the depth information fusion mode is used to model a computer a virtual object is superimposed into the image, and the depth information of the target object is used to indicate a distance between the target object and the terminal device;
  • the second information acquiring module 33 is configured to acquire depth information of the virtual object
  • the overlay module 34 is configured to overlay the virtual object into the image based on depth information of the target object and depth information of the virtual object.
  • FIG. 4 is a block diagram of a virtual real object synthesizing apparatus according to an exemplary embodiment.
  • the overlay module 34 includes a first overlay sub-module 341.
  • the first superposition sub-module 341 is configured to superimpose, on the image, a portion of the virtual object that is not occluded by the target object when depth information of the target object is smaller than depth information of the virtual object.
  • the overlay module further includes a second overlay sub-module 352.
  • the second superposition sub-module 342 is configured to superimpose the virtual object on the image when the depth information of the target object is greater than or equal to the depth information of the virtual object.
  • the camera device of the terminal device includes at least two cameras, and the first information acquiring module 32 includes a first determining sub-module 321 .
  • the first determining sub-module 321 is configured to determine depth information of the target object according to a positional relationship between the target object and the at least two cameras, and a distance between the at least two cameras.
  • the second information acquiring module 33 includes an obtaining submodule 331 and a second determining submodule 332.
  • the obtaining submodule 331 is configured to acquire location information of the virtual object in the image
  • the second determining submodule 332 is configured to determine depth information of the virtual object according to location information of the virtual object.
  • FIG. 5 is a block diagram of an apparatus 800 for virtual reality object composition, according to an exemplary embodiment.
  • device 800 can be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a gaming console, a tablet device, a medical device, a fitness device, a personal digital assistant, and the like.
  • apparatus 800 can include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, And a communication component 816.
  • Processing component 802 typically controls the overall operation of device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations.
  • Processing component 802 can include one or more processors 820 to execute instructions to perform all or part of the steps of the above described methods.
  • processing component 802 can include one or more modules to facilitate interaction between component 802 and other components.
  • processing component 802 can include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.
  • Memory 804 is configured to store various types of data to support operation at device 800. Examples of such data include instructions for any application or method operating on device 800, contact data, phone book data, messages, pictures, videos, and the like.
  • the memory 804 can be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable.
  • SRAM static random access memory
  • EEPROM electrically erasable programmable read only memory
  • EPROM Electrically erasable programmable read only memory
  • PROM Programmable Read Only Memory
  • ROM Read Only Memory
  • Magnetic Memory Flash Memory
  • Disk Disk or Optical Disk.
  • Power component 806 provides power to various components of device 800.
  • Power component 806 can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for device 800.
  • the multimedia component 808 includes a screen between the device 800 and the user that provides an output interface.
  • the screen can include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen can be implemented as a touch screen to receive input signals from the user.
  • the touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor may sense not only the boundary of the touch or sliding action, but also the duration and pressure associated with the touch or slide operation.
  • the multimedia component 808 includes a front camera and/or a rear camera. When the device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera can receive external multimedia data. Each front and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
  • the audio component 810 is configured to output and/or input an audio signal.
  • the audio component 810 includes a microphone (MIC) that is configured to receive an external audio signal when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode.
  • the received audio signal may be further stored in memory 804 or transmitted via communication component 816.
  • the audio component 810 also includes a speaker for outputting an audio signal.
  • the I/O interface 812 provides an interface between the processing component 802 and the peripheral interface module, which may be a keyboard, a click wheel, a button, or the like. These buttons may include, but are not limited to, a home button, a volume button, a start button, and a lock button.
  • Sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of device 800.
  • sensor assembly 814 can detect an open/closed state of device 800, relative positioning of components, such as the display and keypad of device 800, and sensor component 814 can also detect a change in position of one component of device 800 or device 800. The presence or absence of user contact with device 800, device 800 orientation or acceleration/deceleration, and temperature variation of device 800.
  • Sensor assembly 814 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact.
  • Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
  • the sensor assembly 814 can also include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
  • Communication component 816 is configured to facilitate wired or wireless communication between device 800 and other devices.
  • the device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof.
  • communication component 816 receives broadcast signals or broadcast associated information from an external broadcast management system via a broadcast channel.
  • the communication component 816 also includes a near field communication (NFC) module to facilitate short range communication.
  • NFC near field communication
  • the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
  • RFID radio frequency identification
  • IrDA infrared data association
  • UWB ultra-wideband
  • Bluetooth Bluetooth
  • device 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable A gate array (FPGA), controller, microcontroller, microprocessor, or other electronic component implementation for performing the above methods.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGA field programmable A gate array
  • controller microcontroller, microprocessor, or other electronic component implementation for performing the above methods.
  • non-transitory computer readable storage medium comprising instructions, such as a memory 804 comprising instructions executable by processor 820 of apparatus 800 to perform the above method.
  • the non-transitory computer readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.
  • FIG. 6 is a block diagram of an apparatus 1900 for virtual and real object composition, according to an exemplary embodiment.
  • device 1900 can be provided as a server.
  • apparatus 1900 includes a processing component 1922 that further includes one or more processors, and memory resources represented by memory 1932 for storing instructions executable by processing component 1922, such as an application.
  • An application stored in memory 1932 can include one or more modules each corresponding to a set of instructions.
  • processing component 1922 is configured to execute instructions to perform the methods described above.
  • Apparatus 1900 can also include a power supply component 1926 configured to perform power management of apparatus 1900, a wired or wireless network interface 1950 configured to connect apparatus 1900 to the network, and an input/output (I/O) interface 1958.
  • Device 1900 can operate based on an operating system stored in memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.
  • non-transitory computer readable storage medium comprising instructions, such as a memory 1932 comprising instructions executable by processing component 1922 of apparatus 1900 to perform the above method.
  • the non-transitory computer readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device.

Abstract

一种虚实对象合成方法及装置，包括获取终端设备捕捉的图像中的目标对象（S11）；在深度信息融合模式下，通过终端设备的摄像装置获取目标对象的深度信息（S12）；获取虚拟对象的深度信息（S13）；基于目标对象的深度信息和虚拟对象的深度信息，将虚拟对象叠加到图像中（S14）。不同深度信息的对象的遮挡关系不同，通过获取目标对象后，基于目标对象的深度信息和虚拟对象的深度信息，将虚拟对象叠加到终端设备捕捉的图像中，根据该虚实对象合成方法及装置能够减少叠加过程中的计算量，可以较好应用于终端设备中的AR应用，从而实时在终端设备捕捉的图像中正确显示虚拟对象。

Description

虚实对象合成方法及装置
本申请基于申请号为201810029995.2、申请日为2018年1月12日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本公开涉及图像处理技术领域，尤其涉及一种虚实对象合成方法及装置。
背景技术
AR(Augmented Reality，增强现实)技术是通过计算机系统提供的信息增加用户对现实世界感知的技术，可以将虚拟的信息应用到真实世界，并将计算机生成的虚拟对象叠加到真实场景中，从而实现对现实的增强。
相关技术中的虚实对象合成方法，虽然可以在某些情况下正确处理虚实对象的遮挡关系，然而存在计算量较大，不适用于手机、平板电脑等终端设备的问题。
发明内容
为克服相关技术中存在的问题，本公开提供一种虚实对象合成方法及装置，能够实时在终端设备捕捉的图像中正确显示虚拟对象。
根据本公开实施例的第一方面，提供一种虚实对象合成方法，该方法应用于终端设备，该方法包括：获取所述终端设备捕捉的图像中的目标对象；在所述深度信息融合模式下，通过所述终端设备的摄像装置获取所述目标对象的深度信息，所述深度信息融合模式用于将计算机建模产生的虚拟对象叠加到所述图像中，所述目标对象的深度信息用于表示目标对象与终端设备之间的距离；获取虚拟对象的深度信息；基于所述目标对象的深度信息和所述虚拟对象的深度信息，将所述虚拟对象叠加 到所述图像中。
在一种可能的实现方式中，基于所述目标对象的深度信息和所述虚拟对象的深度信息，将所述虚拟对象叠加到所述图像中，包括：若所述目标对象的深度信息小于所述虚拟对象的深度信息，则在所述图像上叠加所述虚拟对象未被所述目标对象遮挡的部分。
在一种可能的实现方式中，基于所述目标对象的深度信息和所述虚拟对象的深度信息，将所述虚拟对象叠加到所述图像中，包括：若所述目标对象的深度信息大于或等于所述虚拟对象的深度信息，则在所述图像上叠加所述虚拟对象。
在一种可能的实现方式中，所述终端设备的摄像装置包括至少两个摄像头，通过所述终端设备的摄像装置获取所述目标对象的深度信息，包括：根据所述目标对象与所述至少两个摄像头的位置关系，以及所述至少两个摄像头之间的距离确定所述目标对象的深度信息。
在一种可能的实现方式中，获取虚拟对象的深度信息，包括：获取所述虚拟对象的位置的位置信息；根据所述位置信息，确定所述虚拟对象的深度信息。
根据本公开实施例的第二方面，提供一种虚实对象合成装置，该装置应用于终端设备，该装置包括：对象获取模块，用于获取所述终端设备捕捉的图像中的目标对象；第一信息获取模块，用于在所述深度信息融合模式下，通过所述终端设备的摄像装置获取所述目标对象的深度信息，所述深度信息融合模式用于将计算机建模产生的虚拟对象叠加到所述图像中，所述目标对象的深度信息用于表示目标对象与终端设备之间的距离；第二信息获取模块，用于获取虚拟对象的深度信息；叠加模块，用于基于所述目标对象的深度信息和所述虚拟对象的深度信息，将所述虚拟对象叠加到所述图像中。
在一种可能的实现方式中，所述叠加模块包括：第一叠加子模块，用于当所述目标对象的深度信息小于所述虚拟对象的深度信息时，在所述图像上叠加所述虚拟对象未被所述目标对象遮挡的部分。
在一种可能的实现方式中，所述叠加模块还包括：第二叠加子模块，用于当所述目标对象的深度信息大于或等于所述虚拟对象的深度信息 时，在所述图像上叠加所述虚拟对象。
在一种可能的实现方式中，述第一获取模块包括：第一确定子模块，用于根据所述目标对象与所述至少两个摄像头的位置关系，以及所述至少两个摄像头之间的距离确定所述目标对象的深度信息。
在一种可能的实现方式中，所述第二获取模块包括：获取子模块，用于获取所述虚拟对象的位置的位置信息；第二确定子模块，用于根据所述位置信息，确定所述虚拟对象的深度信息。
本公开的实施例提供的技术方案可以包括以下有益效果：不同深度信息的对象的遮挡关系不同，本公开实施例中，获取目标对象后，终端设备基于目标对象的深度信息和虚拟对象的深度信息，将虚拟对象叠加到终端设备捕捉的图像中，可以在获取到目标对象时根据深度信息的比较结果确定叠加方式，而非不做比较直接叠加或者比较所有对象的深度信息后叠加，可以减少叠加过程中的计算量，从而可以较好应用于终端设备中的AR应用。并且，本公开实施例利用终端设备的摄像装置获取目标对象的深度信息，有利于实施例在终端设备上的应用。因此，根据本公开各方面的虚实对象合成方法及装置，能够实时在终端设备捕捉的图像中正确显示虚拟对象。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理。
图1是根据一示例性实施例示出的一种虚实对象合成方法的流程图。
图2是根据一示例性实施例示出的一种虚实对象合成方法的流程图。
图3是根据一示例性实施例示出的一种虚实对象合成装置的框图。
图4是根据一示例性实施例示出的一种虚实对象合成装置的框图。
图5是根据一示例性实施例示出的一种虚实对象合成装置的框图。
图6是根据一示例性实施例示出的一种虚实对象合成装置的框图。
具体实施例
这里将详细地对示例性实施例进行说明，其示例表示在附图中。下面的描述涉及附图时，除非另有表示，不同附图中的相同数字表示相同或相似的要素。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
图1是根据一示例性实施例示出的一种虚实对象合成方法的流程图，如图1所示，该虚实对象合成方法用于终端设备中，例如手机、平板电脑等，该虚实对象合成方法包括以下步骤：
在步骤S11中，获取所述终端设备捕捉的图像中的目标对象。
其中，终端设备捕捉的图像可以为真实场景对应的图像，终端设备可以通过自身的摄像装置捕捉所述图像。在一种可能的实现方式中，终端设备可以实时捕捉所述图像，终端设备还可以连续捕捉多幅图像。可以理解的是，终端设备连续捕捉的多幅实时图像可以组成视频。
目标对象可以为真实场景中的真实对象，例如，可以为真实的人或者物体。目标对象可以是真实场景中的某个特定对象，也可以是真实场景中某类对象。例如，真实场景中存在多个人，目标对象可以为多个人中的某个人，也可以是真实场景中所有的人。在一个示例中，目标对象可以为与虚拟对象具有遮挡关系的对象。本公开对目标对象不做限定。
在一种可能的实现方式中，终端设备可以通过相关技术中的图像识别技术识别并获取所述图像中的目标对象。
在一种可能的实现方式中，目标对象可以在终端设备捕捉的图像中移动，例如，人可以在真实场景中走来走去。在一种可能的实现方式中，目标图像可以进入图像，或者从图像中消失，例如人走入真实场景或者离开真实场景。
步骤S12，在深度信息融合模式下，通过所述终端设备的摄像装置获取所述目标对象的深度信息，所述深度信息融合模式用于将计算机建 模产生的虚拟对象叠加到所述图像中，所述目标对象的深度信息用于表示目标对象与终端设备之间的距离。
AR技术可以将虚拟对象叠加到真实场景中。其中，虚拟对象可以用于表示计算机建模产生的对象，例如虚拟的人、物体等。虚拟对象可以是计算机建立的数学模型，该数学模型可包含表示虚拟对象的轮廓、纹理等特征的数据，这些数据可基于真实的人、物体等真实对象进行提取，也可以根据需要人为创建。可基于这些数据进行图像渲染，已将虚拟对象展示在真实场景中。终端设备可以更改虚拟对象的位置，从而使虚拟对象在真实场景对应的图像中移动。本公开对虚拟对象的生成方式不做限定。
在一个示例中，终端设备可以在本地产生虚拟对象，还可以从其他设备获取虚拟对象。其中，终端设备从其他设备获取虚拟对象后，可以在本地调整虚拟对象。
在一个示例中，终端设备可以在未获取到目标对象时，在捕捉的图像之前直接显示虚拟对象。例如，终端设备可以在所述图像所在图层之上的图层显示所述虚拟对象。这样，终端设备可以快速、方便的将虚拟对象叠加到真实场景中。本公开对未获取到目标对象时的操作不做限制。
在一个示例中，终端设备可以在获取到目标对象时，启动深度信息融合模式。其中，深度信息融合模式可以用于将虚拟对象叠加到所述图像中。例如，深度信息融合模式可以基于深度信息确定虚拟对象与目标对象的遮挡关系，根据遮挡关系确定将虚拟对象叠加到图像中的方式。在深度信息融合模式下，终端设备中虚拟对象的融合更加真实。当获取到目标对象时，说明终端设备捕捉的图像中可能存在与虚拟对象具有遮挡关系的对象，此时不正确的遮挡可能会造成融合效果较差，某些场景无法实现，因此终端设备可以启动深度信息融合模式以实现更加真实的融合。
在一个示例中，目标对象为人，虚拟对象为凳子。当获取到人时，可以启动深度信息融合模式，从而实现人站在凳子前，坐在凳子上等场景。
目标对象的深度信息用于表示目标对象与终端设备之间的距离。现实的客观世界是一个三维的空间，经过摄像装置成像后变为了丢失第三维深度信息的二维图像。终端设备可以通过摄像装置获取目标对象的深度信息。
在一种可能的实现方式中，所述终端设备的摄像装置至少包括两个摄像头，终端设备可以根据目标对象与所述至少两个摄像头的位置关系，以及所述至少两个摄像头之间的距离确定所述目标对象的深度信息。
以终端设备的摄像装置包括两个摄像头为例，终端设备可以根据目标对象与两个摄像头的连线与两个摄像头的连线之间的夹角，以及两个摄像头之间的距离，确定所述目标对象的深度信息。以上仅为确定目标对象的深度信息的一个示例，终端设备还可以根据相关技术中的其他方式确定目标对象的深度信息。
在步骤S13中，获取虚拟对象的深度信息。
终端设备可以在捕捉到的图像的不同位置放置虚拟对象对应的虚拟模型，且可以移动虚拟模型的位置。虚拟对象不是终端设备捕捉的图像中真实存在的对象，对应于一个虚拟模型。虚拟模型显示在图像上时可以称为虚拟对象。
在一种可能的实现方式中，虚拟对象的深度信息可以为固定不变的。以终端设备本地生成虚拟模型为例，终端设备可以在生成虚拟模型的过程中，记录虚拟模型与深度信息的对应关系。此时，在图像中移动虚拟模型时，虚拟模型的深度信息保持不变。在一种可能的实现方式中，终端设备可以根据虚拟模型与深度信息的对应关系获取虚拟对象对应的深度信息。
在一种可能的实现方式中，虚拟对象的深度信息可以随着虚拟模型在图像中位置的移动进行变化。以终端设备本地生成虚拟模型为例，终端设备可以在生成虚拟模型的过程中，将深度信息记录在虚拟模型的位置信息中，并可以将虚拟模型的位置信息作为虚拟对象的位置信息。此时，在图像中移动虚拟模型时，虚拟模型的深度信息与虚拟模型在图像中的位置有关。在一种可能的实现方式中，终端设备可以获取虚拟对象 的位置的位置信息；根据所述位置信息，确定所述虚拟对象的深度信息。
在步骤S14中，基于所述目标对象的深度信息和所述虚拟对象的深度信息，将所述虚拟对象叠加到所述图像中。
可以理解的是，图像中的对象距离终端设备的摄像装置越远，其深度信息越大。深度信息较大的对象可以被深度信息较小的对象遮挡，终端设备的捕捉的图像中可以只显示深度信息较大的对象的一部分。
图2是根据一示例性实施例示出的一种虚实对象合成方法的流程图，如图2所示，步骤S14包括以下步骤：
在步骤S141中，确定所述目标对象的深度信息是否小于所述虚拟对象的深度信息。若所述目标对象的深度信息小于所述虚拟对象的深度信息，则执行步骤S142；否则，执行步骤S143。
在步骤S142中，在所述图像上叠加所述虚拟对象未被所述目标对象遮挡的部分。
在一种可能的实现方式中，可以获取所述目标对象每个像素点的像素位置，以及所述虚拟对象每个像素点的像素位置。当一个像素位置上既存在目标对象的像素点，又存在虚拟对象的像素点时，可以不在该位置绘制虚拟对象的像素点。当一个像素位置上，不存在目标对象的像素点，但存在虚拟对象的像素点时，可以在该位置绘制虚拟对象的像素点。
在一个示例中，目标对象为人，虚拟对象为凳子，人的深度信息小于凳子的深度信息。终端设备可以在所述图像上叠加凳子未被人遮挡的部分。这样，可以呈现人站在凳子前，坐在凳子上等场景。
在步骤S143中，在所述图像上叠加所述虚拟对象。
在一个示例中，目标对象为人，虚拟对象为凳子，人的深度信息大于或等于凳子的深度信息。终端设备可以直接在所述图像上叠加凳子。这样，可以呈现人站在凳子后等场景。
不同深度信息的对象的遮挡关系不同，本实施例中，当获取到目标对象时，终端设备基于目标对象的深度信息和虚拟对象的深度信息，将 虚拟对象叠加到终端设备捕捉的图像中，可以在获取到目标对象时根据深度信息的比较结果确定叠加方式，而非不做比较直接叠加或者比较所有对象的深度信息后叠加，可以减少叠加过程中的计算量，从而可以较好应用于终端设备中的AR应用。并且，本公开实施例利用终端设备的摄像装置获取目标对象的深度信息，有利于实施例在终端设备上的应用。因此，根据本实施例虚实对象合成方法，能够实时在终端设备捕捉的图像中正确显示虚拟对象。
图3是根据一示例性实施例示出的一种虚实对象合成装置框图。参照图3，该虚实对象合成装置30应用于终端设备，该装置30包括对象获取模块31、第一信息获取模块32、第二信息获取模块33和叠加模块34。
该对象获取模块31被配置为获取所述终端设备捕捉的图像中的目标对象；
该第一信息获取模块32被配置为在所述深度信息融合模式下，通过所述终端设备的摄像装置获取所述目标对象的深度信息，所述深度信息融合模式用于将计算机建模产生的虚拟对象叠加到所述图像中，所述目标对象的深度信息用于表示目标对象与终端设备之间的距离；
该第二信息获取模块33被配置为获取虚拟对象的深度信息；
该叠加模块34被配置为基于所述目标对象的深度信息和所述虚拟对象的深度信息，将所述虚拟对象叠加到所述图像中。
图4是根据一示例性实施例示出的一种虚实对象合成装置框图。参照图4，在一种可能的实现方式中，该叠加模块34包括第一叠加子模块341。
该第一叠加子模块341被配置为当所述目标对象的深度信息小于所述虚拟对象的深度信息时，在所述图像上叠加所述虚拟对象未被所述目标对象遮挡的部分。
在一种可能的实现方式中，该叠加模块还包括第二叠加子模块352。
该第二叠加子模块342被配置为当所述目标对象的深度信息大于或等于所述虚拟对象的深度信息时，在所述图像上叠加所述虚拟对象。
在一种可能的实现方式中，所述终端设备的摄像装置包括至少两个摄像头，该第一信息获取模块32包括第一确定子模块321。
该第一确定子模块321被配置为根据所述目标对象与所述至少两个摄像头的位置关系，以及所述至少两个摄像头之间的距离确定所述目标对象的深度信息。
在一种可能的实现方式中，该第二信息获取模块33包括获取子模块331和第二确定子模块332。
该获取子模块331被配置为获取所述虚拟对象在所述图像中的位置信息；
该第二确定子模块332被配置为根据所述虚拟对象的位置信息，确定所述虚拟对象的深度信息。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
图5是根据一示例性实施例示出的一种用于虚实对象合成的装置800的框图。例如，装置800可以是移动电话，计算机，数字广播终端，消息收发设备，游戏控制台，平板设备，医疗设备，健身设备，个人数字助理等。
参照图5，装置800可以包括以下一个或多个组件：处理组件802，存储器804，电源组件806，多媒体组件808，音频组件810，输入/输出(I/O)的接口812，传感器组件814，以及通信组件816。
处理组件802通常控制装置800的整体操作，诸如与显示，电话呼叫，数据通信，相机操作和记录操作相关联的操作。处理组件802可以包括一个或多个处理器820来执行指令，以完成上述的方法的全部或部分步骤。此外，处理组件802可以包括一个或多个模块，便于处理组件802和其他组件之间的交互。例如，处理组件802可以包括多媒体模块，以方便多媒体组件808和处理组件802之间的交互。
存储器804被配置为存储各种类型的数据以支持在装置800的操 作。这些数据的示例包括用于在装置800上操作的任何应用程序或方法的指令，联系人数据，电话簿数据，消息，图片，视频等。存储器804可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，如静态随机存取存储器(SRAM)，电可擦除可编程只读存储器(EEPROM)，可擦除可编程只读存储器(EPROM)，可编程只读存储器(PROM)，只读存储器(ROM)，磁存储器，快闪存储器，磁盘或光盘。
电源组件806为装置800的各种组件提供电力。电源组件806可以包括电源管理系统，一个或多个电源，及其他与为装置800生成、管理和分配电力相关联的组件。
多媒体组件808包括在所述装置800和用户之间的提供一个输出接口的屏幕。在一些实施例中，屏幕可以包括液晶显示器(LCD)和触摸面板(TP)。如果屏幕包括触摸面板，屏幕可以被实现为触摸屏，以接收来自用户的输入信号。触摸面板包括一个或多个触摸传感器以感测触摸、滑动和触摸面板上的手势。所述触摸传感器可以不仅感测触摸或滑动动作的边界，而且还检测与所述触摸或滑动操作相关的持续时间和压力。在一些实施例中，多媒体组件808包括一个前置摄像头和/或后置摄像头。当装置800处于操作模式，如拍摄模式或视频模式时，前置摄像头和/或后置摄像头可以接收外部的多媒体数据。每个前置摄像头和后置摄像头可以是一个固定的光学透镜系统或具有焦距和光学变焦能力。
音频组件810被配置为输出和/或输入音频信号。例如，音频组件810包括一个麦克风(MIC)，当装置800处于操作模式，如呼叫模式、记录模式和语音识别模式时，麦克风被配置为接收外部音频信号。所接收的音频信号可以被进一步存储在存储器804或经由通信组件816发送。在一些实施例中，音频组件810还包括一个扬声器，用于输出音频信号。
I/O接口812为处理组件802和外围接口模块之间提供接口，上述外围接口模块可以是键盘，点击轮，按钮等。这些按钮可包括但不限于：主页按钮、音量按钮、启动按钮和锁定按钮。
传感器组件814包括一个或多个传感器，用于为装置800提供各个 方面的状态评估。例如，传感器组件814可以检测到装置800的打开/关闭状态，组件的相对定位，例如所述组件为装置800的显示器和小键盘，传感器组件814还可以检测装置800或装置800一个组件的位置改变，用户与装置800接触的存在或不存在，装置800方位或加速/减速和装置800的温度变化。传感器组件814可以包括接近传感器，被配置用来在没有任何的物理接触时检测附近物体的存在。传感器组件814还可以包括光传感器，如CMOS或CCD图像传感器，用于在成像应用中使用。在一些实施例中，该传感器组件814还可以包括加速度传感器，陀螺仪传感器，磁传感器，压力传感器或温度传感器。
通信组件816被配置为便于装置800和其他设备之间有线或无线方式的通信。装置800可以接入基于通信标准的无线网络，如WiFi，2G或3G，或它们的组合。在一个示例性实施例中，通信组件816经由广播信道接收来自外部广播管理系统的广播信号或广播相关信息。在一个示例性实施例中，所述通信组件816还包括近场通信(NFC)模块，以促进短程通信。例如，在NFC模块可基于射频识别(RFID)技术，红外数据协会(IrDA)技术，超宽带(UWB)技术，蓝牙(BT)技术和其他技术来实现。
在示例性实施例中，装置800可以被一个或多个应用专用集成电路(ASIC)、数字信号处理器(DSP)、数字信号处理设备(DSPD)、可编程逻辑器件(PLD)、现场可编程门阵列(FPGA)、控制器、微控制器、微处理器或其他电子元件实现，用于执行上述方法。
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器804，上述指令可由装置800的处理器820执行以完成上述方法。例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
图6是根据一示例性实施例示出的一种用于虚实对象合成的装置1900的框图。例如，装置1900可以被提供为一服务器。参照图6，装置1900包括处理组件1922，其进一步包括一个或多个处理器，以及由存储 器1932所代表的存储器资源，用于存储可由处理组件1922的执行的指令，例如应用程序。存储器1932中存储的应用程序可以包括一个或一个以上的每一个对应于一组指令的模块。此外，处理组件1922被配置为执行指令，以执行上述方法。
装置1900还可以包括一个电源组件1926被配置为执行装置1900的电源管理，一个有线或无线网络接口1950被配置为将装置1900连接到网络，和一个输入输出(I/O)接口1958。装置1900可以操作基于存储在存储器1932的操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM或类似。
在示例性实施例中，还提供了一种包括指令的非临时性计算机可读存储介质，例如包括指令的存储器1932，上述指令可由装置1900的处理组件1922执行以完成上述方法。例如，所述非临时性计算机可读存储介质可以是ROM、随机存取存储器(RAM)、CD-ROM、磁带、软盘和光数据存储设备等。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本公开的其它实施方案。本申请旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由下面的权利要求指出。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。

Claims (12)

  1. 一种虚实对象合成方法，其特征在于，所述方法应用于终端设备，所述方法包括：
    获取所述终端设备捕捉的图像中的目标对象；
    在深度信息融合模式下，通过所述终端设备的摄像装置获取所述目标对象的深度信息，所述深度信息融合模式用于将计算机建模产生的虚拟对象叠加到所述图像中，所述目标对象的深度信息用于表示目标对象与终端设备之间的距离；
    获取虚拟对象的深度信息；
    基于所述目标对象的深度信息和所述虚拟对象的深度信息，将所述虚拟对象叠加到所述图像中。
  2. 根据权利要求1所述的虚实对象合成方法，其特征在于，基于所述目标对象的深度信息和所述虚拟对象的深度信息，将所述虚拟对象叠加到所述图像中，包括：
    若所述目标对象的深度信息小于所述虚拟对象的深度信息，则在所述图像上叠加所述虚拟对象未被所述目标对象遮挡的部分。
  3. 根据权利要求1所述的虚实对象合成方法，其特征在于，基于所述目标对象的深度信息和所述虚拟对象的深度信息，将所述虚拟对象叠加到所述图像中，包括：
    若所述目标对象的深度信息大于或等于所述虚拟对象的深度信息，则在所述图像上叠加所述虚拟对象。
  4. 根据权利要求1至3任一项所述的虚实对象合成方法，其特征在于，所述终端设备的摄像装置包括至少两个摄像头，通过所述终端设备的摄像装置获取所述目标对象的深度信息，包括：
    根据所述目标对象与所述至少两个摄像头的位置关系，以及所述至少两个摄像头之间的距离确定所述目标对象的深度信息。
  5. 根据权利要求1至3任一项所述的虚实对象合成方法，其特征在于，获取虚拟对象的深度信息，包括：
    获取放置所述虚拟对象的位置的位置信息；
    根据所述位置信息，确定所述虚拟对象的深度信息。
  6. 一种虚实对象合成装置，其特征在于，所述装置应用于终端设备，所述装置包括：
    对象获取模块，用于获取所述终端设备捕捉的图像中的目标对象；
    第一信息获取模块，用于在所述深度信息融合模式下，通过所述终端设备的摄像装置获取所述目标对象的深度信息，所述深度信息融合模式用于将计算机建模产生的虚拟对象叠加到所述图像中，所述目标对象的深度信息用于表示目标对象与终端设备之间的距离；
    第二信息获取模块，用于获取虚拟对象的深度信息；
    叠加模块，用于基于所述目标对象的深度信息和所述虚拟对象的深度信息，将所述虚拟对象叠加到所述图像中。
  7. 根据权利要求6所述的虚实对象合成装置，其特征在于，所述叠加模块包括：
    第一叠加子模块，用于当所述目标对象的深度信息小于所述虚拟对象的深度信息时，在所述图像上叠加所述虚拟对象未被所述目标对象遮挡的部分。
  8. 根据权利要求6所述的虚实对象合成装置，其特征在于，所述叠加模块还包括：
    第二叠加子模块，用于当所述目标对象的深度信息大于或等于所述虚拟对象的深度信息时，在所述图像上叠加所述虚拟对象。
  9. 根据权利要求6至8任一项所述的虚实对象合成装置，其特征在于，所述终端设备的摄像装置包括至少两个摄像头，所述第一信息获取模块包括：
    第一确定子模块，用于根据所述目标对象与所述至少两个摄像头的位置关系，以及所述至少两个摄像头之间的距离确定所述目标对象的深度信息。
  10. 根据权利要求6至8任一项所述的虚实对象合成装置，其特征在于，所述第二信息获取模块包括：
    获取子模块，用于获取放置所述虚拟对象的位置的位置信息；
    第二确定子模块，用于根据所述位置信息，确定所述虚拟对象的深 度信息。
  11. 一种虚实对象合成装置，其特征在于，包括：
    处理器；
    用于存储处理器可执行指令的存储器；
    其中，所述处理器被配置为执行如权利要求1至5中任一项所述的方法。
  12. 一种非临时性计算机可读存储介质，当所述存储介质中的指令由处理器执行时实现权利要求1至5中任一项所述的方法。
PCT/CN2018/101241 2018-01-12 2018-08-20 虚实对象合成方法及装置 WO2019137006A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
RU2018143709A RU2715797C1 (ru) 2018-01-12 2018-08-20 Способ и устройство для синтеза объектов виртуальной реальности
JP2018567578A JP2020507136A (ja) 2018-01-12 2018-08-20 Ｖｒオブジェクトの合成方法、装置、プログラム及び記録媒体
KR1020197004558A KR102194094B1 (ko) 2018-01-12 2018-08-20 가상과 실제 물체의 합성 방법, 장치, 프로그램 및 기록매체

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810029995.2 2018-01-12
CN201810029995.2A CN108182730B (zh) 2018-01-12 2018-01-12 虚实对象合成方法及装置

Publications (1)

Publication Number Publication Date
WO2019137006A1 true WO2019137006A1 (zh) 2019-07-18

Family

ID=62550371

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/101241 WO2019137006A1 (zh) 2018-01-12 2018-08-20 虚实对象合成方法及装置

Country Status (7)

Country Link
US (1) US11636653B2 (zh)
EP (1) EP3511864A1 (zh)
JP (1) JP2020507136A (zh)
KR (1) KR102194094B1 (zh)
CN (1) CN108182730B (zh)
RU (1) RU2715797C1 (zh)
WO (1) WO2019137006A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11636653B2 (en) 2018-01-12 2023-04-25 Beijing Xiaomi Mobile Software Co., Ltd. Method and apparatus for synthesizing virtual and real objects

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108961197A (zh) * 2018-06-27 2018-12-07 联想(北京)有限公司 一种对象合成方法及装置
CN110716685B (zh) * 2018-07-11 2023-07-18 广东虚拟现实科技有限公司 图像显示方法，图像显示装置、系统及其实体对象
US10785413B2 (en) * 2018-09-29 2020-09-22 Apple Inc. Devices, methods, and graphical user interfaces for depth-based annotation
CN109474816B (zh) * 2018-12-28 2024-04-05 上海北冕信息科技有限公司 增强现实的虚实融合装置及其虚实融合方法、设备、介质
CN109922331B (zh) * 2019-01-15 2021-12-07 浙江舜宇光学有限公司 一种图像处理方法及装置
CN111651031B (zh) * 2019-03-04 2023-08-29 广东虚拟现实科技有限公司 虚拟内容的显示方法、装置、终端设备及存储介质
JP2021064320A (ja) * 2019-10-17 2021-04-22 ソニー株式会社 情報処理装置、情報処理方法、及びプログラム
CN110889890B (zh) * 2019-11-29 2023-07-28 深圳市商汤科技有限公司 图像处理方法及装置、处理器、电子设备及存储介质
CN111223192B (zh) * 2020-01-09 2023-10-03 北京华捷艾米科技有限公司 一种图像处理方法及其应用方法、装置及设备
US11727650B2 (en) 2020-03-17 2023-08-15 Apple Inc. Systems, methods, and graphical user interfaces for displaying and manipulating virtual objects in augmented reality environments
CN111416938B (zh) * 2020-03-27 2021-11-02 咪咕文化科技有限公司 一种增强现实合拍方法、设备及计算机可读存储介质
CN111638798A (zh) * 2020-06-07 2020-09-08 上海商汤智能科技有限公司 一种ar合影方法、装置、计算机设备及存储介质
CN111640203B (zh) * 2020-06-12 2024-04-12 上海商汤智能科技有限公司 一种图像处理方法及装置
CN111898640B (zh) * 2020-06-28 2023-10-31 武汉旷视金智科技有限公司 模拟抓拍机推送图片的方法、装置、测试系统及电子设备
CN112422945A (zh) * 2020-09-01 2021-02-26 华为技术有限公司 图像处理方法、移动终端及存储介质
CN112394815A (zh) * 2020-11-20 2021-02-23 歌尔科技有限公司 基于增强现实的绘画辅助方法、增强现实设备和存储介质
CN112906467A (zh) * 2021-01-15 2021-06-04 深圳市慧鲤科技有限公司 合影图像生成方法及装置、电子设备和存储介质
US11941764B2 (en) 2021-04-18 2024-03-26 Apple Inc. Systems, methods, and graphical user interfaces for adding effects in augmented reality environments
CN113269782B (zh) * 2021-04-21 2023-01-03 青岛小鸟看看科技有限公司 数据生成方法、装置及电子设备
CN113538318B (zh) * 2021-08-24 2023-12-15 北京奇艺世纪科技有限公司 图像处理方法、装置、终端设备以及可读存储介质
CN114564108A (zh) * 2022-03-03 2022-05-31 北京小米移动软件有限公司 图像展示的方法、装置和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102473324A (zh) * 2009-08-18 2012-05-23 Metaio有限公司 用于在真实环境中表示虚拟信息的方法
CN103489214A (zh) * 2013-09-10 2014-01-01 北京邮电大学 增强现实系统中基于虚拟模型预处理的虚实遮挡处理方法
CN104021590A (zh) * 2013-02-28 2014-09-03 北京三星通信技术研究有限公司 虚拟试穿试戴系统和虚拟试穿试戴方法
CN105931289A (zh) * 2016-04-14 2016-09-07 大连新锐天地传媒有限公司 实现真实模型遮盖虚拟物体的系统及方法
CN106030335A (zh) * 2014-03-28 2016-10-12 英特尔公司 使用微功率脉冲雷达确定移动显示位置和取向
CN108182730A (zh) * 2018-01-12 2018-06-19 北京小米移动软件有限公司 虚实对象合成方法及装置

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6166744A (en) * 1997-11-26 2000-12-26 Pathfinder Systems, Inc. System for combining virtual images with real-world scenes
JP2002157607A (ja) * 2000-11-17 2002-05-31 Canon Inc 画像生成システム、画像生成方法および記憶媒体
JP2004145448A (ja) * 2002-10-22 2004-05-20 Toshiba Corp 端末装置、サーバ装置および画像加工方法
JP4522129B2 (ja) * 2004-03-31 2010-08-11 キヤノン株式会社 画像処理方法および画像処理装置
DE102008060301B4 (de) 2008-12-03 2012-05-03 Grenzebach Maschinenbau Gmbh Verfahren und Vorrichtung zum kraftschlüssigen Verbinden von glasartigen Bauteilen mit Metallen sowie Computerprogramm und maschinenlesbarer Träger zur Durchführung des Verfahrens
JP2012058968A (ja) * 2010-09-08 2012-03-22 Namco Bandai Games Inc プログラム、情報記憶媒体及び画像生成システム
US8884984B2 (en) * 2010-10-15 2014-11-11 Microsoft Corporation Fusing virtual content into real content
JP5791434B2 (ja) * 2011-08-31 2015-10-07 任天堂株式会社 情報処理プログラム、情報処理システム、情報処理装置および情報処理方法
US9224237B2 (en) * 2013-09-27 2015-12-29 Amazon Technologies, Inc. Simulating three-dimensional views using planes of content
JP2015114307A (ja) * 2013-12-16 2015-06-22 ソニー株式会社 画像処理装置と画像処理方法および撮像装置
US9690370B2 (en) * 2014-05-05 2017-06-27 Immersion Corporation Systems and methods for viewport-based augmented reality haptic effects
JP5762600B1 (ja) * 2014-06-06 2015-08-12 キヤノン株式会社 情報処理装置及び情報処理方法
US20160019718A1 (en) * 2014-07-16 2016-01-21 Wipro Limited Method and system for providing visual feedback in a virtual reality environment
US10726593B2 (en) * 2015-09-22 2020-07-28 Fyusion, Inc. Artificially rendering images using viewpoint interpolation and extrapolation
RU2606874C1 (ru) * 2015-12-02 2017-01-10 Виталий Витальевич Аверьянов Способ управления устройством формирования среды дополненной реальности
GB2551396B (en) * 2016-06-17 2018-10-10 Imagination Tech Ltd Augmented reality occlusion
JP2018097141A (ja) * 2016-12-13 2018-06-21 富士ゼロックス株式会社 頭部装着型表示装置、仮想物体表示システム

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102473324A (zh) * 2009-08-18 2012-05-23 Metaio有限公司 用于在真实环境中表示虚拟信息的方法
CN104021590A (zh) * 2013-02-28 2014-09-03 北京三星通信技术研究有限公司 虚拟试穿试戴系统和虚拟试穿试戴方法
CN103489214A (zh) * 2013-09-10 2014-01-01 北京邮电大学 增强现实系统中基于虚拟模型预处理的虚实遮挡处理方法
CN106030335A (zh) * 2014-03-28 2016-10-12 英特尔公司 使用微功率脉冲雷达确定移动显示位置和取向
CN105931289A (zh) * 2016-04-14 2016-09-07 大连新锐天地传媒有限公司 实现真实模型遮盖虚拟物体的系统及方法
CN108182730A (zh) * 2018-01-12 2018-06-19 北京小米移动软件有限公司 虚实对象合成方法及装置

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11636653B2 (en) 2018-01-12 2023-04-25 Beijing Xiaomi Mobile Software Co., Ltd. Method and apparatus for synthesizing virtual and real objects

Also Published As

Publication number Publication date
KR20190086658A (ko) 2019-07-23
EP3511864A1 (en) 2019-07-17
JP2020507136A (ja) 2020-03-05
RU2715797C1 (ru) 2020-03-03
CN108182730B (zh) 2022-08-12
CN108182730A (zh) 2018-06-19
US20190221041A1 (en) 2019-07-18
US11636653B2 (en) 2023-04-25
KR102194094B1 (ko) 2020-12-22

Similar Documents

Publication Publication Date Title
WO2019137006A1 (zh) 虚实对象合成方法及装置
US9674395B2 (en) Methods and apparatuses for generating photograph
US20170304735A1 (en) Method and Apparatus for Performing Live Broadcast on Game
CN106408603B (zh) 拍摄方法及装置
EP3179408A2 (en) Picture processing method and apparatus, computer program and recording medium
WO2017088266A1 (zh) 图片处理方法及装置
CN106210496B (zh) 照片拍摄方法及装置
CN108154465B (zh) 图像处理方法及装置
WO2016127671A1 (zh) 图像滤镜生成方法及装置
WO2016192325A1 (zh) 视频文件的标识处理方法及装置
CN110853095B (zh) 相机定位方法、装置、电子设备及存储介质
CN109922252B (zh) 短视频的生成方法及装置、电子设备
CN109218709B (zh) 全息内容的调整方法及装置和计算机可读存储介质
CN116939275A (zh) 直播虚拟资源展示方法、装置、电子设备、服务器及介质
KR102557592B1 (ko) 이미지 표시 방법 및 장치, 전자 기기, 컴퓨터 판독 가능 저장 매체
CN111586296B (zh) 图像拍摄方法、图像拍摄装置及存储介质
CN113315903B (zh) 图像获取方法和装置、电子设备、存储介质
US9619016B2 (en) Method and device for displaying wallpaper image on screen
CN113989424A (zh) 三维虚拟形象的生成方法、装置及电子设备
CN113286073A (zh) 拍摄方法、拍摄装置及存储介质
CN108159686B (zh) 投影设备投影的方法、装置及存储介质
CN106598217B (zh) 显示方法、显示装置和电子设备
CN109447929B (zh) 图像合成方法及装置
CN110458962B (zh) 一种图像处理方法、装置、电子设备及存储介质
CN106713748B (zh) 发送图片的方法及装置

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2018567578

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20197004558

Country of ref document: KR

Kind code of ref document: A

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

Ref document number: 18899877

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18899877

Country of ref document: EP

Kind code of ref document: A1