WO2021244140A1 - 物体测量、虚拟对象处理方法及装置、介质和电子设备 - Google Patents

物体测量、虚拟对象处理方法及装置、介质和电子设备 Download PDF

Info

Publication number
WO2021244140A1
WO2021244140A1 PCT/CN2021/086654 CN2021086654W WO2021244140A1 WO 2021244140 A1 WO2021244140 A1 WO 2021244140A1 CN 2021086654 W CN2021086654 W CN 2021086654W WO 2021244140 A1 WO2021244140 A1 WO 2021244140A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
vertex coordinates
infrared image
dimensional
dimensional vertex
Prior art date
Application number
PCT/CN2021/086654
Other languages
English (en)
French (fr)
Inventor
曾凡涛
Original Assignee
Oppo广东移动通信有限公司
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 Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Priority to EP21818887.8A priority Critical patent/EP4160532A4/en
Publication of WO2021244140A1 publication Critical patent/WO2021244140A1/zh
Priority to US18/061,411 priority patent/US20230113647A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • 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
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • 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
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • 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
    • 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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • 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
    • G06T2207/10024—Color image
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10048—Infrared image
    • 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
    • G06T2207/20112—Image segmentation details
    • G06T2207/20164—Salient point detection; Corner detection

Definitions

  • the present disclosure relates to the field of measurement technology, and in particular, to an object measurement method, a virtual object processing method, an object measurement device, a virtual object processing device, a computer-readable storage medium, and electronic equipment.
  • the surveyor can use a measuring tool such as a tape measure to perform manual measurement.
  • This method requires the surveyor to carry a special measuring tool and record after the measurement, which is cumbersome and inefficient.
  • AR Augmented Reality
  • the deep learning method is usually used to obtain the size information of the object.
  • an object measurement method including: acquiring a depth image of a scene, and determining point cloud data of the scene according to the depth image; performing plane segmentation processing on the point cloud data to determine the surface of the object in the scene Information; combine the surface information of the object to determine the three-dimensional vertex coordinates of the object; use the three-dimensional vertex coordinates of the object to calculate the measurement parameters of the object.
  • a virtual object processing method is provided, which is applied to an electronic device capable of displaying virtual objects, including: using the above object measurement method to measure measurement parameters of objects in a scene, and generate measurement parameters associated with the objects The virtual object in order to display the virtual object on the electronic device.
  • an object measuring device including: a point cloud determination module configured to obtain a depth image of a scene, and determine the point cloud data of the scene according to the depth image; and a plane segmentation module configured to The point cloud data is subjected to plane segmentation processing to determine the surface information of the object in the scene; the object vertex determination module is configured to determine the three-dimensional vertex coordinates of the object in combination with the surface information of the object; the parameter calculation module is configured to use the three-dimensional vertex coordinates of the object Calculate the measurement parameters of the object.
  • a virtual object processing device applied to an electronic device capable of displaying virtual objects, including: an object measuring device configured to measure the measurement parameters of an object in a scene by using the object measurement method described above;
  • the processing module is configured to generate a virtual object associated with the measurement parameter of the object, so as to display the virtual object on the electronic device.
  • a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the above-mentioned object measurement method or virtual object processing method is realized.
  • an electronic device including a processor; a memory, configured to store one or more programs, and when the one or more programs are executed by the processor, the processor realizes the foregoing objects Measurement method or virtual object processing method.
  • FIG. 1 shows a schematic diagram of an exemplary system architecture for AR measurement according to an embodiment of the present disclosure
  • Figure 2 shows a schematic structural diagram of an electronic device suitable for implementing embodiments of the present disclosure
  • FIG. 3 schematically shows a flowchart of an object measuring method according to an exemplary embodiment of the present disclosure
  • FIG. 4 schematically shows a flowchart of a virtual object processing method according to an exemplary embodiment of the present disclosure
  • FIG. 5 schematically shows a flowchart of the entire process of AR measurement according to an embodiment of the present disclosure
  • FIG. 6 shows a schematic diagram of a display effect after performing AR measurement according to an embodiment of the present disclosure
  • FIG. 7 shows a schematic diagram of a display effect after performing AR measurement according to another embodiment of the present disclosure.
  • Fig. 8 schematically shows a block diagram of an object measuring device according to an exemplary embodiment of the present disclosure
  • FIG. 9 schematically shows a block diagram of a virtual object processing apparatus according to an exemplary embodiment of the present disclosure.
  • FIG. 1 shows a schematic diagram of an exemplary system architecture for AR measurement according to an embodiment of the present disclosure.
  • the system architecture for AR measurement described in the embodiments of the present disclosure may be deployed in an electronic device.
  • the electronic device can be any device with AR processing function, including but not limited to mobile phones, tablets, AR glasses, AR helmets, etc.
  • the system architecture for implementing AR measurement in the embodiment of the present disclosure may include an Inertial Measurement Unit (IMU) 11, an RGB camera 12, a depth sensing device 13, an infrared sensing device 14, and an object measuring device. 15. AR platform 16 and AR measurement application 17.
  • IMU Inertial Measurement Unit
  • RGB camera RGB camera
  • depth sensing device 13
  • infrared sensing device 14 14
  • object measuring device 15
  • AR platform 16 and AR measurement application 17 may include an Inertial Measurement Unit (IMU) 11, an RGB camera 12, a depth sensing device 13, an infrared sensing device 14, and an object measuring device. 15.
  • the inertial measurement unit 11 may include a gyroscope and an accelerometer, which can measure the angular velocity and acceleration of the electronic device, respectively.
  • the RGB photographing device 12 can be any camera that photographs RGB images, and the present disclosure does not limit the type thereof.
  • the inertial information of the corresponding frame can be evaluated by means of IMU pre-integration.
  • the IMU pre-integration is a time-based integration, and inertial information such as the position, speed, and rotation angle of the corresponding two images can be obtained.
  • the pose information can be obtained, where the pose information may include, for example, 6DOF (6 Degrees Of Freedom, 6 degrees of freedom) posture information.
  • the depth sensing device 13 may be a device for generating a depth image of a scene, that is, it may be used for collecting depth information of the environment.
  • the depth sensing device 13 may be, for example, a TOF (Time Of Flight) module, a structured light module or a binocular vision module.
  • TOF Time Of Flight
  • the infrared sensing device 14 may be a device for generating an infrared image of a scene, which may be various types of infrared sensors.
  • the object measuring device 15 may be a device for measuring objects in the scene in combination with the depth data sensed by the depth sensing device 13.
  • the AR platform 16 may be a platform constructed based on an existing AR engine (for example, ARCore, ARKit, etc.).
  • the AR measurement application 17 may be an AR application program for human-computer interaction. Through the display interface corresponding to the AR application program, the user can view the virtual objects associated with the measurement parameters of the objects in the scene. In some instances, the user can also perform operations on the virtual object.
  • the object measuring device 15 uses the depth image collected by the depth sensing device 13 to measure objects in the scene
  • the object measuring device 15 acquires the depth image of the scene collected by the depth sensing device 13, and determines the point of the scene based on the depth image Cloud data
  • the object measuring device 15 can perform plane segmentation processing on the point cloud data to determine the plane information in the scene, that is, to determine the surface information of the object in the scene; subsequently, the object measuring device 15 can according to the surface of the object
  • the information determines the three-dimensional vertex coordinates of the object, and uses the three-dimensional vertex coordinates of the object to calculate the measurement parameters of the object.
  • the measurement parameters described in the present disclosure include one or more of length information, width information, height information, surface area information, and volume information of an object.
  • the object to be measured for the present disclosure is usually a regular object. However, those skilled in the art can think that the object to be measured can also be an irregular object based on the concept of this solution.
  • the measurement scheme also belongs to the protection scope of the present disclosure.
  • the depth sensing device 13 cannot collect all the depth information of the object, which will cause inaccurate determination of the apex of the object.
  • the object measuring device 15 may combine the sensing results of the depth sensing device 13 and the infrared sensing device 14 to calculate the measurement parameters of the object, so as to avoid the problem of using only the sensing data of the depth sensing device 13 The problem of inaccurate recognition of object vertices.
  • the object measuring device 15 uses the depth image collected by the depth sensor device 13 and the infrared image collected by the infrared sensor device 14 to measure objects in the scene
  • the object measuring device 15 acquires the scene collected by the depth sensor device 13
  • the depth image is used to determine the point cloud data of the scene according to the depth image
  • the object measurement device 15 can perform plane segmentation processing on the point cloud data to determine the surface information of the object in the scene
  • the object measurement device 15 obtains the object measurement device 15
  • the object measuring device 15 when the object measuring device 15 measures the measurement parameters of the object, it can also combine the image collected by the RGB camera 12 and the sensing result of the depth sensing device 13 to improve the accuracy of the object vertex recognition. Specifically, an image texture analysis can be performed on the RGB image captured by the RGB camera 12 to determine the three-dimensional vertex coordinates of the object in the coordinate system of the RGB camera 12, and combined with the depth image captured by the depth sensing device 13, finally used It is used to calculate the three-dimensional vertex coordinates of the measurement parameters of the object.
  • the object measuring device 15 may also combine the data sent by the RGB camera 12, the depth sensing device 13, and the infrared sensing device 14 to calculate the measurement data of the object. , Which all belong to the protection scope of this disclosure.
  • some other embodiments of the present disclosure further include configuring virtual objects associated with the measurement parameters and displaying them on the interface of the AR measurement application of the electronic device.
  • the measurement parameters can be displayed on the interface in the form of virtual text for the user to view.
  • the object measuring device 15 can send the three-dimensional vertex coordinates and measurement parameters of the object in the coordinate system of the depth sensing device 13 to the AR platform 16, and the AR platform 16 can send the three-dimensional vertex of the object in the coordinate system of the depth sensing device 13
  • the coordinates are converted to coordinates in the coordinate system of the AR platform 16, and in the AR measurement application 17, the rendering of the three-dimensional frame outside the object is realized, and the virtual three-dimensional frame is displayed on the interface. It should be understood that in AR measurement, the virtual three-dimensional frame is always circumscribed to the object.
  • the three-dimensional vertex coordinates and/or measurement parameters of the object can be stored in the electronic device or the cloud, so that the electronic device can directly obtain the information when it runs the AR measurement application 17 in the same scene next time, or other electronic devices in the same scene This information can be obtained when the AR measurement application 17 is run.
  • Fig. 2 shows a schematic diagram of an electronic device suitable for implementing exemplary embodiments of the present disclosure. It should be noted that the electronic device shown in FIG. 2 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.
  • the electronic device of the present disclosure includes at least a processor and a memory.
  • the memory is used to store one or more programs.
  • the processor can implement the object measurement method or Virtual object processing method.
  • the electronic device 200 may include: a processor 210, an internal memory 221, an external memory interface 222, a Universal Serial Bus (USB) interface 230, a charging management module 240, and a power management module 241, battery 242, antenna 1, antenna 2, mobile communication module 250, wireless communication module 260, audio module 270, speaker 271, receiver 272, microphone 273, earphone interface 274, sensor module 280, display screen 290, camera module 291 , Indicator 292, motor 293, button 294, Subscriber Identification Module (SIM) card interface 295, etc.
  • SIM Subscriber Identification Module
  • the sensor module 280 may include a depth sensor, a pressure sensor, a gyroscope sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, and a bone conduction sensor.
  • the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 200.
  • the electronic device 200 may include more or fewer components than shown, or combine certain components, or split certain components, or arrange different components.
  • the illustrated components can be implemented in hardware, software, or a combination of software and hardware.
  • the processor 210 may include one or more processing units.
  • the processor 210 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), and an image signal processor. (Image Signal Processor, ISP), controller, video codec, digital signal processor (Digital Signal Processor, DSP), baseband processor and/or neural network processor (Neural-etwork Processing Unit, NPU), etc.
  • AP application processor
  • ISP image Signal Processor
  • controller video codec
  • digital signal processor Digital Signal Processor
  • DSP digital Signal Processor
  • NPU neural network processor
  • the different processing units may be independent devices or integrated in one or more processors.
  • a memory may be provided in the processor 210 for storing instructions and data.
  • the USB interface 230 is an interface that complies with the USB standard specification, and specifically may be a MiniUSB interface, a MicroUSB interface, a USBTypeC interface, and the like.
  • the USB interface 230 can be used to connect a charger to charge the electronic device 200, and can also be used to transfer data between the electronic device 200 and peripheral devices. It can also be used to connect earphones and play audio through earphones.
  • the interface can also be used to connect other electronic devices, such as AR devices.
  • the charging management module 240 is used to receive charging input from the charger.
  • the charger can be a wireless charger or a wired charger.
  • the power management module 241 is used to connect the battery 242, the charging management module 240, and the processor 210.
  • the power management module 241 receives input from the battery 242 and/or the charging management module 240, and supplies power to the processor 210, the internal memory 221, the display screen 290, the camera module 291, and the wireless communication module 260.
  • the wireless communication function of the electronic device 200 can be implemented by the antenna 1, the antenna 2, the mobile communication module 250, the wireless communication module 260, the modem processor, and the baseband processor.
  • the mobile communication module 250 may provide a wireless communication solution including 2G/3G/4G/5G and the like applied to the electronic device 200.
  • the wireless communication module 260 can provide applications on the electronic device 200 including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), and global navigation satellites.
  • WLAN wireless local area networks
  • BT Bluetooth
  • GNSS Global Navigation Satellite System
  • FM Frequency Modulation
  • NFC Near Field Communication
  • IR Infrared
  • the electronic device 200 implements a display function through a GPU, a display screen 290, an application processor, and the like.
  • the GPU is a microprocessor for image processing and is connected to the display screen 290 and the application processor.
  • the GPU is used to perform mathematical and geometric calculations for graphics rendering.
  • the processor 210 may include one or more GPUs that execute program instructions to generate or change display information.
  • the electronic device 200 can implement a shooting function through an ISP, a camera module 291, a video codec, a GPU, a display screen 290, and an application processor.
  • the electronic device 200 may include 1 or N camera modules 291, and N is a positive integer greater than 1. If the electronic device 200 includes N cameras, one of the N cameras is the main camera.
  • the internal memory 221 may be used to store computer executable program code, where the executable program code includes instructions.
  • the internal memory 221 may include a storage program area and a storage data area.
  • the external memory interface 222 may be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 200.
  • the electronic device 200 can implement audio functions through an audio module 270, a speaker 271, a receiver 272, a microphone 273, a headphone interface 274, an application processor, and the like. For example, music playback, recording, etc.
  • the audio module 270 is used for converting digital audio information into an analog audio signal for output, and also for converting an analog audio input into a digital audio signal.
  • the audio module 270 can also be used to encode and decode audio signals.
  • the audio module 270 may be provided in the processor 210, or part of the functional modules of the audio module 270 may be provided in the processor 210.
  • the speaker 271 also called a "speaker” is used to convert audio electrical signals into sound signals.
  • the electronic device 200 can listen to music through the speaker 271, or listen to a hands-free call.
  • the microphone 273, also called “microphone” or “microphone”, is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can approach the microphone 273 through the mouth to make a sound, and input the sound signal to the microphone 273.
  • the electronic device 200 may be provided with at least one microphone 273.
  • the earphone interface 274 is used to connect wired earphones.
  • the depth sensor is used to obtain depth information of the scene.
  • the pressure sensor is used to sense the pressure signal and can convert the pressure signal into an electrical signal.
  • the gyroscope sensor can be used to determine the movement posture of the electronic device 200.
  • the air pressure sensor is used to measure air pressure.
  • the magnetic sensor includes a Hall sensor.
  • the electronic device 200 may use a magnetic sensor to detect the opening and closing of the flip holster.
  • the acceleration sensor can detect the magnitude of the acceleration of the electronic device 200 in various directions (generally three axes).
  • the distance sensor is used to measure distance.
  • the proximity light sensor may include, for example, a light emitting diode (LED) and a light detector, such as a photodiode.
  • the fingerprint sensor is used to collect fingerprints.
  • the temperature sensor is used to detect temperature.
  • the touch sensor can pass the detected touch operation to the application processor to determine the type of touch event.
  • the visual output related to the touch operation can be provided through the display screen 290.
  • the ambient light sensor is used to sense the brightness of the ambient light. Bone conduction sensors can acquire vibration signals.
  • the button 294 includes a power button, a volume button, and so on.
  • the button 294 may be a mechanical button. It can also be a touch button.
  • the motor 293 can generate vibration prompts. The motor 293 can be used for incoming call vibration notification, and can also be used for touch vibration feedback.
  • the indicator 292 can be an indicator light, which can be used to indicate the charging status, power change, or to indicate messages, missed calls, notifications, and so on.
  • the SIM card interface 295 is used to connect to the SIM card.
  • the electronic device 200 interacts with the network through the SIM card to implement functions such as call and data communication.
  • the present application also provides a computer-readable storage medium.
  • the computer-readable storage medium may be included in the electronic device described in the foregoing embodiment; or it may exist alone without being assembled into the electronic device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • the computer-readable storage medium can send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device.
  • the program code contained on the computer-readable storage medium can be transmitted by any suitable medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the foregoing.
  • the computer-readable storage medium carries one or more programs, and when the one or more programs are executed by an electronic device, the electronic device implements the methods described in the following embodiments.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the above-mentioned module, program segment, or part of code contains one or more for realizing the specified logic function.
  • Executable instructions may also occur in a different order from the order marked in the drawings. For example, two blocks shown one after the other can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved.
  • each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by It is realized by a combination of dedicated hardware and computer instructions.
  • the units described in the embodiments of the present disclosure may be implemented in software or hardware, and the described units may also be provided in a processor. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances.
  • the involved RGB camera, depth sensor, and infrared sensor are all devices after the camera parameter calibration is completed, and the present disclosure does not limit the calibration process.
  • the time stamps of the collected RGB image, depth image and infrared image are synchronized.
  • the present disclosure does not limit the number of objects in the scene, and the following object measurement schemes can be used to measure the measurement parameters of each object.
  • FIG. 3 schematically shows a flowchart of an object measurement method of an exemplary embodiment of the present disclosure.
  • the object measurement method may include the following steps:
  • the scene referred to in the exemplary embodiments of the present disclosure refers to a real scene containing an object, and a depth sensing device equipped in an electronic device can sense the scene to obtain a depth image of the scene.
  • the camera parameters of the depth sensing device can be used for calculation to obtain the point cloud data corresponding to the depth image.
  • the camera parameters of the depth sensing device that took the depth image can be obtained, and the camera parameters can be specifically expressed as:
  • f x and f y represent the focal length of the camera of the depth sensing device
  • u 0 and v 0 represent the center coordinates of the depth image.
  • f x , f y , u 0 and v 0 can be calculated by calibration.
  • the calibration process can be completed offline or online.
  • linear calibration methods for example, Faugeras calibration method, etc.
  • nonlinear optimization calibration methods for example, Levenberg-Marquadt algorithm, etc.
  • two-step calibration method can be used (For example, Tsai two-step method, Zhang Zhengyou calibration algorithm, etc.) or other methods to calculate f x , f y , u 0 and v 0 , which are not particularly limited in this exemplary embodiment.
  • Zhang Zhengyou calibration algorithm Take the Zhang Zhengyou calibration algorithm as an example. You can place an image with a checkerboard as the calibration image in front of the camera. Since four quantities need to be calculated, you can use Zhang Zhengyou when shooting at least 3 images from different angles and positions.
  • the calibration algorithm linearly and uniquely solves f x , f y , u 0 and v 0 .
  • the above-mentioned at least three images can be used as calibration images, and the calibration image is processed by Zhang Zhengyou calibration algorithm to automatically calculate camera parameters.
  • the calibration image may also be an image other than an image drawn with a checkerboard, which is not particularly limited in this exemplary embodiment.
  • the camera parameters and the depth information of each pixel on the depth image can be used to calculate the three-dimensional data corresponding to the depth information as the point cloud data of the scene. Specifically, the following formula can be used for calculation:
  • u and v are the coordinate points of each pixel on the depth image
  • Z c is the z-axis value of the camera coordinate. Since it is in the reference coordinate system of the depth sensing device itself, R is the unit matrix and T is 0.
  • f x , f y , u 0 , v 0 and u, v, Z W are known, X W and Y W can be solved, and finally X W , Y W , Z W are obtained , and the three-dimensional scene is generated Point cloud data.
  • a random sample consensus (RANSAC) algorithm may be used to perform plane segmentation on the point cloud data.
  • the geometric constraint information described in the present disclosure may include, but is not limited to: planes or surfaces are intersecting (that is, there are overlapping point clouds), and the side surface and the placement surface (ground or desktop) are mutually intersecting. Vertical, etc.
  • the point cloud data may be denoised before the plane segmentation processing is performed on the point cloud data.
  • the point cloud data may be denoised.
  • filters may be used to implement the denoising processing, which is not limited in the present disclosure.
  • S36 Determine the three-dimensional vertex coordinates of the object in combination with the surface information of the object.
  • the three-dimensional vertex coordinates of the object can be determined directly by using the object surface information determined based on the plane segmentation. For example, determine the coordinates of 4 vertices on the upper surface of a rectangular parallelepiped placed on the ground in the scene. Combined with the distance between the ground and the upper surface, the height information of the cuboid is obtained. Using the height information and the normal vector of the upper surface, the coordinates of the four vertices of the lower surface of the cuboid can be obtained. That is, the three-dimensional vertex coordinates of the object are determined.
  • the depth image collected by the depth sensing device may be incomplete or inaccurate.
  • the depth image and infrared image can be combined to calculate the three-dimensional vertices of the object. coordinate.
  • the infrared sensing device equipped in the electronic device can sense the scene, obtain an infrared image of the scene, and extract the corner point information of the object in the infrared image.
  • an embodiment of the present disclosure may also perform brightness equalization processing on the infrared image to avoid the situation that the image is too dark or too bright. For example, normalization, histogram equalization, and other processing methods can be used to make the brightness distribution of the infrared image uniform, and make the average brightness of each pixel of the infrared image greater than the brightness threshold.
  • the SUSAN corner point detection algorithm can be used to extract the corner point information of the object in the infrared image.
  • the value of the corner response function can be calculated for each pixel based on an approximate circular template containing several elements in the pixel field. If it is greater than the threshold and is a local maximum, the point is determined to be corner.
  • the relationship between the straight lines in the infrared image can be used to further determine the corner points.
  • a corner point extraction process can be performed on the infrared image, and the corner point obtained by this process is determined as the first corner point information of the infrared image.
  • the straight line extraction process can be performed on the infrared image to obtain the straight line information of the infrared image.
  • the straight line information can be extracted from the infrared image by using methods such as Hough transform and HOG feature extraction. Subsequently, the intersection point between the straight lines can be determined from the obtained straight line information as the second corner point information of the infrared image.
  • the redundant corner point information is eliminated to determine the corner point information of the object in the infrared image.
  • the electronic device can determine the three-dimensional vertex coordinates of the object according to the corner point information of the object in the infrared image and the surface information of the object determined in step S34.
  • the corner point information of the object in the infrared image can be used to determine the two-dimensional vertex coordinates of the object in the infrared image.
  • the depth information and the geometric constraint information of the object can be used for constraint.
  • the range of the planar point cloud on the object can be determined according to the surface information of the object, and the range of the planar point cloud on the object and the geometric constraint information of the object can be used as constraints to limit the determined corner points to determine the infrared image
  • the two-dimensional vertex coordinates of the middle object can be used to limit the determined corner points to determine the infrared image.
  • the two-dimensional vertex coordinates of the object in the infrared image and the camera camera parameters of the infrared sensing device can be used to calculate the three-dimensional vertex coordinates of the object in the coordinate system of the infrared sensing device.
  • the formula used in the specific calculation is similar to the formula in step S32, and will not be repeated here.
  • the three-dimensional vertex coordinates of the object can be determined.
  • a ray directed to the three-dimensional vertex coordinates in the coordinate system of the infrared sensing device is constructed. Therefore, there will be an intersection point between the ray and the plane corresponding to the surface information of the object.
  • the intersection point is determined as the three-dimensional vertex coordinates of the object in the coordinate system of the depth sensing device, and the object is determined in the coordinate system of the depth sensing device.
  • the three-dimensional vertex coordinates are determined as the three-dimensional vertex coordinates of the object determined in step S36.
  • the measurement parameter of the object includes one or more of length information, width information, height information, surface area information, and volume information of the object.
  • the three-dimensional vertex coordinates determined in step S36 include the three-dimensional vertex coordinates of the upper surface of the object.
  • the three-dimensional vertex coordinates of the upper surface can be used to calculate the three-dimensional vertex coordinates of the lower surface, and the three-dimensional vertex coordinates of the upper and lower surfaces can be used to calculate the measurement parameters of the object.
  • the process of calculating the three-dimensional vertex coordinates of the lower surface of the object firstly, use the plane segmentation processing result for the point cloud data to determine the plane information of the plane (such as the ground or the desktop) on which the object is placed; Plane information and the surface information of the upper surface of the object, calculate the height information of the object, that is, you can calculate the distance between two planes to obtain the height information of the object; then, combine the height information of the object and the three-dimensional vertex coordinates of the upper surface of the object As well as the normal vector of the upper surface of the object, the three-dimensional vertex coordinates of the lower surface of the object can be calculated.
  • the plane information of the plane such as the ground or the desktop
  • the present disclosure automatically measures objects with the help of scene depth information. Compared with the deep learning solution, the present disclosure does not need to collect a large number of object information for training, and avoids objects that have not been pre-trained. The problem of inaccurate measurement results improves the robustness and application range of object measurement; on the other hand, in some embodiments of the present disclosure, infrared images are combined to further improve the accuracy of identifying the three-dimensional vertex coordinates of the object. Make the calculated measurement parameters more accurate.
  • the present disclosure also provides a solution for realizing the generation and display of virtual objects by using the above-mentioned object measurement method. Specifically, the present disclosure also provides a virtual object processing method, which is applied to an electronic device capable of displaying virtual objects.
  • the virtual object processing method of the exemplary embodiment of the present disclosure may include the following steps:
  • Step S40 to step S46 are the same as the implementation process of step S32 to step S38 described above, and will not be repeated here.
  • the virtual object includes a three-dimensional virtual frame corresponding to the object.
  • the three-dimensional vertex coordinates of the object can be obtained, and the three-dimensional vertex coordinates of the object can be converted into the coordinate system of the augmented reality platform. Three-dimensional coordinates.
  • the RGB image pose information can be obtained based on the RGB image captured by the RGB camera and the inertial data detected by the IMU, where the time stamp of the RGB image and the time stamp of the depth image used when determining the three-dimensional vertex coordinates of the object Unanimous.
  • the camera parameters of the RGB shooting device and the camera parameters of the depth sensing device When the camera parameters of the RGB shooting device and the camera parameters of the depth sensing device are acquired, the camera parameters of the RGB shooting device, the camera parameters of the depth sensing device, and the pose information of the RGB image can be used to convert the three-dimensional vertices of the object
  • the coordinates are converted into three-dimensional coordinates in the coordinate system of the RGB camera, and the three-dimensional coordinates can be determined as the three-dimensional coordinates in the coordinate system of the augmented reality platform.
  • the specific conversion process still involves the conversion process of three-dimensional data and two-dimensional data. For details, please refer to the formula in step S32, which will not be repeated here.
  • the geometric constraints of the object can be used to render and generate a three-dimensional virtual frame corresponding to the object.
  • the three-dimensional virtual frame may be displayed on the interface.
  • the virtual object may be a virtual text generated after the measurement parameter is converted.
  • the number of virtual objects generated in step S48 may be one or more.
  • the virtual objects may include both a three-dimensional virtual frame and virtual text.
  • step S502 the depth image of the scene collected by the depth sensing device can be acquired; in step S504, based on the camera parameters of the depth sensing device, the depth image can be used to generate point cloud data; in step S506, the point cloud The data is processed by plane segmentation to obtain the surface information of the objects in the scene.
  • step S508 the infrared image of the scene collected by the infrared sensing device can be acquired; in step S510, the corner point information and straight line information of the infrared image can be extracted; in step S512, it can be based on the extracted corner point information and The straight line information determines the two-dimensional vertex coordinates of the object in the infrared image.
  • the depth point cloud data can be used to constrain, so that the determined vertex coordinates are more accurate.
  • step S514 using the two-dimensional vertex coordinates and the camera parameters of the infrared sensing device, the three-dimensional vertex coordinates of the object in the infrared sensing device coordinate system can be calculated.
  • step S5166 the three-dimensional vertex coordinates of the object in the depth sensing device coordinate system can be determined by using the surface information of the object determined from the depth image and the three-dimensional vertex coordinates in the infrared sensing device coordinate system.
  • step S5108 the three-dimensional vertex coordinates of the object can be used to calculate the measurement parameters of the object.
  • a virtual object associated with the measurement parameter of the object may be generated and displayed on the application program interface of the electronic device.
  • Fig. 6 shows a schematic diagram of a display effect after performing AR measurement according to an embodiment of the present disclosure.
  • a cuboid box 62 is placed on the table 61.
  • the electronic device 60 starts the AR measurement application and executes the above virtual object processing method
  • the three-dimensional frame 63 of the box 62 can be displayed on the application interface of the electronic device 60 .
  • the three-dimensional frame 63 can be configured in various colors and styles.
  • the three-dimensional frame 63 is configured in the manner of anchor points, and no matter how the user's viewing angle changes, that is, no matter how the electronic device 60 moves, the relative position of the three-dimensional frame 63 and the box 62 is fixed.
  • FIG. 7 shows a schematic diagram of a display effect after performing AR measurement according to another embodiment of the present disclosure.
  • a cuboid box 72 is placed on the table 71.
  • the measurement parameters corresponding to the box 72 can be displayed on the application interface of the electronic device 70
  • the virtual text is, for example, "object volume: 18 cm 3 ".
  • the virtual text can be configured in various colors and styles.
  • the electronic device may also detect the environment around the object, and if it detects objects of a preset type, avoid these objects and perform virtual operations.
  • the display of the object can be set by the user, and the detection process can be implemented using a classification model of deep learning, which is not limited in the present disclosure.
  • another virtual object can be arranged around the object, which has increased interest or realized the configuration of AR games.
  • a virtual cartoon character can be placed on the upper surface of the object, and the user can also use the controls on the interface to control the virtual cartoon character to walk, jump, wave, etc. Show of action.
  • this example embodiment also provides an object measuring device.
  • FIG. 8 schematically shows a block diagram of an object measuring device according to an exemplary embodiment of the present disclosure.
  • the object measurement device 8 may include a point cloud determination module 81, a plane segmentation module 83, an object vertex determination module 85, and a parameter calculation module 87.
  • the point cloud determination module 81 may be configured to acquire a depth image of the scene, and determine the point cloud data of the scene according to the depth image; the plane segmentation module 83 may be configured to perform plane segmentation processing on the point cloud data To determine the surface information of the object in the scene; the object vertex determination module 85 may be configured to determine the three-dimensional vertex coordinates of the object in combination with the surface information of the object; the parameter calculation module 87 may be configured to use the The three-dimensional vertex coordinates calculate the measurement parameters of the object.
  • the object vertex determination module 85 may be configured to perform: obtain an infrared image of the scene, extract corner point information of the object in the infrared image; according to the corner point information of the object in the infrared image and the surface information of the object , To determine the three-dimensional vertex coordinates of the object.
  • the process of extracting the corner point information of the object in the infrared image by the object vertex determination module 85 may be configured to perform: performing a corner point extraction process on the infrared image to obtain the first corner point information of the infrared image; Perform the straight line extraction process on the infrared image to obtain the straight line information of the infrared image; use the straight line information of the infrared image to determine the second corner point information of the infrared image; combine the first corner point information and the second corner point information of the infrared image to determine the infrared The corner point information of the object in the image.
  • the process of determining the three-dimensional vertex coordinates of the object by the object vertex determining module 85 according to the corner point information of the object in the infrared image and the surface information of the object may be configured to perform: combining the corner points of the object in the infrared image The information determines the two-dimensional vertex coordinates of the object in the infrared image; the two-dimensional vertex coordinates of the object in the infrared image, the camera parameters of the infrared sensing device that shoots the infrared image, and the surface information of the object are used to determine the three-dimensional vertex coordinates of the object.
  • the process of determining the two-dimensional vertex coordinates of the object in the infrared image by the object vertex determining module 85 in combination with the corner point information of the object in the infrared image may be configured to execute: The range of the plane point cloud; use the corner point information of the object in the infrared image, the range of the plane point cloud on the object, and the geometric constraint information of the object to determine the two-dimensional vertex coordinates of the object in the infrared image.
  • the process of determining the three-dimensional vertex coordinates of the object by the object vertex determination module 85 may be configured to perform: using the two-dimensional vertex coordinates of the object in the infrared image and the camera parameters of the infrared sensing device to calculate the object's position The three-dimensional vertex coordinates in the coordinate system of the infrared sensing device; taking the camera optical center coordinates of the depth sensing device that took the depth image as a starting point, construct a ray directed to the three-dimensional vertex coordinates in the coordinate system of the infrared sensing device; The intersection point of the plane corresponding to the surface information of the object is determined as the three-dimensional vertex coordinates of the object in the coordinate system of the depth sensing device, and the three-dimensional vertex coordinates of the object in the coordinate system of the depth sensing device are determined as the three-dimensional vertex coordinates of the object ; Among them, the camera coordinate system of the depth sensing device and the infrared sensing
  • the object vertex determination module 85 may be further configured to perform brightness equalization processing on the infrared image before extracting the corner point information of the object in the infrared image.
  • the three-dimensional vertex coordinates of the object include the three-dimensional vertex coordinates of the upper surface of the object; in this case, the parameter calculation module 87 may be configured to perform: using the plane segmentation processing result for the point cloud data, Determine the plane information of the plane where the object is placed; calculate the height information of the object according to the plane information of the plane where the object is placed and the surface information of the upper surface of the object; combine the height information of the object, the three-dimensional vertex coordinates of the upper surface of the object and the method of the upper surface of the object Vector, calculate the three-dimensional vertex coordinates of the bottom surface of the object; use the three-dimensional vertex coordinates of the top surface of the object and the three-dimensional vertex coordinates of the bottom surface of the object to calculate the measurement parameters of the object.
  • the measurement parameter of the object includes one or more of length information, width information, height information, surface area information, and volume information of the object.
  • the point cloud determination module 81 may be configured to execute: acquire the camera parameters of the depth sensing device that takes the depth image; use the camera parameters of the depth sensing device to take the depth image and the depth image The depth information of the pixel is calculated and the three-dimensional data corresponding to the depth information is calculated as the point cloud data of the scene.
  • this exemplary embodiment also provides a virtual object processing apparatus, which is applied to an electronic device capable of displaying virtual objects.
  • FIG. 9 schematically shows a block diagram of a virtual object processing apparatus according to an exemplary embodiment of the present disclosure.
  • a virtual object processing device 9 may include the above-mentioned object measuring device 8 and an object processing module 91.
  • the object processing module 91 is configured to generate a virtual object associated with the measurement parameter of the object, so as to display the virtual object on the electronic device.
  • the virtual object includes a three-dimensional virtual frame corresponding to the object; in this case, the object processing module 91 may be configured to perform: obtain the three-dimensional vertex coordinates of the object; convert the three-dimensional vertex coordinates of the object It is the three-dimensional coordinates in the coordinate system of the augmented reality platform; based on the three-dimensional coordinates in the coordinate system of the augmented reality platform, a three-dimensional virtual frame corresponding to the object is generated by rendering.
  • the process of the object processing module 91 converting the three-dimensional vertex coordinates of the object into the three-dimensional coordinates in the augmented reality platform coordinate system may be configured to perform: obtain the pose information of the RGB image; wherein, the RGB image The time stamp of is consistent with the time stamp of the depth image used when determining the three-dimensional vertex coordinates of the object; the camera parameters of the RGB shooting device that captures the RGB image and the camera parameters of the depth sensing device that captures the depth image; the use of RGB images Convert the three-dimensional vertex coordinates of the object to the three-dimensional coordinates in the coordinate system of the RGB camera to obtain the three-dimensional coordinates in the coordinate system of the augmented reality platform .
  • the exemplary embodiments described herein can be implemented by software, or can be implemented by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or on the network , Including several instructions to make a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) execute the method according to the embodiment of the present disclosure.
  • a non-volatile storage medium which can be a CD-ROM, U disk, mobile hard disk, etc.
  • Including several instructions to make a computing device which can be a personal computer, a server, a terminal device, or a network device, etc.
  • modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory.
  • the features and functions of two or more modules or units described above may be embodied in one module or unit.
  • the features and functions of a module or unit described above can be further divided into multiple modules or units to be embodied.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Geometry (AREA)
  • Computer Graphics (AREA)
  • Computer Hardware Design (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

一种物体测量方法、虚拟对象处理方法、物体测量装置、虚拟对象处理装置、计算机可读存储介质和电子设备，涉及测量领域。该方法包括：获取场景的深度图像，根据深度图像确定场景的点云数据(S32)；对点云数据进行平面分割处理，以确定场景中物体的表面信息(S34)；结合物体的表面信息确定物体的三维顶点坐标(S36)；利用物体的三维顶点坐标计算物体的测量参数(S38)。另外，还可以生成与测量参数相关联的虚拟对象，并在电子设备上显示出该虚拟对象，以便用户查看，该方法可以提高物体测量的准确性。

Description

物体测量、虚拟对象处理方法及装置、介质和电子设备
相关申请的交叉引用
本申请要求于2020年06月03日提交的申请号为202010495293.0、名称为“物体测量、虚拟对象处理方法及装置、介质和电子设备”的中国专利申请的优先权，该中国专利申请的全部内容通过引用全部并入本文。
技术领域
本公开涉及测量技术领域，具体而言，涉及一种物体测量方法、虚拟对象处理方法、物体测量装置、虚拟对象处理装置、计算机可读存储介质和电子设备。
背景技术
在生产和生活中，往往需要对真实世界中的物体进行测量。测量人员可以利用例如卷尺等测量工具进行手动测量，这种方式需要测量人员携带专门的测量工具并在测量后进行记录，过程繁琐，效率低。
随着AR(Augmented Reality，增强现实)技术的发展，AR测量方案应运而生。目前，在AR测量的方法中，通常采用深度学习的方法获取物体的尺寸信息。
发明内容
根据本公开的第一方面，提供了一种物体测量方法，包括：获取场景的深度图像，根据深度图像确定场景的点云数据；对点云数据进行平面分割处理，以确定场景中物体的表面信息；结合物体的表面信息确定物体的三维顶点坐标；利用物体的三维顶点坐标计算物体的测量参数。
根据本公开的第二方面，提供了一种虚拟对象处理方法，应用于能够显示虚拟对象的电子设备，包括：利用上述物体测量方法测量场景中物体的测量参数，生成与物体的测量参数相关联的虚拟对象，以便在电子设备上显示出虚拟对象。
根据本公开的第三方面，提供了一种物体测量装置，包括：点云确定模块，被配置为获取场景的深度图像，根据深度图像确定场景的点云数据；平面分割模块，被配置为对点云数据进行平面分割处理，以确定场景中物体的表面信息；物体顶点确定模块，被配置为结合物体的表面信息确定物体的三维顶点坐标；参数计算模块，被配置为利用物体的三维顶点坐标计算物体的测量参数。
根据本公开的第四方面，提供了一种虚拟对象处理装置，应用于能够显示虚拟对象的电子设备，包括：物体测量装置，被配置为利用上述物体测量方法测量场景中物体的测量参数；对象处理模块，被配置为生成与物体的测量参数相关联的虚拟对象，以便在电子设备上显示出虚拟对象。
根据本公开的第五方面，提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现上述的物体测量方法或虚拟对象处理方法。
根据本公开的第六方面，提供了一种电子设备，包括处理器；存储器，被配置为存储一个或多个程序，当一个或多个程序被处理器执行时，使得处理器实现上述的物体测量方法或虚拟对象处理方法。
附图说明
图1示出了本公开实施例的进行AR测量的示例性系统架构的示意图；
图2示出了适于用来实现本公开实施例的电子设备的结构示意图；
图3示意性示出了根据本公开的示例性实施方式的物体测量方法的流程图；
图4示意性示出了根据本公开的示例性实施方式的虚拟对象处理方法的流程图；
图5示意性示出了本公开一个实施例的AR测量的整个过程的流程图；
图6示出了本公开一个实施例的执行AR测量后的显示效果的示意图；
图7示出了本公开另一个实施例的执行AR测量后的显示效果的示意图；
图8示意性示出了根据本公开的示例性实施方式的物体测量装置的方框图；
图9示意性示出了根据本公开的示例性实施方式的虚拟对象处理装置的方框图。
具体实施方式
现在将参考附图更全面地描述示例实施方式。然而，示例实施方式能够以多种形式实施，且不应被理解为限于在此阐述的范例；相反，提供这些实施方式使得本公开将更加全面和完整，并将示例实施方式的构思全面地传达给本领域的技术人员。所描述的特征、结构或特性可以以任何合适的方式结合在一个或更多实施方式中。在下面的描述中，提供许多具体细节从而给出对本公开的实施方式的充分理解。然而，本领域技术人员将意识到，可以实践本公开的技术方案而省略所述特定细节中的一个或更多，或者可以采用其它的方法、组元、装置、步骤等。在其它情况下，不详细示出或描述公知技术方案以避免喧宾夺主而使得本公开的各方面变得模糊。
此外，附图仅为本公开的示意性图解，并非一定是按比例绘制。图中相同的附图标记表示相同或类似的部分，因而将省略对它们的重复描述。附图中所示的一些方框图是功能实体，不一定必须与物理或逻辑上独立的实体相对应。可以采用软件形式来实现这些功能实体，或在一个或多个硬件模块或集成电路中实现这些功能实体，或在不同网络和/或处理器装置和/或微控制器装置中实现这些功能实体。
附图中所示的流程图仅是示例性说明，不是必须包括所有的步骤。例如，有的步骤还可以分解，而有的步骤可以合并或部分合并，因此实际执行的顺序有可能根据实际情况改变。另外，下面所有的术语“第一”、“第二”仅是为了区分的目的，不应作为本公开内容的限制。
图1示出了本公开实施例的进行AR测量的示例性系统架构的示意图。
应当理解的是，本公开实施例所述的进行AR测量的系统架构可以部署在电子设备中。该电子设备可以是任意具有AR处理功能的设备，包括但不限于手机、平板、AR眼镜、AR头盔等。
如图1所示，本公开实施例实现AR测量的系统架构可以包括惯性测量单元(Inertial Measurement Unit，IMU)11、RGB拍摄装置12、深度感测装置13、红外感测装置14、物体测量装置15、AR平台16和AR测量应用17。
惯性测量单元11可以包括陀螺仪和加速度计，可以分别测量电子设备的角速度和加速度。RGB拍摄装置12可以为任意拍摄RGB图像的相机，本公开对其类型不做限制。
由于惯性测量单元11的工作频率通常比RGB拍摄装置12的频率高，可以采用IMU预积分的方式评估对应帧的惯性信息。其中，IMU预积分是基于时间的积分，可以得到对应两个图像的位置、速度与旋转角度等惯性信息。
通过惯性测量单元11和RGB拍摄装置12的工作，可以得到位姿信息，其中，位姿信息可以例如包括6DOF(6Degrees Of Freedom，6自由度)姿态信息。
深度感测装置13可以是用于生成场景深度图像的装置，也就是说，其可以用于采集环境的深度信息。深度感测装置13可以例如是TOF(Time Of Flight，飞行时间)模组、结构光模组或双目视觉模组。
红外感测装置14可以是用于生成场景红外图像的装置，其可以是各种类型的红外传感器。
物体测量装置15可以是用于结合深度感测装置13所感测的深度数据对场景中物体进行测量的装置。
AR平台16可以是基于现有AR引擎(例如，ARCore、ARKit等)构建出的平台。
AR测量应用17可以是用于人机交互的AR应用程序，通过该AR应用程序对应的显示界面，用户可以查看与场景中物体的测量参数相关联的虚拟对象。在一些实例中，用户还可以对该虚拟对象进行操作。
在物体测量装置15利用深度感测装置13采集的深度图像对场景中物体进行测量的实例中，首先，物体测量装置15获取深度感测装置13采集的场景深度图像，根据深度图像确定场景的点云数据；接下来，物体测量装置15可以对点云数据进行平面分割处理，以确定场景中的平面信息，也就是确定出场景中物体的表面信息；随后，物体测量装置15可以根据物体的表面信息确定出物体的三维顶点坐标，并利用物体的三维顶点坐标计算物体的测量参数。
本公开所述的测量参数包括物体的长度信息、宽度信息、高度信息、表面面积信息、体积信息中的一个或多个。另外，本公开针对的待测量的物体通常是规则物体，然而，本领域技术人员可以基于本方案的构思，联想到待测量物体还可以是不规则物体，采用本公开的构思实现不规则物体的测量方案，也属于本公开的保护范围。
上面的实施例中，仅利用深度信息计算物体的测量参数。然而，由于可能存在的物体表面颜色深、采集角度不佳、深度感测装置13性能缺陷等原因，深度感测装置13不能采集物体的全部深度信息，这样会造成确定出物体顶点不准确。
在这种情况下，物体测量装置15可以结合深度感测装置13和红外感测装置14的感测结果，来计算物体的测量参数，以避免仅采用深度感测装置13的感测数据而造成物体顶点识别不准确的问题。
在物体测量装置15利用深度感测装置13采集的深度图像以及红外感测装置14采集的红外图像对场景中物体进行测量的实例中，首先，物体测量装置15获取深度感测装置13采集的场景深度图像，根据深度图像确定场景的点云数据；接下来，物体测量装置15可以对点云数据进行平面分割处理，以确定场景中物体的表面信息；另外，物体测量装置15获取物体测量装置15获取红外感测装置14采集的红外图像，提取红外图像中的角点信息和直线信息，利用角点信息和直线信息确定出物体在红外图像中的二维顶点坐标，并根据该二维顶点坐标计算出物体在红外感测装置14的坐标系下的三维顶点坐标；随后，物体测量装置15利用物体在红外感测装置14的坐标系下的三维顶点坐标以及确定出的物体的表面信息，确定出物体在深度感测装置13坐标系下的三维顶点坐标，并利用物体在深度感测装置13坐标系下的三维顶点坐标计算物体的测量参数。
此外，物体测量装置15在对物体的测量参数进行测量时，还可以结合RGB拍摄装置12采集的图像以及深度感测装置13的感测结果，以提高物体顶点识别的准确性。具体的，可以对RGB拍摄装置12拍摄的RGB图像进行图像纹理分析，以确定出物体在RGB拍摄装置12坐标系下的三维顶点坐标，并结合深度感测装置13采集的深度图像，最终得到用于计算物体的测量参数的三维顶点坐标。
应当理解的是，在进一步得到更加准确的物体顶点坐标的实例中，物体测量装置15还可以结合RGB拍摄装置12、深度感测装置13、红外感测装置14发送的数据来计算物体的测量数据，这均属于本公开的保护范围。
在物体测量装置15计算出物体的测量参数后，本公开另一些实施例还包括配置与测量参数相关联的虚拟对象，并显示在电子设备的AR测量应用的界面上。
例如，可以将测量参数以虚拟文本的形式显示在界面上，以便用户查看。
又例如，物体测量装置15可以将物体在深度感测装置13坐标系下的三维顶点坐标以及测量参数发送给AR平台16，AR平台16可以将物体在深度感测装置13坐标系下的三维顶点坐标转换为在AR平台16坐标系下的坐标，在AR测量应用17中，实现物体外接三维边框的渲染，并在界面上显示出该虚拟的三维边框。应当理解的是，在AR 测量中，该虚拟的三维边框始终外接于物体。
另外，物体的三维顶点坐标和/或测量参数可以存储在电子设备或云端，以便该电子设备下次在相同场景下运行AR测量应用17时可以直接获取这些信息，或者其他电子设备在相同场景下运行AR测量应用17时可以获取到这些信息。
图2示出了适于用来实现本公开示例性实施方式的电子设备的示意图。需要说明的是，图2示出的电子设备仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。
本公开的电子设备至少包括处理器和存储器，存储器用于存储一个或多个程序，当一个或多个程序被处理器执行时，使得处理器可以实现本公开示例性实施方式的物体测量方法或虚拟对象处理方法。
具体的，如图2所示，电子设备200可以包括：处理器210、内部存储器221、外部存储器接口222、通用串行总线(Universal Serial Bus，USB)接口230、充电管理模块240、电源管理模块241、电池242、天线1、天线2、移动通信模块250、无线通信模块260、音频模块270、扬声器271、受话器272、麦克风273、耳机接口274、传感器模块280、显示屏290、摄像模组291、指示器292、马达293、按键294以及用户标识模块(Subscriber Identification Module，SIM)卡接口295等。其中传感器模块280可以包括深度传感器、压力传感器、陀螺仪传感器、气压传感器、磁传感器、加速度传感器、距离传感器、接近光传感器、指纹传感器、温度传感器、触摸传感器、环境光传感器及骨传导传感器等。
可以理解的是，本申请实施例示意的结构并不构成对电子设备200的具体限定。在本申请另一些实施例中，电子设备200可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件、软件或软件和硬件的组合实现。
处理器210可以包括一个或多个处理单元，例如：处理器210可以包括应用处理器(Application Processor，AP)、调制解调处理器、图形处理器(Graphics Processing Unit，GPU)、图像信号处理器(Image Signal Processor，ISP)、控制器、视频编解码器、数字信号处理器(Digital Signal Processor，DSP)、基带处理器和/或神经网络处理器(Neural-etwork Processing Unit，NPU)等。其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个处理器中。另外，处理器210中还可以设置存储器，用于存储指令和数据。
USB接口230是符合USB标准规范的接口，具体可以是MiniUSB接口，MicroUSB接口，USBTypeC接口等。USB接口230可以用于连接充电器为电子设备200充电，也可以用于电子设备200与外围设备之间传输数据。也可以用于连接耳机，通过耳机播放音频。该接口还可以用于连接其他电子设备，例如AR设备等。
充电管理模块240用于从充电器接收充电输入。其中，充电器可以是无线充电器，也可以是有线充电器。电源管理模块241用于连接电池242、充电管理模块240与处理器210。电源管理模块241接收电池242和/或充电管理模块240的输入，为处理器210、内部存储器221、显示屏290、摄像模组291和无线通信模块260等供电。
电子设备200的无线通信功能可以通过天线1、天线2、移动通信模块250、无线通信模块260、调制解调处理器以及基带处理器等实现。
移动通信模块250可以提供应用在电子设备200上的包括2G/3G/4G/5G等无线通信的解决方案。
无线通信模块260可以提供应用在电子设备200上的包括无线局域网(Wireless Local Area Networks，WLAN)(如无线保真(Wireless Fidelity，Wi-Fi)网络)、蓝牙(Bluetooth，BT)、全球导航卫星系统(Global Navigation Satellite System，GNSS)、调频(Frequency Modulation，FM)、近距离无线通信技术(Near Field Communication，NFC)、红外技术(Infrared，IR)等无线通信的解决方案。
电子设备200通过GPU、显示屏290及应用处理器等实现显示功能。GPU为图像处理的微处理器，连接显示屏290和应用处理器。GPU用于执行数学和几何计算，用于图形渲染。处理器210可包括一个或多个GPU，其执行程序指令以生成或改变显示信息。
电子设备200可以通过ISP、摄像模组291、视频编解码器、GPU、显示屏290及应用处理器等实现拍摄功能。在一些实施例中，电子设备200可以包括1个或N个摄像模组291，N为大于1的正整数，若电子设备200包括N个摄像头，N个摄像头中有一个是主摄像头。
内部存储器221可以用于存储计算机可执行程序代码，所述可执行程序代码包括指令。内部存储器221可以包括存储程序区和存储数据区。外部存储器接口222可以用于连接外部存储卡，例如Micro SD卡，实现扩展电子设备200的存储能力。
电子设备200可以通过音频模块270、扬声器271、受话器272、麦克风273、耳机接口274及应用处理器等实现音频功能。例如音乐播放、录音等。
音频模块270用于将数字音频信息转换成模拟音频信号输出，也用于将模拟音频输入转换为数字音频信号。音频模块270还可以用于对音频信号编码和解码。在一些实施例中，音频模块270可以设置于处理器210中，或将音频模块270的部分功能模块设置于处理器210中。
扬声器271，也称“喇叭”，用于将音频电信号转换为声音信号。电子设备200可以通过扬声器271收听音乐，或收听免提通话。受话器272，也称“听筒”，用于将音频电信号转换成声音信号。当电子设备200接听电话或语音信息时，可以通过将受话器272靠近人耳接听语音。麦克风273，也称“话筒”，“传声器”，用于将声音信号转换为电信号。当拨打电话或发送语音信息时，用户可以通过人嘴靠近麦克风273发声，将声音信号输入到麦克风273。电子设备200可以设置至少一个麦克风273。耳机接口274用于连接有线耳机。
针对电子设备200中传感器模块280可以包括的传感器，深度传感器用于获取景物的深度信息。压力传感器用于感受压力信号，可以将压力信号转换成电信号。陀螺仪传感器可以用于确定电子设备200的运动姿态。气压传感器用于测量气压。磁传感器包括霍尔传感器。电子设备200可以利用磁传感器检测翻盖皮套的开合。加速度传感器可检测电子设备200在各个方向上(一般为三轴)加速度的大小。距离传感器用于测量距离。接近光传感器可以包括例如发光二极管(LED)和光检测器，例如光电二极管。指纹传感器用于采集指纹。温度传感器用于检测温度。触摸传感器可以将检测到的触摸操作传递给应用处理器，以确定触摸事件类型。可以通过显示屏290提供与触摸操作相关的视觉输出。环境光传感器用于感知环境光亮度。骨传导传感器可以获取振动信号。
按键294包括开机键，音量键等。按键294可以是机械按键。也可以是触摸式按键。马达293可以产生振动提示。马达293可以用于来电振动提示，也可以用于触摸振动反馈。指示器292可以是指示灯，可以用于指示充电状态，电量变化，也可以用于指示消息，未接来电，通知等。SIM卡接口295用于连接SIM卡。电子设备200通过SIM卡和网络交互，实现通话以及数据通信等功能。
本申请还提供了一种计算机可读存储介质，该计算机可读存储介质可以是上述实施例中描述的电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。
计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机可读存储介质可以是任何包含或存储程序的有形 介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读存储介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读存储介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等等，或者上述的任意合适的组合。
计算机可读存储介质承载有一个或者多个程序，当上述一个或者多个程序被一个该电子设备执行时，使得该电子设备实现如下述实施例中所述的方法。
附图中的流程图和框图，图示了按照本公开各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，上述模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图或流程图中的每个方框、以及框图或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现，所描述的单元也可以设置在处理器中。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定。
在下面的描述中，涉及到的RGB拍摄装置、深度感测装置和红外感测装置均是完成相机参数标定后的装置，本公开对标定的过程不做限制。另外，采集到的RGB图像、深度图像和红外图像的时间戳同步。
需要说明的是，本公开对场景中存在的物体的数量不做限制，均可以采用下述物体测量方案测量出各物体的测量参数。
图3示意性示出了本公开的示例性实施方式的物体测量方法的流程图。参考图3，该物体测量方法可以包括以下步骤：
S32.获取场景的深度图像，根据深度图像确定场景的点云数据。
本公开示例性实施方式所说的场景指代的是包含物体的真实场景，电子设备中配备的深度感测装置可以对场景进行感测，得到场景的深度图像。
在确定场景的点云数据的过程中，可以利用深度感测装置的相机参数进行计算，以得到与深度图像对应的点云数据。
首先，可以获取拍摄深度图像的深度感测装置的相机参数，该相机参数具体可以表示为：
Figure PCTCN2021086654-appb-000001
其中，f x和f y表示深度感测装置的摄像头焦距，u 0和v 0表示深度图像的中心坐标。本领域技术人员可以理解的是，f x、f y、u 0和v 0可以通过标定的方式计算出。
标定的过程可以在离线或在线的情况下完成，举例而言，可以采用线性标定方法(例如，Faugeras标定法等)、非线性优化标定方法(例如，Levenberg-Marquadt算法等)、两步标定法(例如，Tsai两步法、张正友标定算法等)或其他方法计算f x、f y、u 0和v 0，本示例性实施例中对此不做特殊限定。
以张正友标定算法为例，可以将画有棋盘格的图像作为标定图像放置于摄像头前方，由于需要计算出四个量，因此，当以不同角度和位置拍摄至少3幅图像时，即可利用张正友标定算法线性唯一求解出f x、f y、u 0和v 0。
也就是说，在本公开的示例性实施方式中，可以将上述至少3幅图像作为标定图像， 利用张正友标定算法对所述标定图像进行处理，自动计算出相机参数。
此外，标定图像还可以是除画有棋盘格的图像之外的其他图像，本示例性实施方式中对此不做特殊限定。
在确定出深度感测装置的相机参数后，可以利用该相机参数以及深度图像上各像素的深度信息，计算与深度信息对应的三维数据，作为场景的点云数据。具体可以采用下述公式进行计算：
Figure PCTCN2021086654-appb-000002
其中，u、v为深度图像上各像素的坐标点，Z c为相机坐标的z轴值，由于在深度感测装置自身参考坐标系下，因此，R为单位矩阵，T为0。在已知f x、f y、u 0、v 0以及u、v、Z W的情况下，即可求解出X W和Y W，最终得到X W、Y W、Z W，生成场景的三维点云数据。
S34.对点云数据进行平面分割处理，以确定场景中物体的表面信息。
在本公开的示例性实施方式中，可以采用随机抽样一致(random sample consensus，RANSAC)算法对点云数据进行平面分割。
例如，对点云数据进行随机采样，对采样的深度点进行平面拟合，检测拟合出的平面与深度点的相对关系，根据相对关系实现深度点的剔除与更新操作，以确定出场景中各平面信息，再结合物体的几何约束信息，得到物体的表面信息。
以规则物体为例，本公开所述的几何约束信息可以包括但不限于：平面之间或表面之间是相交的(即存在重叠的点云)，侧表面与放置面(地面或桌面)是相互垂直的，等等。
在一些实施例中，在对点云数据进行平面分割处理之前，可以对点云数据进行去噪处理，例如，可以采用不同类型的滤波器实现对去噪处理，本公开对此不做限制。
S36.结合物体的表面信息确定物体的三维顶点坐标。
根据本公开的一些实施例，在基于深度感测装置采集的深度图像完整且准确的情况下，可以直接利用基于平面分割而确定出的物体表面信息确定出物体的三维顶点坐标。例如，确定出场景中放置于地面上的长方体的上表面4个顶点坐标。再结合地面与上表面的距离，得到该长方体的高度信息，利用高度信息以及上表面的法向量，可以得到该长方体的下表面4个顶点坐标。即，确定出物体的三维顶点坐标。
然而，可能出现深度感测装置采集的深度图像不完整或精确性不高的问题，在这种情况下，根据本公开的另一些实施例，可以结合深度图像和红外图像来计算物体的三维顶点坐标。
首先，电子设备中配备的红外感测装置可以对场景进行感测，得到场景的红外图像，并提取红外图像中物体的角点信息。
另外，在提取红外图像中物体的角点信息之前，本公开一个实施例还可以对红外图像进行亮度均衡处理，以避免图像过暗或过亮的情况。例如，可以通过归一化处理、直方图均衡化等处理手段使红外图像的亮度分布均匀，并使红外图像各像素的平均亮度大于亮度阈值。
针对提取红外图像中物体的角点信息的过程，根据本公开的一个实施例，可以采用例如SUSAN角点检测算法来提取红外图像中物体的角点信息。例如，可以基于像素领域包含若干元素的近似圆形模板，对每个像素基于该模板领域的图像灰度计算角点响应函数的数值，如果大于阈值且为局部极大值，则确定该点为角点。
鉴于单纯角点的提取过程可能存在角点提取不全的问题，可以利用红外图像中直线 的关系来进一步确定出角点。
根据本公开的另一个实施例，一方面，可以对红外图像执行角点提取过程，将利用此过程得到角点确定为红外图像的第一角点信息。另一方面，可以对红外图像执行直线提取过程，得到红外图像的直线信息，具体的，可以采用Hough变换、HOG特征提取等方法从红外图像中提取出直线信息。随后，可以从得到的直线信息中确定直线间相交的点作为红外图像的第二角点信息。
针对红外图像的第一角点信息和第二角点信息，剔除冗余的角点信息，以确定出红外图像中物体的角点信息。
接下来，电子设备可以根据红外图像中物体的角点信息以及步骤S34确定出的物体的表面信息，确定物体的三维顶点坐标。
在得到红外图像中物体的角点信息后，可以利用该角点信息确定红外图像中物体的二维顶点坐标。为了进一步使此二维顶点坐标准确，可以利用深度信息以及物体的几何约束信息进行约束。具体的，可以根据物体的表面信息确定物体上平面点云的范围，将物体上平面点云的范围以及物体的几何约束信息作为约束条件，对确定出的角点进行限制，以确定出红外图像中物体的二维顶点坐标。
在得到红外图像中物体的二维顶点坐标后，可以利用红外图像中物体的二维顶点坐标和红外感测装置的相机相机参数计算出物体在红外感测装置的坐标系下的三维顶点坐标，具体计算所用公式与步骤S32中的公式类似，不再赘述。
利用物体在红外感测装置的坐标系下的三维顶点坐标以及物体的表面信息，可以确定物体的三维顶点坐标。
具体的，以深度传感器的相机光心坐标为起点，构建射向红外感测装置的坐标系下的三维顶点坐标的射线。由此，该射线与物体的表面信息对应的平面会存在交点，将该交点确定为物体在深度感测装置的坐标系下的三维顶点坐标，并将物体在深度感测装置的坐标系下的三维顶点坐标，确定为步骤S36中确定出的物体的三维顶点坐标。
本领域技术人员可以理解的是，深度感测装置与红外感测装置的相机坐标系相同。
S38.利用物体的三维顶点坐标计算物体的测量参数。
在本公开的示例性实施方式中，物体的测量参数包括物体的长度信息、宽度信息、高度信息、表面面积信息、体积信息中的一个或多个。
容易看出，在物体的三维顶点确定的情况下，上述测量参数即可用常规计算方法计算出，本公开对此过程不进行限定。
根据本公开的一些实施例，步骤S36确定出的三维顶点坐标包括物体上表面的三维顶点坐标。在这种情况下，可以利用上表面的三维顶点坐标计算出下表面的三维顶点坐标，再利用上、下表面的三维顶点坐标计算物体的测量参数。
针对计算物体下表面的三维顶点坐标的过程，首先，利用针对点云数据的平面分割处理结果，确定放置物体的平面(如地面或桌面)的平面信息；接下来，可以根据放置物体的平面的平面信息以及物体上表面的表面信息，计算物体的高度信息，也就是说，可以计算两个平面的距离，以得到物体的高度信息；随后，结合物体的高度信息、物体上表面的三维顶点坐标以及物体上表面的法向量，可以计算物体下表面的三维顶点坐标。
基于上述物体测量方法，一方面，本公开借助于场景深度信息自动测量物体，相比于深度学习的方案，本公开不需要收集大量物体的信息进行训练，且避免了对于没有预训练过的物体，测量结果不准确的问题，提高了物体测量的鲁棒性和适用范围；另一方面，在本公开的一些实施方式中，结合了红外图像，进一步提高了识别物体三维顶点坐标的准确性，使得计算出的测量参数更加准确。
进一步的，本公开还提供了一种利用上述物体测量方法实现虚拟对象生成并显示的方案。具体的，本公开还提供了一种虚拟对象处理方法，该虚拟对象处理方法应用于能够显 示虚拟对象的电子设备。
参考图4，本公开示例性实施方式的虚拟对象处理方法可以包括以下步骤：
S40.获取场景的深度图像，根据深度图像确定场景的点云数据；
S42.对点云数据进行平面分割处理，以确定场景中物体的表面信息；
S44.结合物体的表面信息确定物体的三维顶点坐标；
S46.利用物体的三维顶点坐标计算物体的测量参数；
S48.生成与物体的测量参数相关联的虚拟对象，以便在电子设备上显示出虚拟对象。
步骤S40至步骤S46与上述步骤S32至步骤S38的实现过程相同，在此不再赘述。
根据本公开的一些实施例，虚拟对象包括与物体对应的三维虚拟边框。在这种情况下，针对步骤S48中生成与物体的测量参数相关联的虚拟对象的过程，首先，可以获取物体的三维顶点坐标，并将物体的三维顶点坐标转换为增强现实平台坐标系下的三维坐标。
具体的，基于RGB拍摄装置所拍摄的RGB图像以及由IMU检测的惯性数据可以得到RGB图像位姿信息，其中，RGB图像的时间戳与在确定物体的三维顶点坐标时所用的深度图像的时间戳一致。
在获取到RGB拍摄装置的相机参数以及深度感测装置的相机参数的情况下，可以利用RGB拍摄装置的相机参数、深度感测装置的相机参数以及RGB图像的位姿信息，将物体的三维顶点坐标转换为RGB拍摄装置的坐标系下的三维坐标，并可以将此三维坐标确定为增强现实平台坐标系下的三维坐标。具体转换的过程仍涉及三维数据与二维数据的转换过程，具体参见步骤S32中的公式，在此不再赘述。
在确定出物体在增强现实平台坐标系下的三维坐标后，可以利用物体的几何约束，渲染生成与物体对应的三维虚拟边框。
在一个实施例中，当用户在电子设备的界面上进行与虚拟对象显示相关的操作(例如，点击物体、长按物体等)后，可以在界面上显示出该三维虚拟边框。
根据本公开的另一些实施例，虚拟对象可以是对测量参数进行转换后生成的虚拟文本。
需要说明的是，步骤S48中生成的虚拟对象的数量可以是一个或多个，例如，虚拟对象可以既包括三维虚拟边框又包括虚拟文本。
下面将参考图5对本公开一个实施例的AR测量过程进行说明。
在步骤S502中，可以获取由深度感测装置采集的场景的深度图像；在步骤S504中，基于深度感测装置的相机参数，可以利用深度图像生成点云数据；在步骤S506中，对点云数据进行平面分割处理，得到场景中物体的表面信息。
在步骤S508中，可以获取由红外感测装置采集的场景的红外图像；在步骤S510中，可以提取红外图像的角点信息和直线信息；在步骤S512中，可以基于提取到的角点信息和直线信息，确定红外图像中物体的二维顶点坐标。另外，在确定红外图像中物体的二维顶点坐标时，可以利用深度点云数据加以约束，使得确定出的顶点坐标更加准确。在步骤S514中，利用二维顶点坐标以及红外感测装置的相机参数，可以计算物体在红外感测装置坐标系下的三维顶点坐标。
在步骤S516中，可以利用基于由深度图像确定出的物体的表面信息以及红外感测装置坐标系下的三维顶点坐标，确定物体在深度感测装置坐标系下的三维顶点坐标。
在步骤S518中，可以利用物体的三维顶点坐标计算物体的测量参数。
在步骤S520中，可以生成与物体的测量参数相关联的虚拟对象并显示在电子设备的应用程序界面上。
图6示出了本公开一个实施例的执行AR测量后的显示效果的示意图。参考图6，桌子61上放置有一个长方体的箱子62，在电子设备60开启AR测量应用并执行上述虚拟对象处理方法后，在电子设备60的应用程序界面上可以显示出箱子62的三维边框63。另外，通过渲染操作，三维边框63可以被配置为各种颜色和样式。
可以理解的是，三维边框63以锚点的方式配置，无论用户观察视角如何变化，即无论电子设备60如何移动，三维边框63与箱子62的相对位置固定不变。
图7示出了本公开另一个实施例的执行AR测量后的显示效果的示意图。参考图7，桌子71上放置有一个长方体的箱子72，在电子设备70开启AR测量应用并执行上述虚拟对象处理方法后，在电子设备70的应用程序界面上可以显示出箱子72对应的测量参数的虚拟文本，如图所示，该虚拟文本例如为“物体体积：18cm 3”。另外，通过渲染操作，虚拟文本可以被配置为各种颜色和样式。
为了避免虚拟对象遮挡场景中可能存在的其他物体，在本公开的一些实施例中，电子设备还可以对物体周围的环境进行检测，如果检测出预设类型的对象，则避开这些对象进行虚拟对象的显示。其中，预设类型可以由用户自行设定，检测的过程可以采用深度学习的分类模型来实现，本公开对此不做限制。
此外，在显示上述虚拟对象之外，在电子设备判断出物体的测量参数满足预设要求时，可以在物体的周围配置另外的虚拟对象，已增加趣味性或实现AR游戏的配置。例如，在确定出物体的上表面面积大于面积阈值的情况下，可以在物体的上表面配置虚拟卡通人物，用户还可以利用界面上的控件控制该虚拟卡通人物进行行走、跳跃、招手等各种动作的展示。
基于上述虚拟对象处理方法，一方面，通过生成与物体的测量参数相关联的虚拟对象并显示，用户可以直观的了解到与物体测量参数相关的信息，整个过程自动进行，方便快捷，无需用户手动测量并记录测量结果；另一方面，通过虚拟对象的配置还可以增加了AR应用的趣味性。
应当注意，尽管在附图中以特定顺序描述了本公开中方法的各个步骤，但是，这并非要求或者暗示必须按照该特定顺序来执行这些步骤，或是必须执行全部所示的步骤才能实现期望的结果。附加的或备选的，可以省略某些步骤，将多个步骤合并为一个步骤执行，以及/或者将一个步骤分解为多个步骤执行等。
进一步的，本示例实施方式中还提供了一种物体测量装置。
图8示意性示出了本公开的示例性实施方式的物体测量装置的方框图。参考图8，根据本公开的示例性实施方式的物体测量装置8可以包括点云确定模块81、平面分割模块83、物体顶点确定模块85、参数计算模块87。
具体的，点云确定模块81可以被配置为获取场景的深度图像，根据所述深度图像确定所述场景的点云数据；平面分割模块83可以被配置为对所述点云数据进行平面分割处理，以确定所述场景中物体的表面信息；物体顶点确定模块85可以被配置为结合所述物体的表面信息确定所述物体的三维顶点坐标；参数计算模块87可以被配置为利用所述物体的三维顶点坐标计算所述物体的测量参数。
根据本公开的示例性实施例，物体顶点确定模块85可以被配置为执行：获取场景的红外图像，提取红外图像中物体的角点信息；根据红外图像中物体的角点信息以及物体的表面信息，确定物体的三维顶点坐标。
根据本公开的示例性实施例，物体顶点确定模块85提取红外图像中物体的角点信息的过程可以被配置为执行：对红外图像执行角点提取过程，得到红外图像的第一角点信息；对红外图像执行直线提取过程，得到红外图像的直线信息；利用红外图像的直线信息，确定红外图像的第二角点信息；结合红外图像的第一角点信息和第二角点信息，确定红外图像中物体的角点信息。
根据本公开的示例性实施例，物体顶点确定模块85根据红外图像中物体的角点信息以及物体的表面信息确定物体的三维顶点坐标的过程可以被配置为执行：结合红外图像中物体的角点信息确定红外图像中物体的二维顶点坐标；利用红外图像中物体的二维顶点坐标、拍摄红外图像的红外感测装置的相机参数以及物体的表面信息，确定物体的三 维顶点坐标。
根据本公开的示例性实施例，物体顶点确定模块85结合红外图像中物体的角点信息确定红外图像中物体的二维顶点坐标的过程可以被配置为执行：根据物体的表面信息，确定物体上平面点云的范围；利用红外图像中物体的角点信息、物体上平面点云的范围以及物体的几何约束信息，确定红外图像中物体的二维顶点坐标。
根据本公开的示例性实施例，物体顶点确定模块85确定物体的三维顶点坐标的过程可以被配置为执行：利用红外图像中物体的二维顶点坐标以及红外感测装置的相机参数，计算物体在红外感测装置的坐标系下的三维顶点坐标；以拍摄深度图像的深度感测装置的相机光心坐标为起点，构建射向红外感测装置的坐标系下的三维顶点坐标的射线；将射线与物体的表面信息对应平面的交点，确定为物体在深度感测装置的坐标系下的三维顶点坐标，并将物体在深度感测装置的坐标系下的三维顶点坐标确定为物体的三维顶点坐标；其中，深度感测装置与红外感测装置的相机坐标系相同。
根据本公开的示例性实施例，物体顶点确定模块85在提取红外图像中物体的角点信息之前，还可以被配置为执行：对红外图像进行亮度均衡处理。
根据本公开的示例性实施例，物体的三维顶点坐标包括物体上表面的三维顶点坐标；在这种情况下，参数计算模块87可以被配置为执行：利用针对点云数据的平面分割处理结果，确定放置物体的平面的平面信息；根据放置物体的平面的平面信息以及物体上表面的表面信息，计算物体的高度信息；结合物体的高度信息、物体上表面的三维顶点坐标以及物体上表面的法向量，计算物体下表面的三维顶点坐标；利用物体上表面的三维顶点坐标和物体下表面的三维顶点坐标，计算物体的测量参数。
根据本公开的示例性实施例，物体的测量参数包括物体的长度信息、宽度信息、高度信息、表面面积信息、体积信息中的一个或多个。
根据本公开的示例性实施例，点云确定模块81可以被配置为执行：获取拍摄深度图像的深度感测装置的相机参数；利用拍摄深度图像的深度感测装置的相机参数以及深度图像上各像素的深度信息，计算出与深度信息对应的三维数据，作为场景的点云数据。
由于本公开实施方式的物体测量装置的各个功能模块与上述方法实施方式中相同，因此在此不再赘述。
进一步的，本示例实施方式中还提供了一种虚拟对象处理装置，该虚拟对象处理装置应用于能够显示虚拟对象的电子设备。
图9示意性示出了本公开的示例性实施方式的虚拟对象处理装置的方框图。参考图9，根据本公开的示例性实施方式的虚拟对象处理装置9可以包括上述物体测量装置8和对象处理模块91。
其中，对物体测量装置8不再赘述。另外，对象处理模块91被配置为生成与物体的测量参数相关联的虚拟对象，以便在电子设备上显示出虚拟对象。
根据本公开的示例性实施例，虚拟对象包括与物体对应的三维虚拟边框；在这种情况下，对象处理模块91可以被配置为执行：获取物体的三维顶点坐标；将物体的三维顶点坐标转换为增强现实平台坐标系下的三维坐标；基于增强现实平台坐标系下的三维坐标，渲染生成与物体对应的三维虚拟边框。
根据本公开的示例性实施例，对象处理模块91将物体的三维顶点坐标转换为增强现实平台坐标系下的三维坐标的过程可以被配置为执行：获取RGB图像的位姿信息；其中，RGB图像的时间戳与在确定物体的三维顶点坐标时所用的深度图像的时间戳一致；获取拍摄RGB图像的RGB拍摄装置的相机参数，以及拍摄拍摄深度图像的深度感测装置的相机参数；利用RGB图像的位姿信息、RGB拍摄装置的相机参数和深度感测装置的相机参数，将物体的三维顶点坐标转换为RGB拍摄装置的坐标系下的三维坐标，以得到增强现实平台坐标系下的三维坐标。
由于本公开实施方式的虚拟对象处理装置的各个功能模块与上述方法实施方式中相同，因此在此不再赘述。
通过以上的实施方式的描述，本领域的技术人员易于理解，这里描述的示例实施方式可以通过软件实现，也可以通过软件结合必要的硬件的方式来实现。因此，根据本公开实施方式的技术方案可以以软件产品的形式体现出来，该软件产品可以存储在一个非易失性存储介质(可以是CD-ROM，U盘，移动硬盘等)中或网络上，包括若干指令以使得一台计算设备(可以是个人计算机、服务器、终端装置、或者网络设备等)执行根据本公开实施方式的方法。
此外，上述附图仅是根据本公开示例性实施例的方法所包括的处理的示意性说明，而不是限制目的。易于理解，上述附图所示的处理并不表明或限制这些处理的时间顺序。另外，也易于理解，这些处理可以是例如在多个模块中同步或异步执行的。
应当注意，尽管在上文详细描述中提及了用于动作执行的设备的若干模块或者单元，但是这种划分并非强制性的。实际上，根据本公开的实施方式，上文描述的两个或更多模块或者单元的特征和功能可以在一个模块或者单元中具体化。反之，上文描述的一个模块或者单元的特征和功能可以进一步划分为由多个模块或者单元来具体化。
本领域技术人员在考虑说明书及实践这里公开的内容后，将容易想到本公开的其他实施例。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。

Claims (20)

  1. 一种物体测量方法，包括：
    获取场景的深度图像，根据所述深度图像确定所述场景的点云数据；
    对所述点云数据进行平面分割处理，以确定所述场景中物体的表面信息；
    结合所述物体的表面信息确定所述物体的三维顶点坐标；
    利用所述物体的三维顶点坐标计算所述物体的测量参数。
  2. 根据权利要求1所述的物体测量方法，其中，结合所述物体的表面信息确定所述物体的三维顶点坐标包括：
    获取所述场景的红外图像，提取所述红外图像中所述物体的角点信息；
    根据所述红外图像中所述物体的角点信息以及所述物体的表面信息，确定所述物体的三维顶点坐标。
  3. 根据权利要求2所述的物体测量方法，其中，提取所述红外图像中所述物体的角点信息包括：
    对所述红外图像执行角点提取过程，得到所述红外图像的第一角点信息；
    对所述红外图像执行直线提取过程，得到所述红外图像的直线信息；
    利用所述红外图像的直线信息，确定所述红外图像的第二角点信息；
    结合所述红外图像的所述第一角点信息和所述第二角点信息，确定所述红外图像中所述物体的角点信息。
  4. 根据权利要求2所述的物体测量方法，其中，根据所述红外图像中所述物体的角点信息以及所述物体的表面信息，确定所述物体的三维顶点坐标，包括：
    结合所述红外图像中所述物体的角点信息确定所述红外图像中所述物体的二维顶点坐标；
    利用所述红外图像中所述物体的二维顶点坐标、拍摄所述红外图像的红外感测装置的相机参数以及所述物体的表面信息，确定所述物体的三维顶点坐标。
  5. 根据权利要求4所述的物体测量方法，其中，结合所述红外图像中所述物体的角点信息确定所述红外图像中所述物体的二维顶点坐标包括：
    根据所述物体的表面信息，确定所述物体上平面点云的范围；
    利用所述红外图像中所述物体的角点信息、所述物体上平面点云的范围以及所述物体的几何约束信息，确定所述红外图像中所述物体的二维顶点坐标。
  6. 根据权利要求4所述的物体测量方法，其中，利用所述红外图像中所述物体的二维顶点坐标、拍摄所述红外图像的红外感测装置的相机参数以及所述物体的表面信息，确定所述物体的三维顶点坐标，包括：
    利用所述红外图像中所述物体的二维顶点坐标以及所述红外感测装置的相机参数，计算所述物体在所述红外感测装置的坐标系下的三维顶点坐标；
    以拍摄所述深度图像的深度感测装置的相机光心坐标为起点，构建射向所述红外感测装置的坐标系下的三维顶点坐标的射线；
    将所述射线与所述物体的表面信息对应平面的交点，确定为所述物体在所述深度感测装置的坐标系下的三维顶点坐标，并将所述物体在所述深度感测装置的坐标系下的三维顶点坐标确定为所述物体的三维顶点坐标；
    其中，所述深度感测装置与所述红外感测装置的相机坐标系相同。
  7. 根据权利要求2所述的物体测量方法，其中，在提取所述红外图像中所述物体的角点信息之前，所述物体测量方法还包括：
    对所述红外图像进行亮度均衡处理。
  8. 根据权利要求1至7中任一项所述的物体测量方法，其中，所述物体的三维顶 点坐标包括所述物体上表面的三维顶点坐标；其中，利用所述物体的三维顶点坐标计算所述物体的测量参数包括：
    利用针对所述点云数据的平面分割处理结果，确定放置所述物体的平面的平面信息；
    根据放置所述物体的平面的平面信息以及所述物体上表面的表面信息，计算所述物体的高度信息；
    结合所述物体的高度信息、所述物体上表面的三维顶点坐标以及所述物体上表面的法向量，计算所述物体下表面的三维顶点坐标；
    利用所述物体上表面的三维顶点坐标和所述物体下表面的三维顶点坐标，计算所述物体的测量参数。
  9. 根据权利要求8所述的物体测量方法，其中，所述物体的测量参数包括所述物体的长度信息、宽度信息、高度信息、表面面积信息、体积信息中的一个或多个。
  10. 根据权利要求1所述的物体测量方法，其中，根据所述深度图像确定所述场景的点云数据包括：
    获取拍摄所述深度图像的深度感测装置的相机参数；
    利用拍摄所述深度图像的深度感测装置的相机参数以及所述深度图像上各像素的深度信息，计算出与所述深度信息对应的三维数据，作为所述场景的点云数据。
  11. 一种虚拟对象处理方法，应用于能够显示虚拟对象的电子设备，包括：
    利用权利要求1至10中任一项所述的物体测量方法，测量场景中物体的测量参数；
    生成与所述物体的测量参数相关联的虚拟对象，以便在所述电子设备上显示出所述虚拟对象。
  12. 根据权利要求11所述的虚拟对象处理方法，其中，所述虚拟对象包括与所述物体对应的三维虚拟边框；其中，生成与所述物体的测量参数相关联的虚拟对象包括：
    获取所述物体的三维顶点坐标；
    将所述物体的三维顶点坐标转换为增强现实平台坐标系下的三维坐标；
    基于所述增强现实平台坐标系下的三维坐标，渲染生成与所述物体对应的三维虚拟边框。
  13. 根据权利要求12所述的虚拟对象处理方法，其中，将所述物体的三维顶点坐标转换为增强现实平台坐标系下的三维坐标包括：
    获取RGB图像的位姿信息；其中，所述RGB图像的时间戳与在确定所述物体的三维顶点坐标时所用的深度图像的时间戳一致；
    获取拍摄所述RGB图像的RGB拍摄装置的相机参数，以及拍摄拍摄所述深度图像的深度感测装置的相机参数；
    利用所述RGB图像的位姿信息、所述RGB拍摄装置的相机参数和所述深度感测装置的相机参数，将所述物体的三维顶点坐标转换为所述RGB拍摄装置的坐标系下的三维坐标，以得到所述增强现实平台坐标系下的三维坐标。
  14. 一种物体测量装置，包括：
    点云确定模块，被配置为获取场景的深度图像，根据所述深度图像确定所述场景的点云数据；
    平面分割模块，被配置为对所述点云数据进行平面分割处理，以确定所述场景中物体的表面信息；
    物体顶点确定模块，被配置为结合所述物体的表面信息确定所述物体的三维顶点坐标；
    参数计算模块，被配置为利用所述物体的三维顶点坐标计算所述物体的测量参数。
  15. 根据权利要求14所述的物体测量装置，其中，所述物体顶点确定模块被配置为获取所述场景的红外图像，提取所述红外图像中所述物体的角点信息，并根据所述红 外图像中所述物体的角点信息以及所述物体的表面信息，确定所述物体的三维顶点坐标。
  16. 根据权利要求15所述的物体测量装置，其中，所述物体顶点确定模块提取所述红外图像中所述物体的角点信息的过程配置为：对所述红外图像执行角点提取过程，得到所述红外图像的第一角点信息；对所述红外图像执行直线提取过程，得到所述红外图像的直线信息；利用所述红外图像的直线信息，确定所述红外图像的第二角点信息；结合所述红外图像的所述第一角点信息和所述第二角点信息，确定所述红外图像中所述物体的角点信息。
  17. 一种虚拟对象处理装置，应用于能够显示虚拟对象的电子设备，包括：
    物体测量装置，被配置为利用权利要求1至10中任一项所述的物体测量方法，测量场景中物体的测量参数；
    对象处理模块，被配置为生成与所述物体的测量参数相关联的虚拟对象，以便在所述电子设备上显示出所述虚拟对象。
  18. 根据权利要求17所述的虚拟对象处理装置，其中，所述虚拟对象包括与所述物体对应的三维虚拟边框；所述对象处理模块被配置为：获取所述物体的三维顶点坐标；将所述物体的三维顶点坐标转换为增强现实平台坐标系下的三维坐标；基于所述增强现实平台坐标系下的三维坐标，渲染生成与所述物体对应的三维虚拟边框。
  19. 一种计算机可读存储介质，其上存储有计算机程序，所述程序被处理器执行时实现如权利要求1至10中任一项所述的物体测量方法或如权利要求11至13中任一项所述的虚拟对象处理方法。
  20. 一种电子设备，包括：
    处理器；
    存储器，被配置为存储一个或多个程序，当所述一个或多个程序被所述处理器执行时，使得所述处理器实现如权利要求1至10中任一项所述的物体测量方法或如权利要求11至13中任一项所述的虚拟对象处理方法。
PCT/CN2021/086654 2020-06-03 2021-04-12 物体测量、虚拟对象处理方法及装置、介质和电子设备 WO2021244140A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21818887.8A EP4160532A4 (en) 2020-06-03 2021-04-12 OBJECT MEASUREMENT METHOD AND APPARATUS, VIRTUAL OBJECT PROCESSING METHOD AND APPARATUS, ELECTRONIC MEDIUM AND DEVICE
US18/061,411 US20230113647A1 (en) 2020-06-03 2022-12-02 Object measurement method, virtual object processing method, and electronic device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010495293.0 2020-06-03
CN202010495293.0A CN111784765B (zh) 2020-06-03 2020-06-03 物体测量、虚拟对象处理方法及装置、介质和电子设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/061,411 Continuation US20230113647A1 (en) 2020-06-03 2022-12-02 Object measurement method, virtual object processing method, and electronic device

Publications (1)

Publication Number Publication Date
WO2021244140A1 true WO2021244140A1 (zh) 2021-12-09

Family

ID=72753703

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/086654 WO2021244140A1 (zh) 2020-06-03 2021-04-12 物体测量、虚拟对象处理方法及装置、介质和电子设备

Country Status (4)

Country Link
US (1) US20230113647A1 (zh)
EP (1) EP4160532A4 (zh)
CN (1) CN111784765B (zh)
WO (1) WO2021244140A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111784765B (zh) * 2020-06-03 2024-04-26 Oppo广东移动通信有限公司 物体测量、虚拟对象处理方法及装置、介质和电子设备
CN112484678B (zh) * 2020-10-29 2022-03-11 贝壳找房(北京)科技有限公司 一种基于虚拟三维空间的精准测量方法及装置
CN112414396A (zh) * 2020-11-05 2021-02-26 山东产研信息与人工智能融合研究院有限公司 现实场景中物体模位置测量方法、装置、存储介质及设备
CN112270702A (zh) * 2020-11-12 2021-01-26 Oppo广东移动通信有限公司 体积测量方法及装置、计算机可读介质和电子设备
CN113240789B (zh) 2021-04-13 2023-05-23 青岛小鸟看看科技有限公司 虚拟对象构建方法及装置
CN116243795B (zh) * 2023-02-20 2024-06-21 南方科技大学 基于混合现实的物品抓取方法及混合现实设备
CN117274525B (zh) * 2023-11-21 2024-03-29 江西格如灵科技股份有限公司 一种虚拟卷尺测量仿真方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106813568A (zh) * 2015-11-27 2017-06-09 阿里巴巴集团控股有限公司 物体测量方法及装置
US20190130636A1 (en) * 2011-03-04 2019-05-02 General Electric Company Method and device for displaying a two-dimensional image of a viewed object simultaneously with an image depicting the three-dimensional geometry of the viewed object
CN109916301A (zh) * 2019-03-27 2019-06-21 青岛小鸟看看科技有限公司 一种体积测量方法和深度相机模组
CN110006340A (zh) * 2019-03-26 2019-07-12 华为技术有限公司 一种物体尺寸测量方法和电子设备
CN111784765A (zh) * 2020-06-03 2020-10-16 Oppo广东移动通信有限公司 物体测量、虚拟对象处理方法及装置、介质和电子设备

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2835830A1 (en) * 2011-05-11 2012-11-15 Proiam, Llc Enrollment apparatus, system, and method featuring three dimensional camera
US20140104413A1 (en) * 2012-10-16 2014-04-17 Hand Held Products, Inc. Integrated dimensioning and weighing system
US10089750B2 (en) * 2017-02-02 2018-10-02 Intel Corporation Method and system of automatic object dimension measurement by using image processing
CN108416804A (zh) * 2018-02-11 2018-08-17 深圳市优博讯科技股份有限公司 获取目标物体体积的方法、装置、终端设备及存储介质
CN108648230A (zh) * 2018-05-14 2018-10-12 南京阿凡达机器人科技有限公司 一种包裹尺寸测量方法、系统、储存介质及移动终端
CN109029253B (zh) * 2018-06-29 2020-08-25 南京阿凡达机器人科技有限公司 一种包裹体积测量方法、系统、储存介质及移动终端

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190130636A1 (en) * 2011-03-04 2019-05-02 General Electric Company Method and device for displaying a two-dimensional image of a viewed object simultaneously with an image depicting the three-dimensional geometry of the viewed object
CN106813568A (zh) * 2015-11-27 2017-06-09 阿里巴巴集团控股有限公司 物体测量方法及装置
CN110006340A (zh) * 2019-03-26 2019-07-12 华为技术有限公司 一种物体尺寸测量方法和电子设备
CN109916301A (zh) * 2019-03-27 2019-06-21 青岛小鸟看看科技有限公司 一种体积测量方法和深度相机模组
CN111784765A (zh) * 2020-06-03 2020-10-16 Oppo广东移动通信有限公司 物体测量、虚拟对象处理方法及装置、介质和电子设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4160532A4 *

Also Published As

Publication number Publication date
EP4160532A4 (en) 2023-12-06
CN111784765B (zh) 2024-04-26
EP4160532A1 (en) 2023-04-05
CN111784765A (zh) 2020-10-16
US20230113647A1 (en) 2023-04-13

Similar Documents

Publication Publication Date Title
WO2021244140A1 (zh) 物体测量、虚拟对象处理方法及装置、介质和电子设备
CN108682038B (zh) 位姿确定方法、装置及存储介质
CN108537845B (zh) 位姿确定方法、装置及存储介质
CN110555883B (zh) 相机姿态追踪过程的重定位方法、装置及存储介质
CN108682036B (zh) 位姿确定方法、装置及存储介质
CN111325842B (zh) 地图构建方法、重定位方法及装置、存储介质和电子设备
US12020385B2 (en) Augmented reality processing method, storage medium, and electronic device
CN109947886B (zh) 图像处理方法、装置、电子设备及存储介质
CN112270754B (zh) 局部网格地图构建方法及装置、可读介质和电子设备
CN110647865A (zh) 人脸姿态的识别方法、装置、设备及存储介质
WO2020221012A1 (zh) 图像特征点的运动信息确定方法、任务执行方法和设备
CN111445583B (zh) 增强现实处理方法及装置、存储介质和电子设备
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
CN112581358B (zh) 图像处理模型的训练方法、图像处理方法及装置
CN112270702A (zh) 体积测量方法及装置、计算机可读介质和电子设备
CN111338474A (zh) 虚拟对象位姿校准方法及装置、存储介质和电子设备
CN110991445B (zh) 竖排文字识别方法、装置、设备及介质
WO2019000464A1 (zh) 一种图像显示方法、装置、存储介质和终端
CN112235650A (zh) 视频处理方法、装置、终端及存储介质
CN111982293B (zh) 体温测量方法、装置、电子设备及存储介质
CN116137025A (zh) 视频图像矫正方法及装置、计算机可读介质和电子设备
CN114093020A (zh) 动作捕捉方法、装置、电子设备及存储介质
CN113033590A (zh) 图像特征匹配方法、装置、图像处理设备及存储介质
CN113689484B (zh) 深度信息的确定方法、装置、终端及存储介质
CN118135255A (zh) 图像匹配模型的训练方法、图像匹配的方法及计算机设备

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: 21818887

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: 2021818887

Country of ref document: EP

Effective date: 20221229