WO2021077721A1 - Procédé, appareil et système pour reconstruire un modèle tridimensionnel d'un corps humain, et support de stockage lisible - Google Patents

Procédé, appareil et système pour reconstruire un modèle tridimensionnel d'un corps humain, et support de stockage lisible Download PDF

Info

Publication number
WO2021077721A1
WO2021077721A1 PCT/CN2020/089885 CN2020089885W WO2021077721A1 WO 2021077721 A1 WO2021077721 A1 WO 2021077721A1 CN 2020089885 W CN2020089885 W CN 2020089885W WO 2021077721 A1 WO2021077721 A1 WO 2021077721A1
Authority
WO
WIPO (PCT)
Prior art keywords
image sequence
human body
depth
server
depth image
Prior art date
Application number
PCT/CN2020/089885
Other languages
English (en)
Chinese (zh)
Inventor
张吉
张遥
李竹
王琳
Original Assignee
深圳奥比中光科技有限公司
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 深圳奥比中光科技有限公司 filed Critical 深圳奥比中光科技有限公司
Publication of WO2021077721A1 publication Critical patent/WO2021077721A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/55—Depth or shape recovery from multiple images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/521—Depth or shape recovery from laser ranging, e.g. using interferometry; from the projection of structured light
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
    • H04N19/597—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding specially adapted for multi-view video sequence encoding
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person

Definitions

  • This application relates to the field of computer vision technology, and in particular to a method, device, system and readable storage medium for reconstructing a three-dimensional human body model.
  • Three-dimensional reconstruction is the future core basic technology for the development of computer vision.
  • the current development and application is aimed at groups with specific shapes and characteristics, such as the human body, in film and television entertainment and life applications.
  • the embodiments of the present application provide a method, device, system, and readable storage medium for reconstructing a three-dimensional human body model, and provide an efficient solution for reconstructing a three-dimensional human body model.
  • an embodiment of the present application provides a method for reconstructing a three-dimensional human body model, including:
  • the depth camera converts the infrared image sequence Disparity image sequence or depth image sequence, so that the server does not need to directly process the infrared image sequence, reduces the amount of data calculation of the server, reduces the system resource occupation, and greatly improves the efficiency of human body 3D model reconstruction; on the other hand, the depth camera will By uploading the compressed data after compression and encoding to the server, the data transmission efficiency is improved, and the efficiency of the reconstruction of the three-dimensional human body model is further improved.
  • an apparatus for reconstructing a three-dimensional human body model including:
  • the image acquisition unit is used to acquire multiple frames of infrared image sequences including various parts of the human body;
  • An image processing unit configured to process the infrared image sequence to obtain a corresponding parallax image sequence or depth image sequence
  • a compression coding unit configured to perform compression coding on the disparity image sequence and the first parameter, or perform compression coding on the depth image sequence and the second parameter;
  • the data uploading unit is configured to upload compressed data that has been compressed and encoded to a server, and the compressed data is used to instruct the server to decompress and decode the received compressed data to reconstruct a real three-dimensional human body model.
  • an embodiment of the present application provides a depth camera, including a memory, a processor, and a computer program stored in the memory and running on the processor.
  • the processor executes the computer program, Implement the method as described in the first aspect.
  • an embodiment of the present application provides a depth camera, including the device as described in the second aspect.
  • an embodiment of the present application provides a system for reconstructing a three-dimensional human body model, including a server, and the depth camera according to the third aspect or the fourth aspect, and the server is configured to compare the received compressed data After decompression and decoding, a real three-dimensional model of the human body is reconstructed.
  • an embodiment of the present application provides a computer-readable storage medium that stores a computer program that implements the method described in the first aspect when the computer program is executed by a processor.
  • embodiments of the present application provide a computer program product, which when the computer program product runs on an electronic device, causes the electronic device to execute the method described in the first aspect.
  • Fig. 1 is a schematic diagram of a system for reconstructing a three-dimensional human body model provided by an embodiment of the present application
  • FIG. 2 is a schematic diagram of a distribution network of a system for reconstructing a three-dimensional human body model provided by an embodiment of the present application;
  • FIG. 3 is a schematic structural diagram of an apparatus for reconstructing a three-dimensional human body model provided by an embodiment of the present application
  • FIG. 4 is a schematic structural diagram of an apparatus for reconstructing a three-dimensional human body model provided by an embodiment of the present application
  • Fig. 5 is a schematic structural diagram of an apparatus for reconstructing a three-dimensional human body model provided by an embodiment of the present application
  • Fig. 6 is a schematic structural diagram of an apparatus for reconstructing a three-dimensional human body model provided by an embodiment of the present application
  • FIG. 7 is a schematic structural diagram of an apparatus for reconstructing a three-dimensional human body model provided by an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of an apparatus for reconstructing a three-dimensional human body model provided by an embodiment of the present application.
  • FIG. 1 shows a system for reconstructing a three-dimensional human body model provided by the present application, including a depth camera 101 connected in two-to-two communication, a client (mobile phone shown in FIG. 1) 102, and a server 103.
  • the measurement principle of the system is: the client 102 initiates a measurement instruction to the depth camera 101, and after receiving the measurement instruction, the depth camera 101 takes a picture of the human body to collect multiple frames of parallax image sequences or depth image sequences including various parts of the human body and upload them To the server 103, the server 103 performs real three-dimensional (3D) reconstruction of the human body according to the received parallax image sequence or depth image sequence, and selects key parts on the 3D model for measurement, so as to obtain the corresponding data of the measured human body. After the measurement is completed, The final three-dimensional data is transmitted to the client 102 that initiated the measurement instruction.
  • 3D three-dimensional
  • FIG. 2 is an implementation diagram of the distribution network process in one of the embodiments of this application.
  • the specific process is as follows: the client 102 starts the network configuration and searches for connectable Bluetooth devices. When it finds the Deepin Camera 101, it connects to it with Bluetooth. After the connection is successful, the Deepin Camera 101 will scan the nearby WiFi QR code and generate it. The WiFi list is transmitted to the client 102 through a Bluetooth unit (not shown). The client 102 selects a WiFi and enters the WiFi password. If the connection is successful, the network configuration is completed.
  • the Deepin Camera can use its WiFi unit (not shown) ) Access the server 103.
  • WiFi unit not shown
  • FIG. 2 the WiFi distribution network is taken as an example for description, and the basis is only an exemplary description, and cannot be construed as a specific limitation to the present application.
  • the depth camera may be a depth camera based on structured light, binocular, and time of flight (TOF) technology.
  • the depth camera may also be a depth camera including a color camera module, such as a depth camera including an RGB camera module. In this way, both depth images containing depth information and color images containing rich texture information can be obtained.
  • the client may also be a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR)/virtual reality (VR) device, a notebook computer, a super mobile personal computer (
  • AR augmented reality
  • VR virtual reality
  • UMPC ultra-mobile personal computer
  • PDA personal digital assistant
  • the server may also be an independent server, a server cluster, or a distributed server, etc.
  • the embodiments of the present application do not impose any restriction on the specific type of the server.
  • FIG. 3 shows an implementation flowchart of a method for reconstructing a three-dimensional human body model provided by an embodiment of the present application.
  • the method includes steps S110 to S130. This method is suitable for situations where the human body needs to be reconstructed in three dimensions. This method can be applied to the depth camera shown in Figure 1.
  • the specific implementation principle of each step is as follows.
  • S110 Collect multiple frames of infrared image sequences including various parts of the human body.
  • the depth camera collects infrared images of the human body from different angles to form an infrared image sequence including various parts of the human body.
  • the image acquisition unit of the depth camera 101 includes a binocular IR camera module, wherein the baseline distance of the left and right IR cameras is 150 mm.
  • the depth camera 101 When taking pictures of the human body, place the depth camera 101 vertically and stick it on a vertical wall, about 0.8m to 1.2m from the ground. The subject keeps standing at a preset posture, distance and position and at a preset angle Rotate, for example, the subject’s hands hang down at a certain angle in A-pose, and rotate at a distance of 1m to 2m from the depth camera.
  • the depth camera uses the image acquisition unit to continuously take pictures to obtain multiple frames (eg 300 frames) Sequence of infrared images from different angles.
  • the image acquisition unit further includes a color camera module (not shown in FIG. 1), such as an RGB camera module.
  • a color camera module such as an RGB camera module.
  • the image acquisition unit further includes a laser projection module (not shown in Figure 1).
  • the laser projection module emits a laser with a wavelength of 825 nm.
  • the image acquisition unit collects infrared speckles. image. Therefore, when the laser projection module is in the working state, it should also detect whether there is an object within the dangerous distance range. Once an object intrusion is detected, the laser projection module should be turned off.
  • the depth camera further includes a distance measurement unit. Specifically, when the image acquisition unit is turned on, the distance measurement unit is simultaneously turned on, and when an object is detected within 1 m, the laser module is turned off.
  • the distance measuring unit may be a distance sensor or a proximity sensor or the like.
  • a photo-diode can be placed near the DOE, for example, it can be placed obliquely 45 degrees above the top angle of the DOE to detect the amount of light (luminous intensity), where the amount of light is equal to that of the PD.
  • the voltage across the PD is proportional. When the voltage across the PD exceeds the threshold, it is judged that the DOE is destroyed, and the laser projection module needs to be turned off at this time.
  • S120 Process the infrared image sequence to obtain a corresponding parallax image sequence or depth image sequence.
  • the depth camera processes the infrared image sequence to obtain the corresponding parallax image sequence or depth image sequence.
  • the image processing unit of the depth camera processes the infrared image sequence to obtain the corresponding parallax image sequence or depth image sequence.
  • the image processing unit includes a parallax image acquisition unit and a depth image acquisition unit.
  • the parallax image acquisition unit is used to process the above-mentioned infrared image sequence to obtain the parallax image sequence, for example, the deviation of the spatial point in the two infrared images can be calculated according to the stereo matching algorithm to obtain a series of parallax images, or to calculate the reference speckle The deviation between the image and the acquired infrared speckle image to obtain a series of parallax images.
  • the depth image acquiring unit is configured to process the disparity image sequence to acquire the depth image sequence, for example, the disparity image sequence may be further converted into a depth image sequence according to the mapping relationship between the disparity and the depth.
  • the depth camera judges that the human body is in a preset posture and distance according to the parallax image sequence or the depth image sequence. If it is determined that the human body is in a preset posture and distance according to the parallax image sequence or the depth image sequence, the parallax image sequence or the depth image sequence is sent to the server, and the server performs the reconstruction of the human body 3D model according to the parallax image sequence or the depth image sequence sent by the depth camera.
  • the depth camera includes a position detection unit and a data upload unit.
  • the pose detection unit judges whether the human body is in a preset posture and distance based on the first frame or the first few depth images, so that when the human body is in the preset posture and distance, the data upload unit will
  • the parallax image sequence or the depth image sequence is sent to a server, and the server receives the parallax image sequence or the depth image sent by a depth camera to reconstruct a three-dimensional human body model.
  • the position detection unit mainly detects whether the following two conditions meet the requirements: 1) Whether the human body is in the central area of the depth image and occupies more than 80% of the screen; 2) Whether the human body is hanging down at a certain angle with both hands Standing in a posture.
  • the position detection unit can use the image segmentation algorithm to segment the target area (including the area of the human body) and the background area, and calculate the distance between the center of the target area and the geometric center of the depth image, when the distance is less than the preset value , It is judged that the human body is in the central area of the depth image, and at the same time, the proportion value of the target area in the entire depth image is calculated, and it is judged whether it is greater than 80%; for condition 2), the position detection unit can process the first frame or Perform key point detection (including but not limited to head, waist, hand, elbow, shoulder joint points and soles of feet, etc.) in the first few frames of depth images to extract human bone data and calculate the angle between the arm and the torso. Within a preset range, for example, 15 to 30 degrees, condition 2) is satisfied. When the above two conditions are met, it can be determined that the human body is in the preset posture and distance. At this time, the image acquisition unit can continue to image the human body.
  • key point detection including but not limited
  • the depth camera further includes a reminder unit.
  • the reminder unit sends out an adjustment reminder to adjust the posture and distance of the human body until it continues to collect data.
  • the sequence of parallax images or the sequence of depth images determines that the human body is in a preset posture and distance.
  • the reminder unit when the human body is not in the preset posture and distance, the reminder unit will issue a related reminder according to the current posture and/or distance of the human body, for example, a broadcast: "Please step forward/back/left/right” Or "open your arms and keep your posture", the subjects can perform corresponding operations according to the broadcast content.
  • a broadcast "Please step forward/back/left/right” Or "open your arms and keep your posture"
  • the subjects can perform corresponding operations according to the broadcast content.
  • the reminding unit when the distance between the standing position of the human body and the depth camera (or laser projection module) is within the dangerous distance range, the reminding unit will remind the subject to move backward through a broadcast.
  • the image acquisition unit will continuously collect infrared images of the subject to judge the rationality of the current subject’s standing position.
  • the reminding unit may be a speaker.
  • the parallax image sequence is determined according to the parallax image sequence or depth image sequence when the human body is in a preset posture and distance.
  • the depth image sequence is sent to the server for human body 3D model reconstruction.
  • the depth camera converts the infrared image sequence into a parallax image sequence or a depth image sequence, so that the server does not need to directly process the infrared image sequence, reducing the amount of data calculation on the server. The system resource occupation is reduced, and the efficiency of human body 3D model reconstruction is greatly improved.
  • the depth camera sends the parallax image sequence or depth image sequence that determines that the human body is in the preset posture and distance to the server for human body 3D model reconstruction.
  • the accuracy and completeness of data collection are improved, and the accuracy of the reconstruction of the three-dimensional model of the human body is further improved.
  • the method further includes: performing multi-distance calibration on the depth data in the depth image sequence.
  • the depth camera further includes a multi-distance calibration unit, which is used to perform multi-distance calibration on the depth data in the depth image sequence to reduce the systematic error of the measurement.
  • the depth camera in addition to the multi-distance calibration unit, also includes a valid frame detection unit.
  • the valid frame detection unit is used to screen the calibrated depth image sequence to remove redundant frames and further reduce The amount of data for subsequent 3D reconstruction.
  • the method further includes: masking the selected depth image sequence Process to obtain a sequence of deep human mask images.
  • the depth camera further includes a depth human body mask image acquisition unit for performing mask processing on the above-mentioned filtered depth image sequence to acquire a depth human body mask image sequence.
  • a pre-made sensory image sequence may be used.
  • the interest region mask is multiplied by the above-mentioned depth image sequence to remove the background area to obtain the depth human body mask image sequence.
  • the method further includes: calculating the depth human body mask image sequence to obtain the parallax human body mask image sequence.
  • the above-mentioned depth camera further includes a parallax human body mask image acquisition unit, configured to calculate the above-mentioned depth human body mask image to obtain a parallax human body mask image sequence.
  • a parallax human body mask image acquisition unit configured to calculate the above-mentioned depth human body mask image to obtain a parallax human body mask image sequence.
  • the method further includes: calculating the screened depth image sequence to obtain skeleton information of the human body.
  • the depth camera further includes a skeleton acquisition unit for calculating the above-mentioned filtered depth image sequence to obtain human body skeleton information, which is mainly used for subsequent three-dimensional reconstruction.
  • the depth camera may upload the acquired data to the server through compression coding.
  • the depth camera also includes a compression encoding unit for compressing and encoding the depth human mask image sequence, the second parameters (including the internal parameters of the depth camera), and the human skeleton information, and compressing them to 10% of the original data size.
  • % Is then uploaded to the server through the data upload unit, which shortens the data transmission time, thereby further improving the efficiency of the three-dimensional human body model. It should be noted that uploading the depth image data does not need to upload multiple parameters at the same time.
  • the system design is relatively simple, but the dynamic range is relatively large, and the adjacent pixels change greatly at a long distance, which is not conducive to compression coding.
  • the compression encoding unit compresses and encodes the parallax human body mask image sequence, the first parameters (including the internal parameters of the depth camera, the parallax conversion depth parameter, and the multi-distance calibration parameter), and the human skeleton information, and It is compressed to 10% of the original data size and then uploaded to the server through the data upload unit.
  • the dynamic range of parallax image data is relatively small (each pixel can be expressed in 12bit or less), the change between neighboring pixels is small, and lower bit rates can be obtained, but multi-distance calibration needs to be uploaded Parameters and other additional parameters.
  • the server When the depth camera uploads the acquired data to the server through compression and encoding, the server first decodes and decompresses the received compressed data to obtain the parallax human body mask image sequence, the first parameter, and the human body skeleton information; or the deep human body
  • the mask image sequence, the second parameter, and the human body skeleton information are used to perform three-dimensional reconstruction of the human body through the data obtained after the above-mentioned decoding and decompression.
  • the server includes a decoding and decompression unit and a three-dimensional reconstruction unit.
  • the server receives the compressed data
  • the received compressed and encoded data is decoded and decompressed by the decoding and decompression unit to obtain the parallax human body mask image sequence, the first parameters, and the human body skeleton information; or the depth human body mask image sequence,
  • the second parameter and the human skeleton information, and the data obtained after the above-mentioned decoding and decompression are subjected to the three-dimensional reconstruction of the human body by the three-dimensional reconstruction unit.
  • the server when the server receives a parallax human mask image sequence, it also needs to convert the parallax human mask image sequence into a depth human mask image sequence according to the parallax conversion depth parameter, and then according to the depth camera internal parameters and multi-distance
  • the calibration parameters correct the depth data in the depth human body mask image sequence to reduce the system measurement error.
  • the server further includes a data measuring unit, which is used to measure the dimensions of the required body part and push the measurement result to the client.
  • the measurement locations include, but are not limited to: chest circumference, waist circumference, hip circumference, upper arm circumference, lower arm circumference, thigh circumference, calf circumference, and the like.
  • FIG. 4 shows a structural block diagram of a device for reconstructing a three-dimensional human body model provided by an embodiment of the present application, and the device for reconstructing a three-dimensional human body model is configured in a depth camera.
  • the device for reconstructing a three-dimensional human body model is configured in a depth camera.
  • the device includes:
  • the image acquisition unit 41 is used to acquire multiple frames of infrared image sequences including various parts of the human body;
  • the image processing unit 42 is configured to process the infrared image sequence to obtain a corresponding parallax image sequence or depth image sequence;
  • the data uploading unit 43 is configured to send the parallax image sequence or the depth image sequence to the server if it is determined that the human body is at a preset posture and distance according to the parallax image sequence or the depth image sequence.
  • the image sequence or the depth image sequence is used to instruct the server to reconstruct a three-dimensional model of a real human body.
  • the device further includes:
  • the position detection unit 44 is configured to determine whether the human body is in a preset posture and distance according to the parallax image sequence or the depth image sequence;
  • the reminding unit 45 is configured to send an adjustment reminder if it is determined according to the parallax image sequence or the depth image sequence that the human body is not in the preset posture and distance, until according to the continuously collected parallax image sequence or the depth The image sequence determines that the human body is in a preset posture and distance.
  • the device further includes:
  • the multi-distance calibration unit 46 is configured to perform multi-distance calibration on the depth data in the depth image sequence.
  • the device further includes:
  • the multi-distance calibration unit 46 is configured to perform multi-distance calibration on the depth data in the depth image sequence
  • the effective frame detection unit 47 is configured to screen the calibrated depth image sequence to obtain the screened depth image sequence.
  • the device further includes:
  • the skeleton obtaining unit 48 is configured to calculate the depth image sequence after screening to obtain skeleton information of the human body.
  • the depth human body mask image sequence acquiring unit 49 is configured to perform mask processing on the screened depth image sequence to acquire the depth human body mask image sequence.
  • the parallax human body mask image sequence acquiring unit 50 is configured to calculate the depth human body mask image sequence to obtain the parallax human body mask image sequence.
  • the compression encoding unit 51 is used for compressing and encoding the deep human body mask image sequence, the second parameter, and the human body skeleton information; or for compressing and encoding the parallax human body mask image sequence, the first parameter, and the human body skeleton information, Get compressed coded data.
  • the data uploading unit 43 is configured to upload the compressed coded data to the server, and the compressed coded data is used to instruct the server to reconstruct the three-dimensional model of the human body.
  • the embodiments of the present application also provide a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in each of the foregoing method embodiments can be realized.
  • the embodiments of the present application provide a computer program product.
  • the computer program product runs on an electronic device, the electronic device can realize the steps in the foregoing method embodiments when the electronic device is executed.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the computer program can be stored in a computer-readable storage medium. When executed by the processor, the steps of the foregoing method embodiments can be implemented.
  • the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file, or some intermediate forms.
  • the computer-readable medium may at least include: any entity or device capable of carrying computer program code to the photographing device/terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (Random Access Memory, RAM), electric carrier signal, telecommunications signal, and software distribution medium.
  • ROM read-only memory
  • RAM random access memory
  • electric carrier signal telecommunications signal
  • software distribution medium Such as U disk, mobile hard disk, floppy disk or CD-ROM, etc.
  • computer-readable media cannot be electrical carrier signals and telecommunication signals.
  • the disclosed apparatus/network equipment and method may be implemented in other ways.
  • the device/network device embodiments described above are only illustrative.
  • the division of the modules or units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units.
  • components can be combined or integrated into another system, or some features can be omitted or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Optics & Photonics (AREA)
  • Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
  • Image Processing (AREA)

Abstract

La présente invention peut s'appliquer au domaine technique de la vision artificielle. L'invention concerne un procédé de reconstruction d'un modèle tridimensionnel d'un corps humain, lequel procédé est appliqué à une caméra de profondeur. Le procédé comprend : la collecte d'une séquence de multiples trames d'images infrarouges qui comprennent diverses parties d'un corps humain ; le traitement de la séquence d'images infrarouges pour acquérir une séquence d'images de parallaxe correspondante ou une séquence d'images de profondeur ; la compression et le codage de la séquence d'images de parallaxe et d'un premier paramètre, ou la compression et le codage de la séquence d'images de profondeur et d'un second paramètre ; et le téléversement des données compressées qui ont été compressées et codées à un serveur, les données compressées étant utilisées pour ordonner au serveur de décompresser et de décoder les données compressées reçues, puis de reconstruire un modèle tridimensionnel réel d'un corps humain réel. Au moyen de la présente invention, la reconstruction efficace d'un modèle tridimensionnel d'un corps humain est réalisée.
PCT/CN2020/089885 2019-10-25 2020-05-12 Procédé, appareil et système pour reconstruire un modèle tridimensionnel d'un corps humain, et support de stockage lisible WO2021077721A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201911025195.4A CN110874851A (zh) 2019-10-25 2019-10-25 重建人体三维模型的方法、装置、系统和可读存储介质
CN201911025195.4 2019-10-25

Publications (1)

Publication Number Publication Date
WO2021077721A1 true WO2021077721A1 (fr) 2021-04-29

Family

ID=69717909

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/089885 WO2021077721A1 (fr) 2019-10-25 2020-05-12 Procédé, appareil et système pour reconstruire un modèle tridimensionnel d'un corps humain, et support de stockage lisible

Country Status (2)

Country Link
CN (1) CN110874851A (fr)
WO (1) WO2021077721A1 (fr)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110874851A (zh) * 2019-10-25 2020-03-10 深圳奥比中光科技有限公司 重建人体三维模型的方法、装置、系统和可读存储介质
CN113192185B (zh) * 2021-05-18 2022-05-17 清华大学 一种动态光场重建方法、装置及设备
CN113727105B (zh) * 2021-09-08 2022-04-26 北京医百科技有限公司 一种深度图压缩方法、装置、系统及存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110148868A1 (en) * 2009-12-21 2011-06-23 Electronics And Telecommunications Research Institute Apparatus and method for reconstructing three-dimensional face avatar through stereo vision and face detection
US20130034264A1 (en) * 2011-08-04 2013-02-07 National Taiwan University Locomotion analysis method and locomotion analysis apparatus
CN104008571A (zh) * 2014-06-12 2014-08-27 深圳奥比中光科技有限公司 基于深度相机的人体模型获取方法及网络虚拟试衣系统
CN108876836A (zh) * 2018-03-29 2018-11-23 北京旷视科技有限公司 一种深度估计方法、装置、系统及计算机可读存储介质
CN109903379A (zh) * 2019-03-05 2019-06-18 电子科技大学 一种基于点云优化采样的三维重建方法
CN110874851A (zh) * 2019-10-25 2020-03-10 深圳奥比中光科技有限公司 重建人体三维模型的方法、装置、系统和可读存储介质

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100263935B1 (ko) * 1997-12-30 2000-08-16 윤종용 운동 시차의 수평 시차로의 변환을 이용한 2차원 연속 영상의 3차원 영상 변환장치 및 방법
CN102178530A (zh) * 2011-01-24 2011-09-14 天津大学 基于三维点云数据的人体尺寸自动测量方法
CN105678842A (zh) * 2016-01-11 2016-06-15 湖南拓视觉信息技术有限公司 室内环境三维地图制作方法及装置
CN105847777B (zh) * 2016-03-24 2018-04-17 湖南拓视觉信息技术有限公司 一种传输三维深度图像的方法及装置
CN106997614B (zh) * 2017-03-17 2021-07-20 浙江光珀智能科技有限公司 一种基于深度相机的大规模场景3d建模方法及其装置
CN106981091B (zh) * 2017-04-27 2020-04-17 深圳奥比中光科技有限公司 人体三维建模数据处理方法及装置
CN108053476B (zh) * 2017-11-22 2021-06-04 上海大学 一种基于分段三维重建的人体参数测量系统及方法
CN108154551B (zh) * 2017-11-29 2021-04-30 奥比中光科技集团股份有限公司 实时动态重建三维人体模型的方法及系统
CN108335353B (zh) * 2018-02-23 2020-12-22 清华-伯克利深圳学院筹备办公室 动态场景的三维重建方法、装置和系统、服务器、介质
CN108510573B (zh) * 2018-04-03 2021-07-30 南京大学 一种基于深度学习的多视点人脸三维模型重建的方法
CN108876897B (zh) * 2018-04-20 2022-10-18 杭州电子科技大学 快速运动下的场景三维重建方法
CN108596128B (zh) * 2018-04-28 2020-06-26 京东方科技集团股份有限公司 对象识别方法、装置及存储介质
CN108769646B (zh) * 2018-05-06 2020-02-18 Oppo广东移动通信有限公司 三维视频通信方法及系统、电子装置、服务器和可读存储介质
CN108596923B (zh) * 2018-05-14 2020-10-16 江苏哈工智能机器人股份有限公司 三维数据的获取方法、装置以及电子设备
CN109344706A (zh) * 2018-08-28 2019-02-15 杭州电子科技大学 一种可单人操作的人体特殊姿势照片的获取方法
CN109413152B (zh) * 2018-09-25 2021-02-26 上海瑾盛通信科技有限公司 图像处理方法、装置、存储介质及电子设备
CN109410318B (zh) * 2018-09-30 2020-09-08 先临三维科技股份有限公司 三维模型生成方法、装置、设备和存储介质
CN109544677B (zh) * 2018-10-30 2020-12-25 山东大学 基于深度图像关键帧的室内场景主结构重建方法及系统
CN109584358A (zh) * 2018-11-28 2019-04-05 深圳市商汤科技有限公司 一种三维人脸重建方法及装置、设备和存储介质
CN110276831B (zh) * 2019-06-28 2022-03-18 Oppo广东移动通信有限公司 三维模型的建构方法和装置、设备、计算机可读存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110148868A1 (en) * 2009-12-21 2011-06-23 Electronics And Telecommunications Research Institute Apparatus and method for reconstructing three-dimensional face avatar through stereo vision and face detection
US20130034264A1 (en) * 2011-08-04 2013-02-07 National Taiwan University Locomotion analysis method and locomotion analysis apparatus
CN104008571A (zh) * 2014-06-12 2014-08-27 深圳奥比中光科技有限公司 基于深度相机的人体模型获取方法及网络虚拟试衣系统
CN108876836A (zh) * 2018-03-29 2018-11-23 北京旷视科技有限公司 一种深度估计方法、装置、系统及计算机可读存储介质
CN109903379A (zh) * 2019-03-05 2019-06-18 电子科技大学 一种基于点云优化采样的三维重建方法
CN110874851A (zh) * 2019-10-25 2020-03-10 深圳奥比中光科技有限公司 重建人体三维模型的方法、装置、系统和可读存储介质

Also Published As

Publication number Publication date
CN110874851A (zh) 2020-03-10

Similar Documents

Publication Publication Date Title
WO2021077721A1 (fr) Procédé, appareil et système pour reconstruire un modèle tridimensionnel d'un corps humain, et support de stockage lisible
CN110874864B (zh) 获取对象三维模型的方法、装置、电子设备及系统
CN110853133A (zh) 重建人体三维模型的方法、装置、系统和可读存储介质
CN111060023B (zh) 一种高精度3d信息采集的设备及方法
CN103971408B (zh) 三维人脸模型生成系统及方法
US11504055B2 (en) Systems and methods for analyzing cutaneous conditions
CN110335343B (zh) 基于rgbd单视角图像人体三维重建方法及装置
JP6429772B2 (ja) ３ｄ走査および位置決めシステム
US20060104503A1 (en) Apparatus and method for rapidly measuring 3-Dimensional foot sizes from multi-images
US8917317B1 (en) System and method for camera calibration
WO2024032670A1 (fr) Procédé, appareil et système de reconstruction tridimensionnelle
US11722652B2 (en) Method and system for multi-wavelength depth encoding for three- dimensional range geometry compression
Reichinger et al. Evaluation of methods for optical 3-D scanning of human pinnas
CN111060008B (zh) 一种3d智能视觉设备
CN114152217B (zh) 基于监督学习的双目相位展开方法
KR20130081037A (ko) 인체 치수 측정 시스템 및 그 방법
CN107493452B (zh) 视频画面处理方法、装置和终端
KR20210068409A (ko) 정보 처리 장치, 정보 처리 방법 및 정보 처리 프로그램
CN111064949B (zh) 用于移动终端的智能3d采集模组
WO2019091010A1 (fr) Procédé, appareil et système de balayage tridimensionnel, support de stockage et processeur
US20230306636A1 (en) Object three-dimensional localizations in images or videos
JP2015156540A (ja) 画像処理装置、画像処理方法および画像処理プログラム
CN117372657A (zh) 关键点旋转模型的训练方法及装置、电子设备和存储介质
CN104899916B (zh) 基于光栅投影的人体颈椎三维重构方法及装置
CN107507272A (zh) 建立人体三维模型的方法、装置和终端设备

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: 20878480

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: 20878480

Country of ref document: EP

Kind code of ref document: A1