WO2023048347A1 - 3차원 객체모델 생성 장치 및 그 방법 - Google Patents
3차원 객체모델 생성 장치 및 그 방법 Download PDFInfo
- Publication number
- WO2023048347A1 WO2023048347A1 PCT/KR2022/001020 KR2022001020W WO2023048347A1 WO 2023048347 A1 WO2023048347 A1 WO 2023048347A1 KR 2022001020 W KR2022001020 W KR 2022001020W WO 2023048347 A1 WO2023048347 A1 WO 2023048347A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- skeleton information
- deep learning
- skeleton
- learning module
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000006243 chemical reaction Methods 0.000 claims description 87
- 238000013135 deep learning Methods 0.000 claims description 52
- 210000000988 bone and bone Anatomy 0.000 claims description 23
- 238000012937 correction Methods 0.000 claims description 18
- 230000005484 gravity Effects 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 230000003014 reinforcing effect Effects 0.000 claims description 4
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 230000001172 regenerating effect Effects 0.000 claims description 2
- 238000013136 deep learning model Methods 0.000 abstract 1
- 230000009466 transformation Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 239000000284 extract Substances 0.000 description 8
- 238000000605 extraction Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 7
- 230000009471 action Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—3D [Three Dimensional] animation
- G06T13/40—3D [Three Dimensional] animation of characters, e.g. humans, animals or virtual beings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2215/00—Indexing scheme for image rendering
- G06T2215/16—Using real world measurements to influence rendering
Definitions
- the present disclosure relates to an apparatus and method for generating a 3D object model, and more particularly, to an apparatus for generating a 3D model of a target object from a 2D image and a method performed by the apparatus.
- a 3D model is used, the posture and motion of a target object can be more precisely and accurately analyzed. Accordingly, an attempt is made to analyze the accuracy of a user's motion (eg, a swing motion, a rehabilitation exercise motion) using a 3D model of a person in fields such as golf and rehabilitation. In addition, as part of this, research on a method of generating a 3D model of a person from a 2D image of a person's motion is being actively conducted.
- a user's motion eg, a swing motion, a rehabilitation exercise motion
- the proposed method acquires a plurality of 2D images by photographing a target object while rotating a camera, and generates a 3D model of the target object by synthesizing the acquired 2D images.
- the proposed method requires multiple 2D images taken at different rotation angles, it is difficult to be widely used in various fields, and there is a clear limitation that a 3D model cannot be generated from a 2D image at a single viewpoint. .
- a technical problem to be solved through some embodiments of the present disclosure is to provide a device capable of accurately generating a 3D model of a target object from a 2D image and a method performed by the device.
- Another technical problem to be solved through some embodiments of the present disclosure is to provide a method for accurately converting 2D skeleton information into 3D skeleton information.
- Another technical problem to be solved through some embodiments of the present disclosure is to provide a deep learning module capable of accurately converting 2D skeleton information into 3D skeleton information.
- an apparatus for generating a 3D object model includes a memory for storing one or more instructions, and by executing the one or more stored instructions, 2 of a target object An operation of acquiring 2D skeleton information extracted from a dimensional image, an operation of converting the 2D skeleton information into 3D skeleton information through a deep learning module, and a 3D model for the target object based on the 3D skeleton information. It may include a processor that performs an operation of generating.
- the deep learning module is a GCN (Graph Convolutional Networks) based module, receives the 2D skeleton information and extracts feature data, and decodes the extracted feature data to generate the 3D skeleton.
- GCN Graph Convolutional Networks
- the processor further acquires object information other than the 2D skeleton information from the 2D image, and the transforming operation includes the 2D skeleton information and the other object information to the deep learning module. It may include an operation of obtaining the 3D skeleton information by inputting.
- the deep learning module is learned based on an error between 3D skeleton information predicted from 2D skeleton information for learning and correct answer information, and the error is center of gravity error, bone length error, and joint angle error. may include at least one of them.
- the deep learning module is learned using 2D skeleton information corrected based on domain information of an object, and the correction includes at least one of adding a new connection line between key points constituting the skeleton and reinforcing the connection line.
- the domain may be defined to be classified based on the operational characteristics of the object.
- the processor further obtains object information other than the 2D skeleton information from the 2D image and corrects a 3D model generated based on the other object information
- the correcting operation may include extracting 3D skeleton information from the generated 3D model, correcting the extracted 3D skeleton information according to the other object information, and based on the corrected 3D skeleton information.
- An operation of regenerating a 3D model of the target object may be included.
- a method for generating a 3D object model is a method performed in a computing device, which includes obtaining 2D skeleton information extracted from a 2D image of a target object.
- the method may include converting the 2D skeleton information into 3D skeleton information through a deep learning module and generating a 3D model of the target object based on the 3D skeleton information.
- a computer program is combined with a computing device, obtaining 2D skeleton information extracted from a 2D image of a target object, and a deep learning module. Converting the 2D skeleton information into 3D skeleton information and generating a 3D model for the target object based on the 3D skeleton information may be stored in a computer readable recording medium to execute the steps. .
- a 3D model of a target object may be accurately generated using various object information extracted from a 2D image of the target object.
- a 3D model of the target object may be accurately generated by using posture information, shape information, bone information, joint information, and body part information of the target object.
- the pose, motion, etc. of the target object may be more accurately analyzed through the generated 3D model.
- a 3D model of the target object may be accurately generated from a 2D image of a single viewpoint.
- 2D skeleton information may be converted into 3D skeleton information, and a 3D model of a target object may be generated based on the 3D skeleton information and object information. Accordingly, a 3D model of the target object may be more accurately generated. For example, even when some errors exist in the 2D skeleton information due to occlusion or distortion in the 2D image, a 3D model of the target object can be accurately generated through the 3D skeleton information. In addition, even if there are few errors in the 2D skeleton information, a more complete 3D model can be created by further using depth-dimensional skeleton information.
- conversion accuracy of skeleton information can be greatly improved by learning the conversion module based on various errors such as center of gravity errors, bone length errors, joint angle errors, and the like.
- conversion accuracy of skeleton information can be further improved by learning the conversion module using 2D skeleton information corrected by reflecting the operating characteristics of the domain.
- a 3D model of the target object may be more elaborately created.
- FIG. 1 is an exemplary diagram for explaining an apparatus for generating a 3D object model and input/output data thereof according to some embodiments of the present disclosure.
- FIG. 2 is an exemplary flowchart schematically illustrating a method for generating a 3D object model according to a first embodiment of the present disclosure.
- FIG 3 is an exemplary diagram for amplifying a method for generating a 3D object model according to the first embodiment of the present disclosure.
- FIG. 4 is an exemplary diagram for explaining a method of extracting 2D skeleton information according to some embodiments of the present disclosure.
- FIG. 5 is an exemplary flowchart schematically illustrating a method for generating a 3D object model according to a second embodiment of the present disclosure.
- FIG. 6 is an exemplary diagram for amplifying a method for generating a 3D object model according to a second embodiment of the present disclosure.
- 7 to 10 are exemplary diagrams for explaining a structure and a learning method of a conversion module according to some embodiments of the present disclosure.
- FIG. 11 is an exemplary diagram for explaining a method for improving conversion accuracy of skeleton information according to the first embodiment of the present disclosure.
- FIG. 12 is an exemplary diagram for explaining a method for improving conversion accuracy of skeleton information according to a second embodiment of the present disclosure.
- FIG. 13 is an exemplary flowchart schematically illustrating a method for generating a 3D object model according to a third embodiment of the present disclosure.
- FIG. 14 is an exemplary diagram for amplifying a method for generating a 3D object model according to a third embodiment of the present disclosure.
- FIG. 15 illustrates an exemplary computing device capable of implementing a 3D object model generating device according to some embodiments of the present disclosure.
- first, second, A, B, (a), and (b) may be used. These terms are only used to distinguish the component from other components, and the nature, sequence, or order of the corresponding component is not limited by the term.
- FIG. 1 is an exemplary diagram for explaining a 3D object model generating apparatus 1 and input/output data thereof according to some embodiments of the present disclosure.
- a 3D object model generating device 1 receives a 2D image 3 of a target object and generates and outputs a 3D model 5 of the target object.
- the 3D object model generating apparatus 1 may generate a 3D mesh model 5 of the target object from a 2D image 3 of the target object.
- a specific method of generating the 3D model 5 by the 3D object model generating apparatus 1 will be described in detail later with reference to FIG. 2 and the following drawings.
- the 3D object model generating device 1 will be abbreviated as "generating device 1".
- the 2D image 3 is an image of a target object and may be a video image composed of a plurality of consecutive frame images (see 30 in FIG. 3), a specific frame image, or a single image.
- the 2D image 3 may be a video image obtained by photographing the motion of the target object with a video camera or an image of a specific frame constituting the video image.
- the type of target object may be a human as shown, but the scope of the present disclosure is not limited thereto, and the target object may be another type of object (eg, animal). However, in order to provide convenience of understanding, the following description will continue assuming that the type of target object is "human”.
- the type of the 3D model 5 may be a mesh model as shown, but the scope of the present disclosure is not limited thereto, and the 3D model 5 may be a different type of model (eg, a voxel model). It could be. However, in order to provide convenience of understanding, the following description will continue assuming that the type of the 3D model 5 is a "mesh model".
- the generating device 1 may analyze the motion of the target object using the 3D model 5 .
- the generating device 1 may continuously generate a 3D model (e.g. 5) that simulates the motion of the target object from a video image (ie, a plurality of frame images) in which the motion of the target object is captured.
- the generating device 1 may analyze the 3D model (e.g. 5) to more precisely and accurately determine the operation of the target object.
- the generating device 1 may determine the accuracy of the motion by analyzing the 3D model (eg 5) that simulates the motion of the human object.
- the generating device 1 may determine the accuracy of an exercise motion performed by a person, such as a golf motion or a rehabilitation exercise motion. In addition, when the accuracy is less than the reference value, the generating device 1 may generate and provide a 3D model that simulates an accurate exercise motion.
- FIG. 1 shows that the generating device 1 is implemented as one computing device as an example, the generating device 1 may be implemented as a plurality of computing devices.
- a first function of the generating device 1 may be implemented in a first computing device and a second function may be implemented in a second computing device.
- specific functions of the generating device 1 may be implemented in a plurality of computing devices.
- the computing device may be, for example, a notebook, a desktop, a laptop, etc., but is not limited thereto, and may include any type of device having a computing function. Reference is made to FIG. 15 for an example of a computing device.
- the generating device 1 according to some embodiments of the present disclosure and its input/output data have been described.
- a method of generating a 3D object model that can be performed in the generation device 1 will be described in detail with reference to the drawings below in FIG. 2 .
- Each step of the 3D object model generation method may be implemented as one or more instructions that can be executed by a processor of the computing device (e.g. 1).
- each step of the method described below may be implemented as one or more instructions that may be executed by a processor of the generating device 1 .
- description will be continued on the assumption that all steps of the method to be described later are performed by the generating device 1 illustrated in FIG. 1 . Therefore, when the subject of a specific step (action) is omitted, it can be understood as being performed by the generating device 1 . However, in some cases, some steps of the method to be described later may be performed in another computing device.
- FIG. 2 is an exemplary flowchart schematically illustrating a method for generating a 3D object model according to a first embodiment of the present disclosure.
- this is only a preferred embodiment for achieving the object of the present disclosure, and it goes without saying that some steps may be added or deleted as needed.
- the method according to the present embodiment may start at step S120 of extracting object information from a 2D image.
- the generating device 1 may extract various object information 32 from the 2D image 31 of the target object through the extraction module 10 .
- the 2D image 31 may be, for example, one of a plurality of frame images constituting the video image 30 .
- the object information 32 may include, for example, pose information, shape information, orientation information, body part information, motion information, bone information, joint information, etc. It is not limited to this.
- the posture information may include, for example, information about a posture class, a 2D skeleton, and the like, but is not limited thereto.
- the 2D skeleton information may include, for example, 2D positional coordinates of key-points corresponding to parts such as joints and connection information of the keypoints, but is not limited thereto.
- the shape information may include information about the shape or volume of the entire body or part, but is not limited thereto.
- the direction information may include information about a target object or a direction of a camera, but is not limited thereto.
- the body part information may include information about the area of each body part, the center of gravity, etc., but is not limited thereto.
- the motion information may include information about motion classes, movement speeds of keypoints, etc., but is not limited thereto.
- the bone information may include information about the length and direction of the bone, but is not limited thereto.
- the length of the bone may be calculated based on, for example, the distance between key points constituting the 2D skeleton, but is not limited thereto.
- the joint information may include information about the angle of the joint, but is not limited thereto.
- the angle of the joint may be calculated based on the angle formed by the key points constituting the 2D skeleton, but is not limited thereto.
- the extraction module 10 is a module having an extraction function for the object information 32, and may be implemented in any way.
- the extraction module 10 may be implemented as a CNN (Convolutional Neural Networks)-based deep learning module specialized in image analysis, or may be implemented as an image analysis module (eg, edge detection module, etc.) not based on deep learning. .
- CNN Convolutional Neural Networks
- image analysis module eg, edge detection module, etc.
- the extraction module 10 may be composed of a plurality of modules.
- the extraction module 10 may be configured to include a module for extracting posture information (eg, 2D skeleton information) of a target object, a module for extracting body part information, and the like.
- posture information eg, 2D skeleton information
- the extraction module 10 may include a convolutional pose machine (CPM)-based deep learning module 11, and the generating device 1 may include a deep learning module 11 ), it is possible to extract the 2D skeleton information 35 by detecting a plurality of key points (e.g. 34) corresponding to joints in the 2D image 31.
- the 2D skeleton information 35 may be information composed of the detected keypoint (e.g. 34) and its 2D coordinates (e.g. X1, Y1).
- a 3D model of the target object may be generated based on the extracted object information. Specifically, as shown in FIG. 3 , the generating device 1 may generate a 3D model 33 of the target object from object information 32 through the generating module 20 .
- the generation module 20 is a model that generates a 3D model based on the object information 32, and may be implemented in any way.
- the generation module 20 may be a module that generates (renders) a 3D mesh model for a target object by using the object information 32 as a parameter.
- the generation module 20 may be, for example, a skinned multi-person linear model (SMPL) based module.
- SMPL skinned multi-person linear model
- a 3D model for a target object is obtained by extracting various object information such as posture information (e.g. 2D skeleton information), body part information, and shape information from a 2D image and using the extracted object information. can be created accurately.
- posture information e.g. 2D skeleton information
- body part information e.g. 2D skeleton information
- shape information e.g. 2D shape information
- FIG. 5 is an exemplary flowchart schematically illustrating a method for generating a 3D object model according to a second embodiment of the present disclosure.
- this is only a preferred embodiment for achieving the object of the present disclosure, and it goes without saying that some steps may be added or deleted as needed.
- the method according to the present embodiment relates to a method of more accurately generating a 3D model of a target object by converting 2D skeleton information into 3D skeleton information.
- the method according to the present embodiment may also start at step S220 of extracting object information from a 2D image of a target object.
- the generating device 1 may extract object information 52 from the 2D image 51 through the extraction module 10 .
- This step S220 is the same as the step S120 described above, so a description thereof will be omitted.
- 2D skeleton information may be converted into 3D skeleton information.
- the generating device 1 may convert 2D skeleton information into 3D skeleton information through the conversion module 40 .
- the generating device 1 may input 2D skeleton information and object information 52 to the conversion module 40 and obtain 3D skeleton information from the conversion module 40 .
- the 3D skeleton information may mean skeleton information in which the location coordinates of keypoints are 3D coordinates (ie, depth information is further included).
- the conversion module 40 may be a deep learning module trained to convert 2D skeleton information into 3D skeleton information.
- the structure and learning method of the conversion module 40 will be described in detail later with reference to FIGS. 7 to 12 .
- a 3D model of the target object may be generated based on the 3D skeleton information and other object information.
- the generation device 1 may generate a 3D model 53 of a target object from 3D skeleton information and other object information 52 through the generation module 20. there is.
- the 3D model 53 of the target object can be generated more accurately, because 3D skeleton information can provide additional information (ie, depth information), and 2D skeleton information can be converted into 3D skeleton information.
- 3D skeleton information can provide additional information (ie, depth information)
- 2D skeleton information can be converted into 3D skeleton information.
- errors included in the 2D skeleton information can be corrected during the conversion process. For example, if there is occlusion or distortion in the 2D image, some errors may be included in the 2D skeleton information, and the conversion module 40 reflects the object information 52 to generate 3D skeleton information In this error information can be corrected.
- Step S260 is almost the same as step S140 described above, so further explanation will be omitted.
- the conversion module 40 may be a deep learning module trained to convert 2D skeleton information into 3D skeleton information. Specifically, the conversion module 40 may be a deep learning module learned to convert 2D skeleton information into 3D skeleton information in consideration of object information (ie, object information other than 2D skeleton information; feature of FIG. 6 ). .
- object information ie, object information other than 2D skeleton information; feature of FIG. 6 .
- the conversion module 40 may be implemented with various types of deep learning modules.
- the transformation module 41 may be implemented as a deep learning module based on Graph Convolutional Networks (GCN).
- GCN Graph Convolutional Networks
- the 2D skeleton information 61 may be input to the conversion module 41 in the form of an adjacency matrix 63 (Adj-M) and a feature matrix 62 (Fea-M).
- keypoint connection information may be input in the form of an adjacency matrix 63
- location coordinates of keypoints may be input in the form of a feature matrix 62
- various object information e.g. 52
- object information may also be input to the conversion module 41 in the form of a feature matrix (e.g. 62).
- a detailed structure of the conversion module 40 may be designed and implemented in various ways.
- the transform module 42 may be implemented as a deep learning module having an encoder (E) and a decoder (D) structure.
- a deep learning module may include an auto-encoder, a variational autoencoder (VAE), a U-net, a W-net, and the like, but the scope of the present disclosure is not limited thereto.
- the encoder E may extract feature data (e.g. latent vector) from input 2D skeleton information 71 and object information (not shown), and the decoder D may extract the extracted feature data.
- 3D skeleton information 72 may be output by decoding.
- the encoder (E) and/or the decoder (D) may be based on GCN.
- the encoder U E and the decoder U D constituting the transform module 43 may conceptually have a U-shaped structure.
- the encoder (U E ) and/or the decoder (U D ) may be based on GCN.
- the encoder ( UE ) extracts a plurality of feature data (eg 73 to 75) having different abstraction levels by performing a down-sampling process on the input 2D skeleton information and object information. can For example, the encoder U E repeatedly performs a graph convolution operation through a plurality of GCN blocks (layers), thereby generating data having more intensive features (eg, feature data 75 is more intensive than feature data 74).
- the decoder U D may perform an up-sampling process on the extracted plurality of extracted data (eg 73 to 75).
- the transformation module 43 utilizes the feature data (eg 73 to 75) extracted by the encoder ( UE ) and the feature data (eg 76, 77) generated by the decoder ( UD ) together. High conversion accuracy can be guaranteed.
- the conversion module 43 may have a W-shaped structure in which the U-shaped structure illustrated in FIG. 9 is repeatedly formed.
- the transformation module 40 may consist of one or more deep learning modules.
- transform module 40 may consist of one deep learning module.
- the conversion module 40 may be a deep learning module trained to receive 2D skeleton information and various object information (e.g. bone information, joint information, body part information, etc.) and output 3D skeleton information.
- object information e.g. bone information, joint information, body part information, etc.
- the conversion module 40 can convert 2D skeleton information into 3D skeleton information by comprehensively considering various object information.
- the transformation module 40 may be composed of a plurality of deep learning modules receiving different object information.
- the conversion module 40 includes a first deep learning module 44 and a second deep learning module 45 that receive different object information 72 and 74. can be configured.
- the first deep learning module 44 may receive the 2D skeleton information 81 and the first object information 82 (e.g. bone information) and output 3D first skeleton information 83
- the 2 deep learning module 45 may output 3-dimensional second skeleton information 85 by receiving the 2-dimensional skeleton information 81 and second object information 84 (eg joint information).
- the generation device 1 may calculate 3D skeleton information to be input to the generation module 20 by synthesizing (eg, averaging, etc.) the first skeleton information 83 and the second skeleton information 85 .
- the object information 82 and 84 may be input to the deep learning modules 44 and 45 in the form of a feature matrix.
- the conversion module 40 may be trained using learning data composed of 2D skeleton information for learning, object information for learning, and correct answer information (ie, 3D skeleton correct answer information).
- the transformation module 40 may be trained in a direction to reduce an error between 3D skeleton information predicted from 2D skeleton information for learning and object information for learning (hereinafter, abbreviated as "prediction information") and correct answer information.
- prediction information 3D skeleton correct answer information predicted from 2D skeleton information for learning and object information for learning
- specific types of errors may vary depending on embodiments.
- transform module 40 may be learned based on the center of gravity error.
- the center of gravity error may be calculated based on the difference between the center of gravity calculated from prediction information and the center of gravity calculated from correct answer information.
- the center of gravity error may be calculated based on the difference between the center of gravity calculated from the two-dimensional skeleton information for learning input to the conversion module 40 and the center of gravity calculated from prediction information.
- the center of gravity error may be calculated for each body part, but the scope of the present disclosure is not limited thereto.
- the conversion module 40 can predict 3D skeleton information by further considering the center of gravity of the input 2D skeleton information.
- transform module 40 may be learned based on bone length error.
- the bone length error may be calculated based on the difference between the bone length calculated from prediction information and the bone length calculated from correct answer information.
- the bone length can be calculated based on the distance between keypoints.
- the conversion module 40 can predict 3D skeleton information by further considering the bone length according to the input 2D skeleton information or bone information.
- the transform module 40 may be learned based on the angular error of the joint.
- the angle error of the joint may be calculated based on the difference between the joint angle calculated from the prediction information and the joint angle calculated from the correct answer information.
- the conversion module 40 can predict 3D skeleton information by further considering joint angles according to input 2D skeleton information or joint information.
- transform module 40 may be learned based on the symmetry error. For example, when the 2-dimensional skeleton for learning input to the conversion module 40 has a symmetric structure (e.g. vertical symmetry, left-right symmetry), the conversion module in the direction of reducing the error based on the degree of symmetry of the predicted 3-dimensional skeleton ( 40) can be learned. According to this embodiment, conversion accuracy for a two-dimensional skeleton having a symmetrical structure can be further improved.
- a symmetric structure e.g. vertical symmetry, left-right symmetry
- transform module 40 may be learned based on projection error.
- the projection error may be calculated based on a difference between 2D skeleton information generated from prediction information through a projection operation and 2D skeleton information for learning input to the transformation module 40 .
- the performance of the transformation module 40 can be further improved by further learning the projection error.
- the conversion module 40 may be trained based on a combination of various embodiments described above.
- the present embodiment is a method for improving the conversion accuracy of skeleton information by training the conversion module 46 using the two-dimensional skeleton information 91 corrected using the operating characteristics of the domain. it's about
- the domain of the target object may be defined to be classified based on the operating characteristics of the target object.
- objects sharing common operating characteristics may belong to the same domain.
- the domain of the target object may be classified into soccer (ie, an object related to a soccer motion), golf, and rehabilitation treatment.
- the domain of the target object may be divided into a foot motion (ie, an object related to a foot motion), a hand motion, and the like.
- the domain of the target object may be defined in a more subdivided form, such as a first motion related to golf and a second motion related to golf.
- the 2D skeleton information 91 for learning may be corrected based on the operating characteristics of the domain.
- the performance of the conversion module 46 can be improved by training the conversion module 46 using the corrected 2D skeleton information 92 .
- the correction of the 2D skeleton information 91 may include, for example, adding a new connection line between key points constituting the skeleton, reinforcing the connection line (eg, amplifying the adjacent matrix value representing the connection line), etc., but the scope of the present disclosure is limited to this. It is not limited.
- the domain of the target object is golf.
- a new connection line 93 is added between key points corresponding to both hands in the two-dimensional skeleton information 91, or a connection line between key points corresponding to the hand part is strengthened.
- Calibration may be performed.
- the transformation module 46 may be learned using the corrected 2D skeleton information 92 .
- the performance of the conversion module 46 ie, conversion accuracy of the skeleton information
- the 2D skeleton information is corrected based on the domain information of the target object, and the corrected 2D skeleton information may be input to the conversion module 46.
- the present embodiment relates to a method of improving conversion accuracy of skeleton information by constructing conversion modules 47 and 48 for each domain of a target object.
- the first conversion module 47 may be built by learning training data belonging to the first domain
- the second conversion module 48 may be built by learning training data belonging to the second domain.
- the first conversion module 47 can convert the input 2D skeleton information 94 into 3D skeleton information 95 in which the characteristics of the first domain (e.g. motion characteristics) are reflected
- the second conversion The module 48 can convert the input 2D skeleton information 96 into 3D skeleton information 97 in which the characteristics of the second domain are reflected.
- the generating device 1 determines a transformation module corresponding to the domain of the target object from among a plurality of transformation modules 47 and 48, and converts 2D skeleton information into 3D skeleton information through the determined transformation module. can do.
- This embodiment relates to a method for improving conversion accuracy of skeleton information by training the conversion module 40 with training data including domain information.
- the conversion module 40 may be learned using learning data composed of 2D skeleton information for learning, object information, domain information, and correct answer information.
- 2-dimensional skeleton information for learning, object information, and domain information are input to the conversion module 40, and the conversion module 40 in the direction of reducing the error between the 3-dimensional skeleton information and correct answer information predicted by the conversion module 40 this can be learned.
- the conversion module 40 can convert 2D skeleton information into 3D skeleton information by reflecting the domain characteristics (eg, motion characteristics) of the target object.
- domain information of a target object may be input to the conversion module 40 .
- the present embodiment relates to a method for improving conversion accuracy of skeleton information by training the conversion module 40 using 2-dimensional skeleton information corrected based on the movement speed of keypoints constituting the skeleton.
- the movement speed of the keypoint may be extracted along with the 2D skeleton information.
- the conversion module 40 may be learned using 2D skeleton information for learning generated by correcting (eg, adding a new connection line, reinforcing a connection line) between key points having a moving speed equal to or greater than a reference value. In this case, since the conversion module 40 can predict 3D skeleton information by concentrating on a body part with a relatively large movement, conversion accuracy of skeleton information can be improved.
- the 2D skeleton information is corrected based on the moving speed of the keypoint, and the corrected 2D skeleton information is It can be input to the conversion module 40.
- 2D skeleton information is converted into 3D skeleton information through the conversion module 40, and a 3D model may be generated based on the 3D skeleton information and object information. Accordingly, a 3D model of the target object may be more accurately generated. For example, even when some errors exist in the 2D skeleton information due to occlusion or distortion in the 2D image, a 3D model of the target object can be accurately generated. In addition, even if there are few errors in the 2D skeleton information, a more complete 3D model can be generated by further providing depth-dimensional skeleton information to the generation module 20 .
- 2D skeleton information can be accurately converted into 3D skeleton information.
- conversion accuracy of skeleton information can be greatly improved by learning the conversion module based on various errors such as center of gravity errors, bone length errors, joint angle errors, and the like.
- conversion accuracy of the skeleton information can be further improved by correcting the 2D skeleton information by reflecting the operating characteristics of the domain and learning the conversion module using the corrected 2D skeleton information.
- FIG. 13 is an exemplary flowchart schematically illustrating a method for generating a 3D object model according to a third embodiment of the present disclosure.
- this is only a preferred embodiment for achieving the object of the present disclosure, and it goes without saying that some steps may be added or deleted as needed.
- the method according to the present embodiment relates to a method of more accurately generating a 3D model of a target object by correcting the 3D model using object information extracted from a 2D image.
- Steps S320 to S360 are the same as steps S220 to S260 described above, respectively, so descriptions thereof will be omitted.
- step S380 the 3D model of the target object may be calibrated.
- a specific correction method may vary according to embodiments.
- a 3D model 113 is formed based on object information 112 (e.g. 2D skeleton information, bone information, joint information) extracted from the 2D image 111.
- object information 112 e.g. 2D skeleton information, bone information, joint information
- the generating device 1 may extract 3D skeleton information from the 3D model 113 and correct the 3D skeleton information through the correction module 100 .
- the generation device 1 may regenerate the 3D model 113 of the target object by providing the corrected 3D skeleton information and the object information 112 to the generation module 20 .
- the correction module 100 may perform a function of correcting the input 3D skeleton information to match the input object information.
- the accuracy of the 3D model 113 can be further improved by correcting the 3D model 113 to conform to the object information 112 extracted from the 2D image 111 .
- the object information 112 is information directly extracted from the 2D image 111, it is information with relatively high accuracy.
- an error may occur in the process of generating the 3D model 113 by the generation module 20 based on it. Therefore, if a process of correcting the 3D model 113 conforms to the object information 112 is further performed, the error of the generation module 20 is minimized and a more sophisticated 3D model 113 can be generated. .
- the correction module 100 may be implemented as a deep learning module or other types of modules.
- the correction module 100 may be implemented as a deep learning module trained to receive 3D skeleton information and object information 112 and output calibrated 3D skeleton information.
- the correction module 100 may have the same or similar structure as the conversion module 40 described above, and may be implemented by learning in the same or similar manner.
- the correction module 100 may be implemented as a module that performs a predetermined correction logic on 3D skeleton information input according to the object information 112 .
- 3D object information (e.g. 3D skeleton information, 3D bone information, 3D joint information, 3D body part information, etc.) extracted from a 3D model (e.g. 113) Based on this, the 3D model (e.g. 113) can be calibrated.
- the generation device 1 may correct input 3D object information using a deep learning-based correction module (e.g. 100).
- the correction module (e.g. 100) may be a deep learning module that has learned training data composed of 3D skeleton information before correction, 3D object information, and corrected 3D skeleton information.
- the correction module (e.g. 100) according to the present embodiment may also have the same or similar structure as the above-described conversion model 40 and may be implemented by learning in the same or similar manner.
- the generation device 1 may determine the generation accuracy of the 3D model, and may perform the correction step S380 in response to the determination that the determined accuracy is equal to or less than a reference value. For example, the generation device 1 may extract 3D skeleton information from a 3D model and convert the 3D skeleton information into 2D skeleton information through a projection operation. Also, the generating device 1 may determine generation accuracy of the 3D model based on a difference between the converted 2D skeleton information and the 2D skeleton information extracted from the 2D image. According to this embodiment, by performing the correction step S380 only when the generation accuracy of the 3D model is equal to or less than the reference value, the computing cost input to the generation device 1 can be reduced.
- a 3D model of a target object may be more elaborately created by correcting the 3D model using object information extracted from a 2D image.
- 15 is an exemplary hardware configuration diagram illustrating computing device 120 .
- the computing device 120 includes one or more processors 121, a bus 123, a communication interface 124, and a memory (loading) a computer program executed by the processor 121 ( 122) and a storage 125 for storing the computer program 126.
- the computing device 120 may further include various components other than the components shown in FIG. 15 .
- the computing device 120 may be configured in a form in which some of the components shown in FIG. 15 are omitted.
- each component of the computing device 120 will be described.
- the processor 121 may control overall operations of each component of the computing device 120 .
- the processor 121 may include at least one of a Central Processing Unit (CPU), a Micro Processor Unit (MPU), a Micro Controller Unit (MCU), a Graphic Processing Unit (GPU), or any type of processor well known in the art of the present disclosure. can be configured to include Also, the processor 121 may perform an operation for at least one application or program for executing an operation/method according to embodiments of the present disclosure.
- Computing device 120 may include one or more processors.
- the memory 122 may store various data, commands and/or information.
- Memory 122 may load one or more programs 126 from storage 125 to execute operations/methods according to embodiments of the present disclosure.
- Memory 122 may be implemented with volatile memory such as RAM, but the scope of the present disclosure is not limited thereto.
- the bus 123 may provide a communication function between components of the computing device 120 .
- the bus 123 may be implemented as various types of buses such as an address bus, a data bus, and a control bus.
- the communication interface 124 may support wired and wireless Internet communication of the computing device 120 . Also, the communication interface 124 may support various communication methods other than Internet communication. To this end, the communication interface 124 may include a communication module well known in the art of the present disclosure. In some cases, the communication interface 124 may be omitted.
- storage 125 may non-temporarily store one or more computer programs 126 .
- the storage 125 may be a non-volatile memory such as read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, etc., a hard disk, a removable disk, or a device well known in the art. It may be configured to include any known type of computer-readable recording medium.
- computer program 126 may include one or more instructions that when loaded into memory 122 cause processor 121 to perform operations/methods in accordance with various embodiments of the present disclosure. That is, the processor 121 may perform an operation/method according to various embodiments of the present disclosure by executing one or more instructions.
- the computer program 126 may include an operation of obtaining 2D skeleton information extracted from a 2D image of a target object, an operation of converting 2D skeleton information into 3D skeleton information through a deep learning module, and an operation of converting 3D skeleton information into 3D skeleton information. It may include instructions that perform an operation of generating a 3D model of the target object based on the information.
- the generating device 1 according to some embodiments of the present disclosure may be implemented through the computing device 120 .
- the technical idea of the present disclosure described with reference to FIGS. 1 to 15 so far may be implemented as computer readable code on a computer readable medium.
- the computer-readable recording medium may be, for example, a removable recording medium (CD, DVD, Blu-ray disc, USB storage device, removable hard disk) or a fixed recording medium (ROM, RAM, computer-equipped hard disk).
- ROM, RAM, computer-equipped hard disk can
- the computer program recorded on the computer-readable recording medium may be transmitted to another computing device through a network such as the Internet, installed in the other computing device, and thus used in the other computing device.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (14)
- 하나 이상의 인스트럭션들(instructions)을 저장하는 메모리;상기 저장된 하나 이상의 인스트럭션들을 실행함으로써,대상 객체의 2차원 이미지에서 추출된 2차원 스켈레톤 정보를 획득하는 동작,딥러닝 모듈을 통해 상기 2차원 스켈레톤 정보를 3차원 스켈레톤 정보로 변환하는 동작 및상기 3차원 스켈레톤 정보를 기초로 상기 대상 객체에 대한 3차원 모델을 생성하는 동작을 수행하는 프로세서를 포함하는,3차원 객체모델 생성 장치.
- 제1 항에 있어서,상기 딥러닝 모듈은,GCN(Graph Convolutional Networks) 기반의 모듈이고,상기 2차원 스켈레톤 정보를 입력받아 특징 데이터를 추출하는 인코더와 상기 추출된 특징 데이터를 디코딩하여 상기 3차원 스켈레톤 정보를 출력하는 디코더를 포함하는,3차원 객체모델 생성 장치.
- 제2 항에 있어서,상기 인코더는 다운샘플링 프로세스를 수행하여 추상화 레벨이 상이한 복수의 특징 데이터를 추출하고,상기 디코더는 상기 복수의 특징 데이터를 이용하여 업샘플링 프로세스를 수행하는,3차원 객체모델 생성 장치.
- 제1 항에 있어서,상기 프로세서는 상기 2차원 이미지에서 상기 2차원 스켈레톤 정보 외의 다른 객체 정보를 더 획득하고,상기 변환하는 동작은,상기 2차원 스켈레톤 정보와 상기 다른 객체 정보를 상기 딥러닝 모듈에 입력하여 상기 3차원 스켈레톤 정보를 획득하는 동작을 포함하는,3차원 객체모델 생성 장치.
- 제4 항에 있어서,상기 다른 객체 정보는,뼈의 길이를 포함하는 뼈 정보,관절의 각도를 포함하는 관절 정보 및신체 부위의 면적을 포함하는 신체 부위 정보 중 적어도 하나를 포함하는,3차원 객체모델 생성 장치.
- 제4 항에 있어서,상기 딥러닝 모듈은 상기 추가 객체 정보 중 제1 객체 정보를 입력받는 제1 딥러닝 모듈과 제2 객체 정보를 입력받는 제2 딥러닝 모듈을 포함하고,상기 획득하는 동작은,상기 제1 딥러닝 모듈을 통해 출력된 제1 스켈레톤 정보와 상기 제2 딥러닝 모듈을 통해 출력된 제2 스켈레톤 정보를 종합하여 상기 3차원 스켈레톤 정보를 획득하는 동작을 포함하는,3차원 객체모델 생성 장치.
- 제1 항에 있어서,상기 딥러닝 모듈은 학습용 2차원 스켈레톤 정보로부터 예측된 3차원 스켈레톤 정보와 정답 정보 간의 오차에 기초하여 학습된 것이고,상기 오차는 무게 중심 오차, 뼈 길이 오차 및 관절의 각도 오차 중 적어도 하나를 포함하는,3차원 객체모델 생성 장치.
- 제1 항에 있어서,상기 딥러닝 모듈은 객체의 도메인 정보에 기초하여 보정된 2차원 스켈레톤 정보를 이용하여 학습된 것이고,상기 보정은 스켈레톤을 구성하는 키포인트 간의 신규 연결선 추가 및 연결선 강화 중 적어도 하나를 포함하되,상기 도메인은 객체의 동작 특성에 기초하여 구분되도록 정의된 것인,3차원 객체모델 생성 장치.
- 제1 항에 있어서,상기 딥러닝 모듈의 학습용 2차원 스켈레톤 정보는 연속된 프레임 이미지에서 추출된 2차원 스켈레톤 정보를 키포인트의 이동 속도에 기초하여 키포인트 간의 연결선을 보정함으로써 생성된 것인,3차원 객체모델 생성 장치.
- 제1 항에 있어서,상기 딥러닝 모듈은 복수개이고,상기 변환하는 동작은,상기 복수개의 딥러닝 모듈 중에서 상기 대상 객체의 도메인에 대응되는 딥러닝 모듈을 결정하는 동작 및상기 결정된 딥러닝 모듈을 통해 상기 2차원 스켈레톤 정보를 상기 3차원 스켈레톤 정보로 변환하는 동작을 포함하되,상기 도메인은 객체의 동작 특성에 기초하여 구분되도록 정의된 것인,3차원 객체모델 생성 장치.
- 제1 항에 있어서,상기 변환하는 동작은,상기 2차원 스켈레톤 정보와 상기 대상 객체의 도메인 정보를 상기 딥러닝 모듈에 입력하여 상기 3차원 스켈레톤 정보를 획득하는 동작을 포함하되,상기 도메인은 객체의 동작 특성에 기초하여 구분되도록 정의된 것인,3차원 객체모델 생성 장치.
- 제1 항에 있어서,상기 프로세서는,상기 2차원 이미지에서 상기 2차원 스켈레톤 정보 외의 다른 객체 정보를 더 획득하고,상기 다른 객체 정보를 기초로 생성된 3차원 모델을 보정하는 동작을 더 수행하되,상기 보정하는 동작은,상기 생성된 3차원 모델로부터 3차원 스켈레톤 정보를 추출하는 동작,상기 다른 객체 정보에 따라 상기 추출된 3차원 스켈레톤 정보를 보정하는 동작 및상기 보정된 3차원 스켈레톤 정보를 기초로 상기 대상 객체에 대한 3차원 모델을 다시 생성하는 동작을 포함하는,3차원 객체모델 생성 장치.
- 컴퓨팅 장치에서 수행되는 방법으로서,대상 객체의 2차원 이미지에서 추출된 2차원 스켈레톤 정보를 획득하는 단계;딥러닝 모듈을 통해 상기 2차원 스켈레톤 정보를 3차원 스켈레톤 정보로 변환하는 단계; 및상기 3차원 스켈레톤 정보를 기초로 상기 대상 객체에 대한 3차원 모델을 생성하는 단계를 포함하는,3차원 객체모델 생성 방법.
- 컴퓨팅 장치와 결합되어,대상 객체의 2차원 이미지에서 추출된 2차원 스켈레톤 정보를 획득하는 단계;딥러닝 모듈을 통해 상기 2차원 스켈레톤 정보를 3차원 스켈레톤 정보로 변환하는 단계; 및상기 3차원 스켈레톤 정보를 기초로 상기 대상 객체에 대한 3차원 모델을 생성하는 단계를 실행시키기 위하여 컴퓨터 판독가능한 기록매체에 저장된,컴퓨터 프로그램.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2024519589A JP2024537799A (ja) | 2021-09-27 | 2022-01-20 | 3次元オブジェクトモデル生成装置及びその方法 |
US18/696,147 US20240394968A1 (en) | 2021-09-27 | 2022-01-20 | Apparatus for generating 3-dimensional object model and method thereof |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020210127251A KR102421776B1 (ko) | 2021-09-27 | 2021-09-27 | 3차원 객체모델 생성 장치 및 그 방법 |
KR10-2021-0127251 | 2021-09-27 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023048347A1 true WO2023048347A1 (ko) | 2023-03-30 |
Family
ID=82607435
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2022/001020 WO2023048347A1 (ko) | 2021-09-27 | 2022-01-20 | 3차원 객체모델 생성 장치 및 그 방법 |
Country Status (4)
Country | Link |
---|---|
US (1) | US20240394968A1 (ko) |
JP (1) | JP2024537799A (ko) |
KR (2) | KR102421776B1 (ko) |
WO (1) | WO2023048347A1 (ko) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102526091B1 (ko) * | 2022-11-21 | 2023-04-26 | 주식회사 드랩 | 제품 사용 이미지 생성 시스템 및 제품 사용 이미지 생성 방법 |
KR102705610B1 (ko) * | 2022-11-28 | 2024-09-11 | 주식회사 인공지능연구원 | 다시점 카메라 기반 다관절 객체의 입체영상캡쳐 장치 및 방법 |
KR102612586B1 (ko) * | 2022-12-12 | 2023-12-11 | 박치호 | 동영상 내 관절 인식에 따른 비정상 이미지 프레임을 제거 및 복원하는 전자 장치의 제어 방법 |
KR102619701B1 (ko) * | 2022-12-30 | 2024-01-02 | 주식회사 쓰리아이 | 동적 객체에 대한 3차원 자세 추정 데이터 생성 방법 및 그를 위한 컴퓨팅 장치 |
KR102721960B1 (ko) * | 2024-05-22 | 2024-10-25 | 제이크로커스 주식회사 | 3d 객체 모델 생성 장치 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017170264A1 (ja) * | 2016-03-28 | 2017-10-05 | 株式会社3D body Lab | 骨格特定システム、骨格特定方法、及びコンピュータプログラム |
KR20210003937A (ko) * | 2018-05-23 | 2021-01-12 | 모비디어스 리미티드 | 딥 러닝 시스템 |
KR20210091276A (ko) * | 2018-11-16 | 2021-07-21 | 아리엘 에이아이, 인크. | 3차원 객체 재구성 |
KR20210093795A (ko) * | 2020-01-20 | 2021-07-28 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | 3d 관절 점 회귀 모델의 생성 방법 및 장치 |
KR20210108044A (ko) * | 2020-02-25 | 2021-09-02 | 제주한라대학교산학협력단 | 디지털 트윈 기술을 위한 영상 분석 시스템 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101884565B1 (ko) | 2017-04-20 | 2018-08-02 | 주식회사 이볼케이노 | 2차원 이미지를 이용한 객체의 3차원 모델링 장치 및 방법 |
-
2021
- 2021-09-27 KR KR1020210127251A patent/KR102421776B1/ko active IP Right Grant
-
2022
- 2022-01-20 US US18/696,147 patent/US20240394968A1/en active Pending
- 2022-01-20 JP JP2024519589A patent/JP2024537799A/ja active Pending
- 2022-01-20 WO PCT/KR2022/001020 patent/WO2023048347A1/ko active Application Filing
- 2022-06-17 KR KR1020220073851A patent/KR102473287B1/ko active IP Right Grant
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017170264A1 (ja) * | 2016-03-28 | 2017-10-05 | 株式会社3D body Lab | 骨格特定システム、骨格特定方法、及びコンピュータプログラム |
KR20210003937A (ko) * | 2018-05-23 | 2021-01-12 | 모비디어스 리미티드 | 딥 러닝 시스템 |
KR20210091276A (ko) * | 2018-11-16 | 2021-07-21 | 아리엘 에이아이, 인크. | 3차원 객체 재구성 |
KR20210093795A (ko) * | 2020-01-20 | 2021-07-28 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | 3d 관절 점 회귀 모델의 생성 방법 및 장치 |
KR20210108044A (ko) * | 2020-02-25 | 2021-09-02 | 제주한라대학교산학협력단 | 디지털 트윈 기술을 위한 영상 분석 시스템 |
Also Published As
Publication number | Publication date |
---|---|
US20240394968A1 (en) | 2024-11-28 |
KR102421776B1 (ko) | 2022-07-19 |
JP2024537799A (ja) | 2024-10-16 |
KR102473287B1 (ko) | 2022-12-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2023048347A1 (ko) | 3차원 객체모델 생성 장치 및 그 방법 | |
WO2018143770A1 (en) | Electronic device for creating panoramic image or motion picture and method for the same | |
WO2013031424A1 (ja) | 画像処理装置、および画像処理方法、並びにプログラム | |
JP2017134617A (ja) | 位置推定装置、プログラム、位置推定方法 | |
KR101021470B1 (ko) | 영상 데이터를 이용한 로봇 움직임 데이터 생성 방법 및 생성 장치 | |
US8284292B2 (en) | Probability distribution constructing method, probability distribution constructing apparatus, storage medium of probability distribution constructing program, subject detecting method, subject detecting apparatus, and storage medium of subject detecting program | |
CN111563924A (zh) | 图像深度确定方法及活体识别方法、电路、设备和介质 | |
JP2020198133A (ja) | 動作特定装置、動作特定方法及び動作特定プログラム | |
KR20220095831A (ko) | 구조물 균열 측정 시스템, 방법, 및 상기 방법을 실행시키기 위한 컴퓨터 판독 가능한 프로그램을 기록한 기록 매체 | |
JP2006245677A (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 | |
CN110910478A (zh) | Gif图生成方法、装置、电子设备及存储介质 | |
JP2002312791A (ja) | 画像処理装置および方法、記録媒体、並びにプログラム | |
JP5530391B2 (ja) | カメラポーズ推定装置、カメラポーズ推定方法及びカメラポーズ推定プログラム | |
WO2021040345A1 (ko) | 전자 장치 및 전자 장치의 제어 방법 | |
JP2004228770A (ja) | 画像処理システム | |
WO2016021829A1 (ko) | 동작 인식 방법 및 동작 인식 장치 | |
CN111950517A (zh) | 一种目标检测方法、模型训练方法,电子设备及存储介质 | |
JP6839116B2 (ja) | 学習装置、推定装置、学習方法、推定方法及びコンピュータプログラム | |
JP2012185655A (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 | |
CN105493101B (zh) | 包括在辅助对象定位中使用加速数据的图像帧处理 | |
JP2019092089A (ja) | 画像処理装置、画像表示システム、画像処理方法、およびプログラム | |
JP2005309782A (ja) | 画像処理装置 | |
WO2024029880A1 (ko) | 시선 방향을 검출하는 딥러닝 기반의 시선 방향 검출 모델을 학습하는 학습방법 및 학습 장치, 이를 이용한 테스트 방법 및 테스트 장치 | |
JP4112925B2 (ja) | 画像入力装置、画像入力方法、及びコンピュータが実行するためのプログラム | |
WO2018052183A1 (ko) | 족부 스캔 장치 및 그의 족부 스캔 방법 |
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: 22873054 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2024519589 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 18696147 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 22873054 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 02.09.2024) |