WO2021210046A1 - 情報処理装置、制御方法及び記憶媒体 - Google Patents
情報処理装置、制御方法及び記憶媒体 Download PDFInfo
- Publication number
- WO2021210046A1 WO2021210046A1 PCT/JP2020/016311 JP2020016311W WO2021210046A1 WO 2021210046 A1 WO2021210046 A1 WO 2021210046A1 JP 2020016311 W JP2020016311 W JP 2020016311W WO 2021210046 A1 WO2021210046 A1 WO 2021210046A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- label
- feature point
- symmetry
- feature
- additional information
- Prior art date
- Legal status (The legal status 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 status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/68—Analysis of geometric attributes of symmetry
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
Definitions
- the present disclosure relates to technical fields of information processing devices, control methods, and storage media that extract features based on images.
- Patent Document 1 stores feature data representing the features of the appearance of an object, and extracts features of an object existing in real space based on an image obtained from an image pickup device and the above feature data.
- an image processing apparatus that constructs an environment map that expresses the position of the object, and displays a description of a series of procedures of work to be performed in the real space with reference to the environment map.
- the present disclosure provides an information processing device, a control method, and a storage medium capable of suitably performing feature extraction.
- One aspect of the information processing device is an information processing device, in which the position of a feature point of a symmetric object having symmetry and a first label unique to the feature point are determined based on the captured image captured by the image pickup unit.
- the feature point acquisition means for acquiring the combination with the second label defined to be integrated or changed based on the symmetry, the additional information for breaking the symmetry, and the feature point based on the second label. It has a label determining means for determining the first label to be attached to each of the above.
- One aspect of the storage medium is to integrate or change the position of the feature point of the symmetric object having symmetry and the first label peculiar to the feature point based on the symmetry based on the captured image captured by the imaging unit. Based on the feature point acquisition means for acquiring the combination with the second label defined as described above, the additional information for breaking the symmetry, and the second label, the feature point to be attached to each of the feature points. It is a storage medium that stores a program that functions a computer as a label determining means for determining a first label.
- the display device 1 includes a light source unit 10, an optical element 11, a communication unit 12, an input unit 13, a storage unit 14, an imaging unit (camera) 15, and a position / orientation detection sensor 16. And a control unit 17.
- the communication unit 12 exchanges data with an external device based on the control of the control unit 17. For example, when a user uses the display device 1 for watching sports or watching a play, the communication unit 12 should display the display device 1 from a server device managed by an entertainer based on the control of the control unit 17. Receive information about virtual objects.
- the input unit 13 generates an input signal based on the user's operation and transmits it to the control unit 17.
- the input unit 13 is, for example, a button, a cross key, a voice input device, or the like for the user to give an instruction to the display device 1.
- the control unit 17 has, for example, a processor such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit), a volatile memory that functions as a working memory of the processor, and performs overall control of the display device 1. ..
- a processor such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit)
- a volatile memory that functions as a working memory of the processor, and performs overall control of the display device 1. ..
- the storage unit 14 has a non-volatile memory in which the control unit 17 stores various information necessary for controlling the display device 1.
- the storage unit 14 may include a removable storage medium such as a flash memory. Further, the storage unit 14 stores a program executed by the control unit 17.
- the storage unit 14 stores the feature extractor parameter D1 and the additional information generation data D2.
- the additional information generation data D2 is data used for generating the additional information "Ia" which is information that breaks the symmetry of the reference structure Rtag.
- the additional information Ia is, in other words, information for converting the second label into the first label by uniquely specifying the orientation of the reference structure Rtag in the captured image Im.
- the additional information Ia is information indicating any one of 1 to N (N is the number of integrated labels) according to the positional relationship between the display device 1 and the reference structure Rtag.
- the first example of the additional information generation data D2 is seat information indicating the position of the seat when the wearer of the display device 1 observes the reference structure Rtag.
- This seat information is information that can grasp the positional relationship with the reference structure Rtag (that is, the direction of the other when one is used as a reference).
- the second example of the additional information generation data D2 is the absolute position information of the reference structure Rtag.
- the display device 1 refers to the display device 1 and the reference device 1 based on the current position of the display device 1 detected by the position / orientation detection sensor 16 and the position of the reference structure Rtag indicated by the additional information generation data D2. Additional information Ia is generated according to the positional relationship with the structure Rtag.
- the third example of the additional information generation data D2 is an inference device for inferring the positional relationship between the feature structure existing around the reference structure Rtag and the reference structure Rtag based on the captured image Im (“feature inference device”). It is also called.).
- feature inferior may be modeled to directly output the additional information Ia.
- the feature is an object whose positional relationship with respect to the reference structure Rtag is predetermined.
- the features are necessary (always installed) in the competition or game performed in the reference structure Rtag, such as the referee's table of the tennis court and the piece holder of shogi.
- the feature is a feature of the stadium with the reference structure Rtag, such as an entrance to the reference structure Rtag, a floor portion with a unique color or pattern around the reference structure Rtag. You may.
- the additional information generation unit 41 generates additional information Ia that breaks the symmetry of the reference structure Rtag based on the additional information generation data D2.
- the additional information generation unit 41 determines whether the display device 1 exists on the north side, the south side, the west side, or the east side of the reference structure Rtag as the above positional relationship, and determines whether the display device 1 exists on the north side, the south side, the west side, or the east side.
- the corresponding additional information Ia is generated.
- the additional information generation unit 41 generates additional information Ia indicating a detailed direction as the number of integrated labels N increases. In other words, the additional information generation unit 41 generates information as additional information Ia that can specify at least one of the directions divided by the label integration number N.
- the additional information generation unit 41 is supplied from the captured image acquisition unit 40 to the feature inference device configured based on the additional information generation data D2.
- the captured image Im is input.
- the additional information generation unit 41 generates additional information Ia according to the positional relationship between the feature existing around the reference structure Rtag and the reference structure Rtag in the captured image Im.
- the second label feature extraction unit 42 responds to the symmetry of the reference structure Rtag based on the information output from the feature extractor by inputting the captured image Im into the feature extractor configured based on the feature extractor parameter D1.
- the feature points to which the second label is added are extracted.
- the second label feature extraction unit 42 uses the information indicating the combination of the coordinate values in the captured image Im of the feature points and the second label (also referred to as “first feature point information F1”) in the first label determination unit 43. Supply to.
- each of these components may be realized by using a user-programmable integrated circuit such as an FPGA (field-programmable gate array) or a microcomputer.
- this integrated circuit may be used to realize a program composed of each of the above components.
- each component may be realized by hardware other than the processor. The above is the same in other embodiments described later.
- the additional information generation unit 41 determines that the display device 1 exists on the north side or the east side of the reference structure Rtag based on the seat information or the like, the additional information Ia is set to "0" and the display device 1 is set. If it is determined that the information exists on the south side or the west side of the reference structure Rtag, the additional information Ia is set to "1". Similarly, when the additional information generation unit 41 determines that the referee table 9 exists on the front side or the right side with respect to the reference structure Rtag based on the captured image Im, the display device 1 is located on the north side or the reference structure Rtag. Since it is the same as when it exists on the east side, the additional information Ia is set to "0".
- the first label determination unit 43 attaches the first labels Pa0 to Pa6 to the feature points of the court side existing on the back side or the right side, and attaches the first labels Pa0 to Pa6 to the front side or the left side.
- the first labels Pa7 to Pa13 are attached to the existing courtside feature points.
- the additional information Ia is "1"
- the first label determination unit 43 attaches the first labels Pa0 to Pa6 to the feature points of the court side existing on the front side or the left side, and attaches the first labels Pa0 to Pa6 to the back side or the right side.
- the first labels Pa7 to Pa13 are attached to the existing courtside feature points.
- the first label determination unit 43 identifies the court side existing on the back side in the captured image Im as the west side court side based on the additional information Ia.
- the court side existing on the front side in the captured image Im is identified as the east side court side.
- identification information such as an identification number is pre-assigned to each division area based on the absolute positional relationship of each division area, and the first label determination unit 43 recognizes the identification information of each division area. .. Then, the first label determination unit 43 assigns a first label to each feature point for each identified division region.
- the first label determination unit 43 has each feature point existing in each division region based on the positional relationship of each division region for N divided label integrations in the captured image Im and the additional information Ia.
- a first label can be given to the product.
- the learning device 3 has a display unit 30, a communication unit 31, an input unit 32, a control unit 33, and a storage unit 34.
- the control unit 33 has, for example, a processor such as a CPU, GPU, or quantum processor, a volatile memory that functions as a working memory of the processor, and the like, and controls the entire learning device 3.
- the storage unit 34 has a non-volatile memory in which the control unit 33 stores various information necessary for learning.
- the storage unit 34 stores the feature extractor parameter D1 and the additional information generation data D2 generated after learning, and the learning data D3 used for learning.
- the first learning unit 37 sets the feature extractor parameter D1 by performing learning on the feature extractor (first learning) based on the learning data D3 to which the second label is added for each feature point by the label conversion unit 36. Generate.
- the first learning unit 37 has, for example, an error (loss) between the feature point information and the second label output by the feature extractor when the learning image is input to the feature extractor and the correct answer data.
- the algorithm for determining the above parameters to minimize the loss may be any learning algorithm used in machine learning such as gradient descent or backpropagation.
- the first learning unit 37 stores the parameters of the feature extractor after learning as the feature extractor parameter D1.
- the feature extractor parameter D1 may be immediately transmitted to the display device 1 by the communication unit 31, or may be supplied to the display device 1 via a storage medium that can be attached to and detached from the learning device 3 and the display device 1.
- FIG. 8 is an example of a flowchart showing an outline of processing executed by the learning device 3 in the first embodiment.
- the additional information generation unit 41 acquires the additional information Ia based on the additional information generation data D2 (step S23).
- the additional information generation unit 41 specifies the positional relationship between the display device 1 and the reference structure Rtag based on the additional information generation data D2, and generates additional information Ia according to the specified positional relationship.
- the additional information generation data D2 is a parameter of the feature inference device
- the additional information generation unit 41 inputs the captured image Im to the feature inference device configured based on the additional information generation data D2. Additional information Ia is acquired based on the inference result of.
- the process of acquiring the additional information Ia in step S23 may be performed before step S21 or before step S22.
- the symmetry object for feature extraction is not limited to the reference structure Rtag of a field such as a sport or a game, and the symmetry is not limited to n times symmetry and may have other symmetry.
- FIG. 13 (A) is a front view of the symmetric object 80 having translational symmetry
- FIG. 13 (B) is an enlarged view of the inside of the broken line frame 81 of the symmetric object 80.
- the target locations for feature extraction are indicated by broken line frames, and the first labels “1” to “14” attached to each location are clearly indicated.
- the symmetric object 80 is a ladder having seven steps here, and has translational symmetry for each step. Then, the joint portion of the vertical bar and the horizontal bar in each stage is defined as a target location for feature extraction.
- the second target portion on the left side is placed at the target location on the left side regardless of the number of stages in the symmetric object 80.
- the label "0" is attached, and the second label "1" is attached to the target location on the right side.
- the learning device 3 generates the feature extractor parameter D1 by learning the feature extractor based on the learning data D3 with the second label.
- the display device 1 analyzes the captured image Im showing the entire symmetric object 80 to generate additional information Ia indicating which stage each target portion corresponds to.
- the display device 1A transmits the upload signal "S1", which is information necessary for the server device 2 to perform the calibration process and the like, to the server device 2.
- the upload signal S1 includes, for example, the captured image Im generated by the imaging unit 15 and the output signal of the position / orientation detection sensor 16. Then, when the display device 1A receives the distribution signal "S2" transmitted from the server device 2, the display device 1A displays the virtual object by controlling the light emission of the light source unit 10 based on the distribution signal S2.
- the display device 1 is not limited to an AR device configured to be worn on the user's head.
- the display device 1 may be a display terminal such as a smartphone having a camera and a display display (display unit).
- the display device 1 has a display instead of the light source unit 1, and performs feature extraction of the reference structure Rtag on the landscape image captured by the imaging unit 15. Then, the display device 1 superimposes a virtual object corresponding to an image showing some information on the reference structure Rtag on the above landscape image and displays it on the display. Even in this case, the display device 1 can accurately extract the features of the reference structure Rtag and display the virtual object at an appropriate position.
- the feature point acquisition means 41A sets the position of the feature point of the symmetric object having symmetry and the first label peculiar to the feature point to the symmetry of the symmetry object based on the captured image “Im” captured by the imaging unit 15A. Obtain a combination with a second label defined to be integrated or modified based on.
- the feature point acquisition unit 41A can be a combination of the second label feature extraction unit 42 in FIG. 2 or the first label feature extraction unit 42ax and the second label determination unit 42ay in FIG.
- the label determining means 43A determines the first label to be attached to each of the feature points based on the additional information for breaking the symmetry and the second label.
- the label determining means 43A can be the first label determining unit 43 of FIG. 2 or FIG.
- FIG. 16 is an example of a flowchart executed by the display device 1A in the third embodiment.
- the feature point acquisition means 41A of the information processing device 4 acquires a combination of the position of the feature point of the symmetric object having symmetry and the second label based on the captured image Im captured by the imaging unit 15A (step). S41).
- the label determining means 43A of the information processing apparatus 4 determines the first label to be attached to each of the feature points based on the additional information for breaking the symmetry and the second label (step S42). ..
- Non-temporary computer-readable media include various types of tangible storage media.
- Examples of non-temporary computer-readable media include magnetic storage media (eg, flexible disks, magnetic tapes, hard disk drives), magneto-optical storage media (eg, magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, It includes a CD-R / W and a semiconductor memory (for example, a mask ROM, a PROM (Programmable ROM), an EPROM (Erasable PROM), a flash ROM, and a RAM (RandomAccessMemory)).
- Feature point acquisition means to acquire the combination of A storage medium for storing a program that functions a computer as a label determining means for determining the first label to be attached to each of the feature points based on the additional information for breaking the symmetry and the second label. ..
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Geometry (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
Description
(1)概略構成
図1は、第1実施形態に係る表示装置1の概略構成図である。表示装置1は、ユーザが装着可能な装置であり、例えば眼鏡型に構成されたシースルー型であって、ユーザの頭部に装着可能に構成されている。そして、表示装置1は、スポーツ観戦や劇(コンサートを含む)の観賞などにおいて、実在する風景に視覚情報を重ねて表示することで、拡張現実(AR:Augmented Reality)を実現する。上記の視覚情報は、2次元又は3次元により表された仮想のオブジェクトであり、以後では、「仮想オブジェクト」とも呼ぶ。なお、表示装置1は、ユーザの片眼にのみ仮想オブジェクトを表示してもよく、両眼に対して仮想オブジェクトを表示してもよい。
図2は、制御部17の機能的な構成を示すブロック図である。図2に示すように、制御部17は、機能的には、撮像画像取得部40と、付加情報生成部41と、第2ラベル特徴抽出部42と、第1ラベル決定部43と、調整部44と、表示制御部45と、を有する。以下に説明するように、制御部17は、撮像画像Imから抽出した特徴点に対し、付加情報Iaに基づき、付加すべき第1ラベルを決定する。これにより、制御部17は、対称性を有する基準構造物Rtagに対しても正確な特徴抽出処理を行う。なお、図2では、データの授受が行われるブロック同士を実線(かつデータの授受が必須でないブロック同士を破線)により結んでいるが、データの授受が行われるブロックの組合せは図2に限定されない。後述する他の機能ブロックの図においても同様である。
次に、図2において説明した制御部17の処理について、基準構造物Rtagをテニスコートとした例を用いて具体例に説明する。
ここで、特徴抽出器及び特徴物推論器の学習について説明する。
図8は、第1実施形態において学習装置3が実行する処理概要を示すフローチャートの一例である。
次に、上述した第1実施形態に好適な変形例について説明する。以下の変形例は、任意に組み合わせてもよい。
表示装置1は、特徴点の位置と当該特徴点が属する第1ラベルとに関する情報を出力するように学習された特徴抽出器の出力と、付加情報Iaとに基づき、各特徴点への正確な第1ラベルの付与を行ってもよい。
特徴抽出の対象となる対称物は、スポーツやゲームなどのフィールド等の基準構造物Rtagに限定されず、また、対称性はn回対称に限らず、他の対称性を有してもよい。
表示装置1が実行する処理を、表示装置1と通信を行うサーバ装置が実行してもよい。
表示装置1が使用される位置が基準構造物Rtagに対して相対的に予め定まっている場合には、付加情報Iaは、予め記憶部14に記憶されてもよい。この場合、第1ラベル決定部43は、記憶部14から付加情報Iaを読み出すことで取得する。この場合、付加情報生成部41は存在しなくともよい。
表示装置1は、ユーザの頭部に装着可能に構成されたARデバイスに限定されない。これに代えて、表示装置1は、カメラと表示ディスプレイ(表示部)を有するスマートフォンなどの表示端末であってもよい。この場合、表示装置1は、図1の構成において、光源ユニット1に代えてディスプレイを有し、撮像部15が撮像した風景の画像に対して基準構造物Rtagの特徴抽出等を行う。そして、表示装置1は、基準構造物Rtagに対して何らかの情報を示した画像に相当する仮想オブジェクトを、上記の風景の画像に重畳してディスプレイに表示する。この場合であっても、表示装置1は、基準構造物Rtagの特徴抽出を的確に行い、仮想オブジェクトを適切な位置に表示させることができる。
図15は、第3実施形態における情報処理装置4の概略構成を示す。図14に示すように、情報処理装置4は、特徴点取得手段41Aと、ラベル決定手段43Aとを有する。情報処理装置4は、例えば、表示装置1の制御部17又はサーバ装置2の制御部27により実現される。
撮像部が撮像した撮像画像に基づき、対称性を有する対称物の特徴点の位置と、当該特徴点に固有の第1ラベルを前記対称性に基づき統合又は変更するように定義された第2ラベルとの組合せを取得する特徴点取得手段と、
前記対称性を破るための付加情報と、前記第2ラベルとに基づき、前記特徴点の各々に対して付すべき前記第1ラベルを決定するラベル決定手段と、
を有する情報処理装置。
前記対称物と前記撮像部との位置関係に応じた前記付加情報を生成する付加情報生成手段を有する、付記1に記載の情報処理装置。
前記付加情報生成手段は、前記撮像部の装着者の座席情報又は前記撮像部の位置を示す位置情報に基づき、前記位置関係を認識する、付記2に記載の情報処理装置。
前記撮像画像に基づき、前記付加情報を生成する付加情報生成手段を有する、付記1に記載の情報処理装置。
前記付加情報生成手段は、前記撮像画像における、前記対称物の周辺に存在する特徴物と前記対称物との位置関係に基づき、前記付加情報を生成する、付記4に記載の情報処理装置。
前記特徴点取得手段は、入力された画像から前記第2ラベルと前記特徴点の位置との組合せを出力するように学習された特徴抽出器に前記撮像画像を入力することで、前記第2ラベルと前記特徴点の位置との組合せを取得する、付記1~5のいずれか一項に記載の情報処理装置。
前記対称物が撮像された学習画像において正解となる特徴点の位置及び第1ラベルの組合せを示す正解データの当該第1ラベルを、前記対称性に基づき統合又は変更した第2ラベルに変換するラベル変換手段と、
前記学習画像と、前記第2ラベルを含む前記正解データとに基づき、前記特徴抽出器の学習を行う学習手段と、
を有する付記6に記載の情報処理装置。
前記学習画像に基づき、前記対称物の対称性を判定する対称性判定手段をさらに有する、付記7に記載の情報処理装置。
前記特徴点取得手段は、入力された画像から前記第1ラベルと前記特徴点の位置との組合せを抽出するように構成された特徴抽出器に前記撮像画像を入力することで、前記第1ラベルと前記特徴点の位置との組合せを取得後、前記第1ラベルを前記対称性に基づき前記第2ラベルに変換することで、前記第2ラベルと前記特徴点の位置との組合せを取得する、付記1~8のいずれか一項に記載の情報処理装置。
前記撮像部と、
前記第1ラベル毎の特徴点の位置に基づき、風景に重ねて、又は撮像部が当該風景を撮像した画像に重ねて仮想オブジェクトを表示する表示部と、
を有する表示装置である、付記1~9のいずれか一項に記載の情報処理装置。
前記撮像部を有し、風景に重ねて仮想オブジェクトを表示する表示装置に対し、前記仮想オブジェクトを表示するための表示信号を送信するサーバ装置である、付記1~10のいずれか一項に記載の情報処理装置。
コンピュータにより、
撮像部が撮像した撮像画像から、対称性を有する対称物の特徴点の位置と、当該特徴点に固有の第1ラベルを前記対称性に基づき統合又は変更するように定義された第2ラベルとの組合せを取得し、
前記対称性を破るための付加情報と、前記第2ラベルとに基づき、前記特徴点の各々に対して付すべき前記第1ラベルを決定する、
制御方法。
撮像部が撮像した撮像画像から、対称性を有する対称物の特徴点の位置と、当該特徴点に固有の第1ラベルを前記対称性に基づき統合又は変更するように定義された第2ラベルとの組合せを取得する特徴点取得手段と、
前記対称性を破るための付加情報と、前記第2ラベルとに基づき、前記特徴点の各々に対して付すべき前記第1ラベルを決定するラベル決定手段
としてコンピュータを機能させるプログラムを格納する記憶媒体。
2 サーバ装置
3 学習装置
4 情報処理装置
10 光源ユニット
11 光学素子
12 通信部
13 入力部
14 記憶部
15 撮像部
16 位置姿勢検出センサ
Claims (13)
- 撮像部が撮像した撮像画像に基づき、対称性を有する対称物の特徴点の位置と、当該特徴点に固有の第1ラベルを前記対称性に基づき統合又は変更するように定義された第2ラベルとの組合せを取得する特徴点取得手段と、
前記対称性を破るための付加情報と、前記第2ラベルとに基づき、前記特徴点の各々に対して付すべき前記第1ラベルを決定するラベル決定手段と、
を有する情報処理装置。 - 前記対称物と前記撮像部との位置関係に応じた前記付加情報を生成する付加情報生成手段を有する、請求項1に記載の情報処理装置。
- 前記付加情報生成手段は、前記撮像部の装着者の座席情報又は前記撮像部の位置を示す位置情報に基づき、前記位置関係を認識する、請求項2に記載の情報処理装置。
- 前記撮像画像に基づき、前記付加情報を生成する付加情報生成手段を有する、請求項1に記載の情報処理装置。
- 前記付加情報生成手段は、前記撮像画像における、前記対称物の周辺に存在する特徴物と前記対称物との位置関係に基づき、前記付加情報を生成する、請求項4に記載の情報処理装置。
- 前記特徴点取得手段は、入力された画像から前記第2ラベルと前記特徴点の位置との組合せを出力するように学習された特徴抽出器に前記撮像画像を入力することで、前記第2ラベルと前記特徴点の位置との組合せを取得する、請求項1~5のいずれか一項に記載の情報処理装置。
- 前記対称物が撮像された学習画像において正解となる特徴点の位置及び第1ラベルの組合せを示す正解データの当該第1ラベルを、前記対称性に基づき統合又は変更した第2ラベルに変換するラベル変換手段と、
前記学習画像と、前記第2ラベルを含む前記正解データとに基づき、前記特徴抽出器の学習を行う学習手段と、
を有する請求項6に記載の情報処理装置。 - 前記学習画像に基づき、前記対称物の対称性を判定する対称性判定手段をさらに有する、請求項7に記載の情報処理装置。
- 前記特徴点取得手段は、入力された画像から前記第1ラベルと前記特徴点の位置との組合せを抽出するように構成された特徴抽出器に前記撮像画像を入力することで、前記第1ラベルと前記特徴点の位置との組合せを取得後、前記第1ラベルを前記対称性に基づき前記第2ラベルに変換することで、前記第2ラベルと前記特徴点の位置との組合せを取得する、請求項1~8のいずれか一項に記載の情報処理装置。
- 前記撮像部と、
前記第1ラベル毎の特徴点の位置に基づき、風景に重ねて、又は撮像部が当該風景を撮像した画像に重ねて仮想オブジェクトを表示する表示部と、
を有する表示装置である、請求項1~9のいずれか一項に記載の情報処理装置。 - 前記撮像部を有し、風景に重ねて仮想オブジェクトを表示する表示装置に対し、前記仮想オブジェクトを表示するための表示信号を送信するサーバ装置である、請求項1~10のいずれか一項に記載の情報処理装置。
- コンピュータにより、
撮像部が撮像した撮像画像から、対称性を有する対称物の特徴点の位置と、当該特徴点に固有の第1ラベルを前記対称性に基づき統合又は変更するように定義された第2ラベルとの組合せを取得し、
前記対称性を破るための付加情報と、前記第2ラベルとに基づき、前記特徴点の各々に対して付すべき前記第1ラベルを決定する、
制御方法。 - 撮像部が撮像した撮像画像から、対称性を有する対称物の特徴点の位置と、当該特徴点に固有の第1ラベルを前記対称性に基づき統合又は変更するように定義された第2ラベルとの組合せを取得する特徴点取得手段と、
前記対称性を破るための付加情報と、前記第2ラベルとに基づき、前記特徴点の各々に対して付すべき前記第1ラベルを決定するラベル決定手段
としてコンピュータを機能させるプログラムを格納する記憶媒体。
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2022514882A JP7364052B2 (ja) | 2020-04-13 | 2020-04-13 | 情報処理装置、制御方法及びプログラム |
| PCT/JP2020/016311 WO2021210046A1 (ja) | 2020-04-13 | 2020-04-13 | 情報処理装置、制御方法及び記憶媒体 |
| US17/916,823 US12354320B2 (en) | 2020-04-13 | 2020-04-13 | Information processing device, control method, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2020/016311 WO2021210046A1 (ja) | 2020-04-13 | 2020-04-13 | 情報処理装置、制御方法及び記憶媒体 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2021210046A1 true WO2021210046A1 (ja) | 2021-10-21 |
Family
ID=78084733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2020/016311 Ceased WO2021210046A1 (ja) | 2020-04-13 | 2020-04-13 | 情報処理装置、制御方法及び記憶媒体 |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US12354320B2 (ja) |
| JP (1) | JP7364052B2 (ja) |
| WO (1) | WO2021210046A1 (ja) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023119412A1 (ja) * | 2021-12-21 | 2023-06-29 | 日本電気株式会社 | 情報処理装置、制御方法及び記憶媒体 |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US12062201B2 (en) * | 2022-08-26 | 2024-08-13 | Adobe Inc. | Generating symmetrical repeat edits for images |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010104181A1 (ja) * | 2009-03-13 | 2010-09-16 | 日本電気株式会社 | 特徴点生成システム、特徴点生成方法および特徴点生成プログラム |
| JP2010272092A (ja) * | 2009-05-25 | 2010-12-02 | Canon Inc | 画像検索装置およびその方法 |
| JP2012038795A (ja) * | 2010-08-04 | 2012-02-23 | Nikon Corp | 検出条件最適化方法、プログラム作成方法、並びに露光装置及びマーク検出装置 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5728159B2 (ja) | 2010-02-02 | 2015-06-03 | ソニー株式会社 | 画像処理装置、画像処理方法及びプログラム |
-
2020
- 2020-04-13 WO PCT/JP2020/016311 patent/WO2021210046A1/ja not_active Ceased
- 2020-04-13 US US17/916,823 patent/US12354320B2/en active Active
- 2020-04-13 JP JP2022514882A patent/JP7364052B2/ja active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010104181A1 (ja) * | 2009-03-13 | 2010-09-16 | 日本電気株式会社 | 特徴点生成システム、特徴点生成方法および特徴点生成プログラム |
| JP2010272092A (ja) * | 2009-05-25 | 2010-12-02 | Canon Inc | 画像検索装置およびその方法 |
| JP2012038795A (ja) * | 2010-08-04 | 2012-02-23 | Nikon Corp | 検出条件最適化方法、プログラム作成方法、並びに露光装置及びマーク検出装置 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023119412A1 (ja) * | 2021-12-21 | 2023-06-29 | 日本電気株式会社 | 情報処理装置、制御方法及び記憶媒体 |
| JP7639942B2 (ja) | 2021-12-21 | 2025-03-05 | 日本電気株式会社 | 情報処理装置、制御方法及びプログラム |
Also Published As
| Publication number | Publication date |
|---|---|
| JPWO2021210046A1 (ja) | 2021-10-21 |
| US20230186591A1 (en) | 2023-06-15 |
| US12354320B2 (en) | 2025-07-08 |
| JP7364052B2 (ja) | 2023-10-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12072496B2 (en) | Information processing device, control method, and storage medium | |
| US10642564B2 (en) | Display system, display device, information display method, and program | |
| CN114642874B (zh) | 显示系统及服务器 | |
| EP3230693B1 (en) | Visual perception enhancement of displayed color symbology | |
| US8933965B2 (en) | Method for calculating light source information and generating images combining real and virtual images | |
| US20250037457A1 (en) | Image processing apparatus, image processing method, and program | |
| US20090237564A1 (en) | Interactive immersive virtual reality and simulation | |
| KR20230017837A (ko) | 분화를 포함하는 안경류 | |
| CN105589199A (zh) | 显示装置、显示装置的控制方法以及程序 | |
| JP2015502584A (ja) | 可搬装置、仮想現実システムおよび方法 | |
| CN107710284A (zh) | 用于在虚拟图像生成系统中更有效地显示文本的技术 | |
| US10665034B2 (en) | Imaging system, display apparatus and method of producing mixed-reality images | |
| US11778283B2 (en) | Video distribution system for live distributing video containing animation of character object generated based on motion of actors | |
| JP7364052B2 (ja) | 情報処理装置、制御方法及びプログラム | |
| TWI436270B (zh) | 虛擬望遠方法及其裝置 | |
| JP7775357B2 (ja) | プログラム、方法および情報処理装置 | |
| JP7293057B2 (ja) | 放射線量分布表示システムおよび放射線量分布表示方法 | |
| US12211228B2 (en) | Information processing device, control method, and storage medium | |
| JP7639942B2 (ja) | 情報処理装置、制御方法及びプログラム | |
| US12412298B2 (en) | Learning device, control method, and storage medium | |
| JP7568106B2 (ja) | 情報処理装置、制御方法及びプログラム | |
| KR20220000165A (ko) | 가상 현실 게임용 중계 화면 생성 방법 및 이를 수행하는 가상 현실 시스템 | |
| JP7643549B2 (ja) | 情報処理装置、制御方法及びプログラム | |
| WO2023281587A1 (ja) | 情報処理装置、制御方法及び記憶媒体 | |
| US20210312714A1 (en) | Method and system for practicing group formations using augmented reality |
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: 20930801 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2022514882 Country of ref document: JP Kind code of ref document: A |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20930801 Country of ref document: EP Kind code of ref document: A1 |
|
| WWG | Wipo information: grant in national office |
Ref document number: 17916823 Country of ref document: US |