WO2017161476A1 - Rating and advising for selection of augmented reality markers - Google Patents

Rating and advising for selection of augmented reality markers Download PDF

Info

Publication number
WO2017161476A1
WO2017161476A1 PCT/CN2016/076826 CN2016076826W WO2017161476A1 WO 2017161476 A1 WO2017161476 A1 WO 2017161476A1 CN 2016076826 W CN2016076826 W CN 2016076826W WO 2017161476 A1 WO2017161476 A1 WO 2017161476A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
sub
marker
user
creation system
Prior art date
Application number
PCT/CN2016/076826
Other languages
English (en)
French (fr)
Inventor
Kar-Wing Edward Lor
King Wai Chow
Laifa Fang
Original Assignee
Hong Kong Applied Science and Technology Research Institute Company Limited
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 Hong Kong Applied Science and Technology Research Institute Company Limited filed Critical Hong Kong Applied Science and Technology Research Institute Company Limited
Priority to PCT/CN2016/076826 priority Critical patent/WO2017161476A1/en
Priority to CN201680000108.8A priority patent/CN105830095B/zh
Publication of WO2017161476A1 publication Critical patent/WO2017161476A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • 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
    • G06V10/77—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
    • G06V10/771—Feature selection, e.g. selecting representative features from a multi-dimensional feature space
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
    • G06V10/993—Evaluation of the quality of the acquired pattern
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items

Definitions

  • the present invention relates to determining whether a sub-image selected from an image and suggested by a user of an augmented reality (AR) content creation system is suitable for use as a marker in an AR client application, and advising the user a more suitable sub-image in case the user-suggested sub-image is not suitable.
  • AR augmented reality
  • AR is a live view of a physical scene augmented with computer-generated virtual objects such as texts, graphics, sound, etc.
  • An AR client application processes a video image digitally to add one or more virtual objects thereto.
  • the AR client application matches the image content with reference images stored in the system. This process is generally referred to as image recognition. If a portion of the image is recognized to be a particular reference image, then the one or more virtual objects associated with this reference image are augmented to the image.
  • a reference image is also known as a marker.
  • a marker database in the AR client application is dedicated to store markers. The markers in the marker database are introduced or suggested by AR-content creators or editors.
  • An AR-content creator usually selects a portion of the image, i.e. a sub-image of the image, and requests an AR content creation system to use the sub-image as a marker.
  • the marker is to be used in image recognition, it is advantageous if the suggested sub-image bears some contextual properties that enable image recognition to robustly and reliably detect this suggested sub-image in a video image under consideration and identify this sub-image unambiguously. It is desirable if the AR-content creator can determine suitability of the suggested sub-image for AR applications.
  • US2015/0161168, US2015/0161174, US8645370, US2007/0237426 and US2011/0176724 provide different ranking methods for images, these methods are not directed to AR marker creation or marker suitability ranking.
  • US2015/0109337 provides a method for rating suitability, or “augmentability” , of an image to AR.
  • the augmentability of the image is based on light exposure of the image, the motion of the image capturing device, features in the image, and blurriness of the image.
  • the resultant rating output is fed back to a user for indicating augmentability of the image in AR applications.
  • augmentability advice is given, how to modify the image in order to enhance augmentability is not provided. As a result, the user is required to use a trial-and-error method in finding out an image suitable for AR.
  • the technique provides real-time feedback to a user such that identifying suitable markers for the AR marker creation becomes efficient.
  • the present invention is concerned with an AR content creation system
  • An aspect of the present invention is to provide a method for updating the marker database with a new marker by the AR content creation system when the user selects a first sub-image of an image and requests, at the user device, the AR content creation system to use the first sub-image as the new marker.
  • a suitability score of the first sub-image is computed.
  • the suitability score of any test image is used for rating feature richness of the test image and uniqueness of the test image against existing markers already stored in the marker database such that a first test image having a value of the suitability score higher than a second test image’s is more suitable than the second test image to be the new marker; .
  • the second sub-image, the suitability score thereof and the suitability score of the first sub-image are presented to the user through the user device.
  • real-time provision of an advice to the user is achieved by suggesting the user to use the second sub- image instead of the first sub-image as the new marker in updating the marker database so as to increase feature richness or uniqueness of the new marker.
  • the suitability score of any test image is computed by a computing process comprising identifying feature points of the test image and generating a signature of the test image according to the feature points.
  • the computing process further includes determining a feature-richness score for rating feature richness of the test image and determining a uniqueness score for rating uniqueness of the test image against the existing markers already stored in the marker database.
  • the feature-richness score is determined according to the number of the feature points.
  • the uniqueness score is determined by comparing the signature of the test image with signatures of the existing markers.
  • the search process is preferably set out as follows. Based on a first boundary enclosing a first portion of the image where the first portion is used as the first sub-image, a candidate sub-image for consideration to be the second sub-image is generated by outwardly expanding the first boundary to give a second boundary and forming the candidate sub-image as a second portion of the image enclosed by the second boundary. The generating of the candidate sub-image is repeated until one of the following two conditions is met. First, the candidate sub-image lastly generated has a value of the suitability score not less than the pre-determined threshold value. The lastly-generated candidate sub-image becomes the second sub-image. Second, a pre-determined number of candidate sub-images have been generated but none of the candidate sub-images generated has a value of the suitability score not less than the pre-determined threshold value. Then the second sub-image is not found.
  • FIG. 1 depicts a flowchart of updating the marker database in accordance with an exemplary embodiment of the present invention.
  • FIG. 2 depicts, in accordance with one embodiment of the present invention, a flowchart for illustrating generation of a suitability score for any test image.
  • FIG. 3A depicts a first bounding rectangle for generating a second bounding rectangle defining a candidate sub-image for consideration to be selected as a second sub-image.
  • FIG. 3B illustrates, by an example, forming a second bounding rectangle by expanding a first bounding rectangle horizontally with a center thereof as an anchor.
  • FIG. 3C illustrates, by an example, forming a second bounding rectangle by expanding a first bounding rectangle vertically with a center thereof as an anchor.
  • FIG. 3D illustrates, by an example, forming a second bounding rectangle by expanding a first bounding rectangle both horizontally and vertically with a center thereof as an anchor.
  • FIG. 3E illustrates, by an example, forming a second bounding rectangle by expanding a first bounding rectangle with a vertex thereof as an anchor.
  • FIG. 3F illustrates, by an example, forming a second bounding rectangle by expanding a first bounding rectangle with a side thereof as an anchor.
  • FIG. 4 depicts a mobile computing device used for implementing an AR client application and an AR contention creation system in accordance with one embodiment of the present invention.
  • FIG. 5 depicts, in accordance with one embodiment of the present invention, an AR content creation system comprising a user device, a marker database located in a computing cloud, and a computing server located in the computing cloud and communicable with the user device and the marker database.
  • An AR-content creator is a person who selects markers from video images, where the markers are intended to be used by an AR client application in image recognition. When the AR-content creator interacts with the AR content creation system such as inputting the markers into the system, the AR-content creator is a user of the AR content creation system.
  • a marker database is a database for storing markers. As the marker database is primarily used for image recognition, the contents of the marker database are any data that can help identify the markers in image recognition. Furthermore, each marker is associated with one or more virtual objects for augmentation with a video image when the individual marker is identified in this video image.
  • a marker database for storing markers hereby means a database containing (1) any data that can help identify the markers in image recognition, such as features, signatures, fingerprints, entire images, of the markers, or a combination thereof, and (2) optionally one or more virtual objects for each of the markers, or a pointer to another database containing the one or more virtual objects. Selecting which kinds of data to be stored in the marker database for the markers is determined by those skilled in the art according to actual situations.
  • a user device” in an AR content creation system is a device at least functioning as an interface between the AR content creation system and a user thereof.
  • the user device in most practical cases is realized by including one or more processors for performing computing and control functions, a display for displaying visual information to the user, and an input device for receiving inputs from the user.
  • Examples of a user device include an Internet-enabled desktop computer and a smartphone.
  • a mobile computing device is a portable electronic device having computing power and configured to provide wireless communications.
  • a mobile computing device may be a smartphone or a handheld tablet computer.
  • a cloud is construed and interpreted in the sense of cloud computing or, synonymously, distributed computing over a network unless otherwise specified.
  • a server is interpreted in the sense of computing.
  • a server is generally equipped with one or more processors for executing program instructions, and one or more storages for storing data.
  • a server may be a standalone computing server, or a distributed server in the cloud.
  • “A sub-image” of an image is a selected portion of the image. The sub-image is bounded by an (imaginary) boundary on the image where the boundary encloses the selected portion of the image.
  • An AR content creation system under consideration at least comprises a marker database for storing markers, and a user device at least functioning as an interface for communicating between the AR content creation system and a user.
  • An aspect of the present invention is to provide a method for updating the marker database with a new marker by the AR content creation system when the user selects a first sub-image of an image and makes a request to the AR content creation system to use the first sub-image as the new marker.
  • the user makes the request at the user device.
  • the first sub-image may be of any shape such as a rectangle, a polygon, a circle, or an ellipse.
  • FIG. 1 depicts a flowchart of updating the marker database in accordance with an exemplary embodiment of the present invention.
  • a suitability score of the first sub-image is computed (step 110) when the user makes the aforementioned request.
  • the suitability score of any test image is used for rating (1) feature richness of the test image and (2) uniqueness of the test image against existing markers already stored in the marker database. Abundance of features in the test image makes image recognition of the test image less prone to error, reducing both the chance of miss and the chance of false detection in the eventual image recognition process in the AR client application. If the test image is distinctive enough (i.e. sufficiently dissimilar) from all of the existing markers, the AR client application is less confused in image recognition of the test image.
  • the suitability score is defined to be positively correlated with the suitability of the test image for an AR client application.
  • a first test image having a value of the suitability score higher than a second test image’s is more suitable than the second test image to be the new marker. It is apparent to those skilled in the art that equivalently, the suitability score may also be defined to be negatively correlated with the suitability. Although the disclosure herein uses the first case of defining the suitability score for illustrating the present invention, the present invention encompasses both cases.
  • a threshold value is determined for the AR content creation system such that a test image having a suitability score less than the threshold value is deemed to be of low quality and is not suitable for use as a marker in an AR client application. Similarly, the test image is deemed to be suitable to be a marker in the AR client application if the suitability score of the test image is greater than or equal to this pre-determined threshold value.
  • the threshold value is determined by one skilled in the art according to an actual situation.
  • a step 114 the suitability score of first sub-image is compared with the threshold value. If this suitability score is greater than or equal to the threshold value, the marker database is updated with the first sub-image as the new marker (step 116) . Otherwise, a search process 180 is initiated.
  • the search process 180 is used to search for a second sub-image having a suitability score not less than the threshold value.
  • unsuitability is due to problems in feature richness and uniqueness, causing difficulty in image recognition. It follows that incorporating additional features that are distinctive enough to the first sub-image is a solution to the problems. If a portion of the image neighboring the first sub-image is added to the first sub-image, it is possible that the number of features in the resultant sub-image of the image is increased, leading to a resultant suitability score that is greater than the suitability score of the first sub-image. Therefore, the search process 180 is conducted under a constraint that the second sub-image completely contains the first sub-image.
  • a candidate sub-image for consideration to be the second sub-image is generated.
  • the generation of the candidate sub-image is based on a first boundary enclosing a first portion of the image where the first portion is used as the first sub-image.
  • the candidate sub-image is generated by outwardly expanding the first boundary to give a second boundary and by forming the candidate sub-image as a second portion of the image enclosed by the second boundary. After the candidate sub-image is generated, the suitability sore of this candidate sub-image is computed.
  • the step 120 is repeated until the candidate sub-image lastly generated has a value of the suitability score not less than the threshold value, or until a pre-determined number of candidate sub-images have been generated but none of the candidate sub-images generated has a value of the suitability score not less than the threshold value.
  • the termination of repeating the step 120 is controlled by the step 124 and 126.
  • the suitability score of the candidate sub-image generated in the step 120 is compared with the threshold value. If this suitability score is not less than the threshold value, the candidate sub-image lastly generated becomes the second sub-image (in the step 130) . Otherwise, the number of the candidate sub-images that have been generated is checked with the aforementioned pre-determined number in the step 126.
  • the step 120 is repeated in case the number of the candidate sub-images having been generated is still less than this pre-determined number.
  • step 120 If in the step 120 it is found that the pre-determined number of candidate sub-images is reached, then it is determined that the second sub-image is not found.
  • Other appropriate action (s) as determined by those skilled in the art according to actual situations are taken (step 128) .
  • the user may use one of the images previously tested with the highest score, even though it is below the threshold, or use some other criteria to select an appropriate image.
  • the AR content creation system may assist the user by presenting, to the user through the user device, one candidate sub-image having a highest suitability score among the candidate sub-images that have been generated.
  • the second sub-image, the suitability score thereof and the suitability score of the first sub-image are presented to the user through the user device (step 140) .
  • An advice is also provided to the user by suggesting the user to use the second sub-image instead of the first sub-image as the new marker in updating the marker database to increase feature richness or uniqueness of the new marker.
  • the presentation of the second sub-image, the suitability score thereof and the suitability score of the first sub-image is done substantially-immediately after the second sub-image is found in the search process 180. It follows that real-time provision of the advice to the user is achieved.
  • step 150 After the advice is provided to the user in the step 140, other follow-up actions as determined by those skilled in the art according to actual situations are proceeded (step 150) .
  • the AR content creation system requests the user to approve using the second sub-image as the new marker in updating the marker database.
  • FIG. 2 is a flowchart for illustrating generation of a suitability score for any test image according to one embodiment of the present invention.
  • a step 210 feature points of the test image are identified.
  • Each of the feature points is a point where the point and its neighborhood constitute distinctiveness against other points/pixel in the image.
  • a feature point is a corner appeared in the test image.
  • US2015/0213325 provides an example on a technique for identifying feature points.
  • a signature of the test image is generated according to the feature points identified in the step 210.
  • An example of generating the signature is provided in US2015/0227796, in which a fingerprint (corresponding to a signature) is generated based on salient points of an image (corresponding to feature points) .
  • a feature-richness score for rating feature richness of the test image is determined.
  • the feature-richness score is determined according to the number of the feature points identified in the step 210.
  • the feature-richness score is a monotonic increasing function of the number of the feature points. A greater number of the feature points yields a higher feature-richness score.
  • a uniqueness score for rating uniqueness of the test image against the existing markers already stored in the marker database is determined.
  • the uniqueness score is determined by comparing the signature of the test image with signatures of the existing markers. If the signature of the test image is close to or similar to any of the signatures of the existing markers, the uniqueness score is low. A low uniqueness score indicates that in image recognition, the AR content creation system is easy to confuse the test image and at least one of the markers already stored in the marker database, leading to image-recognition error in performing AR.
  • S SUI is the suitability score
  • S FR is the feature-richness score
  • S UNI is the uniqueness score
  • ⁇ and ⁇ are non-zero positive numbers functioning as weighting factors for S FR and S UNI , respectively
  • f (S, c) is a monotonic increasing function of a score S.
  • the generation of the candidate sub-image in the step 120 is realized as follows. Regardless of the shape of the first boundary for the first sub-image, there is a bounding shape that bounds the first boundary on the image. For example, if the bounding shape is a rectangle, expanding the bounding rectangle into a bigger bounding rectangle that contains the former bounding rectangle gives a proportional expansion to the first boundary. The first boundary after this proportional expansion gives the second boundary that defines the candidate sub-image that is generated.
  • the aforesaid bounding rectangle is named as a first bounding rectangle, and the resultant bounding rectangle after expansion is called as a second bounding rectangle.
  • FIG. 3A depicts a first bounding rectangle 310 used for generating a second bounding rectangle 315.
  • the first bounding rectangle 310 has four vertices 371-374, four sides 376-379, and a center 370.
  • a candidate sub-image is defined by a second bounding rectangle 315 expanded from the first bounding rectangle 310.
  • the first bounding rectangle 310 is outwardly expanded to yield the second bounding rectangle 315 through one of the following geometric operations.
  • an anchor is a point or a line which is held stationary in geometrically expanding the first bounding rectangle 310 into the second bounding rectangle 315.
  • the first bounding rectangle 310 is expanded horizontally with the center 370 as an anchor 331 of geometric operation, forming a second bounding rectangle 321.
  • the first bounding rectangle 310 is expanded vertically with the center 370 as an anchor 332 of geometric operation, forming a second bounding rectangle 322.
  • the first bounding rectangle 310 is expanded both horizontally and vertically with the center 370 as an anchor 333 of geometric operation, forming a second bounding rectangle 323.
  • the first bounding rectangle 310 is expanded with the vertex 374 as an anchor 334 of geometric operation, forming a second bounding rectangle 324. Any of the other three vertices 371-373 may also be the anchor 334.
  • the first bounding rectangle 310 is expanded with the side 378 as an anchor 335 of geometric operation, forming a second bounding rectangle 325. Any of the other three sides 376, 377 and 379 may also be the anchor 335.
  • the rectangular bounding shape mentioned above is used as one example for illustration only. Other bounding shapes may be used instead of the rectangular bounding shape.
  • a circular bounding shape may be used.
  • the circular bounding shape i.e. a circle, can be expanded by using, e.g., the centre of the circle or a point on the circumference of the circle, as an anchor.
  • an AR content creation system using one of the embodiments of the method disclosed above is implemented in a standalone mobile computing device.
  • the mobile computing device also acts as a user interface for communicating with the user.
  • the mobile computing device is also used for an AR client application.
  • FIG. 4 depicts an example of the mobile computing device for implementing the AR content creation system.
  • a mobile computing device 410 comprises a display 470 for displaying information sent from an AR client application, an input means 480 for receiving inputs from a user (input can be received via a touch sensor, a keypad, or some other means such as voice) , one or more storages 450 for installing a marker database 455, and one or more processors 460 for performing the steps 110, 114, 116 and the search process 180 and for instructing the display 470 to display the advice in the step 140.
  • an AR content creation system adopting an embodiment of the method disclosed above is implemented by including a user device, a marker database, and a computing server communicable with the user device and the marker database, where the marker database and the computing server are remotely located from the user device.
  • the user device may be a desktop computer connected to the computing server through a wired connection, or may be a mobile computing device wirelessly communicating with the computing server.
  • FIG. 5 depicts yet another practical implementation of an AR content creation system configured to execute a process according to an embodiment of the method disclosed above.
  • An AR content creation system 500 comprises a user device 510, a marker database 540, and a computing server 530 communicable with the user device 510 and the marker database 540.
  • the user device 510 is connected to the computing service 530 via a communication link 515.
  • the user device 510 is a desktop computer.
  • the user device 510 is a mobile computing device such that the communication link 515 is a wireless link. In both options, it is not desirable to overload the communication link 515. As will soon be evidenced, the AR content creation system depicted in FIG. 5 is configured to avoid this overloading problem.
  • the computing server 530 and the marker database 540 are located in a computing cloud 520.
  • a local copy of the image is stored in the computing server 530.
  • coordinates of the first sub-image on the image are sent from the user device 510 to the computing server 530 via the communication link 515 without a need to send the first sub-image thereto.
  • the computing server 530 then creates a local copy of the first sub-image based on the received coordinates and the local copy of the image. It follows that communication burden on the communication link 515 due to transmitting the first sub-image to the computing server 530 is avoided.
  • the computing of the suitability score of any test image and the executing of the search process 180 to search for the second sub-image are performed by the computing server 530.
  • coordinates of the second sub-image are transmitted to the user device 510.
  • the user device 510 is then able to reconstruct a local copy of the second sub-image, thereby avoiding another communication burden on the communication link 515 due to transmitting the second sub-image to the user device 510.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Library & Information Science (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Processing Or Creating Images (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
PCT/CN2016/076826 2016-03-21 2016-03-21 Rating and advising for selection of augmented reality markers WO2017161476A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2016/076826 WO2017161476A1 (en) 2016-03-21 2016-03-21 Rating and advising for selection of augmented reality markers
CN201680000108.8A CN105830095B (zh) 2016-03-21 2016-03-21 用于选择增强现实标记的评级和建议

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/076826 WO2017161476A1 (en) 2016-03-21 2016-03-21 Rating and advising for selection of augmented reality markers

Publications (1)

Publication Number Publication Date
WO2017161476A1 true WO2017161476A1 (en) 2017-09-28

Family

ID=56532315

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/076826 WO2017161476A1 (en) 2016-03-21 2016-03-21 Rating and advising for selection of augmented reality markers

Country Status (2)

Country Link
CN (1) CN105830095B (zh)
WO (1) WO2017161476A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102428921B1 (ko) * 2017-09-22 2022-08-04 삼성전자주식회사 Ar 서비스를 제공하는 방법 및 디바이스

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013044983A1 (en) * 2011-09-30 2013-04-04 Layar B.V. Feedback to user for indicating augmentability of an image
WO2015065854A1 (en) * 2013-10-28 2015-05-07 Google Inc. Image cache for replacing portions of images
CN105282393A (zh) * 2014-06-16 2016-01-27 柯尼卡美能达株式会社 在文档中插入标记的图像处理装置

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2014144035A1 (en) * 2013-03-15 2014-09-18 Brian Adams Ballard Method and system for representing and interacting with augmented reality content
CN103310099A (zh) * 2013-05-30 2013-09-18 佛山电视台南海分台 一种利用图像捕获和识别技术实现增强现实的方法和系统

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2013044983A1 (en) * 2011-09-30 2013-04-04 Layar B.V. Feedback to user for indicating augmentability of an image
WO2015065854A1 (en) * 2013-10-28 2015-05-07 Google Inc. Image cache for replacing portions of images
CN105282393A (zh) * 2014-06-16 2016-01-27 柯尼卡美能达株式会社 在文档中插入标记的图像处理装置

Also Published As

Publication number Publication date
CN105830095B (zh) 2019-03-01
CN105830095A (zh) 2016-08-03

Similar Documents

Publication Publication Date Title
US11710279B2 (en) Contextual local image recognition dataset
US10311115B2 (en) Object search method and apparatus
US10496694B2 (en) Rating and advising for selection of augmented reality markers
US9607584B2 (en) Real world analytics visualization
EP2972950B1 (en) Segmentation of content delivery
EP3340615B1 (en) Method and system for visually and remotely controlling touch-enabled device, and relevant device
CN103345516A (zh) 基于应用程序图标的应用程序搜索方法和系统
US20130328760A1 (en) Fast feature detection by reducing an area of a camera image
US20230237777A1 (en) Information processing apparatus, learning apparatus, image recognition apparatus, information processing method, learning method, image recognition method, and non-transitory-computer-readable storage medium
CN112817447B (zh) 一种ar内容显示方法及系统
US20200097568A1 (en) Fashion by trend user interfaces
CN106202222B (zh) 热点事件的确定方法及装置
WO2017161476A1 (en) Rating and advising for selection of augmented reality markers
KR101319667B1 (ko) 증강현실 제공 시스템 및 그 방법과 이에 사용되는 관심 영역 트래킹 방법 및 단말기
US20170277722A1 (en) Search service providing apparatus, system, method, and computer program
CN108304104B (zh) 一种数据获取方法及其设备、存储介质、终端
US11093804B1 (en) Information processing apparatus and non-transitory computer readable medium storing program
US20200034984A1 (en) Learning template representation libraries
CN116580212B (zh) 图像生成方法、图像生成模型的训练方法、装置和设备
KR101599692B1 (ko) Pca 기법을 활용한 어휘의 시각화 방법 및 그 장치
US20240027205A1 (en) Terminal apparatus and method
JP2017224013A (ja) 表示制御システム、表示制御方法、および表示制御プログラム
CN115004131A (zh) 设备和设备定位方法
JP2024084183A (ja) 情報処理装置、情報処理方法及びプログラム
JP2023134183A (ja) 認識装置、認識処理方法、及びプログラム

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 16894835

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16894835

Country of ref document: EP

Kind code of ref document: A1