WO2023054996A1 - Dispositif vestimentaire de reconnaissance d'objet utilisant un suivi de main ou de doigt - Google Patents
Dispositif vestimentaire de reconnaissance d'objet utilisant un suivi de main ou de doigt Download PDFInfo
- Publication number
- WO2023054996A1 WO2023054996A1 PCT/KR2022/014331 KR2022014331W WO2023054996A1 WO 2023054996 A1 WO2023054996 A1 WO 2023054996A1 KR 2022014331 W KR2022014331 W KR 2022014331W WO 2023054996 A1 WO2023054996 A1 WO 2023054996A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- user
- finger
- hand
- control module
- wearable device
- Prior art date
Links
- 239000000284 extract Substances 0.000 claims description 13
- 230000005236 sound signal Effects 0.000 claims 1
- 235000015220 hamburgers Nutrition 0.000 description 38
- 230000001771 impaired effect Effects 0.000 description 18
- 241000287828 Gallus gallus Species 0.000 description 9
- 235000019987 cider Nutrition 0.000 description 9
- 235000013550 pizza Nutrition 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 238000000034 method Methods 0.000 description 8
- 235000016795 Cola Nutrition 0.000 description 7
- 235000011824 Cola pachycarpa Nutrition 0.000 description 7
- 239000000853 adhesive Substances 0.000 description 6
- 230000001070 adhesive effect Effects 0.000 description 6
- 238000007781 pre-processing Methods 0.000 description 5
- 230000003190 augmentative effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000001681 protective effect Effects 0.000 description 3
- 239000000571 coke Substances 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
- A61F9/00—Methods or devices for treatment of the eyes; Devices for putting-in contact lenses; Devices to correct squinting; Apparatus to guide the blind; Protective devices for the eyes, carried on the body or in the hand
- A61F9/08—Devices or methods enabling eye-patients to replace direct visual perception by another kind of perception
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/16—Constructional details or arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/16—Constructional details or arrangements
- G06F1/1613—Constructional details or arrangements for portable computers
- G06F1/163—Wearable computers, e.g. on a belt
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/013—Eye tracking input arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
- G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B21/00—Teaching, or communicating with, the blind, deaf or mute
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B21/00—Teaching, or communicating with, the blind, deaf or mute
- G09B21/001—Teaching or communicating with blind persons
- G09B21/006—Teaching or communicating with blind persons using audible presentation of the information
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L13/00—Speech synthesis; Text to speech systems
Definitions
- the present invention relates to a wearable device for recognizing an object using hand and/or finger tracking, and more specifically, to tracking a user's hand and/or finger and simultaneously tracking an object identified from a forward image according to a user's gaze direction
- the present invention relates to a wearable device for object recognition capable of informing a user of an identification result of an object indicated by a user's hand and/or a finger by voice.
- AR augmented reality
- VR virtual reality
- augmented reality technology is a technology that superimposes virtual objects on the real world that a user sees with real eyes. can do.
- a user working in a work environment where the field of view is extremely limited needs to easily identify objects (eg, pictures, figures, texts or objects, etc.), or visually impaired people who are visually impaired or unable to.
- objects eg, pictures, figures, texts or objects, etc.
- visually impaired people who are visually impaired or unable to.
- the above-mentioned augmented reality technology that is, a technology that superimposes a virtual object on the real world that the user sees with his or her eyes, may be less effective.
- Patent Document 1 Korean Registered Patent Publication No. 10-1823121 (2018. 01. 29 announcement).
- Patent Document 1 discloses a glasses-type character recognition device for the visually impaired that is worn in the form of glasses by a user, analyzes a photographed image, recognizes a character, and guides the user through an auditory signal so that the user can read a character book other than a braille book. has been initiated.
- Patent Literature 1 has extremely limited possibilities for selection by the user.
- a user wearing the text recognition device disclosed in Patent Document 1 can only receive a voice signal converted based on text extracted from an image captured by a photographing unit, and an object located in front that is difficult for the user to see or cannot see. There is a limit to not being able to help you find the location of .
- Patent Document 1 Korea Patent Registration No. 10-1823121 (2018. 01. 29 announcement)
- various wearable devices for recognizing objects including conventional text recognition devices for the visually impaired, have limitations in that they can operate only in specific situations or cannot reflect a user's selection in object recognition results.
- an object of the present invention is to provide a wearable device for recognizing an object capable of guiding a user with a voice of an identification result for an object indicated by a user among objects identified from a forward image according to a user's gaze direction. do.
- the floor desired by the visually impaired person is displayed through the object identification information recognized by the wearable device worn by the visually impaired person. It is an object of the present invention to provide a wearable device for recognizing an object capable of helping the visually impaired to press a button and helping a visually impaired person to touch a desired button without the help of a third party in a touch screen kiosk without voice guidance. can be called a purpose.
- the body wearable on the user's face; a photographing module provided in the main body to obtain an image of a front side in a direction of gaze of a user wearing the main body; a control module that identifies an object included in the image obtained from the photographing module and converts an identification result of the object indicated by a user into a voice signal;
- a wearable device for recognizing objects including; and a guide module outputting the voice signal converted by the control module.
- the object may include at least one selected from pictures, figures, texts, and objects.
- the control module may extract an identification area including the object and an object included in the identification area from the image obtained from the photographing module.
- control module may identify a hand or an arbitrary finger of the user located in the front according to the gaze direction of the user wearing the main body from the image obtained from the photographing module. At the same time, the control module may track the movement of the user's hand or any finger and convert an identification result of an object indicated by the user's hand or any finger into a voice signal.
- control module may include a plurality of first coordinates respectively corresponding to positions of a plurality of objects identified from an image obtained from the photographing module and second coordinates corresponding to a position of a user's hand or an arbitrary finger. can be extracted.
- control module is located at the first coordinate located at the closest distance to the second coordinate corresponding to the position of the user's hand or any finger among the plurality of first coordinates respectively corresponding to the positions of the plurality of objects.
- the identification result for the object of can be converted into a voice signal.
- control module is configured to select a random object located at a first coordinate located at a nearest distance from a second coordinate corresponding to a position of a user's hand or a finger among a plurality of first coordinates respectively corresponding to positions of a plurality of objects.
- An object identification result and direction information for a user's hand or an arbitrary finger to reach the arbitrary object may be converted into a voice signal.
- control module extracts a first coordinate corresponding to a position of an object identified from an image obtained from the photographing module and a second coordinate corresponding to a position of a user's hand or an arbitrary finger.
- direction information for a user's hand or an arbitrary finger to reach an arbitrary object located at the first coordinates may be converted into a voice signal.
- location information on a detailed configuration of an object may be provided to a user by using an adhesive member on which at least one of predetermined pictures, figures, and characters is written.
- the main body may further include an input module for receiving a user's voice signal.
- the control module may derive a command from the voice signal received from the input module, and convert an object identification result based on the command into a voice signal.
- the wearable device for recognizing an object according to the present invention is operable only in a specific situation or has limitations in that a user's selection cannot be reflected in an object recognition result.
- the floor button that the visually impaired person wants to press through the object identification information recognized by the wearable device worn by the visually impaired person It is possible to help the user to press a desired layer without much difficulty by guiding the user with information about the position of the , in which direction the finger can be moved, and the like.
- a visually impaired person can receive button information displayed on the touch screen without the help of a third party, and in which direction and how far a finger can be touched to touch a desired button. You might get information about whether you can move or not.
- a wearable device for recognizing an object provides the user with information for finding the location of the adhesive member so that the user can efficiently and conveniently determine the detailed configuration of the object. can access
- FIG. 1 is a schematic diagram of a wearable device for object recognition according to an embodiment of the present invention.
- FIG. 2 schematically illustrates an example of an object recognition sequence using the wearable device shown in FIG. 1 .
- FIG. 3 schematically illustrates another example of an object recognition sequence using the wearable device shown in FIG. 1 .
- FIG. 4 schematically illustrates another example of an object recognition sequence using the wearable device shown in FIG. 1 .
- instruction means that a user's hand and/or finger points in a direction closest to an object and a direction for reaching an object.
- a wearable device for object recognition includes a main body wearable on a user's face; a photographing module provided in the main body to obtain an image of a front side in a direction of gaze of a user wearing the main body; a control module that identifies an object included in the image obtained from the photographing module and converts an identification result of the object indicated by a user into a voice signal; and a guide module outputting the voice signal converted by the control module.
- the main body is not particularly limited, but preferably has a shape that is easy for the user to wear.
- the main body may be provided in the form of eyeglasses or may be provided in a form attachable to accessories such as glasses worn by a user or a hat.
- the main body will not be limited by its type or shape as long as it is capable of being directly or indirectly worn on the user's face while being equipped with a photographing module, a control module, and a guide module, which will be described later.
- the main body is provided with a photographing module that acquires an image of the front according to the user's gaze direction. If the body is provided in the form of eyeglasses, the photographing module is attached to the front of the eyeglasses to capture a front image in a direction in which a user wearing the body gazes.
- the photographing module may operate when a user's photographing command is input from an input module to be described later, or may operate to obtain a front image at all times regardless of a user's command.
- the main body is provided with a control module that identifies an object included in the image acquired from the photographing module and converts an identification result of the object indicated by the user into a voice signal.
- the control module may include hardware and software designed to enable the wearable device of the present application to perform object recognition and a guiding operation according to the object recognition result.
- not only the photographing module and the guidance module are connected to the control module, but also a power module for supplying power may be connected.
- the control module identifies an object included in the image obtained from the photographing module, and at this time, the object may include at least one selected from pictures, figures, texts, and objects. That is, the user wearing the wearable device can identify pictures, figures, texts and/or objects included in the image obtained from the photographing module and inform the user of the result of the identification. Even in a situation where the front is not identified, it is possible to check which pictures, figures, characters, and/or objects exist anywhere in front of the user.
- the control module may operate to extract an identification area including the object and an object included in the identification area from an image obtained from the photographing module.
- control module may perform pre-processing on the image acquired from the photographing module in order to increase the discrimination of the object.
- Pre-processing of the image may include, for example, white balance adjustment, gray scale conversion, and/or noise removal.
- the control module converts an object identification result into a voice signal according to a user's instruction, and the voice signal is output through a separately provided guidance module.
- the guide module may be provided as an audio output means such as a speaker, earphone, or headphone.
- the speaker is preferably provided in a position close to the ear of a user wearing the same among the main body.
- Image acquisition, object identification, and guidance through the photographing module, control module, and guide module may operate once when a user's command is input or may be repeatedly operated multiple times in real time.
- the main body may further include an input module for receiving a user's voice signal, and in one example, the input module may be provided as a microphone.
- the input module is provided as a microphone, the microphone is preferably provided in a position close to the mouth of a user wearing the input module.
- Another example of the input module is a button provided to transmit a specific command, an external input device, and the like.
- a wearable device derives a command from a user's voice signal, but is not limited thereto.
- a specific command may be input to the wearable device using a predetermined input device.
- FIG. 2 schematically illustrates an example of an object recognition sequence using the wearable device shown in FIG. 1 .
- a method of recognizing an object by the wearable device according to the sequence shown in FIG. 2 and informing the user of the result will be described.
- the wearable device may collect a user's voice signal.
- the control module derives a command from the voice signal received from the input module, and if the derived command is “Notify me of all texts (located in the foreground)”, “Inform me of all pictures (located in the foreground)”, “( In the case of "Notify me of all figures (located in the front)” or “Notify me of all objects (located in the front)", the shooting signal may be transmitted to the shooting module so that the shooting module can acquire an image of the front according to the user's gaze direction. there is.
- control module may perform the function of the command derived according to a predetermined characteristic value once or repeatedly perform it multiple times.
- the control module may selectively perform pre-processing before identifying an object from the image acquired by the photographing module, and may extract an identification area including an object and an object included in the identification area from the image.
- control module may extract and identify objects such as text, pictures, figures, and objects from images.
- objects such as text, pictures, figures, and objects
- OCR optical character reader
- object detection or a technology that performs functions equivalent thereto may be utilized, but is not limited thereto.
- control module identifies the object extracted from the image, and converts the identification result into text.
- control module may vary the type of object to be identified, such as text, picture, figure, or object, according to a command derived from a voice signal, but is not limited thereto.
- control module displays the text “hamburger, chicken, spaghetti, pizza, cola, cider” generate
- the text “hamburger, chicken, spaghetti, pizza, cola, cider” generated by the control module may be converted into a voice signal through a Text To Speech (TTS) method and then output by the guidance module.
- TTS Text To Speech
- control module controls Generates the text "Hamburger, Chicken, Spaghetti, Pizza, Coke, Cider”.
- the control module may generate text corresponding to the picture, figure or object.
- the text “hamburger, chicken, spaghetti, pizza, cola, cider” corresponding to the picture, figure or object may be generated from the image search result for the picture, figure or object, and the text “hamburger, chicken, spaghetti , pizza, cola, cider” may be converted into a voice signal through a Text To Speech (TTS) method and outputted by the guidance module.
- TTS Text To Speech
- FIG. 3 schematically illustrates another example of an object recognition sequence using the wearable device shown in FIG. 1 .
- a method of recognizing an object by the wearable device according to the sequence shown in FIG. 3 and informing the user of the result will be described.
- the wearable device may collect a user's voice signal.
- the control module derives a command from the voice signal received from the input module, and if the derived command is "Tell me a text close to the index finger", “Tell me a picture close to the index finger”, “Tell me a figure close to the index finger”.
- a photographing signal may be transmitted to the photographing module so that the photographing module may obtain an image of the front according to the user's gaze direction.
- the control module may selectively perform pre-processing before identifying an object from the image acquired by the photographing module, and may extract an identification area including an object and an object included in the identification area from the image.
- control module identifies the object extracted from the image, and converts the identification result into text.
- the control module identifies the object extracted from the image and converts the identification result into text as described above.
- the control module generates a plurality of first coordinates respectively corresponding to positions of a plurality of objects identified from images obtained from the photographing module.
- control module identifies a user's hand or an arbitrary finger located in the front according to the gaze direction of the user wearing the main body from the image obtained from the photographing module. That is, when the word "index finger” is identified from the command input by the user, the control module identifies the position of the user's "index finger” in the image and extracts it as the second coordinate.
- control module compares the distance between a plurality of first coordinates respectively corresponding to the positions of the plurality of objects and the second coordinate corresponding to the position of the user's “index finger”, and located at the closest distance to the “index finger”.
- the identification result of an arbitrary object located at the first coordinate is converted into a voice signal.
- the control module displays “hamburger, chicken, spaghetti , Pizza, Coke, Cider” is generated, and first coordinates for each text are generated.
- the first coordinate may be an intermediate coordinate value of an identification area including each text, but is not necessarily limited thereto, and is set according to a predetermined criterion to mutually distinguish the positions of a plurality of texts included in an image. can be a value
- control module generates second coordinates for the position of the user's "index finger” among images acquired in real time from the photographing module through a hand tracking or finger tracking technique.
- the control module converts the text “hamburger” or “the one closest to the index finger is a hamburger” into a voice signal through the Text To Speech (TTS) method.
- TTS Text To Speech
- control module may simultaneously convert a text corresponding to a first coordinate located closest to a second coordinate among a plurality of first coordinates and a position thereof into a voice signal.
- control module may respond with “hamburger is upper left of the index finger” or A voice signal such as "The hamburger is at the 10 o'clock position of the index finger” can be generated.
- FIG. 4 schematically illustrates another example of an object recognition sequence using the wearable device shown in FIG. 1 .
- a method of recognizing an object by the wearable device according to the sequence shown in FIG. 4 and informing the user of the result will be described.
- the wearable device may collect a user's voice signal.
- the control module derives a command from the voice signal received from the input module, and if the derived command is "tell me the location of (arbitrary object name)", the photographing module performs an image on the front according to the user's gaze direction.
- a photographing signal may be transmitted to the photographing module so as to acquire .
- the control module may selectively perform pre-processing before identifying an object from the image acquired by the photographing module, and may extract an identification area including an object and an object included in the identification area from the image.
- control module identifies the object extracted from the image, and converts the identification result into text.
- the control module identifies the object extracted from the image and converts the identification result into text as described above.
- the derived commands are “Give me the location of the text (arbitrary object name)”, “Give me the location of the picture (arbitrary object name)”, “Give me the location of the figure (arbitrary object name)”, “Object (arbitrary object name) If it includes object characteristics such as "tell me the location", the control module may select and identify a specific object.
- the control module generates first coordinates corresponding to a location of an “object” designated by a user among a plurality of objects identified from an image obtained from the photographing module.
- control module identifies a user's hand or an arbitrary finger located in the front according to the gaze direction of the user wearing the main body from the image obtained from the photographing module. That is, the control module identifies the position of the user's hand or fingers in the image, and extracts the position as a plurality of second coordinates (eg, the second coordinate corresponding to the user's index finger, middle finger, etc. can be generated). there is).
- control module compares the distance between the first coordinate corresponding to the position of the "object” designated by the user and the plurality of second coordinates corresponding to the position of the user's hand or any finger, and A finger located at a second coordinate located closest to " is identified, and the direction for the identified finger to reach the "object" is converted into a voice signal.
- control module determines whether “hamburger” exists among the object identification results for the image and, if "hamburger” exists among the object identification results, " A first coordinate corresponding to the location of "hamburger” is created.
- the control module then tracks the location of the user's fingers from the image and generates second coordinates for each finger. If the user's "index finger” is located closest to the text "hamburger", and the user's “index finger” is located in the lower left corner of the text "hamburger”, the control module will display “hamburger is at the upper right of the index finger", “hamburger is It can generate voice signals such as "You are at the 2 o'clock position of your index finger”, "You are at the upper right of your index finger”, or "You are at the 2 o'clock position of your index finger”.
- the control module uses real-time finger tracking technology to say “hamburger is above the index finger”, “hamburger is located at the 12 o'clock position of the index finger” It generates voice signals such as "There is”, “It is on the index finger” or “It is at the 12 o'clock position of the index finger”.
- the control module extracts one second coordinate corresponding to the specific finger and assigns it to the "object” designated by the user. It is compared with the first coordinate corresponding to the position of the user, and the direction for the user's specific finger to reach the first coordinate may be converted into a voice signal.
- control module determines whether "hamburger” exists among the object identification results for the image and "hamburger” among the object identification results. If exists, first coordinates corresponding to the location of the "hamburger" are generated.
- the control module generates second coordinates by tracking the location of the user's index finger from the image. If the user's "index finger” is located to the lower left of the text "hamburger”, the control module will say “hamburger is at the upper right of the index finger”, “hamburger is at the 2 o'clock position of the index finger”, “upper right of the index finger” “ or "You are at the 2 o'clock position of your index finger”.
- the control module uses real-time finger tracking technology to say “hamburger is above the index finger”, “hamburger is located at the 12 o'clock position of the index finger” It generates voice signals such as "There is”, “It is on the index finger” or “It is at the 12 o'clock position of the index finger”.
- the user may designate a specific finger or hand in advance, and the above-mentioned "tell me the location of (arbitrary object name)", “tell me the location of text (arbitrary object name)", “picture (arbitrary object name) location”
- the above-mentioned "tell me the location of (arbitrary object name)", “tell me the location of text (arbitrary object name)", “picture (arbitrary object name) location”
- a plurality of second coordinates for a hand or an arbitrary finger in commands such as "Give me a location of a figure (arbitrary object name)", “Give me a location of an object (arbitrary object name)", a specified hand or a specified
- the second coordinates of the finger may be extracted and compared with the first coordinates corresponding to the location of the object designated by the user, and the direction for the hand or finger designated by the user to reach the first coordinate may be converted into a voice signal.
- a wearable device may provide specific location information to a user by using an adhesive member on which a predetermined picture, figure, and/or text is written.
- an identification result and location information on the handle which is a detailed part of the knife, may be provided.
- control module can use fewer resources or output results faster when identifying an object.
- a wearable device for recognizing an object may deliver an identification result and location information of an arbitrary object. Therefore, even in an environment where it is difficult to receive a user's voice signal due to noise, etc., it is possible to guide the user to accurately find a desired object.
- the wearable device for recognizing an object not only guides the user with information on an object identified from a forward image according to the user's gaze direction, but also guides the user to the object indicated by the user. There is an advantage in that it is possible to guide the identification result for the user by voice.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Biomedical Technology (AREA)
- Acoustics & Sound (AREA)
- Educational Administration (AREA)
- Computational Linguistics (AREA)
- Veterinary Medicine (AREA)
- Educational Technology (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Vascular Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Business, Economics & Management (AREA)
- Ophthalmology & Optometry (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
La présente invention se rapporte à un dispositif vestimentaire de reconnaissance d'objet utilisant un suivi de main et/ou de doigt, et, plus précisément, à un dispositif vestimentaire de reconnaissance d'objet apte à suivre la main et/ou le doigt d'un utilisateur et, simultanément, à guider, vocalement, vers l'utilisateur, un résultat d'identification concernant un objet indiqué par la main et/ou le doigt de l'utilisateur parmi des objets identifiés à partir d'une image de face en fonction de la direction du regard de l'utilisateur.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2021-0129572 | 2021-09-30 | ||
KR1020210129572A KR102629771B1 (ko) | 2021-09-30 | 2021-09-30 | 손 또는 손가락 추적을 이용한 객체 인식용 웨어러블 장치 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023054996A1 true WO2023054996A1 (fr) | 2023-04-06 |
Family
ID=85783141
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2022/014331 WO2023054996A1 (fr) | 2021-09-30 | 2022-09-26 | Dispositif vestimentaire de reconnaissance d'objet utilisant un suivi de main ou de doigt |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR102629771B1 (fr) |
WO (1) | WO2023054996A1 (fr) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016020267A (ja) * | 2014-07-15 | 2016-02-04 | 三菱電機株式会社 | エレベータのタッチパネル式行き先階登録操作盤およびエレベータのタッチパネル式行き先階登録操作盤における利用者判定方法 |
WO2019161313A1 (fr) * | 2018-02-15 | 2019-08-22 | Magic Leap, Inc. | Réverbération virtuelle de réalité mixte |
KR20190133080A (ko) * | 2011-09-19 | 2019-11-29 | 아이사이트 모빌 테크놀로지 엘티디 | 증강 현실 시스템용 터치프리 인터페이스 |
US20190369725A1 (en) * | 2018-06-02 | 2019-12-05 | Awespire Technology Inc. | Guided virtual reality system for relaxing body and mind |
KR20210012198A (ko) * | 2019-07-24 | 2021-02-03 | 이상현 | 시각 장애인을 위한 객체 위치 정보 안내 장치 및 방법 |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20090036183A (ko) * | 2007-10-09 | 2009-04-14 | 슬림디스크 주식회사 | 카메라센서로 찍은 문서 이미지를 시각장애인에게 음성으로알려주는 방법 및 장치 |
KR101823121B1 (ko) | 2016-04-12 | 2018-01-29 | 울산과학기술원 | 시각장애인용 문자 인식 장치 |
-
2021
- 2021-09-30 KR KR1020210129572A patent/KR102629771B1/ko active IP Right Grant
-
2022
- 2022-09-26 WO PCT/KR2022/014331 patent/WO2023054996A1/fr unknown
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20190133080A (ko) * | 2011-09-19 | 2019-11-29 | 아이사이트 모빌 테크놀로지 엘티디 | 증강 현실 시스템용 터치프리 인터페이스 |
JP2016020267A (ja) * | 2014-07-15 | 2016-02-04 | 三菱電機株式会社 | エレベータのタッチパネル式行き先階登録操作盤およびエレベータのタッチパネル式行き先階登録操作盤における利用者判定方法 |
WO2019161313A1 (fr) * | 2018-02-15 | 2019-08-22 | Magic Leap, Inc. | Réverbération virtuelle de réalité mixte |
US20190369725A1 (en) * | 2018-06-02 | 2019-12-05 | Awespire Technology Inc. | Guided virtual reality system for relaxing body and mind |
KR20210012198A (ko) * | 2019-07-24 | 2021-02-03 | 이상현 | 시각 장애인을 위한 객체 위치 정보 안내 장치 및 방법 |
Also Published As
Publication number | Publication date |
---|---|
KR20230046511A (ko) | 2023-04-06 |
KR102629771B1 (ko) | 2024-01-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6975991B2 (en) | Wearable display system with indicators of speakers | |
WO2019013517A1 (fr) | Appareil et procédé pour contexte de commande vocale | |
WO2018128238A1 (fr) | Système et procédé de consultation virtuelle utilisant un dispositif d'affichage | |
KR20170094668A (ko) | 양방향 수화 번역 장치 및 장치가 수행하는 양방향 수화 번역 방법 | |
WO2016017855A1 (fr) | Dispositif à porter sur soi, et procédé de commande de ce dispositif | |
WO2011059202A2 (fr) | Dispositif d'affichage et procédé de commande de ce dernier | |
WO2015199288A1 (fr) | Terminal du type lunettes, et procédé de commande de ce terminal | |
US10922570B1 (en) | Entering of human face information into database | |
WO2018164363A1 (fr) | Procédé de reconnaissance sans contact de parties du corps multiples et dispositif de reconnaissance de parties du corps multiples, utilisant des données biométriques multiples | |
WO2021118179A1 (fr) | Terminal utilisateur, dispositif d'appel vidéo, système d'appel vidéo et son procédé de commande | |
WO2019100915A1 (fr) | Appareil et procédé d'entrée vidéo commandée par électroencéphalogramme et de guidage aveugle d'affichage auditif | |
WO2014088125A1 (fr) | Dispositif de photographie d'images et procédé associé | |
WO2020256475A1 (fr) | Procédé et dispositif de génération de vidéo vocale à l'aide de texte | |
WO2020159302A1 (fr) | Dispositif électronique permettant d'assurer diverses fonctions dans un environnement de réalité augmentée et procédé de fonctionnement associé | |
WO2016021907A1 (fr) | Système de traitement d'informations et procédé utilisant un dispositif à porter sur soi | |
WO2023054996A1 (fr) | Dispositif vestimentaire de reconnaissance d'objet utilisant un suivi de main ou de doigt | |
WO2021230568A1 (fr) | Dispositif électronique permettant de fournir un service de réalité augmentée et son procédé de fonctionnement | |
CN112951236A (zh) | 一种语音翻译设备及方法 | |
WO2020153785A1 (fr) | Dispositif électronique et procédé pour fournir un objet graphique correspondant à des informations d'émotion en utilisant celui-ci | |
WO2018080202A1 (fr) | Dispositif visiocasque et procédé de commande de celui-ci | |
WO2022050742A1 (fr) | Procédé de détection de mouvement de la main d'un dispositif de réalité augmentée portable à l'aide d'une image de profondeur et dispositif de réalité augmentée portable en mesure de détecter un mouvement de la main à l'aide d'une image de profondeur | |
WO2021187771A1 (fr) | Dispositif de réalité augmentée réalisant une reconnaissance audio et son procédé de commande | |
WO2016010328A1 (fr) | Système de traitement d'informations et procédé utilisant un dispositif portatif | |
WO2018034384A1 (fr) | Procédé de commande de carte à puce sur la base d'une reconnaissance vocale et de mouvement, et pointeur laser virtuel l'utilisant | |
JPH1039995A (ja) | 視線・音声入力装置 |
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: 22876768 Country of ref document: EP Kind code of ref document: A1 |