CN109116986B - Gesture recognition system and method based on flexible optical fiber - Google Patents
Gesture recognition system and method based on flexible optical fiber Download PDFInfo
- Publication number
- CN109116986B CN109116986B CN201810889602.5A CN201810889602A CN109116986B CN 109116986 B CN109116986 B CN 109116986B CN 201810889602 A CN201810889602 A CN 201810889602A CN 109116986 B CN109116986 B CN 109116986B
- Authority
- CN
- China
- Prior art keywords
- optical fiber
- finger
- gesture recognition
- gesture
- 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.)
- Active
Links
Images
Classifications
-
- 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
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
- G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
- G06F3/04883—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
- G06F2203/048—Indexing scheme relating to G06F3/048
- G06F2203/04802—3D-info-object: information is displayed on the internal or external surface of a three dimensional manipulable object, e.g. on the faces of a cube that can be rotated by the user
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a gesture recognition system and method based on a flexible optical fiber. Covering the surface of each finger with a malleable linear flexible optical fiber in a wiring mode of repeatedly bending in the longitudinal direction and repeatedly winding in the transverse direction, sending protocol data containing a time mark in a longitudinal optical fiber channel by a micro electro-optical information conversion and sending device, receiving the data by a micro electro-optical information receiving and conversion device, calculating the transmission time and the light quantity in unit time of information in the optical fiber channel, and identifying the bending degree of each finger through the transmission time and the light quantity in unit time; meanwhile, based on the Sagnac effect, the micro photoelectric device simultaneously sends two groups of light rays in opposite directions in the transverse optical fiber channel, calculates the rotation angle rate of each finger by receiving the phase difference of the two groups of light rays, and accurately identifies the static and dynamic gestures of the wearer in real time by combining the bending degree of the fingers. The invention overcomes the defects of the existing gesture recognition technology and improves the simplicity and the accuracy of gesture recognition.
Description
Technical Field
The invention belongs to the technical field of intelligent wearing and gesture recognition, and particularly relates to a gesture recognition system and method based on flexible optical fibers.
Background
Gesture recognition is an emerging biometric recognition technology, and aims to control other devices through gestures of people. Compared with other biological recognition technologies, gesture recognition has the advantage of being non-contact and long-distance. However, most of the current gesture recognition methods are based on two methods, namely an inertial sensor and a computer vision method. The multi-node gesture recognition technology based on the inertial sensor is complex in wearing mode and high in cost, and the gesture recognition method adopting computer vision needs to utilize video acquisition equipment, so that the multi-node gesture recognition technology is influenced by external factors such as light and the like.
Disclosure of Invention
In order to solve the technical problems of the background art, the invention aims to provide a gesture recognition system and method based on a flexible optical fiber, so that the simplicity and the accuracy of gesture recognition are improved.
In order to achieve the technical purpose, the technical scheme of the invention is as follows:
a gesture recognition system based on flexible optical fiber comprises a flexible optical fiber channel, an information acquisition device, an information transfer device and a data processing and display device; the flexible optical fiber channel is made of a linear optical fiber material with ductility, the flexible optical fiber channel comprises 10 paths, wherein 5 paths of flexible optical fiber channels cover the surface of the corresponding finger in a longitudinal repeated bending wiring mode, and the other 5 paths of flexible optical fibers cover the surface of the corresponding finger in a transverse repeated winding wiring mode; the information acquisition devices comprise 5 information acquisition devices, each information acquisition device corresponds to 1 path of flexible optical fiber channel with longitudinal wiring and 1 path of flexible optical fiber channel with transverse wiring on 1 finger, each information acquisition device comprises a micro electro-optical information conversion and transmission device, a micro electro-optical information receiving and conversion device and a wireless communication module, the micro electro-optical information conversion and transmission device converts an electric signal into an optical signal and transmits the optical signal, the micro electro-optical information receiving and conversion device acquires the optical signal transmitted by the corresponding flexible optical fiber channel and converts the optical signal into the electric signal, and the wireless communication module transmits the electric signal to the information transfer device; the information transfer device receives the 5-path wireless communication information, combines the information into 1-path information and transfers the information to the data processing and display device; and the data processing and displaying device performs gesture recognition according to the received information and displays the recognition result.
Furthermore, the flexible optical fiber channels are repeatedly arranged in a winding manner according to the direction parallel to the cross section of the finger or a certain included angle when the flexible optical fiber channels are transversely arranged, and are repeatedly bent and arranged according to the direction perpendicular to the cross section of the finger when the flexible optical fiber channels are longitudinally arranged.
Further, the wireless communication module includes, but is not limited to, a bluetooth module, a WiFi module, and a ZigBee module.
Furthermore, the gesture recognition system also comprises a power supply device, and the power supply device comprises a voltage power supply module and a voltage stabilizing chip.
The gesture recognition method based on the gesture recognition system comprises the following steps:
(1) the micro electro-optical information conversion and transmission device is used for transmitting protocol data containing time marks in a longitudinal channel of the flexible optical fiber channel, the micro electro-optical information receiving and conversion device is used for receiving the data, calculating the transmission time and the unit time light quantity of light in the optical fiber channel, and obtaining a characteristic value representing the bending degree of the finger according to the data;
(2) based on the Sagnac effect, the micro electro-optical information conversion and transmission device is used for simultaneously transmitting two groups of light rays in opposite directions in a transverse channel of the flexible optical fiber channel, the phase difference of the two groups of light rays is received through the micro electro-optical information receiving and conversion device, and the rotation angular rate of each finger is calculated according to the phase difference;
(3) the information transfer device combines the bending degree characteristic values and the rotation angle rates of the 5 fingers to obtain complete gesture information;
(4) and (3) a gesture recognition database and a dynamic gesture model database are pre-established in the data processing and displaying device, a dynamic gesture model of each gesture in the gesture recognition database is stored in the dynamic gesture model database, the gesture information obtained in the step (3) is compared with the gesture stored in the gesture recognition database, the gesture with the highest similarity serves as a recognition result, and the dynamic gesture model corresponding to the gesture is called from the dynamic gesture model database to be displayed.
Further, in step (1), a characteristic value e ═ k characterizing the degree of finger bending1e1+k2e2Wherein e is1Characteristic value representing degree of finger bending expressed by transmission time, e2Characteristic values representing the degree of finger bending expressed by the amount of light per unit time:
wherein, t1The transmission time of light in the flexible optical fiber path when the finger is bent to a certain degree, t2The transmission time of light in the flexible optical fiber path when the finger is completely bent, Q is the light quantity per unit time, beta is a coefficient that the light quantity per unit time is inversely proportional to the bending degree of the finger, and k1、k2Are each e1、e2The confidence coefficient of (c).
Further, in step (2), the rotation angular rate Ω of the finger is calculated according to the following formula:
wherein, Δ θ is the phase difference of the two groups of light, S is the area enclosed by the fiber channel surrounding the finger, N is the number of turns of the fiber, λ is the wavelength of the light, and c is the propagation speed of the light in the flexible fiber channel.
Further, in step (4), the gesture recognition database is used for data collection through a plurality of existing gesture recognition manners, including an inertial sensor-based gesture recognition manner and a visual sensor-based gesture recognition manner, and each type of gesture in the gesture recognition database is characterized by the bending degree and the rotation angular velocity of five fingers.
Further, in step (4), the software used for constructing the dynamic gesture model library includes, but is not limited to, Open CV and 3D Max.
Adopt the beneficial effect that above-mentioned technical scheme brought:
the invention combines the transmission time and the unit time light quantity of the light rays collected by the micro electro-optical information conversion and sending device and the micro electro-optical information receiving and conversion device in the optical fiber channel, can accurately capture the bending state of the fingers of a wearer, and compares the rotation angle rate of each finger obtained based on Sagnac (Sagnac) effect with corresponding parameters in a gesture database to accurately identify the gesture of the wearer in real time. The acquisition device can be installed in various gloves, is simple to wear and more concealed, is less influenced by the outside, and has higher accuracy, reliability and stability of a gesture recognition system.
Drawings
FIG. 1 is a schematic of the present invention.
Detailed Description
The technical scheme of the invention is explained in detail in the following with the accompanying drawings.
The invention arranges the linear flexible optical fiber material with certain ductility as shown in figure 1, and arranges the optical fiber channel on the surface of each finger of the glove according to a plurality of times of reciprocating or winding arrangement, namely, a wiring mode of longitudinal repeated bending and transverse repeated winding.
Acquisition and calculation of light wave information
As shown in fig. 1, a linear flexible optical fiber, an information acquisition device, an information transfer device, and a data processing and display device are used as hardware devices for data acquisition. The information acquisition device is hand wearable equipment and consists of a miniature electric-optical information conversion and transmission device, a miniature optical-electric information receiving and conversion device and a wireless communication module which are arranged as required. When the wearable equipment is successfully connected with the information transfer device, the single chip microcomputer in the wearable equipment sends a starting signal, and the information acquisition module starts to work to acquire information.
1. Collecting and calculating the transmission time of light in the optical fiber channel:
the invention uses the measured length L of the optical fiber, the propagation speed of the light in the special flexible optical fiber channel is c, and the time calculation formula is as follows:
t is the propagation time of the light wave, and the transmission time t of the light in the optical fiber channel can be measured through the micro electro-optical information conversion and transmission device and the micro electro-optical information receiving and conversion device.
The time required for light to transmit in the special flexible optical fiber channel when the finger is bent to a certain degree is t1When the finger is completely bent, the time required for the light to transmit in the special flexible optical fiber channel is t2By the calculation formula:
Δt＝t2-t1 (2)
Δ t is the time difference between when the finger is fully bent and when the finger is bent to some degree, light travels through the fiber path. As the degree of bending of the finger increases, the flexible optical fiber is stretched, the optical path increases gradually but the volume of the optical fiber is unchanged, and the relationship can be expressed as:
in the formula, R1、R2Respectively the radius before and after drawing of the optical fiber, L1、L2The lengths of the optical fiber before and after stretching, respectively. The following formulas (1), (2) and (3) can be obtained:
in the formula, e1A characteristic value representing the degree of finger bending expressed by the transmission time, and the range is set to [0,1 ]]。
The volume of the flexible optical fiber is set as V, L is the length of the flexible optical fiber, and the cross-sectional area is as follows:
meanwhile, let the light quantity per unit time be Q, since the light quantity per unit time is proportional to the cross section of the flexible optical fiber, i.e., inversely proportional to the length of the flexible optical fiber. From this, it is understood that the amount of light per unit time is inversely proportional to the degree of finger flexion, that is:
Q＝αS＝β/e2 (6)
where α is a coefficient in which the amount of light per unit time is proportional to the cross section of the flexible optical fiber, β is a coefficient in which the amount of light per unit time is inversely proportional to the degree of bending of the finger, and e2To represent a characteristic value of the degree of finger bending expressed by the amount of light per unit time, the range thereof was set to [0,1 ]]。
The weighted average equation for determining the relationship between the degree of finger flexion and the amount of light transmitted and emitted per unit time is:
e＝k1e1+k2e2 (7)
in the formula, k1、k2Determining confidence coefficient of finger bending degree for the above two modes, e is comprehensive characteristic value representing finger bending degree, and its range is set as [0, 1%]. The solving mode of the comprehensive characteristic values of the bending degrees of other fingers is the same, and the description is omitted.
2. Calculation of finger rotation angular velocity:
based on the Sagnac effect, the micro-photoelectric device simultaneously sends two groups of light rays in opposite directions in the annular optical fiber channel, the radius of the annular closed optical path is set as R, and when the closed optical path around a single finger rotates at a rotating speed omega relative to the inertial space (namely the rotating angular speed of the finger on the premise of neglecting the rotational angular speed of the earth, wherein omega is vertical to the plane of a loop), the two optical paths of light which are transmitted oppositely are unequal, and an optical path difference is generated. Let a and b be the two beams of light respectively, S is the area enclosed by the fiber track around the finger, and N is the number of turns of the fiber.
The phase difference between the two beams in the transverse optical fiber is as follows:
Δθ＝(8πSNΩ)/λc (8)
where λ is the wavelength of light, and the phase difference Δ θ in the above equation is analyzed by a detector, the rotation angular velocity Ω of a single finger can be obtained. The solving method of the rotation speed of other fingers is the same, and the description is omitted.
(II) information processing and gesture sequence comparison
The bending degree comprehensive characteristic values and the finger rotation angular velocity information collected from the five fingers are transmitted to the information transfer device through a wired or wireless transmission module, and then the information transfer device is combined and packaged and then forwarded to the gesture sequence comparison and recognition system for recognition. The detailed process is as follows:
1. a gesture database is established in the gesture sequence contrast recognition system in advance. In the process of establishing the gesture database, data collection can be performed through various mature technical modes, including a gesture recognition mode based on an inertial sensor or a gesture recognition mode based on a visual sensor. The bending degree of the five fingers and the rotation angular velocity of the five fingers under various hand motion states are collected and are corresponding to corresponding static and dynamic gesture sequences.
2. Obtaining the comprehensive characteristic value e of the bending degree of the five fingersiAnd rotational angular velocity ΩiAnd (i is 1-5), then comparing the bending degree comprehensive characteristic values corresponding to all static and dynamic gesture sequences stored in the gesture sequence comparison and recognition system with the rotation angular velocity, taking the gesture sequence with the highest similarity as the recognized gesture, and sending the three-dimensional dynamic model reappearing file corresponding to the gesture to the three-dimensional dynamic model real-time display system of the gesture sequence.
Real-time display of three-dimensional dynamic model of (tri) gesture
And (3) constructing a real-time display system of the gesture sequence, namely constructing various static and dynamic gesture models in advance through various software such as Open CV, 3D Max and the like, and establishing a model library corresponding to the gesture sequence comparison recognition system. And after the three-dimensional dynamic model reappearing file is received, the real-time display system of the gesture sequence restores and displays the three-dimensional animation model of the real-time gesture.
The embodiments are only for illustrating the technical idea of the present invention, and the technical idea of the present invention is not limited thereto, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the scope of the present invention.
Claims (9)
1. A gesture recognition system based on flexible optical fiber is characterized in that: the system comprises a flexible optical fiber channel, an information acquisition device, an information transfer device and a data processing and displaying device; the flexible optical fiber channel is made of a linear optical fiber material with ductility, the flexible optical fiber channel comprises 10 paths, wherein 5 paths of flexible optical fiber channels cover the surface of the corresponding finger in a longitudinal repeated bending wiring mode, and the other 5 paths of flexible optical fibers cover the surface of the corresponding finger in a transverse repeated winding wiring mode; the information acquisition devices comprise 5 information acquisition devices, each information acquisition device corresponds to 1 path of flexible optical fiber channel with longitudinal wiring and 1 path of flexible optical fiber channel with transverse wiring on 1 finger, each information acquisition device comprises a micro electro-optical information conversion and transmission device, a micro electro-optical information receiving and conversion device and a wireless communication module, the micro electro-optical information conversion and transmission device converts an electric signal into an optical signal and transmits the optical signal, the micro electro-optical information receiving and conversion device acquires the optical signal transmitted by the corresponding flexible optical fiber channel and converts the optical signal into the electric signal, and the wireless communication module transmits the electric signal to the information transfer device; the information transfer device receives the 5-path wireless communication information, combines the information into 1-path information and transfers the information to the data processing and display device; and the data processing and displaying device performs gesture recognition according to the received information and displays the recognition result.
2. The flexible fiber optic based gesture recognition system of claim 1, wherein: the flexible optical fiber channel is repeatedly arranged in a winding manner according to the direction parallel to the cross section of the finger or a certain included angle when the flexible optical fiber channel is transversely arranged, and is repeatedly bent and arranged according to the direction vertical to the cross section of the finger when the flexible optical fiber channel is longitudinally arranged.
3. The flexible fiber optic based gesture recognition system of claim 1, wherein: the wireless communication module includes, but is not limited to, a bluetooth module, a WiFi module, and a ZigBee module.
4. The flexible fiber optic based gesture recognition system of claim 1, wherein: the gesture recognition system further comprises a power supply device, and the power supply device comprises a voltage power supply module and a voltage stabilizing chip.
5. The gesture recognition method based on the gesture recognition system of claim 1, characterized by comprising the following steps:
(1) the micro electro-optical information conversion and transmission device is used for transmitting protocol data containing time marks in a longitudinal channel of the flexible optical fiber channel, the micro electro-optical information receiving and conversion device is used for receiving the data, calculating the transmission time and the unit time light quantity of light in the optical fiber channel, and obtaining a characteristic value representing the bending degree of the finger according to the data;
(2) based on the Sagnac effect, the micro electro-optical information conversion and transmission device is used for simultaneously transmitting two groups of light rays in opposite directions in a transverse channel of the flexible optical fiber channel, the phase difference of the two groups of light rays is received through the micro electro-optical information receiving and conversion device, and the rotation angular rate of each finger is calculated according to the phase difference;
(3) the information transfer device combines the bending degree characteristic values and the rotation angle rates of the 5 fingers to obtain complete gesture information;
(4) and (3) a gesture recognition database and a dynamic gesture model database are pre-established in the data processing and displaying device, a dynamic gesture model of each gesture in the gesture recognition database is stored in the dynamic gesture model database, the gesture information obtained in the step (3) is compared with the gesture stored in the gesture recognition database, the gesture with the highest similarity serves as a recognition result, and the dynamic gesture model corresponding to the gesture is called from the dynamic gesture model database to be displayed.
6. Gesture recognition according to claim 5The method is characterized in that in the step (1), a characteristic value e ═ k representing the degree of finger bending1e1+k2e2Wherein e is1Characteristic value representing degree of finger bending expressed by transmission time, e2Characteristic values representing the degree of finger bending expressed by the amount of light per unit time:
wherein, t1The transmission time of light in the flexible optical fiber path when the finger is bent to a certain degree, t2The transmission time of light in the flexible optical fiber path when the finger is completely bent, Q is the light quantity per unit time, beta is a coefficient that the light quantity per unit time is inversely proportional to the bending degree of the finger, and k1、k2Are each e1、e2The confidence coefficient of (c).
7. The gesture recognition method according to claim 5, wherein in step (2), the rotation angular rate Ω of the finger is calculated according to the following formula:
wherein, Δ θ is the phase difference of the two groups of light, S is the area enclosed by the fiber channel surrounding the finger, N is the number of turns of the fiber, λ is the wavelength of the light, and c is the propagation speed of the light in the flexible fiber channel.
8. The gesture recognition method of claim 5, wherein in step (4), the gesture recognition database is used for data collection through a plurality of existing gesture recognition manners, including an inertial sensor-based gesture recognition manner and a visual sensor-based gesture recognition manner, and each type of gesture in the gesture recognition database is characterized by the bending degree and the rotation angular velocity of five fingers.
9. The gesture recognition method of claim 5, wherein in step (4), the software used for constructing the dynamic gesture model library includes but is not limited to Open CV and 3D Max.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810889602.5A CN109116986B (en) | 2018-08-07 | 2018-08-07 | Gesture recognition system and method based on flexible optical fiber |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810889602.5A CN109116986B (en) | 2018-08-07 | 2018-08-07 | Gesture recognition system and method based on flexible optical fiber |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109116986A CN109116986A (en) | 2019-01-01 |
| CN109116986B true CN109116986B (en) | 2021-05-18 |
Family
ID=64852642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810889602.5A Active CN109116986B (en) | 2018-08-07 | 2018-08-07 | Gesture recognition system and method based on flexible optical fiber |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109116986B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113495619B (en) * | 2020-04-03 | 2023-11-10 | 北京金坤科创技术有限公司 | Gesture recognition method based on Wi-Fi channel state information phase |
| CN113920809A (en) * | 2021-10-29 | 2022-01-11 | 航天科工武汉磁电有限责任公司 | Mixed reality teaching system for ship fire-fighting training |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201936249U (en) * | 2010-12-28 | 2011-08-17 | 赵剑桥 | Light reflection type mobile sign language identification system |
| CN107015653A (en) * | 2017-04-10 | 2017-08-04 | 南京鼓楼医院 | Data glove and interactive system based on fiber grating |
| KR20170138768A (en) * | 2016-06-08 | 2017-12-18 | 한국과학기술연구원 | Motion capture system using a FBG sensor |
-
2018
- 2018-08-07 CN CN201810889602.5A patent/CN109116986B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201936249U (en) * | 2010-12-28 | 2011-08-17 | 赵剑桥 | Light reflection type mobile sign language identification system |
| KR20170138768A (en) * | 2016-06-08 | 2017-12-18 | 한국과학기술연구원 | Motion capture system using a FBG sensor |
| CN107015653A (en) * | 2017-04-10 | 2017-08-04 | 南京鼓楼医院 | Data glove and interactive system based on fiber grating |
Non-Patent Citations (2)
| Title |
|---|
| Flexible Optical Fiber Bending Transducer for Application in Glove-Based Sensors;Eric Fujiwara等;《IEEE Sensors Journal》;20141031;第14卷(第10期);第3631-3636页 * |
| 数据手套中传感器技术的研究;徐波等;《测控技术》;20020818;第21卷(第08期);第6-9页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109116986A (en) | 2019-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103279186B (en) | Merge the multiple goal motion capture system of optical alignment and inertia sensing | |
| CN109116986B (en) | Gesture recognition system and method based on flexible optical fiber | |
| CN106445130A (en) | Motion capture glove for gesture recognition and calibration method thereof | |
| CN107609490B (en) | Control method, control device, Intelligent mirror and computer readable storage medium | |
| CN107320108B (en) | Joint mobility measuring method | |
| CN114676956A (en) | Old man's risk early warning system that tumbles based on multidimensional data fusion | |
| CN104127188A (en) | Method and device for monitoring amount of exercise of neck | |
| CN209657257U (en) | A kind of data glove and interactive system based on optical fibre bending sensor | |
| CN108151738A (en) | Codified active light marked ball with attitude algorithm | |
| CN104345904A (en) | Finger-type air mouse | |
| CN206048251U (en) | Gesture identification Apery manipulator system based on Multi-sensor Fusion | |
| CN107092882A (en) | A kind of Activity recognition system and its method of work perceived based on sub- action | |
| CN103049102A (en) | Mouse data processing device and mouse data processing method | |
| CN106267781A (en) | Water proof type motion capture system for athletic training | |
| CN106227664A (en) | A kind of method and device testing application program | |
| Wang et al. | Spatiotemporal co-attention hybrid neural network for pedestrian localization based on 6D IMU | |
| US20220375028A1 (en) | Dynamic over-rendering in late-warping | |
| CN106970705A (en) | Motion capture method, device and electronic equipment | |
| US10748320B2 (en) | Animation simulation of biomechanics | |
| Song et al. | Sensor fusion for learning-based tracking of controller movement in virtual reality | |
| US20230334630A1 (en) | Systems and methods for motion measurement drift correction | |
| CN115904086A (en) | Sign language identification method based on wearable calculation | |
| CN207067783U (en) | A kind of underwater robot | |
| CN105879301B (en) | A kind of upper extremity exercise recognition methods towards intelligent Dumbbell | |
| CN116149465A (en) | System and method for carrying out multi-person bare-hand interaction in virtual reality |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |