WO2016026440A1 - Glove for use in collecting data for sign language recognition - Google Patents

Glove for use in collecting data for sign language recognition Download PDF

Info

Publication number
WO2016026440A1
WO2016026440A1 PCT/CN2015/087521 CN2015087521W WO2016026440A1 WO 2016026440 A1 WO2016026440 A1 WO 2016026440A1 CN 2015087521 W CN2015087521 W CN 2015087521W WO 2016026440 A1 WO2016026440 A1 WO 2016026440A1
Authority
WO
WIPO (PCT)
Prior art keywords
glove
azimuth
hand
sensor
phalanx
Prior art date
Application number
PCT/CN2015/087521
Other languages
French (fr)
Chinese (zh)
Inventor
王犇
姜小花
罗红
任骝
张建杰
徐魁
陈彦霖
周正宇
郭文蔚
Original Assignee
博世(中国)投资有限公司
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 博世(中国)投资有限公司 filed Critical 博世(中国)投资有限公司
Publication of WO2016026440A1 publication Critical patent/WO2016026440A1/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input 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
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer

Definitions

  • the present invention relates to the field of data processing, and in particular to a glove for collecting data for sign language recognition.
  • the present invention will provide a new way for the above device to accurately express the meaning of the sign language of deaf people.
  • One of the technical problems solved by one aspect of the present invention is to collect more comprehensive data for sign language recognition, thereby making sign language recognition more accurate.
  • a glove for collecting data for sign language recognition comprising: a plurality of azimuths for sensing a posture of a hand placed on a glove corresponding to a position of a phalanx and a metacarpal bone of the hand Sensor; placed on the data glove for sensing the height of the hand used to calculate The height sensor of the data.
  • the azimuth sensor placed on the glove is used to sense azimuth data of the phalanx and metacarpal of the hand.
  • the glove further comprises: a control unit for collecting data of the plurality of azimuth sensors and height sensor sensing, wherein the data is used to determine the meaning of the gesture.
  • the glove further comprises: an output unit, configured to output the meaning of the collected gesture in the form of voice or text.
  • the height sensor is an air pressure sensor.
  • the azimuth sensor placed on the glove corresponding to the metacarpal bone of the hand is placed at a position corresponding to the two metacarpals.
  • the bag is provided in the glove for fixing the azimuth sensor.
  • the bag is provided on the outside of the glove for fixing the azimuth sensor.
  • the azimuth sensor is placed on the glove only at a position other than the index finger, the middle finger, the ring finger, and the first phalanx of the little finger near the fingertip of the phalane of the hand.
  • the size of the portion of the glove corresponding to each of the phalanges and palms matches the size of the phalanx and palm of the man or woman.
  • the inventors have found that the accuracy of identifying the sign language of deaf people in the prior art is low because the basic data collected is not comprehensive.
  • the prior art only collects the azimuth related data of the hand and the azimuth related data of each phalanx, but the inventors have found that these azimuths sometimes do not necessarily accurately reflect the meaning of the deaf and mute sign language, resulting in accurate sign language.
  • the rate is low.
  • the glove for collecting basic data in the embodiment of the present invention compensates for this defect by collecting highly correlated data on the basis of collecting azimuth related data, and improves the determination accuracy.
  • Figure 1 is a structural view of a hand bone.
  • FIG. 2 is a schematic diagram of parameters required by the inventors to define sign language requirements.
  • 3a-b are schematic illustrations of gloves, respectively, when sign language recognition is performed on the outside and inside of a glove in accordance with a first embodiment of the present invention.
  • 4a-b are schematic illustrations of gloves, respectively, when sign language recognition is performed on the outside and inside of a glove in accordance with a second embodiment of the present invention.
  • Figures 5a-b are schematic illustrations of gloves, respectively, when sign language recognition is performed on the outside and inside of a glove in accordance with a third embodiment of the present invention.
  • Figures 6a-b are schematic illustrations of gloves, respectively, when sign language recognition is performed on the outside and inside of a glove in accordance with a fourth embodiment of the present invention.
  • FIGS. 7a-b are structural block diagrams of a glove when sign language recognition is performed outside and inside the glove in accordance with an embodiment of the present invention.
  • Figures 8a-d show four schematic views of the attachment of an azimuth sensor to a glove, respectively.
  • Figure 1 is a structural view of a hand bone.
  • the phalanx 101 there are three elongate bones connected by joints on five fingers, called the phalanx 101, in which the last phalanx of the thumb is located in the palm of the hand, because of its range of motion and the metacarpal of the palm of the hand.
  • the range of activity is not well correlated and can be considered as the last phalanx 101 of the thumb.
  • the last section of the index finger, middle finger, ring finger, and little finger of the hand refers to the four elongated bones connected by the joint, called the metacarpal bone 102.
  • the metacarpal bone 102 is located in the palm of the hand, and the position and angle of the palm can be known through its position.
  • the positions of the four metacarpals 102 are almost constant, and they are on each axis in the three-axis (for example, front, rear, left and right, up and down) coordinate systems.
  • Azimuth allows the position and angle of the entire palm to be calculated from the position and angle of one of the metacarpals.
  • the azimuth angle ⁇ of the palm ie, the angle with respect to the gravity line 1003
  • the azimuth angle ⁇ of the palm that is, the azimuth angle of the metacarpal bone 102
  • the azimuth of the plurality of metacarpals 102 is averaged.
  • the angle ⁇ 1 can be determined.
  • the gesture of the sign language is determined, and the meaning represented by the sign language is determined.
  • the present invention finds that in the sign language, the hand is placed on the chest Do an action, do the same thing with the hand above the head, that is, the gestures made by the hands are the same, the positions are different, and sometimes the meanings are different.
  • the posture of the hand refers to various postures made when the height of the hand is not considered. In this way, the glove of the existing sign language recognition can judge the meaning of the sign language only by the gesture of the hand, and it may be wrong.
  • Embodiments of the present invention introduce a hand height indicator.
  • the height sensor 12 is placed on the back of the glove of the present invention for sensing the height H of the hand.
  • the height sensor 12 can also be placed at other positions of the glove as long as the height of the glove can be measured. can.
  • This height is a relative height, for example, relative to the height of the person's waist.
  • the glove of the present invention can determine the height of the hand relative to other parts of the user's body, thus enabling the user's gesture. Read more accurately.
  • the meaning of the gesture of one sign language is determined by the gesture of the above hand and the height H of the hand, thereby improving the accuracy of determining the meaning of the sign language.
  • a gesture is a complex of gestures and heights of a hand that can correspond to a certain meaning in sign language.
  • a plurality of azimuth sensors 11 are placed on the glove at positions corresponding to the phalanx and the metacarpal bone for collecting data on the azimuth angles of the phalanx and metacarpal bones to calculate the azimuth angles of the respective phalanx and metacarpal bones.
  • the bending angles ⁇ 2 and ⁇ 3 between the adjacent phalanges 101 of each finger can be obtained by the respective azimuth angles of the adjacent phalanxes
  • the bending angle ⁇ 1 of the last phalanx adjacent to the metacarpal bone and the metacarpal bone can be from the last The azimuth of the phalanx and the metacarpal bone is derived.
  • the above azimuth data generally refers to all data that can be used to calculate the azimuth of the carrier, such as carrier angular velocity, acceleration, etc., and the azimuth of the carrier can be derived.
  • the azimuth data can be obtained by a three-axis microgyroscope, a three-axis micro-acceleration sensor and a three-axis geomagnetic sensor, wherein the three azimuth sensors can be used individually or in combination, and the specific usage is as follows:
  • the azimuth sensor may include only the above-described three-axis microgyroscope.
  • the azimuth sensor may include only the above-described three-axis micro acceleration sensor.
  • the azimuth angle sensor comprises: a three-axis microgyroscope and a three-axis micro-acceleration sensor for measuring angular rates in three coordinate axes and measuring accelerations in the three coordinate axes, respectively .
  • an azimuth angle ⁇ a can be calculated by the angular rate
  • an azimuth angle ⁇ b can also be calculated by the acceleration
  • the premise of this is that the three-axis micro gyroscope and the three-axis micro-acceleration sensor use the same three-axis coordinate system.
  • the triaxial micro-acceleration sensor is characterized by noise sensitivity, but since it is not affected by the previous frame results, there is no drift in results.
  • the triaxial microgyroscope is characterized by insensitivity to noise, but as the result is affected by the previous frame, the resulting drift occurs and an initial azimuth is required. Therefore, this approach concentrates the advantages of the two methods, and achieves a beneficial effect that is neither sensitive to noise nor susceptible to the influence of the previous frame, compared to the prior art.
  • the azimuth sensor includes a three-axis geomagnetic sensor in addition to the above-described three-axis microgyroscope and three-axis micro acceleration sensor.
  • the height sensor 12 of the present invention is an air pressure sensor, although it can of course be implemented with other height sensors. In the implementation of the air pressure sensor, it senses the external air pressure, the ground pressure of different heights is different, and the height of the hand can be calculated by the air pressure.
  • the aforementioned height H can be calculated by subtracting the absolute height of the waist relative to the sea level from the absolute height of the hand relative to the sea level, so that the height of the hand relative to other parts of the body can be determined to determine the meaning of the gesture.
  • the gloved hand is first at the waist, the absolute height of the waist is measured, and then the corresponding gesture is made.
  • the relative height of the hand is equal to the absolute height of the hand minus The absolute height of the waist is derived. In this way, the relative height of the hand making the gesture can be calculated.
  • the meaning of the gesture determined by the glove of the present invention can be outputted by voice through the speaker unit on the glove, or can be displayed in a word by the display on the glove. It can also be output by other devices so that deaf people can communicate with normal people.
  • 3a-3b are schematic views of the glove 1 when the sign language recognition is performed outside the glove and the sign language recognition is performed in the glove, respectively, according to the first embodiment of the present invention.
  • the glove 1 of the present embodiment includes 16 azimuth sensors 11a-11o, 11q and a height sensor 12.
  • 15 azimuth sensors 11a-11o are placed on the glove corresponding to the 15 phalanx 101, wherein the azimuth sensors 11a-11o are placed at the 15 phalanx positions of the hand, and the azimuth sensor 11q is placed at the corresponding metacarpal position.
  • the height sensor 12 is used to sense data of the height of the hand.
  • the control unit 13 receives the data sensed by the plurality of azimuth sensors and height sensors. As shown in FIG.
  • the control unit 13 is coupled with a transceiver module 135.
  • the transceiver module 135 sends the data sensed by the plurality of azimuth sensors and height sensors to the external processor 201 to determine a gesture as shown in FIG. 2.
  • the determined gesture is converted into speech and then passed through the output unit 202 such as a speaker Output in the form of a device or display.
  • an output unit 202 is coupled to the control unit 13 for converting the meaning of the gesture determined by the control unit 13 as shown in FIG. 2 into a speech or text output, the principle of which is shown in FIG. 7b. .
  • the azimuth sensor may be placed only on the glove corresponding to a portion of the phalanx.
  • the azimuth sensor may be placed only on the glove corresponding to a portion of the phalanx.
  • the azimuth sensor 11q is placed only at the position corresponding to the metacarpal bone connected to the middle finger on the glove.
  • the azimuth sensor is placed only at a position corresponding to one of the metacarpals because the difference in azimuth between the metacarpal bones is not as pronounced as the difference between the azimuth angles of the phalanx when the human hand performs various postures, so only in the Positioning the azimuth sensor at a position corresponding to a metacarpal bone can save costs.
  • the azimuth sensor placed on the glove corresponding to the metacarpal bone can also be placed at a position corresponding to more than one metacarpal bone.
  • the azimuth angle of each of the at least two metacarpals can be obtained, and the average angle of the various angles is taken as the azimuth of the hand, which can make the azimuth of the hand more accurate and reduce only
  • the azimuth sensor is placed at a position corresponding to a metacarpal bone
  • the azimuth angle between the metacarpal bones actually has a slight difference in gesture recognition error.
  • azimuth sensors on the four metacarpals, such as the azimuth sensor 11p-s shown in Figures 4a-4b.
  • an azimuth sensor can be placed on the glove at a position corresponding to two or three metacarpals.
  • the azimuth sensor is placed on the glove corresponding to the two metacarpals, as shown in the fourth embodiment of the present invention, as shown in Figures 6a-6b, which reduces the placement of the azimuth only at a position corresponding to one metacarpal.
  • the error caused by the sensor maximizes cost savings.
  • FIGs 5a-5b are schematic illustrations of a glove in accordance with a third embodiment of the present invention.
  • the difference from the first embodiment is that the azimuth sensor placed on the glove corresponding to the position of the phalanx is placed only on the position of the phalanx except the position of the four-finger phalanx, except for the thumb. Index finger, middle finger, ring finger and little finger. That is, the azimuth sensors 11b-e in Figures 3a-3b are removed.
  • the present invention finds that when the human hand makes various gestures, the index finger, the middle finger, and the nameless
  • the degree of bending between the finger and the fingertip of the little finger and the corresponding fingertip to the second phalanx is relatively fixed, and the influence of the opponent's posture is not significant, while the other adjacent phalanx or the last phalanx and the adjacent metacarpal bone
  • the degree of curvature varies greatly, and the posture of the hand is mainly determined by it. Therefore, the azimuth sensor that removes the fingertips of the index finger, the middle finger, the ring finger, and the little finger can also accurately determine the posture of the hand. Therefore, in this embodiment, by removing the azimuth sensor at the fingertip phalanx position of the index finger, the middle finger, the ring finger, and the little finger, the effect of saving the cost and substantially achieving the accuracy of the same determination gesture can be achieved.
  • FIG. 7a-b are structural block diagrams of a glove when sign language recognition is performed outside and inside the glove in accordance with an embodiment of the present invention.
  • Fig. 7a generally shows the situation of Figs. 3a, 4a, 5a, 6a
  • Fig. 7b shows the situation of Figs. 3b, 4b, 5b, 6b.
  • a pocket 199 is provided at the inner side of the glove for fixing the azimuth sensor 11 for accommodating the azimuth sensor 11.
  • the azimuth sensor 11 is bonded to the inner wall of the glove.
  • a pocket 199 is provided at the outer side of the glove for fixing the azimuth sensor 11 for accommodating the azimuth sensor 11.
  • the azimuth sensor 11 is bonded to the outer wall of the glove. There are other ways to fix it.
  • the size of the portion of the glove 1 corresponding to each of the phalanx and the palm is matched with the size of the phalanx and palm of the man or woman, thereby forming the glove 1 suitable for the man or the woman, respectively, thereby avoiding the size of the hand of the man or the woman.
  • the inconsistency brings about the problem that the azimuth sensor or the height sensor senses the data of the wrong position.

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)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

A glove for use in collecting data for sign language recognition. The glove comprises: multiple azimuth sensors (11) arranged on the glove at positions corresponding to the phalanges (101) and the metacarpal bones (102) of the hand and used for sensing postures of the hand; and, a height sensor (12) arranged on the data glove and used for sensing data for calculating the height at which the hand is located. The glove collects comprehensive data for gesture determination, thus allowing improved accuracy in gesture determination.

Description

用于采集手语识别用数据的手套Gloves for collecting data for sign language recognition
本申请要求2014年8月20日提交的、申请号为201410410413.7的中国专利申请的优先权,并且在此以参考的方式插入该中国专利申请的全部内容。The present application claims the priority of the Chinese Patent Application No. 201410410413.7, filed on Aug. 20, 2014, the entire disclosure of which is hereby incorporated by reference.
技术领域Technical field
本发明涉及数据处理领域,尤其涉及一种用于采集手语识别用数据的手套。The present invention relates to the field of data processing, and in particular to a glove for collecting data for sign language recognition.
背景技术Background technique
目前对于聋哑人与正常人之间的交流,需要正常人能够读懂聋哑人的哑语才能够进行。对于读不懂聋哑人的哑语或手势的正常人,如何理解聋哑人通过手势表达的含义,成为一个两者间的沟通的难题。At present, the communication between deaf and normal people requires normal people to read the deaf and mute dumb words. For a normal person who does not understand the mute or gesture of deaf people, how to understand the meaning of deaf-mute people through gestures becomes a problem of communication between the two.
目前有专为聋哑人设计的数据手套。通过在数据手套上设置方位角传感器感测手的方位角和各节指骨的方位角,以此计算各节指骨之间弯曲的角度,发送给处理用的中央计算机。中央计算机以此识别手语,并通过例如扬声器或显示器等将手语的含义以语音或文字等形式输出,从而达到正常人与聋哑人交流的目的。There are currently data gloves designed specifically for deaf people. By setting the azimuth angle of the hand and the azimuth of each phalanx on the data glove, the angle of bending between the phalanx of each node is calculated and sent to the central computer for processing. The central computer recognizes the sign language and outputs the meaning of the sign language in the form of voice or text through, for example, a speaker or a display, thereby achieving the purpose of communication between the normal person and the deaf person.
本发明将提供一种新的方式,使上述设备能准确表达聋哑人的手语的含义。The present invention will provide a new way for the above device to accurately express the meaning of the sign language of deaf people.
发明内容Summary of the invention
本发明的一方面解决的技术问题之一是为手语识别采集更全面的数据,从而使手语识别更准确。One of the technical problems solved by one aspect of the present invention is to collect more comprehensive data for sign language recognition, thereby making sign language recognition more accurate.
根据本发明的一个实施例,提供了一种用于采集手语识别用数据的手套,包括:置于手套上与手的指骨和掌骨对应的位置的用于感测手的姿态的多个方位角传感器;置于数据手套上的用于感测用于计算手的高 度的数据的高度传感器。According to an embodiment of the present invention, there is provided a glove for collecting data for sign language recognition, comprising: a plurality of azimuths for sensing a posture of a hand placed on a glove corresponding to a position of a phalanx and a metacarpal bone of the hand Sensor; placed on the data glove for sensing the height of the hand used to calculate The height sensor of the data.
根据本发明的一个实施例,所述置于手套上的方位角传感器用于感测手的指骨和掌骨的方位角数据。According to an embodiment of the invention, the azimuth sensor placed on the glove is used to sense azimuth data of the phalanx and metacarpal of the hand.
根据本发明的一个实施例,所述手套还包括:用于采集所述多个方位角传感器、高度传感器感测的数据的控制单元,所述数据用以判断手势的含义。According to an embodiment of the invention, the glove further comprises: a control unit for collecting data of the plurality of azimuth sensors and height sensor sensing, wherein the data is used to determine the meaning of the gesture.
根据本发明的一个实施例,所述手套还包括:输出单元,用于将所采集到的手势的含义以语音或文字的形式输出。According to an embodiment of the invention, the glove further comprises: an output unit, configured to output the meaning of the collected gesture in the form of voice or text.
根据本发明的一个实施例,所述高度传感器为气压传感器。According to an embodiment of the invention, the height sensor is an air pressure sensor.
根据本发明的一个实施例,所述置于手套上与手的掌骨对应的位置的方位角传感器放置在与两个掌骨对应的位置上。According to an embodiment of the invention, the azimuth sensor placed on the glove corresponding to the metacarpal bone of the hand is placed at a position corresponding to the two metacarpals.
根据本发明的一个实施例,所述在手套内设置有用于固定上述方位角传感器的袋。According to an embodiment of the invention, the bag is provided in the glove for fixing the azimuth sensor.
根据本发明的一个实施例,所述在手套外侧设置有用于固定方位角传感器的袋。According to an embodiment of the invention, the bag is provided on the outside of the glove for fixing the azimuth sensor.
根据本发明的一个实施例,所述手套上仅在与手的指骨对应的除了食指、中指、无名指以及小指的靠近其指尖的第一节指骨的位置放置上述方位角传感器。According to one embodiment of the invention, the azimuth sensor is placed on the glove only at a position other than the index finger, the middle finger, the ring finger, and the first phalanx of the little finger near the fingertip of the phalane of the hand.
根据本发明的一个实施例,所述手套中与各指骨、手掌对应的部分的尺寸与男人或女人各指骨、手掌的尺寸相匹配。According to an embodiment of the present invention, the size of the portion of the glove corresponding to each of the phalanges and palms matches the size of the phalanx and palm of the man or woman.
本发明人发现,现有技术中之所以识别聋哑人的手语的准确率低是因为采集基础数据不全面。现有技术只采集手的方位角相关数据和各节指骨的方位角相关数据,但本发明人分析发现,仅靠这些方位角有时不一定能够准确反映聋哑人手语的含义,导致判定手语准确率低。本发明实施例的采集基础数据的手套通过在采集方位角相关数据的基础上采集高度相关数据弥补了这一缺陷,提高了判定准确率。The inventors have found that the accuracy of identifying the sign language of deaf people in the prior art is low because the basic data collected is not comprehensive. The prior art only collects the azimuth related data of the hand and the azimuth related data of each phalanx, but the inventors have found that these azimuths sometimes do not necessarily accurately reflect the meaning of the deaf and mute sign language, resulting in accurate sign language. The rate is low. The glove for collecting basic data in the embodiment of the present invention compensates for this defect by collecting highly correlated data on the basis of collecting azimuth related data, and improves the determination accuracy.
附图说明DRAWINGS
图1是手骨的结构图。Figure 1 is a structural view of a hand bone.
图2是本发明人发现的定义手语需要的参数示意图。 2 is a schematic diagram of parameters required by the inventors to define sign language requirements.
图3a-b分别是根据本发明的第一实施例的手语识别在手套外部和内部进行时手套的示意图。3a-b are schematic illustrations of gloves, respectively, when sign language recognition is performed on the outside and inside of a glove in accordance with a first embodiment of the present invention.
图4a-b分别是根据本发明的第二实施例的手语识别在手套外部和内部进行时手套的示意图。4a-b are schematic illustrations of gloves, respectively, when sign language recognition is performed on the outside and inside of a glove in accordance with a second embodiment of the present invention.
图5a-b分别是根据本发明的第三实施例的手语识别在手套外部和内部进行时手套的示意图。Figures 5a-b are schematic illustrations of gloves, respectively, when sign language recognition is performed on the outside and inside of a glove in accordance with a third embodiment of the present invention.
图6a-b分别是根据本发明的第四实施例的手语识别在手套外部和内部进行时手套的示意图。Figures 6a-b are schematic illustrations of gloves, respectively, when sign language recognition is performed on the outside and inside of a glove in accordance with a fourth embodiment of the present invention.
图7a-b是根据本发明实施例的手语识别在手套外部和内部进行时手套的结构框图。7a-b are structural block diagrams of a glove when sign language recognition is performed outside and inside the glove in accordance with an embodiment of the present invention.
图8a-d分别示出了四种将方位角传感器结合在手套上的示意图。Figures 8a-d show four schematic views of the attachment of an azimuth sensor to a glove, respectively.
具体实施方式detailed description
下面参照附图描述本发明的一些优选实施方式。Some preferred embodiments of the invention are described below with reference to the drawings.
图1是手骨的结构图。如图1所示,在5个手指上都有三节依次通过关节连接起来的细长的骨头,叫指骨101,其中拇指的最后一节指骨101位于手掌中,因其活动范围与手掌的掌骨的活动范围关联不大,其可以视为拇指的最后一节指骨101。手的食指、中指、无名指、小指的最后一节指骨通过关节相连的四根细长的骨头,叫掌骨102,该掌骨102位于手掌中,通过其位置可得知手掌的位置和角度。由于四根掌骨102都固定在手掌中,因此在做手语时,这四根掌骨相互之间的位置几乎不变,其在三轴(例如前后、左右、上下)坐标系中每个轴上的方位角可通过其中一根掌骨的位置和角度,就能计算出整个手掌的位置和角度。Figure 1 is a structural view of a hand bone. As shown in Figure 1, there are three elongate bones connected by joints on five fingers, called the phalanx 101, in which the last phalanx of the thumb is located in the palm of the hand, because of its range of motion and the metacarpal of the palm of the hand. The range of activity is not well correlated and can be considered as the last phalanx 101 of the thumb. The last section of the index finger, middle finger, ring finger, and little finger of the hand refers to the four elongated bones connected by the joint, called the metacarpal bone 102. The metacarpal bone 102 is located in the palm of the hand, and the position and angle of the palm can be known through its position. Since the four metacarpals 102 are fixed in the palm of the hand, when the sign language is used, the positions of the four metacarpals are almost constant, and they are on each axis in the three-axis (for example, front, rear, left and right, up and down) coordinate systems. Azimuth allows the position and angle of the entire palm to be calculated from the position and angle of one of the metacarpals.
如图2所示,在表征手语中的手势时,只要用手掌的方位角α(即相对于重力线1003的夹角,手掌的方位角α即一根掌骨102的方位角,当然也可以通过多根掌骨102的方位角求平均的方式得出)、各手指上的相邻指骨101之间的弯曲角β2、β3、与掌骨102相邻的最后一节指骨101与掌骨102之间的弯曲角β1就可以确定。也就是说,当手的手指的上述方位角α、弯曲角β2、β3、β1确定后,这个手语的手势就确定了,其所代表的含义也就确定了。但本发明发现,在手语中,将手放在胸前 做一个动作,与把手举过头顶做一个相同的动作,即,手做出的姿态相同,位置不同,有时代表的含义是不同的。这里,手的姿态是指不考虑手的高度时做出的各种姿态。这样,现有手语识别的手套,仅靠手的姿态来判断手语的含义,就可能出错。As shown in FIG. 2, in characterizing the gesture in the sign language, as long as the azimuth angle α of the palm (ie, the angle with respect to the gravity line 1003, the azimuth angle α of the palm, that is, the azimuth angle of the metacarpal bone 102, can of course also pass The azimuth of the plurality of metacarpals 102 is averaged. The bending angles β2, β3 between adjacent phalanges 101 on each finger, and the bending between the last phalanx 101 and the metacarpal 102 adjacent to the metacarpal 102. The angle β1 can be determined. That is to say, when the azimuth angle α and the bending angles β2, β3, and β1 of the finger of the hand are determined, the gesture of the sign language is determined, and the meaning represented by the sign language is determined. However, the present invention finds that in the sign language, the hand is placed on the chest Do an action, do the same thing with the hand above the head, that is, the gestures made by the hands are the same, the positions are different, and sometimes the meanings are different. Here, the posture of the hand refers to various postures made when the height of the hand is not considered. In this way, the glove of the existing sign language recognition can judge the meaning of the sign language only by the gesture of the hand, and it may be wrong.
本发明的实施例引入一个手高度指标。如图2所示,本发明的手套的手背位置放置高度传感器12,用于感测手的高度H,当然,此高度传感器12也可以放置在手套的其他位置,只要能测定该手套的高度即可。这个高度是相对高度,例如相对于人腰部的高度,通过手相对于腰的高度的计算,本发明的手套能判断出手相对于使用者的身体的其他部位的高度,这样就能使使用者的手势被更精确地解读。也就是说,通过上述手的姿态以及手的高度H来确定一个手语的手势的含义,从而提高了确定手语含义的准确率。手势是能对应于手语中的某个含义的手的姿态和高度的综合体。Embodiments of the present invention introduce a hand height indicator. As shown in FIG. 2, the height sensor 12 is placed on the back of the glove of the present invention for sensing the height H of the hand. Of course, the height sensor 12 can also be placed at other positions of the glove as long as the height of the glove can be measured. can. This height is a relative height, for example, relative to the height of the person's waist. By calculating the height of the hand relative to the waist, the glove of the present invention can determine the height of the hand relative to other parts of the user's body, thus enabling the user's gesture. Read more accurately. That is to say, the meaning of the gesture of one sign language is determined by the gesture of the above hand and the height H of the hand, thereby improving the accuracy of determining the meaning of the sign language. A gesture is a complex of gestures and heights of a hand that can correspond to a certain meaning in sign language.
另外,如图2所示,在手套上与指骨和掌骨对应的位置放置多个方位角传感器11,用于采集指骨和掌骨方位角的数据,以计算各指骨和掌骨的方位角。其中,各手指的相邻指骨101之间的弯曲角β2、β3可以通过该相邻指骨各自的方位角得出,与掌骨相邻的最后一节指骨与该掌骨的弯曲角β1可以从该最后一节指骨和该掌骨的方位角得出。In addition, as shown in FIG. 2, a plurality of azimuth sensors 11 are placed on the glove at positions corresponding to the phalanx and the metacarpal bone for collecting data on the azimuth angles of the phalanx and metacarpal bones to calculate the azimuth angles of the respective phalanx and metacarpal bones. Wherein, the bending angles β2 and β3 between the adjacent phalanges 101 of each finger can be obtained by the respective azimuth angles of the adjacent phalanxes, and the bending angle β1 of the last phalanx adjacent to the metacarpal bone and the metacarpal bone can be from the last The azimuth of the phalanx and the metacarpal bone is derived.
上述方位角的数据泛指所有可以用于计算载体方位角的数据,例如载体角速度、加速度,等等,都可以得出载体的方位角。该方位角数据可以通过三轴微陀螺仪、三轴微加速度传感器和三轴地磁传感器得出,其中,该三种方位角传感器可以单独或组合来使用,具体的使用方式如下:The above azimuth data generally refers to all data that can be used to calculate the azimuth of the carrier, such as carrier angular velocity, acceleration, etc., and the azimuth of the carrier can be derived. The azimuth data can be obtained by a three-axis microgyroscope, a three-axis micro-acceleration sensor and a three-axis geomagnetic sensor, wherein the three azimuth sensors can be used individually or in combination, and the specific usage is as follows:
在第一种实施方式中,方位角传感器可以仅包括上述三轴微陀螺仪。In the first embodiment, the azimuth sensor may include only the above-described three-axis microgyroscope.
在第二种实施方式中,方位角传感器可以仅包括上述三轴微加速度传感器。In the second embodiment, the azimuth sensor may include only the above-described three-axis micro acceleration sensor.
在第三种实施方式中,方位角传感器包括:三轴微陀螺仪和三轴微加速度传感器,分别用于测量三个坐标轴方向上的角速率和测量所述三个坐标轴方向上的加速度。这种方式中,通过角速率能够计算出一个方位角γa,通过加速度也能够计算出一个方位角γb,可以通过加权的方式 计算出最后的方位角γ=kγa+(1-k)γb(其中0≦k≦1)。这样做的前提是,三轴微陀螺仪和三轴微加速度传感器使用的是相同的三轴坐标系。三轴微加速度传感器的特点是对于噪音敏感,但由于其不受前面帧结果的影响,所以不会出现结果漂移。三轴微陀螺仪的特点是对于噪音不敏感,但是由于结果受前面帧的影响,会出现结果漂移,而且需要一个初始方位角。所以,这种方式集中了2种方式的优点,相对于现有技术,达到了既不容易对噪音敏感、又不容易受前面帧的影响的有益效果。In a third embodiment, the azimuth angle sensor comprises: a three-axis microgyroscope and a three-axis micro-acceleration sensor for measuring angular rates in three coordinate axes and measuring accelerations in the three coordinate axes, respectively . In this way, an azimuth angle γ a can be calculated by the angular rate, and an azimuth angle γ b can also be calculated by the acceleration, and the final azimuth angle γ=kγa+(1-k)γb can be calculated by weighting ( Where 0≦k≦1). The premise of this is that the three-axis micro gyroscope and the three-axis micro-acceleration sensor use the same three-axis coordinate system. The triaxial micro-acceleration sensor is characterized by noise sensitivity, but since it is not affected by the previous frame results, there is no drift in results. The triaxial microgyroscope is characterized by insensitivity to noise, but as the result is affected by the previous frame, the resulting drift occurs and an initial azimuth is required. Therefore, this approach concentrates the advantages of the two methods, and achieves a beneficial effect that is neither sensitive to noise nor susceptible to the influence of the previous frame, compared to the prior art.
在第四种实施方式中,方位角传感器除了上述三轴微陀螺仪和三轴微加速度传感器,还包括三轴地磁传感器。本发明的高度传感器12为气压传感器,当然也可以用其他的高度传感器实现。在气压传感器的实现中,其感测外部气压,不同高度的地气压不同,通过气压可以计算手的高度。前述高度H可以通过手相对于海平面的绝对高度减去腰相对于海平面的绝对高度计算出,这样,可以测定手相对于身体的其他部位的高度,以判断手势的含义。使用时,使用者做手势前,把戴有手套的手先在腰部,测得腰部的绝对高度,然后做相应的手势,当需要高度的数值时,手的相对高度就等于手的绝对高度减去腰的绝对高度来得出。这样,就可以计算出做手势的手的相对高度。In the fourth embodiment, the azimuth sensor includes a three-axis geomagnetic sensor in addition to the above-described three-axis microgyroscope and three-axis micro acceleration sensor. The height sensor 12 of the present invention is an air pressure sensor, although it can of course be implemented with other height sensors. In the implementation of the air pressure sensor, it senses the external air pressure, the ground pressure of different heights is different, and the height of the hand can be calculated by the air pressure. The aforementioned height H can be calculated by subtracting the absolute height of the waist relative to the sea level from the absolute height of the hand relative to the sea level, so that the height of the hand relative to other parts of the body can be determined to determine the meaning of the gesture. In use, before the user gestures, the gloved hand is first at the waist, the absolute height of the waist is measured, and then the corresponding gesture is made. When the height value is required, the relative height of the hand is equal to the absolute height of the hand minus The absolute height of the waist is derived. In this way, the relative height of the hand making the gesture can be calculated.
本发明的手套判定的手势含义可以通过手套上的扬声单元以语音的方式输出,也可以通过手套上的显示器以字的方式显示。也可以通过其他设备进行输出,以便使聋哑人可以与正常人进行交流。The meaning of the gesture determined by the glove of the present invention can be outputted by voice through the speaker unit on the glove, or can be displayed in a word by the display on the glove. It can also be output by other devices so that deaf people can communicate with normal people.
图3a-3b分别是根据本发明的第一实施例的手语识别在手套外进行时和手语识别在手套内进行时手套1的示意图。本实施例的手套1包括16个方位角传感器11a-11o,11q和一个高度传感器12。手套上与15个指骨101对应的位置放置有15个方位角传感器11a-11o,其中上述方位角传感器11a-11o被设置于手的15个指骨位置,方位角传感器11q设置于对应的掌骨位置。高度传感器12用于感测手的高度的数据。在图3a中,控制单元13接收所述多个方位角传感器、高度传感器感测的数据。如图7a所示,控制单元13耦合有收发模块135,由收发模块135将所述多个方位角传感器、高度传感器感测的数据发给外部处理器201如结合图2所示那样判定手势。判定的手势转换成语音后通过输出单元202如扬声 器或显示器的形式输出。3a-3b are schematic views of the glove 1 when the sign language recognition is performed outside the glove and the sign language recognition is performed in the glove, respectively, according to the first embodiment of the present invention. The glove 1 of the present embodiment includes 16 azimuth sensors 11a-11o, 11q and a height sensor 12. 15 azimuth sensors 11a-11o are placed on the glove corresponding to the 15 phalanx 101, wherein the azimuth sensors 11a-11o are placed at the 15 phalanx positions of the hand, and the azimuth sensor 11q is placed at the corresponding metacarpal position. The height sensor 12 is used to sense data of the height of the hand. In FIG. 3a, the control unit 13 receives the data sensed by the plurality of azimuth sensors and height sensors. As shown in FIG. 7a, the control unit 13 is coupled with a transceiver module 135. The transceiver module 135 sends the data sensed by the plurality of azimuth sensors and height sensors to the external processor 201 to determine a gesture as shown in FIG. 2. The determined gesture is converted into speech and then passed through the output unit 202 such as a speaker Output in the form of a device or display.
在图3b中,输出单元202耦合到所述控制单元13,用于将控制单元13如结合图2所示判定的手势的含义转换成语音或文字的形式输出,其原理,如图7b所示。In FIG. 3b, an output unit 202 is coupled to the control unit 13 for converting the meaning of the gesture determined by the control unit 13 as shown in FIG. 2 into a speech or text output, the principle of which is shown in FIG. 7b. .
虽然如图3a-b所示,在手套上与所有指骨对应的位置都放置了方位角传感器,但实际上,也可以只在手套上与一部分指骨对应的位置放置方位角传感器。当在手套上仅与特定一部分指骨对应的位置方位角传感器时,仅根据所述特定一部分指骨中相邻指骨之间的弯曲角、所述特定一部分指骨中的最后一节指骨与掌骨之间的弯曲角、手的高度、手的方位角判定手势。Although an azimuth sensor is placed on the glove corresponding to all of the phalanges as shown in Figures 3a-b, in practice, the azimuth sensor may be placed only on the glove corresponding to a portion of the phalanx. When there is only a position azimuth sensor corresponding to a specific portion of the finger bone on the glove, only the bending angle between adjacent phalanges in the specific part of the phalanx, the last phalanx and the metacarpal bone in the specific part of the phalanx is The bending angle, the height of the hand, and the azimuth of the hand determine the gesture.
在图3a-3b中,仅在手套上与中指相连的掌骨对应的位置放置方位角传感器11q。仅在与一个掌骨对应的位置放置方位角传感器是因为,在人手做各种姿态时,各掌骨之间的方位角之间的差别不如各指骨的方位角之间的差别那么明显,因此仅在与一个掌骨对应的位置放置方位角传感器可以节省成本。当然,也可以将所述置于手套上与掌骨对应的位置的方位角传感器放置在一个以上的掌骨对应的位置上。这样,就可以得出所述至少两个掌骨中每个掌骨的方位角,将得出的各方位角取平均值作为手的方位角,可以使得出的手的方位角更准确,减少了只在与一个掌骨对应的位置放置方位角传感器时由于实际上各掌骨之间的方位角确实有微小不同引起的手势识别误差。当然,也可以在四根掌骨上均放置方位角传感器,如图4a-4b所示的方位角传感器11p-s。另外,还可以在手套上与2个或3个掌骨对应的位置放置方位角传感器。优选地是在手套上与2个掌骨对应的位置放置方位角传感器,如图6a-6b根据本发明的第四实施例所示,既减少了仅在与1个掌骨对应的位置上放置方位角传感器带来的误差,又最大化节省了成本。In Figures 3a-3b, the azimuth sensor 11q is placed only at the position corresponding to the metacarpal bone connected to the middle finger on the glove. The azimuth sensor is placed only at a position corresponding to one of the metacarpals because the difference in azimuth between the metacarpal bones is not as pronounced as the difference between the azimuth angles of the phalanx when the human hand performs various postures, so only in the Positioning the azimuth sensor at a position corresponding to a metacarpal bone can save costs. Of course, the azimuth sensor placed on the glove corresponding to the metacarpal bone can also be placed at a position corresponding to more than one metacarpal bone. In this way, the azimuth angle of each of the at least two metacarpals can be obtained, and the average angle of the various angles is taken as the azimuth of the hand, which can make the azimuth of the hand more accurate and reduce only When the azimuth sensor is placed at a position corresponding to a metacarpal bone, the azimuth angle between the metacarpal bones actually has a slight difference in gesture recognition error. Of course, it is also possible to place azimuth sensors on the four metacarpals, such as the azimuth sensor 11p-s shown in Figures 4a-4b. Alternatively, an azimuth sensor can be placed on the glove at a position corresponding to two or three metacarpals. Preferably, the azimuth sensor is placed on the glove corresponding to the two metacarpals, as shown in the fourth embodiment of the present invention, as shown in Figures 6a-6b, which reduces the placement of the azimuth only at a position corresponding to one metacarpal. The error caused by the sensor maximizes cost savings.
图5a-5b是根据本发明的第三实施例的手套的示意图。与第一实施例的区别在于,所述置于手套上与指骨对应的位置的方位角传感器仅放置在除四指尖部指骨位置之外的指骨位置上,所述四指是除大拇指以外的食指、中指、无名指以及小指。也就是说,去除了图3a-3b中的方位角传感器11b-e。本发明发现,在人手做各种手势的时候,食指、中指、无名 指以及小指尖部指骨与其对应的指尖部向下第二节指骨之间的弯曲程度相对固定,对手的姿态的影响不大,而其它相邻指骨或最后一节指骨与其相邻的掌骨之间的弯曲程度差异较大,手的姿态主要由其决定。因此,去除食指、中指、无名指以及小指的指尖的方位角传感器也能准确的确定手的姿态。因此,这一实施例中,通过去掉食指、中指、无名指以及小指的指尖部指骨位置上的方位角传感器,达到了节约成本而基本上能达到同样的判定手势的准确度的效果。Figures 5a-5b are schematic illustrations of a glove in accordance with a third embodiment of the present invention. The difference from the first embodiment is that the azimuth sensor placed on the glove corresponding to the position of the phalanx is placed only on the position of the phalanx except the position of the four-finger phalanx, except for the thumb. Index finger, middle finger, ring finger and little finger. That is, the azimuth sensors 11b-e in Figures 3a-3b are removed. The present invention finds that when the human hand makes various gestures, the index finger, the middle finger, and the nameless The degree of bending between the finger and the fingertip of the little finger and the corresponding fingertip to the second phalanx is relatively fixed, and the influence of the opponent's posture is not significant, while the other adjacent phalanx or the last phalanx and the adjacent metacarpal bone The degree of curvature varies greatly, and the posture of the hand is mainly determined by it. Therefore, the azimuth sensor that removes the fingertips of the index finger, the middle finger, the ring finger, and the little finger can also accurately determine the posture of the hand. Therefore, in this embodiment, by removing the azimuth sensor at the fingertip phalanx position of the index finger, the middle finger, the ring finger, and the little finger, the effect of saving the cost and substantially achieving the accuracy of the same determination gesture can be achieved.
图7a-b是根据本发明实施例的手语识别在手套外部和内部进行时手套的结构框图。图7a概括示出了图3a、4a、5a、6a的情形,图7b概括示出了图3b、4b、5b、6b的情形。7a-b are structural block diagrams of a glove when sign language recognition is performed outside and inside the glove in accordance with an embodiment of the present invention. Fig. 7a generally shows the situation of Figs. 3a, 4a, 5a, 6a, and Fig. 7b shows the situation of Figs. 3b, 4b, 5b, 6b.
可以有多种方式实现方位角传感器11在手套上的固定。如图8a所示,在手套内侧用于固定方位角传感器11的位置有袋199,用于容纳方位角传感器11。如图8b所示,方位角传感器11粘结在手套的内壁。如图8c所示,在手套外侧用于固定方位角传感器11的位置有袋199,用于容纳方位角传感器11。如图8d所示,方位角传感器11粘结在手套的外壁。还可以有其它固定方式。There are a number of ways in which the azimuth sensor 11 can be secured to the glove. As shown in Fig. 8a, a pocket 199 is provided at the inner side of the glove for fixing the azimuth sensor 11 for accommodating the azimuth sensor 11. As shown in Figure 8b, the azimuth sensor 11 is bonded to the inner wall of the glove. As shown in Fig. 8c, a pocket 199 is provided at the outer side of the glove for fixing the azimuth sensor 11 for accommodating the azimuth sensor 11. As shown in Figure 8d, the azimuth sensor 11 is bonded to the outer wall of the glove. There are other ways to fix it.
另外,手套1中与各指骨、手掌对应的部分的尺寸与男人或女人各指骨、手掌的尺寸相匹配,从而形成男人或女人分别适合戴的手套1,从而避免了由于男人、女人手的尺寸不一致带来的方位角传感器或高度传感器感测到错误位置的数据的问题。In addition, the size of the portion of the glove 1 corresponding to each of the phalanx and the palm is matched with the size of the phalanx and palm of the man or woman, thereby forming the glove 1 suitable for the man or the woman, respectively, thereby avoiding the size of the hand of the man or the woman. The inconsistency brings about the problem that the azimuth sensor or the height sensor senses the data of the wrong position.
虽然这里参考具体的实施方式描述了本发明,但是本发明的范围并不局限于所示的细节。在不偏离本发明的基本原理的情况下,可针对这些细节做出各种修改,这些修改都落在本发明的保护范围内。 Although the invention is described herein with reference to the specific embodiments, the scope of the invention is not limited to the details shown. Various modifications may be made to these details without departing from the basic principles of the invention, and such modifications are intended to fall within the scope of the invention.

Claims (10)

  1. 一种用于采集手语识别用数据的手套(1),包括:A glove (1) for collecting data for sign language recognition, comprising:
    置于手套上与手的指骨和掌骨对应的位置的用于感测手的姿态的多个方位角传感器(11,11a-11s);a plurality of azimuth sensors (11, 11a-11s) for sensing the posture of the hand placed on the glove corresponding to the phalanx and metacarpal bone of the hand;
    置于手套上的用于感测用于计算手的高度的数据的高度传感器(12)。A height sensor (12) placed on the glove for sensing data for calculating the height of the hand.
  2. 根据权利要求1所述的手套(1),其特征在于,所述置于手套上的方位角传感器用于感测手的指骨和掌骨的方位角数据。The glove (1) according to claim 1, wherein the azimuth sensor placed on the glove is used to sense azimuth data of the phalanx and metacarpal of the hand.
  3. 根据权利要求1所述的手套(1),其特征在于,所述手套(1)还包括:用于采集所述多个方位角传感器、高度传感器感测的数据的控制单元(13),所述数据用以判断手势的含义。The glove (1) according to claim 1, characterized in that the glove (1) further comprises: a control unit (13) for collecting data of the plurality of azimuth sensors and height sensor sensing, The data is used to determine the meaning of the gesture.
  4. 根据权利要求3所述的手套(1),其特征在于,所述手套(1)还包括:输出单元,用于将所采集到的手势的含义以语音或文字的形式输出。The glove (1) according to claim 3, characterized in that the glove (1) further comprises an output unit for outputting the meaning of the collected gesture in the form of a voice or a text.
  5. 根据权利要求1所述的手套(1),其特征在于,所述高度传感器为气压传感器。The glove (1) according to claim 1, characterized in that the height sensor is an air pressure sensor.
  6. 根据权利要求1所述的手套(1),其特征在于,所述置于手套上与手的掌骨对应的位置的方位角传感器放置在与两个掌骨对应的位置上。The glove (1) according to claim 1, wherein the azimuth sensor placed on the glove corresponding to the metacarpal bone of the hand is placed at a position corresponding to the two metacarpals.
  7. 根据权利要求1所述的手套(1),其特征在于,所述在手套内设置有用于固定上述方位角传感器的袋。The glove (1) according to claim 1, wherein the glove is provided with a pocket for fixing the azimuth sensor.
  8. 根据权利要求1所述的手套(1),其特征在于,所述在手套外侧 设置有用于固定方位角传感器的袋。A glove (1) according to claim 1 wherein said glove is outside A bag for fixing the azimuth sensor is provided.
  9. 根据权利要求2所述的手套(1),其特征在于,所述手套上仅在与手的指骨对应的食指、中指、无名指以及小指的靠近其指尖的第一节指骨的位置以外的位置放置上述方位角传感器。The glove (1) according to claim 2, wherein the glove is only at a position other than the position of the index finger, the middle finger, the ring finger, and the first finger phalanx of the little finger corresponding to the finger keel of the hand. Place the above azimuth sensor.
  10. 根据权利要求1所述的手套(1),其中所述手套(1)中与各指骨、手掌对应的部分的尺寸与男人或女人各指骨、手掌的尺寸相匹配。 The glove (1) according to claim 1, wherein a size of a portion of the glove (1) corresponding to each of the phalanx and the palm is matched to a size of a phalanx or a palm of a man or a woman.
PCT/CN2015/087521 2014-08-20 2015-08-19 Glove for use in collecting data for sign language recognition WO2016026440A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410410413.7A CN105353866A (en) 2014-08-20 2014-08-20 Gloves used for acquiring data for sign language recognition
CN201410410413.7 2014-08-20

Publications (1)

Publication Number Publication Date
WO2016026440A1 true WO2016026440A1 (en) 2016-02-25

Family

ID=55329851

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/087521 WO2016026440A1 (en) 2014-08-20 2015-08-19 Glove for use in collecting data for sign language recognition

Country Status (2)

Country Link
CN (1) CN105353866A (en)
WO (1) WO2016026440A1 (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106448351A (en) * 2016-10-31 2017-02-22 天津工业大学 Intelligent sign language gloves
KR102414497B1 (en) * 2017-09-29 2022-06-29 애플 인크. IMU-Based Gloves
CN109992093B (en) * 2017-12-29 2024-05-03 博世汽车部件(苏州)有限公司 Gesture comparison method and gesture comparison system
US10914567B2 (en) 2018-02-23 2021-02-09 Apple Inc. Magnetic sensor based proximity sensing
CN111920416B (en) * 2020-07-13 2024-05-03 张艳 Hand rehabilitation training effect measuring method, storage medium, terminal and system

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001344053A (en) * 2000-06-01 2001-12-14 Olympus Optical Co Ltd Operation inputting device
JP2007236602A (en) * 2006-03-08 2007-09-20 Akita Univ Motion capture device for finger using magnetic position/posture sensor
US20100023314A1 (en) * 2006-08-13 2010-01-28 Jose Hernandez-Rebollar ASL Glove with 3-Axis Accelerometers
US20110234384A1 (en) * 2010-03-24 2011-09-29 Agrawal Dharma P Apparatus for instantaneous translation of sign language
CN102362709A (en) * 2011-09-13 2012-02-29 苏州市伦琴工业设计有限公司 Interpreting glove for deaf and dumb sign language and interpreting method thereof
CN204044747U (en) * 2014-08-20 2014-12-24 博世(中国)投资有限公司 For gathering the gloves of Sign Language Recognition data

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103049761B (en) * 2013-01-21 2016-08-03 中国地质大学(武汉) Sign Language Recognition Method based on sign language glove and system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001344053A (en) * 2000-06-01 2001-12-14 Olympus Optical Co Ltd Operation inputting device
JP2007236602A (en) * 2006-03-08 2007-09-20 Akita Univ Motion capture device for finger using magnetic position/posture sensor
US20100023314A1 (en) * 2006-08-13 2010-01-28 Jose Hernandez-Rebollar ASL Glove with 3-Axis Accelerometers
US20110234384A1 (en) * 2010-03-24 2011-09-29 Agrawal Dharma P Apparatus for instantaneous translation of sign language
CN102362709A (en) * 2011-09-13 2012-02-29 苏州市伦琴工业设计有限公司 Interpreting glove for deaf and dumb sign language and interpreting method thereof
CN204044747U (en) * 2014-08-20 2014-12-24 博世(中国)投资有限公司 For gathering the gloves of Sign Language Recognition data

Also Published As

Publication number Publication date
CN105353866A (en) 2016-02-24

Similar Documents

Publication Publication Date Title
AU2020273327B2 (en) Systems and methods of swimming analysis
WO2016026440A1 (en) Glove for use in collecting data for sign language recognition
US10860091B2 (en) Motion predictions of overlapping kinematic chains of a skeleton model used to control a computer system
CN106527738B (en) A kind of multi information body feeling interaction glove system and method for virtual reality system
WO2016026450A1 (en) Glove for use in collecting data for sign language recognition
TWI647595B (en) Body posture detection system, wearable device and method
US20080036737A1 (en) Arm Skeleton for Capturing Arm Position and Movement
US20100023314A1 (en) ASL Glove with 3-Axis Accelerometers
US20190339766A1 (en) Tracking User Movements to Control a Skeleton Model in a Computer System
US20100103104A1 (en) Apparatus for user interface based on wearable computing environment and method thereof
JP6269316B2 (en) Input device, input method, and input program
CN108670263A (en) A kind of sleep pose discrimination method based on MPU-6050
US10319257B2 (en) System of converting hand and finger movements into text and audio
US11079860B2 (en) Kinematic chain motion predictions using results from multiple approaches combined via an artificial neural network
US11237632B2 (en) Ring device having an antenna, a touch pad, and/or a charging pad to control a computing device based on user motions
US10441208B2 (en) Muscle power detection device and method for muscle power classification
Lin et al. Data glove embedded with 6-DOF inertial sensors for hand rehabilitation
US20210068674A1 (en) Track user movements and biological responses in generating inputs for computer systems
JP2013106768A (en) State detecting device, electronic device, and program
Apostolopoulos et al. Accuracy of pedometry on a head-mounted display
US9529445B2 (en) Input device and input method
US20210318759A1 (en) Input device to control a computing device with a touch pad having a curved surface configured to sense touch input
US20170192521A1 (en) Context aware movement recognition system
CN106456051A (en) Respiratory monitoring apparatus, method and device
Gholap A Fall Detection Module for Assisted Living

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: 15834366

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15834366

Country of ref document: EP

Kind code of ref document: A1