CN112254849A - Pressure sensor, pressure sensing system, attitude detection method and attitude detection device - Google Patents

Pressure sensor, pressure sensing system, attitude detection method and attitude detection device Download PDF

Info

Publication number
CN112254849A
CN112254849A CN202011522519.8A CN202011522519A CN112254849A CN 112254849 A CN112254849 A CN 112254849A CN 202011522519 A CN202011522519 A CN 202011522519A CN 112254849 A CN112254849 A CN 112254849A
Authority
CN
China
Prior art keywords
output
pressure
input
fabric
conductive
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.)
Granted
Application number
CN202011522519.8A
Other languages
Chinese (zh)
Other versions
CN112254849B (en
Inventor
张景淇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mianjie Shenzhen Network Technology Co ltd
Original Assignee
Mianjie Beijing Network Technology Co ltd
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 Mianjie Beijing Network Technology Co ltd filed Critical Mianjie Beijing Network Technology Co ltd
Priority to CN202011522519.8A priority Critical patent/CN112254849B/en
Publication of CN112254849A publication Critical patent/CN112254849A/en
Application granted granted Critical
Publication of CN112254849B publication Critical patent/CN112254849B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
    • G01L1/00—Measuring force or stress, in general
    • G01L1/18—Measuring force or stress, in general using properties of piezo-resistive materials, i.e. materials of which the ohmic resistance varies according to changes in magnitude or direction of force applied to the material
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1116—Determining posture transitions

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Medical Informatics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Physiology (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Dentistry (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Force Measurement Appropriate To Specific Purposes (AREA)

Abstract

The application relates to a pressure sensor, a pressure sensing system, and a posture detection method and device. The pressure sensor includes: a fabric pressure sensitive layer that changes its own physical parameter upon detection of a change in pressure; a connection member including an input device and an output device; a first fabric conductive layer comprising an input conductive line for transmitting an input electrical signal input by an input device to the first side of the fabric pressure sensitive layer; the second fabric conducting layer comprises an output conducting wire, and the output conducting wire is used for transmitting an output electric signal obtained after an input electric signal passes through the fabric pressure-sensitive layer to an output device; at least one of the input conductive wires and the output conductive wires is a plurality of input conductive wires, the input conductive wires receive input electric signals in sequence according to a preset first time interval, the output conductive wires send output electric signals in sequence according to a preset second time interval, and a cross area between each input conductive wire and each output conductive wire is used as a detection point of the pressure sensor.

Description

Pressure sensor, pressure sensing system, attitude detection method and attitude detection device
Technical Field
The application relates to the technical field of sensors, in particular to a pressure sensor, a pressure sensing system, and a posture detection method and device.
Background
With the rapid development of sensors, more and more pressure sensors are beginning to emerge.
At present, a mode of adding a layer of piezoresistive coating on an FPC circuit intermediate piece is commonly adopted by a pressure sensor, an upper FPC layer and a lower FPC layer of an FPC type are both provided with conducting circuits, and the resistance change between the upper circuit layer and the lower circuit layer is caused by applying pressure on the upper FPC layer and the lower FPC layer to cause the resistance change of the middle piezoresistive coating.
However, bending is prone to permanent damage to the FPC, resulting in poor bending capability of the currently used pressure sensors.
Disclosure of Invention
The embodiment of the application provides a pressure sensor, a pressure sensing system, a posture detection method and a posture detection device, which can reduce the cost of posture detection.
A pressure sensor for detecting gestures, the pressure sensor comprising:
a fabric pressure sensitive layer for changing a physical parameter of itself upon detection of a change in pressure;
a connection part including an input device for receiving an input electrical signal inputted from the outside and an output device for transmitting an output electrical signal to the outside;
a first fabric conductive layer comprising an input conductive thread electrically connected with the input device, the input conductive thread for transmitting the input electrical signal input by the input device to a first side of the fabric pressure sensitive layer;
the second fabric conducting layer comprises an output conducting wire, the output conducting wire is electrically connected with the output device, and the output conducting wire is used for transmitting an output electric signal obtained after the input electric signal passes through the fabric pressure-sensitive layer to the output device;
the pressure sensor comprises an input conductive wire, an output conductive wire, a plurality of input conductive wires and a plurality of output conductive wires, wherein at least one of the input conductive wires and the output conductive wires is a plurality of input conductive wires, when the input conductive wires are the plurality of input conductive wires, the plurality of input conductive wires sequentially receive input electric signals according to a preset first time interval, when the output conductive wires are the plurality of output conductive wires, the plurality of output conductive wires sequentially send the output electric signals according to a preset second time interval, at least one crossing area is arranged between each input conductive wire and each output conductive wire, and the crossing areas are.
In one embodiment, the input conductive lines are a plurality of lines, the output conductive lines are a plurality of lines, the input conductive lines are parallel to each other, the output conductive lines are parallel to each other, and the input conductive lines and the output conductive lines are perpendicular to each other.
A pressure sensing system comprising a pressure sensor as described above, further comprising:
the power supply circuit is electrically connected with the input conductive wires and is used for sequentially sending an input electric signal to one of the input conductive wires according to a preset first time interval when the input conductive wires included in the first fabric conductive layer are multiple;
and the acquisition circuit is electrically connected with the output conductive wires and is used for sequentially acquiring an output electric signal sent by one of the output conductive wires according to a preset second time interval when the output conductive wires of the second fabric conductive layer are multiple, and the output electric signal is used for detecting the posture of the object to be detected.
An attitude detection method is applied to computer equipment, the computer equipment is connected with a pressure sensing system, the pressure sensing system comprises a pressure sensor, the pressure sensor comprises a plurality of detection points, and the plurality of detection points are used for generating an output electric signal in a time-sharing manner, and the method comprises the following steps:
acquiring at least one frame of sensing data obtained when an object to be detected presses a pressure sensor, wherein each frame of sensing data comprises a plurality of pressure indication information, the pressure indication information corresponds to output electric signals generated by a plurality of detection points in a time-sharing manner one by one, and the pressure sensor comprises: a fabric pressure sensitive layer for changing a physical parameter of itself upon detection of a change in pressure; a connection part including an input device for receiving an input electrical signal inputted from the outside and an output device for transmitting an output electrical signal to the outside; a first fabric conductive layer comprising an input conductive thread electrically connected with the input device, the input conductive thread for transmitting the input electrical signal input by the input device to a first side of the fabric pressure sensitive layer; the second fabric conducting layer comprises an output conducting wire, the output conducting wire is electrically connected with the output device, and the output conducting wire is used for transmitting an output electric signal obtained after the input electric signal passes through the fabric pressure-sensitive layer to the output device; when the input conductive lines are multiple, the multiple output conductive lines sequentially send the output electric signals according to a preset second time interval, at least one crossing area is arranged between each input conductive line and each output conductive line, and the crossing areas are used as detection points of the pressure sensor;
and detecting the posture of the object to be detected according to the generation sequence of the plurality of pressure indication information.
In one embodiment, the detecting the posture of the object to be detected according to the generation sequence of the plurality of pieces of pressure indication information includes:
extracting continuous n frames of induction data, wherein n is a natural number more than 2;
determining the attitude stability of the object to be detected according to the continuous n frames of induction data;
and when the gesture stability is characterized as gesture stability, detecting the gesture of the object to be detected according to the generation sequence of a plurality of pressure indication information of at least one frame of sensing data of continuous n frames.
In one embodiment, each piece of pressure indication information includes a pressure indication value, and determining the posture stability of the object to be detected according to n consecutive frames of sensing data includes:
determining the quantity of target indication information in each frame of sensing data according to a plurality of pressure indication values of each frame of sensing data, wherein the target indication information is pressure indication information which is characterized by no pressing;
calculating the quantity difference between the quantity of the target indication information corresponding to any two frames of the continuous n frames;
and when the quantity difference value corresponding to any two frames is not more than the preset quantity difference value, determining that the posture of the object to be detected is stable.
In one embodiment, the detecting the posture of the object to be detected according to the generation sequence of the plurality of pieces of pressure indication information includes:
configuring a plurality of pieces of pressure indication information into a group of input parameters according to a generation sequence, and inputting the input parameters into a detection model trained in advance so as to indicate the detection model to output a detection result based on the input parameters;
and acquiring a detection result output by the detection model, and determining the posture of the object to be detected according to the detection result.
In one embodiment, the detection model is a convolutional neural network model, and the configuring the plurality of pressure indication information into a set of input parameters according to the generation order includes:
configuring a plurality of pieces of pressure indication information into a group of two-dimensional matrix array according to a generation sequence, wherein the arrangement positions of the pressure indication information in the two-dimensional matrix array are the same as the arrangement positions of corresponding detection points in the pressure sensor;
and taking the two-dimensional matrix array as an input parameter input to the convolutional neural network model.
In one embodiment, the pressure indication information is the output electric signal output by the detection point or the pressing pressure mapped by the output electric signal output by the detection point;
if the pressure indicating information is the output electric signal output by the detection point, the pressure indicating numerical value of the pressure indicating information is in negative correlation with the pressing pressure of the object to be detected on the pressure sensor;
if the pressure indication information is mapped pressing pressure, the pressure indication value of the pressure indication information is positively correlated with the pressing pressure of the object to be detected on the pressure sensor.
In one embodiment, the detecting the posture of the object to be detected according to the generation sequence of the plurality of pieces of pressure indication information includes:
detecting the posture of the object to be detected according to the generation sequence of the plurality of pressure indication information to obtain a sitting posture detection result of the object to be detected, wherein the sitting posture detection result comprises at least one and/or a combination of a plurality of types of left-leaning, right-leaning, balancing, shallow sitting, deep sitting, centering, forward-leaning, backward-leaning and centering.
An attitude detection device applied to a computer device, wherein the computer device is connected with a pressure sensing system, the pressure sensing system comprises a pressure sensor, the pressure sensor comprises a plurality of detection points, and the plurality of detection points are used for generating an output electric signal in a time-sharing manner, and the attitude detection device comprises:
the data acquisition module is used for acquiring at least one frame of sensing data obtained when an object to be detected presses the pressure sensor, each frame of sensing data comprises a plurality of pressure indication information, the pressure indication information corresponds to output electric signals generated by a plurality of detection points in a time-sharing manner, and the pressure sensor comprises: a fabric pressure sensitive layer for changing a physical parameter of itself upon detection of a change in pressure; a connection part including an input device for receiving an input electrical signal inputted from the outside and an output device for transmitting an output electrical signal to the outside; a first fabric conductive layer comprising an input conductive thread electrically connected with the input device, the input conductive thread for transmitting the input electrical signal input by the input device to a first side of the fabric pressure sensitive layer; the second fabric conducting layer comprises an output conducting wire, the output conducting wire is electrically connected with the output device, and the output conducting wire is used for transmitting an output electric signal obtained after the input electric signal passes through the fabric pressure-sensitive layer to the output device; when the input conductive lines are multiple, the multiple output conductive lines sequentially send the output electric signals according to a preset second time interval, at least one crossing area is arranged between each input conductive line and each output conductive line, and the crossing areas are used as detection points of the pressure sensor;
and the detection module is used for detecting the posture of the object to be detected according to the generation sequence of the plurality of pressure indication information.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method described above when executing the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
According to the pressure sensor, the pressure sensing system, the posture detection method and the posture detection device, the fabric pressure-sensitive layer, the first fabric conducting layer and the second fabric conducting layer of the pressure sensor are all made of fabric materials, the fabric materials are high in bending capacity, the fabric pressure-sensitive layer, the first fabric conducting layer and the second fabric conducting layer are obtained by replacing the pressure-sensitive layer, the first conducting layer and the second conducting layer with the fabric materials, the problem that the bending capacity is poor due to the fact that an FPC (flexible printed circuit) is used as the conducting layer is solved, and the bending performance of the pressure sensor is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments or the conventional technologies of the present application, the drawings used in the descriptions of the embodiments or the conventional technologies will be briefly introduced below, it is obvious that the drawings in the following descriptions are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is an exploded schematic view of a pressure sensor according to one embodiment;
fig. 2 is a schematic structural diagram of a first fabric conductive layer 130 according to an embodiment;
fig. 3 is a schematic structural diagram of a second fabric conductive layer 140 according to an embodiment;
FIG. 4 is a schematic diagram of a pressure sensing system according to an exemplary embodiment;
FIG. 5 is a diagram illustrating an application scenario of a gesture detection method according to an embodiment;
FIG. 6 is a flow diagram of a method for gesture detection according to an embodiment;
FIG. 7 is a schematic diagram of a two-dimensional matrix array according to an embodiment;
FIG. 8 is a flowchart of a refinement of step S620 in FIG. 6, according to an embodiment;
fig. 9 is a schematic structural diagram of an attitude detection apparatus according to an embodiment.
Description of reference numerals: the pressure sensor comprises a fabric pressure-sensitive layer 110, a connecting component 120, a first fabric conductive layer 130, a second fabric conductive layer 140, an input device 121, an output device 122, an input conductive wire 131, an output conductive wire 141, a pressure sensor 100, a power supply circuit 200 and an acquisition circuit 300.
Detailed Description
To facilitate an understanding of the present application, the present application will now be described more fully with reference to the accompanying drawings. Embodiments of the present application are set forth in the accompanying drawings. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another.
It will be understood that when an element is referred to as being "connected" to another element, it can be directly connected to the other element or be connected to the other element through intervening elements. Further, "connection" in the following embodiments is understood to mean "electrical connection", "communication connection", or the like, if there is a transfer of electrical signals or data between the connected objects.
As used herein, the singular forms "a", "an" and "the" may include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises/comprising," "includes" or "including," etc., specify the presence of stated features, integers, steps, operations, components, parts, or combinations thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, components, parts, or combinations thereof. Also, as used in this specification, the term "and/or" includes any and all combinations of the associated listed items.
The embodiment of the invention provides a pressure sensor, a pressure sensing system, an attitude detection method and an attitude detection device.
Referring to fig. 1, fig. 1 is an exploded view of a pressure sensor according to an embodiment. In one embodiment, as shown in fig. 1, there is provided a pressure sensor, the pressure sensor of the present embodiment for detecting a posture, the pressure sensor of the present embodiment including a fabric pressure-sensitive layer 110, a connection member 120, a first fabric conductive layer 130, and a second fabric conductive layer 140. Wherein:
the fabric pressure sensitive layer 110 includes a first side and a second side, and the fabric pressure sensitive layer 110 is configured to change its physical parameter when a change in pressure is detected. The connection part 120 includes an input device 121 for receiving an input electrical signal inputted from the outside, and an output device 122 for transmitting an output electrical signal to the outside, the input device 121 being provided to receive the input electrical signal inputted from the outside, and the output device 122 being provided to transmit the output electrical signal to the outside. The first fabric conductive layer 130 is electrically connected to the input device 121 and the first side of the fabric pressure sensitive layer 110, respectively, and the first fabric conductive layer 130 is used for transmitting the input electrical signal input by the input device 121 to the first side of the fabric pressure sensitive layer 110. The second fabric conductive layer 140 is connected to the output device 122 and the second side of the fabric pressure sensitive layer 110, respectively, and the second fabric conductive layer 140 is used for transmitting the output electrical signal obtained after the input electrical signal passes through the fabric pressure sensitive layer 110 to the output device 122.
Wherein, the fabric is a flat soft piece block formed by crossing, winding and connecting fine and flexible objects. The fabric pressure-sensitive layer 110 means that a pressure-sensitive device is woven inside the fabric to form a pressure-sensitive area of the fabric layer. The connecting member 120 may be a conductive element such as a flexible circuit board and a conductive braid. The conductive braid refers to a strip-shaped element which is composed of fabric and can conduct electricity. A Flexible Printed Circuit (FPC) is a highly reliable and excellent Flexible Printed Circuit board made of a polyimide or polyester film as a base material. The fabric conductive layer means that a conductive device is woven inside the fabric and is formed in a conductive area of the fabric layer. The input electrical signal and the output electrical signal in this embodiment may be a current signal or a voltage signal, and are not limited herein.
Specifically, the input device 121 transmits an input electrical signal to the first fabric conductive layer 130 after receiving the input electrical signal inputted from the outside. Since the conductive side of the first fabric layer is electrically connected to the first side of the fabric pressure-sensitive layer 110, an input electrical signal is transmitted to the first side of the fabric pressure-sensitive layer 110 through the first conductive device woven in the first fabric layer, and an output electrical signal is formed on the second side of the fabric pressure-sensitive layer 110 after the input electrical signal flows through the fabric pressure-sensitive layer 110. Since the conductive side of the second textile layer is electrically connected with the second side of the textile pressure-sensitive layer 110, the second textile layer can transmit the output electrical signal to the output device 122 and transmit the output electrical signal to the outside through the output device 122. Since the fabric pressure-sensitive layer 110 has pressure-sensitive characteristics and changes its physical parameter when detecting pressure, the pressure sensor of the present embodiment changes the physical parameter of the fabric pressure-sensitive layer 110 when being pressed, and it can determine whether the pressure sensor is pressed, the pressed position, and the pressed force according to the change of the output electrical signal.
In this embodiment, the outside is referred to as a pressure sensor. The pressure sensor may be considered external to the description of the present embodiment.
In one embodiment, the fabric pressure sensitive layer 110 is a fabric pressure sensitive layer and the physical parameter is a resistance value. The fabric pressure sensitive layer 110 changes the magnitude of the resistance value according to the magnitude of the pressure, thereby outputting a different current signal through the output device 122. Specifically, the larger the pressure applied to the pressure sensor, the smaller the resistance value of the fabric pressure-sensitive layer 110, and the larger the output current signal, it can be determined whether the pressure sensor is pressed or the pressure applied according to the change of the current signal.
It is to be understood that the above-mentioned fabric pressure-sensitive layer 110 is merely an example, and the fabric pressure-sensitive layer 110 of the present embodiment is not limited to only a fabric pressure-sensitive layer as long as the function of changing its own physical parameter according to a change in pressure can be achieved.
In this embodiment, since the fabric pressure-sensitive layer 110, the first fabric conductive layer 130, and the second fabric conductive layer 140 of the pressure sensor are all made of fabric materials, the fabric materials have strong bending capability, and the fabric pressure-sensitive layer 110, the first fabric conductive layer 130, and the second fabric conductive layer 140 are obtained by replacing the pressure-sensitive layer, the first conductive layer, and the second conductive layer with fabric materials, so that the problem of poor bending capability caused by using an FPC as a conductive layer is avoided, and the bending performance of the pressure sensor is improved. The pressure sensor of this embodiment can integrate or sew up in fabric spare, for example clothing, yoga mat fabric spare such as, even fabric spare can not lead to functional failure because of the too big damage pressure sensor of degree of buckling when carrying out folding. In addition, the cost and the manufacturing difficulty can be greatly reduced by replacing a large-area FPC circuit of the traditional sensor with a fabric conducting layer.
Referring to fig. 2, fig. 2 is a schematic structural diagram of a first fabric conductive layer 130 according to an embodiment. In one embodiment, as shown in fig. 2, a first fabric conductive layer 130 is provided that includes at least one input conductive line 131. Wherein:
the input conductive line 131 is electrically connected to the input device 121, and the input conductive line 131 is used for transmitting the input electrical signal input by the input device 121 to the first side of the fabric pressure-sensitive layer 110.
In this embodiment, the input conductive thread 131 is sewn in the first fabric conductive layer 130. Specifically, the input conductive line 131 may be woven by a horizontal conductive cloth in a knitting or weaving manner, and a horizontal conductive yarn in the fabric cloth is integrally woven with the entire cloth as the input conductive line 131, thereby forming the first fabric conductive layer 130. The conductive yarn can be pure metal wire or metal-plated fiber with nylon as base material. The input conductive lines 131 are exposed only on one side of the first fabric conductive layer 130, and a single input conductive line 131 forms one horizontally long conductive area. When the input conductive lines 131 are a plurality of lines, the input conductive lines 131 are spaced apart from each other and are not in contact with each other.
It should be noted that, when the input conductive lines 131 are multiple, the multiple input conductive lines 131 sequentially receive the input electrical signals at a preset first time interval.
The present embodiment is suitable for a scene in which an output electrical signal is sent to an acquisition circuit. Specifically, when only one acquisition circuit is provided, and the input electrical signals are simultaneously sent to the plurality of input conductive lines 131, the output electrical signals output by the acquisition circuits are not known to be obtained according to the input electrical signals sent by which input conductive line 131, that is, which pressure detection point is squeezed.
In this embodiment, when the plurality of input conductive lines 131 are provided, the plurality of input conductive lines 131 sequentially receive the input electrical signals according to the preset first time interval, so that it is clear that the output electrical signals are obtained according to the input electrical signals sent by which input conductive line 131, and the accuracy of determining the pressure detection point is improved.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a second fabric conductive layer 140 according to an embodiment. In one embodiment, as shown in fig. 3, a second fabric conductive layer 140 is provided comprising at least one outgoing conductive thread 141. Wherein:
the output conductive line 141 is electrically connected to the output device 122, and the output conductive line 141 is used for transmitting an output electrical signal obtained after the input electrical signal passes through the fabric pressure-sensitive layer 110 to the output device 122.
In the present embodiment, the output conductive thread 141 is sewn in the second fabric conductive layer 140. Specifically, the output conductive line 141 may be woven by a longitudinal conductive cloth in a knitting or weaving manner, and a longitudinal conductive yarn in the fabric cloth is integrally woven with the entire fabric as the output conductive line 141, so as to form the second fabric conductive layer 140. The output conductive lines 141 are exposed only on one side of the second fabric conductive layer 140, and a single output conductive line 141 forms one longitudinal long conductive area. When the output conductive lines 141 are a plurality of lines, the output conductive lines 141 are separated by a certain distance and do not contact with each other.
In one embodiment, the input conductive line 131 and the output conductive line 141 have crossing regions. Specifically, the fabric pressure sensitive layer 110 is sandwiched between the first fabric conductive layer 130 and the second fabric conductive layer 140, and the fabric pressure sensitive layer 110 in the middle of the crossing region of the input conductive wire 131 and the output conductive wire 141 can be used as a pressure detection point of the pressure sensor. It can be understood that each crossing region of the input conductive line 131 and the output conductive line 141 can be used as a pressure detection point of the pressure sensor, and therefore, the larger the number of crossing regions, the more pressure detection points the pressure sensor can detect.
In one embodiment, when the output conductive lines 141 are a plurality of lines, the plurality of output conductive lines 141 sequentially transmit the output electrical signals at a preset second time interval.
The present embodiment is suitable for a scenario where the output electrical signal is sent to one acquisition circuit 300. Specifically, the output electrical signals sent by the plurality of output conductive lines 141 at the same time may cause the output electrical signals to be unknown which output conductive line 141 is outputting, that is, which pressure detection point is pressed.
In this embodiment, when the plurality of output conductive lines 141 are provided, the plurality of output conductive lines 141 sequentially transmit the output electrical signals according to the preset second time interval, so that which output conductive line 141 transmits the output electrical signal can be known clearly, and the accuracy of determining the pressure detection point is improved.
In one embodiment, at least one of the input conductive lines 131 and the output conductive lines 141 is a plurality of lines, and at least one crossing region is provided between each input conductive line 131 and each output conductive line 141, and the crossing region serves as a detection point of the pressure sensor.
In this embodiment, at least one crossing region is provided between each input conductive line 131 and each output conductive line 141, that is, each input conductive line 131 may have only one crossing region between each output conductive line 141, or may have a plurality of crossing regions, different shapes of the input conductive line 131 and the output conductive line 141 may be set as required, and different interaction relationships between the input conductive line 131 and the output conductive line 141 are established to obtain different results.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a pressure sensing system according to an embodiment. In one embodiment, as shown in FIG. 4, a pressure sensing system is provided that includes a pressure sensor 100, a power supply circuit 200, and an acquisition circuit 300. Wherein:
the pressure sensor 100 is used to receive the pressure of the object to be detected. The power supply circuit 200 is electrically connected to the input conductive wires 131, and is configured to sequentially send an input electrical signal to one of the input conductive wires 131 at a preset first time interval when the input conductive wires 131 included in the first fabric conductive layer 130 are multiple. The collecting circuit 300 is electrically connected to the output conductive lines 141, and is configured to sequentially collect an output electrical signal sent by one of the output conductive lines 141 according to a preset second time interval when the output conductive lines 141 of the second fabric conductive layer 140 are multiple, where the output electrical signal is used to detect the posture of the object to be detected.
Continuing with reference to FIG. 4, illustratively, at time T1, acquisition circuit 300 acquires the output electrical signal output by output conductive line 141B 1. Meanwhile, power supply circuit 200 sends the input electrical signal to input conductive line 131a1 at time t1, to input conductive line 131a2 at time t2, and to input conductive line 131A3 at time t3, respectively. If the output electric signal acquired by the acquisition circuit 300 at time t1 changes, the detection point 131a1141B1 is pressed, if the output electric signal acquired by the acquisition circuit 300 at time t2 changes, the detection point 131a2141B1 is pressed, and if the output electric signal acquired by the acquisition circuit 300 at time t3 changes, the detection point 131a3141B1 is pressed. At time T2, acquisition circuit 300 acquires the output electrical signal output by output conductive line 141B 2. Meanwhile, power supply circuit 200 sends the input electrical signal to input conductive line 131a1 at time t4, to input conductive line 131a2 at time t5, and to input conductive line 131A3 at time t6, respectively. If the output electric signal acquired by the acquisition circuit 300 at time t4 changes, the detection point 131a1141B2 is pressed, if the output electric signal acquired by the acquisition circuit 300 at time t5 changes, the detection point 131a2141B2 is pressed, and if the output electric signal acquired by the acquisition circuit 300 at time t6 changes, the detection point 131a3141B2 is pressed.
It should be noted that, when the plurality of input conductive lines 131 and the plurality of output conductive lines 141 exist simultaneously, the second time interval is greater than or equal to the sum of the first time intervals of two adjacent input conductive lines 131 that sequentially receive the input electrical signal. Specifically, adjacent refers to adjacent in time and not adjacent in space, that is, adjacent two input conductive lines 131 are two input electrical signals that adjacently receive the input electrical signals.
It can be understood that when the output electrical signals corresponding to each detection point are collected, the output electrical signals corresponding to the plurality of detection points can form a frame of sensing data, and the sensing data can be used for detecting the gesture. Specifically, the output electrical signals respectively corresponding to the plurality of detection points may be sorted according to the generation sequence and then used as a frame of sensing data.
In one embodiment, the input conductive line 131 is a plurality of lines, the output conductive line 141 is a plurality of lines, the plurality of input conductive lines 131 are parallel to each other, the plurality of output conductive lines 141 are parallel to each other, and the input conductive line 131 and the output conductive line 141 are perpendicular to each other.
In this embodiment, the pressure sensor 100 is provided with the input conductive lines 131 and the output conductive lines 141 which are mutually crossed, the power supply circuit 200 is used for sequentially sending the input electric signal to one of the input conductive lines 131 according to a preset first time interval and sequentially collecting the output electric signal sent by one of the output conductive lines 141 according to a preset second time interval of the collecting circuit 300, so that posture data of an object to be detected can be collected through one pressure sensor 100, and the cost of detecting the posture is reduced.
In one embodiment, a fabric article is provided. The fabric member of this embodiment includes a pressure sensing system. The pressure sensing system may refer to the description of any embodiment, and this embodiment is not described in detail. The fabric member refers to an article composed of fabric, such as clothes, yoga mat, mattress, sofa, shoes, etc., and is not limited herein.
Referring to fig. 5, fig. 5 is a schematic view of an application scenario of a gesture detection method according to an embodiment. In one embodiment, as shown in fig. 5, the pressure sensing system is connected to the computer device 510, the pressure sensing system is placed under the object to be detected, when the object to be detected presses the pressure sensor 100 of the pressure sensing system, since the power supply circuit 200 continuously supplies power, the plurality of detection points of the pressure sensor 100 of the pressure sensing system generate output electrical signals in a time-sharing manner, a frame of sensing data of the object to be recognized can be obtained according to the output electrical signals respectively corresponding to the plurality of detection points, and the pressing gesture of the object to be detected can be recognized according to the sensing data. The sensed data may be transmitted to the computer device 510 via the acquisition circuit 300. In this embodiment, the pressure sensing system is connected to the computer device 510, and may be connected by wire or wirelessly. For example, the pressure sensing system is provided with a WIFI (wireless fidelity) module, and the sensing data is uploaded to the computer device 510 through the WIFI in the environment.
Referring to fig. 6, fig. 6 is a flowchart illustrating a method for detecting a gesture according to an embodiment. The gesture detection method of the present embodiment is explained as being applied to the computer device 510 in fig. 5. In one embodiment, as shown in fig. 6, there is provided a gesture detection method including:
step S610, obtaining at least one frame of sensing data obtained when the object to be detected presses the pressure sensor, where each frame of sensing data includes a plurality of pressure indication information, and the plurality of pressure indication information corresponds to the output electrical signals generated by the plurality of detection points in a time-sharing manner.
The object to be detected refers to a human body, an animal and the like pressing the pressure sensor. The pressure indication information is the pressure magnitude representing the detection point of the pressing pressure sensor. In this embodiment, the pressure indication information may be the magnitude of the pressing pressure, or may be an output electrical signal directly generated by the pressure sensor. Specifically, since the magnitude of the output electrical signal generated by the pressure sensor can change with the magnitude of the pressing pressure, the magnitude of the pressing pressure can be determined by the output electrical signal, and the output electrical signal is used as pressure indication information; the output electrical signal may also be converted into a corresponding pressing pressure as the pressure indication information, which is not limited herein. In this embodiment, each frame of sensing data includes a plurality of pressure indication information, and the plurality of pressure indication information are obtained according to the output electrical signals sequentially output from the plurality of detection points.
It should be noted that, the pressure sensor of this embodiment may refer to the description of any one of the above embodiments, and the description of this embodiment is not repeated.
In one embodiment, if the fabric pressure-sensitive layer is a fabric piezoresistive layer, the output electrical signal decreases with the increase of the pressing pressure, and if the pressure indication information is the output electrical signal output by the detection point, the pressure indication value of the pressure indication information is negatively correlated with the pressing pressure of the object to be detected on the pressure sensor; if the pressure indication information is mapped pressing pressure, the pressure indication value of the pressure indication information is positively correlated with the pressing pressure of the object to be detected on the pressure sensor.
And S620, detecting the posture of the object to be detected according to the generation sequence of the plurality of pieces of pressure indication information.
Wherein, the posture refers to the posture and the appearance of the body. In this embodiment, the posture includes, but is not limited to, one or more of a sitting posture, a sleeping posture, a standing posture and a running posture, which is not limited herein. In this step, when the object to be recognized presses the pressure sensor, the plurality of detection points of the pressure sensor may sequentially generate the output electrical signals, and the distribution of the object to be recognized on the pressure sensor may be determined according to the output electrical signals generated by the plurality of detection points in a time-sharing manner, so as to determine the posture of the object to be recognized.
In this embodiment, at least one frame of sensing data obtained when the object to be detected presses the pressure sensor is obtained, and since the sensing data is output by one pressure sensor, the cost of gesture detection can be reduced.
In one embodiment, detecting the posture of the object to be detected according to the generation sequence of the plurality of pressure indication information includes:
detecting the posture of the object to be detected according to the generation sequence of the plurality of pressure indication information to obtain a sitting posture detection result of the object to be detected, wherein the sitting posture detection result comprises at least one and/or a combination of a plurality of types of left-leaning, right-leaning, balancing, shallow sitting, deep sitting, centering, forward-leaning, backward-leaning and centering.
In the present embodiment, at least one sitting posture of a left side, a right side, a balance, a shallow seat, a deep seat, a center, a forward lean, a backward lean, and a center, and/or a combination of a plurality of sitting postures may be detected according to a generation order of the plurality of pressure indication information. For example, a sitting posture of left, right, balance, shallow, deep, centered, forward, reclining, and centered may be detected according to a generation order of the plurality of pressure indication information; for example, the order of generating the plurality of pressure indication information may be combined in various ways, such as a left and shallow seat, a right and shallow seat, and the like.
In one embodiment, detecting the posture of the object to be detected according to the generation order of the plurality of pressure indication information may include:
configuring a plurality of pieces of pressure indication information into a group of input parameters according to a generation sequence, and inputting the input parameters into a detection model trained in advance so as to indicate the detection model to output a detection result based on the input parameters;
and acquiring a detection result output by the detection model, and determining the posture of the object to be detected according to the detection result.
In this embodiment, the detection result may represent the similarity probability of the input parameter and each gesture. The pose with the highest probability of similarity may be taken as the pose of the object to be recognized. Specifically, the detection model may be an artificial intelligence model obtained by training through supervised learning. And performing label processing on training parameters consisting of a plurality of pressure indication information and corresponding sitting posture results, thereby obtaining a detection model after training is completed through supervised learning training. In this embodiment, optionally, the pressure indication information may be configured into a set of input parameters according to the generation sequence, so as to be input into the detection model, the detection model may obtain a detection result according to the input parameters, and the posture of the object to be recognized may be determined according to the detection result.
For example, if the posture is a sitting posture, the sitting posture is determined by pressure indication information of x, y and z axes output by the pressure sensor, and the x axis is a state value of left and right balance of the object to be recognized, including left, right and balance. The y-axis is three state values of the object to be recognized, namely a shallow seat, a deep seat and a middle seat, and the z-axis is three state values of the object to be recognized, namely a forward leaning state, a backward leaning state and a middle state.
In an embodiment, optionally, the monitoring model is a Recurrent Neural Network (RNN) model, the input parameter is a set of serial data sequentially ordered according to the generation order, and the serial data is input into the RNN model trained in advance, so that a detection result is output through the RNN model.
In another embodiment, optionally, the detection model is a Convolutional Neural Network (CNN) model, and the configuring the plurality of pressure indication information into a set of input parameters according to the generation order includes:
configuring a plurality of pieces of pressure indication information into a group of two-dimensional matrix array according to a generation sequence, wherein the arrangement positions of the pressure indication information in the two-dimensional matrix array are the same as the arrangement positions of corresponding detection points in the pressure sensor;
and taking the two-dimensional matrix array as an input parameter input to the convolutional neural network model.
In this embodiment, the arrangement positions of the pressure indication information in the two-dimensional matrix array correspond to the arrangement positions of the detection points in the pressure sensor, and then the position relationship between each pressure indication information in the two-dimensional matrix array and the adjacent pressure indication information can be kept, so that the posture of the object to be recognized is better restored, the two-dimensional matrix data is detected through the CNN model, and the accuracy of posture detection can be improved. In addition, generally, the CNN model is used for image processing, and it is necessary to convert an image into a two-dimensional matrix array, and then perform convolution and pooling calculations. In the embodiment, the plurality of pieces of pressure indication information are configured into the two-dimensional matrix array according to the generation sequence, and the generated two-dimensional matrix array is the two-dimensional matrix array, so that the image does not need to be converted into the two-dimensional matrix array for detection, the calculation force required by the detection model is reduced, and the time for detecting the posture is shortened.
In one embodiment, the CNN model contains a total of 8 convolutional layers, 2 pooled layers, and 2 fully-connected layers. Where each convolution layer contains a 2d convolution (Conv 2 d), batch normalization (batch normalization), and Relu activation functions. The probabilities of the individual decision results are then output by means of the softmax function.
Referring to fig. 4 and fig. 7 together, fig. 7 is a schematic diagram of a two-dimensional matrix array according to an embodiment. In one embodiment, as shown in fig. 4 and 7, the arrangement position of the pressure indication information in the two-dimensional matrix array is the same as the arrangement position of the corresponding detection point in the pressure sensor.
Referring to fig. 8, fig. 8 is a flowchart illustrating a refinement of step S620 in fig. 6 according to an embodiment. In one embodiment, the step S620 of detecting the posture of the object to be detected according to the generation sequence of the plurality of pieces of pressure indication information includes:
and step S810, extracting n continuous frames of induction data, wherein n is a natural number more than 2.
In this step, n consecutive frames of sensing data are extracted from the sensing data output from the pressure sensor.
And S820, determining the posture stability of the object to be detected according to the continuous n frames of induction data.
The posture stability is a parameter representing whether the posture of the object to be detected is stable or not. Specifically, the attitude stability may represent an attitude stability or an attitude instability, and the like, and is not limited herein.
And S830, when the posture stability is characterized as being stable, detecting the posture of the object to be detected according to the generation sequence of the multiple pressure indication information of at least one frame of induction data of the continuous n frames.
In this step, when the posture stability is characterized as posture stability, the posture of the object to be detected is detected through at least one frame of induction data of n continuous frames. In this embodiment, a manner how to detect the posture of the object to be detected through the generation sequence of the pressure indication information may refer to the description of any one of the embodiments described above, which is not repeated in this embodiment.
In this embodiment, the gesture stability of the object to be detected is determined by extracting n continuous frames of sensing data, and when the gesture stability is characterized by being stable, the gesture is detected by using at least one frame of the n frames of sensing data, that is, when the gesture of the object to be recognized is stable, the gesture is detected by using the stable sensing data, so that the gesture detection accuracy is improved.
In an embodiment, each piece of pressure indication information includes a pressure indication value, and the step S820 of determining the posture stability of the object to be detected according to n consecutive frames of sensing data includes:
determining the quantity of target indication information in each frame of sensing data according to a plurality of pressure indication values of each frame of sensing data, wherein the target indication information is pressure indication information which is characterized by no pressing;
calculating the quantity difference between the quantity of the target indication information corresponding to any two frames of the continuous n frames;
and when the quantity difference value corresponding to any two frames is not more than the preset quantity difference value, determining that the posture of the object to be detected is stable.
In this embodiment, the pressure indication value refers to the value of the pressure indication information. The target indication information refers to pressure indication information which is characterized by no pressing in a plurality of pressure indication information of each frame of sensing data. Specifically, if the pressure indication information is the pressing pressure, the target indication information is the pressure indication information with the pressing pressure being zero; if the pressure indication information is an output electric signal, the target indication information is the pressure indication information corresponding to the output electric signal and the non-pressing pressure. After the number of the target indication information is determined, the number difference value between the number of the target indication information of any two frames of the continuous n frames is calculated. And if the quantity difference of any two frames is not greater than the preset quantity difference, determining that the posture of the detected object is stable. It can be understood that the preset number difference value for judging the sitting posture stability and the preset number difference value for judging the sleeping posture stability are inconsistent, the preset number difference value can be set according to the posture detected as required, and the method is not limited here.
For example, if n is 2, when the number of the target indication information of the first frame is 50, the number of the target indication information of the second frame is 53, and the difference is less than 5 points, it is determined that the two frames are stable. If n is 3, if the number of the target indication information of the third frame is 60 and the difference from the second frame is greater than 5 points, the third frame is an unstable frame. And if n is 3, determining that the posture of the object to be detected is stable when continuous 3 frames are required to be stable.
It should be understood that although the various steps in the flowcharts of fig. 6 and 8 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 6 and-8 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps or stages.
Referring to fig. 9, fig. 9 is a schematic structural diagram of an attitude detection apparatus according to an embodiment. The posture detecting apparatus of the present embodiment is explained as being applied to the computer device in fig. 5. In one embodiment, as shown in fig. 9, a gesture detection apparatus is provided, comprising a data acquisition module 910 and a detection module 920, wherein:
the data acquisition module 910 is configured to acquire at least one frame of sensing data obtained when the pressure sensor is pressed by an object to be detected, where each frame of sensing data includes multiple pieces of pressure indication information, and the multiple pieces of pressure indication information correspond to output electrical signals generated at multiple detection points in a time-sharing manner one to one; a detecting module 920, configured to detect the posture of the object to be detected according to the generation sequence of the multiple pieces of pressure indication information.
In one embodiment, the detection module 920 includes: the induction data extraction unit is used for extracting n continuous frames of induction data, wherein n is a natural number more than 2; the stability determining unit is used for determining the attitude stability of the object to be detected according to the continuous n frames of sensing data; and the detection unit is used for detecting the posture of the object to be detected according to the generation sequence of the plurality of pressure indication information of at least one frame of induction data of continuous n frames when the posture stability is characterized as stable.
In one embodiment, each piece of pressure indication information includes a pressure indication value, and the detection unit is specifically configured to determine, according to a plurality of pressure indication values of each frame of sensing data, a number of pieces of target indication information in each frame of sensing data, where the target indication information is pressure indication information characterized as being non-pressed; calculating the quantity difference between the quantity of the target indication information corresponding to any two frames of the continuous n frames; and when the quantity difference value corresponding to any two frames is not more than the preset quantity difference value, determining that the posture of the object to be detected is stable.
In one embodiment, the detection module 920 further comprises: the configuration unit is used for configuring a plurality of pieces of pressure indication information into a group of input parameters according to a generation sequence, and inputting the input parameters into a detection model which is trained in advance so as to indicate the detection model to output a detection result based on the input parameters; the detection unit is further used for obtaining a detection result output by the detection model and determining the posture of the object to be detected according to the detection result.
In one embodiment, the detection model is a convolutional neural network model, and the configuration unit is specifically configured to configure a plurality of pieces of pressure indication information into a group of two-dimensional matrix arrays according to a generation sequence, where the arrangement positions of the pieces of pressure indication information in the two-dimensional matrix arrays are the same as the arrangement positions of corresponding detection points in the pressure sensors; and taking the two-dimensional matrix array as an input parameter input to the convolutional neural network model.
In one embodiment, the pressure indication information is the output electrical signal output by the detection point or the pressing pressure mapped by the output electrical signal output by the detection point; if the pressure indicating information is the output electric signal output by the detection point, the pressure indicating numerical value of the pressure indicating information is in negative correlation with the pressing pressure of the object to be detected on the pressure sensor; if the pressure indication information is mapped pressing pressure, the pressure indication value of the pressure indication information is positively correlated with the pressing pressure of the object to be detected on the pressure sensor.
In an embodiment, the detecting module 920 is specifically configured to detect the posture of the object to be detected according to the generation sequence of the plurality of pressure indication information, so as to obtain a sitting posture detection result of the object to be detected, where the sitting posture detection result includes at least one of left, right, balance, shallow, deep, centered, forward leaning, reclining, and centered, and/or a combination of multiple types.
For the specific definition of the gesture detection device, see the above definition of the gesture detection method, which is not described herein again. The modules in the gesture detection device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and there may be another division manner in actual implementation.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the above-described method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
In the description herein, references to the description of "some embodiments," "other embodiments," "desired embodiments," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, a schematic description of the above terminology may not necessarily refer to the same embodiment or example.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (13)

1. A pressure sensor for detecting a gesture, the pressure sensor comprising:
a fabric pressure sensitive layer for changing a physical parameter of itself upon detection of a change in pressure;
a connection part including an input device for receiving an input electrical signal inputted from the outside and an output device for transmitting an output electrical signal to the outside;
a first fabric conductive layer comprising an input conductive thread electrically connected with the input device, the input conductive thread for transmitting the input electrical signal input by the input device to a first side of the fabric pressure sensitive layer;
the second fabric conducting layer comprises an output conducting wire, the output conducting wire is electrically connected with the output device, and the output conducting wire is used for transmitting an output electric signal obtained after the input electric signal passes through the fabric pressure-sensitive layer to the output device;
the pressure sensor comprises an input conductive wire, an output conductive wire, a plurality of input conductive wires and a plurality of output conductive wires, wherein at least one of the input conductive wires and the output conductive wires is a plurality of input conductive wires, when the input conductive wires are the plurality of input conductive wires, the plurality of input conductive wires sequentially receive input electric signals according to a preset first time interval, when the output conductive wires are the plurality of output conductive wires, the plurality of output conductive wires sequentially send the output electric signals according to a preset second time interval, at least one crossing area is arranged between each input conductive wire and each output conductive wire, and the crossing areas are.
2. The pressure sensor of claim 1, wherein the input conductive line is a plurality of lines, the output conductive line is a plurality of lines, the plurality of input conductive lines are parallel to each other, the plurality of output conductive lines are parallel to each other, and the input conductive line and the output conductive line are perpendicular to each other.
3. A pressure sensing system comprising the pressure sensor of claim 1 or 2, further comprising:
the power supply circuit is electrically connected with the input conductive wires and is used for sequentially sending an input electric signal to one of the input conductive wires according to a preset first time interval when the input conductive wires included in the first fabric conductive layer are multiple;
and the acquisition circuit is electrically connected with the output conductive wires and is used for sequentially acquiring an output electric signal sent by one of the output conductive wires according to a preset second time interval when the output conductive wires of the second fabric conductive layer are multiple, and the output electric signal is used for detecting the posture of the object to be detected.
4. An attitude detection method is applied to computer equipment, the computer equipment is connected with a pressure sensing system, the pressure sensing system comprises a pressure sensor, the pressure sensor comprises a plurality of detection points, and the plurality of detection points are used for generating an output electric signal in a time-sharing manner, and the method comprises the following steps:
acquiring at least one frame of sensing data obtained when an object to be detected presses a pressure sensor, wherein each frame of sensing data comprises a plurality of pressure indication information, the pressure indication information corresponds to output electric signals generated by a plurality of detection points in a time-sharing manner one by one, and the pressure sensor comprises: a fabric pressure sensitive layer for changing a physical parameter of itself upon detection of a change in pressure; a connection part including an input device for receiving an input electrical signal inputted from the outside and an output device for transmitting an output electrical signal to the outside; a first fabric conductive layer comprising an input conductive thread electrically connected with the input device, the input conductive thread for transmitting the input electrical signal input by the input device to a first side of the fabric pressure sensitive layer; the second fabric conducting layer comprises an output conducting wire, the output conducting wire is electrically connected with the output device, and the output conducting wire is used for transmitting an output electric signal obtained after the input electric signal passes through the fabric pressure-sensitive layer to the output device; when the input conductive lines are multiple, the multiple output conductive lines sequentially send the output electric signals according to a preset second time interval, at least one crossing area is arranged between each input conductive line and each output conductive line, and the crossing areas are used as detection points of the pressure sensor;
and detecting the posture of the object to be detected according to the generation sequence of the plurality of pressure indication information.
5. The posture detection method according to claim 4, wherein the detecting the posture of the object to be detected according to the generation order of the plurality of pieces of pressure indication information includes:
extracting continuous n frames of induction data, wherein n is a natural number more than 2;
determining the attitude stability of the object to be detected according to the continuous n frames of induction data;
and when the gesture stability is characterized as gesture stability, detecting the gesture of the object to be detected according to the generation sequence of a plurality of pressure indication information of at least one frame of sensing data of continuous n frames.
6. The attitude detection method according to claim 5, wherein each piece of pressure indication information includes a pressure indication value, and the determining the attitude stability of the object to be detected based on n consecutive frames of sensing data includes:
determining the quantity of target indication information in each frame of sensing data according to a plurality of pressure indication values of each frame of sensing data, wherein the target indication information is pressure indication information which is characterized by no pressing;
calculating the quantity difference between the quantity of the target indication information corresponding to any two frames of the continuous n frames;
and when the quantity difference value corresponding to any two frames is not more than the preset quantity difference value, determining that the posture of the object to be detected is stable.
7. The posture detection method according to claim 4, wherein the detecting the posture of the object to be detected according to the generation order of the plurality of pieces of pressure indication information includes:
configuring a plurality of pieces of pressure indication information into a group of input parameters according to a generation sequence, and inputting the input parameters into a detection model trained in advance so as to indicate the detection model to output a detection result based on the input parameters;
and acquiring a detection result output by the detection model, and determining the posture of the object to be detected according to the detection result.
8. The pose detection method of claim 7, wherein the detection model is a convolutional neural network model, said configuring a plurality of pressure indication information into a set of input parameters according to a generation order comprising:
configuring a plurality of pieces of pressure indication information into a group of two-dimensional matrix array according to a generation sequence, wherein the arrangement positions of the pressure indication information in the two-dimensional matrix array are the same as the arrangement positions of corresponding detection points in the pressure sensor;
and taking the two-dimensional matrix array as an input parameter input to the convolutional neural network model.
9. The attitude sensing method according to claim 4, wherein the pressure indication information is an output electrical signal output from the sensing point or a pressing pressure mapped to the output electrical signal output from the sensing point;
if the pressure indicating information is the output electric signal output by the detection point, the pressure indicating numerical value of the pressure indicating information is in negative correlation with the pressing pressure of the object to be detected on the pressure sensor;
if the pressure indication information is mapped pressing pressure, the pressure indication value of the pressure indication information is positively correlated with the pressing pressure of the object to be detected on the pressure sensor.
10. The posture detection method according to any one of claims 4 to 9, wherein the detecting the posture of the object to be detected according to the generation order of the plurality of pieces of pressure indication information includes:
detecting the posture of the object to be detected according to the generation sequence of the plurality of pressure indication information to obtain a sitting posture detection result of the object to be detected, wherein the sitting posture detection result comprises at least one and/or a combination of a plurality of types of left-leaning, right-leaning, balancing, shallow sitting, deep sitting, centering, forward-leaning, backward-leaning and centering.
11. An attitude sensing apparatus, applied to a computer device, the computer device being connected to a pressure sensing system, the pressure sensing system including a pressure sensor, the pressure sensor including a plurality of detection points, the plurality of detection points being configured to generate an output electrical signal in a time-sharing manner, the apparatus comprising:
the data acquisition module is used for acquiring at least one frame of sensing data obtained when an object to be detected presses the pressure sensor, each frame of sensing data comprises a plurality of pressure indication information, the pressure indication information corresponds to output electric signals generated by a plurality of detection points in a time-sharing manner, and the pressure sensor comprises: a fabric pressure sensitive layer for changing a physical parameter of itself upon detection of a change in pressure; a connection part including an input device for receiving an input electrical signal inputted from the outside and an output device for transmitting an output electrical signal to the outside; a first fabric conductive layer comprising an input conductive thread electrically connected with the input device, the input conductive thread for transmitting the input electrical signal input by the input device to a first side of the fabric pressure sensitive layer; the second fabric conducting layer comprises an output conducting wire, the output conducting wire is electrically connected with the output device, and the output conducting wire is used for transmitting an output electric signal obtained after the input electric signal passes through the fabric pressure-sensitive layer to the output device; when the input conductive lines are multiple, the multiple output conductive lines sequentially send the output electric signals according to a preset second time interval, at least one crossing area is arranged between each input conductive line and each output conductive line, and the crossing areas are used as detection points of the pressure sensor;
and the detection module is used for detecting the posture of the object to be detected according to the generation sequence of the plurality of pressure indication information.
12. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 4 to 10 when executing the computer program.
13. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 4 to 10.
CN202011522519.8A 2020-12-22 2020-12-22 Pressure sensor, pressure sensing system, attitude detection method and attitude detection device Active CN112254849B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011522519.8A CN112254849B (en) 2020-12-22 2020-12-22 Pressure sensor, pressure sensing system, attitude detection method and attitude detection device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011522519.8A CN112254849B (en) 2020-12-22 2020-12-22 Pressure sensor, pressure sensing system, attitude detection method and attitude detection device

Publications (2)

Publication Number Publication Date
CN112254849A true CN112254849A (en) 2021-01-22
CN112254849B CN112254849B (en) 2021-06-04

Family

ID=74225429

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011522519.8A Active CN112254849B (en) 2020-12-22 2020-12-22 Pressure sensor, pressure sensing system, attitude detection method and attitude detection device

Country Status (1)

Country Link
CN (1) CN112254849B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113178628A (en) * 2021-04-19 2021-07-27 河南利威新能源科技有限公司 Lithium ion battery module and health state monitoring method thereof
CN113358249A (en) * 2021-06-11 2021-09-07 中国科学技术大学 Fabric type piezoresistive sensor array and intelligent object
CN113588144A (en) * 2021-07-23 2021-11-02 南方科技大学 Stress distribution detection system, method and device
CN114983399A (en) * 2022-07-18 2022-09-02 四川爱麓智能科技有限公司 Behavior monitoring and identifying method and interactive feedback system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101201278A (en) * 2007-11-30 2008-06-18 清华大学 System for monitoring curved surface interlaminar extrusion pressure based on array type ultra-thin submissive force sensor
CN101201279A (en) * 2007-12-07 2008-06-18 安徽君诚体育器材有限公司 Apparatus for measuring pressure distribution and method for measuring thereof
CN109489874A (en) * 2019-01-16 2019-03-19 浙江理工大学 A kind of carbon fiber flexible pressure distributed sensor device and its force measuring method
CN109738096A (en) * 2019-01-21 2019-05-10 北京诺亦腾科技有限公司 A kind of applanation detection device
CN209841248U (en) * 2019-04-28 2019-12-24 武汉飞帛丝科技有限公司 Flexible array pressure sensor

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101201278A (en) * 2007-11-30 2008-06-18 清华大学 System for monitoring curved surface interlaminar extrusion pressure based on array type ultra-thin submissive force sensor
CN101201279A (en) * 2007-12-07 2008-06-18 安徽君诚体育器材有限公司 Apparatus for measuring pressure distribution and method for measuring thereof
CN109489874A (en) * 2019-01-16 2019-03-19 浙江理工大学 A kind of carbon fiber flexible pressure distributed sensor device and its force measuring method
CN109738096A (en) * 2019-01-21 2019-05-10 北京诺亦腾科技有限公司 A kind of applanation detection device
CN209841248U (en) * 2019-04-28 2019-12-24 武汉飞帛丝科技有限公司 Flexible array pressure sensor

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113178628A (en) * 2021-04-19 2021-07-27 河南利威新能源科技有限公司 Lithium ion battery module and health state monitoring method thereof
CN113358249A (en) * 2021-06-11 2021-09-07 中国科学技术大学 Fabric type piezoresistive sensor array and intelligent object
CN113358249B (en) * 2021-06-11 2022-09-30 中国科学技术大学 Fabric type piezoresistive sensor array and intelligent object
CN113588144A (en) * 2021-07-23 2021-11-02 南方科技大学 Stress distribution detection system, method and device
CN113588144B (en) * 2021-07-23 2023-08-18 南方科技大学 Stress distribution detection system, method and device
CN114983399A (en) * 2022-07-18 2022-09-02 四川爱麓智能科技有限公司 Behavior monitoring and identifying method and interactive feedback system

Also Published As

Publication number Publication date
CN112254849B (en) 2021-06-04

Similar Documents

Publication Publication Date Title
CN112254849B (en) Pressure sensor, pressure sensing system, attitude detection method and attitude detection device
CN106095099B (en) A kind of user behavior motion detection recognition methods
CN108209863A (en) Non- wearable sleeping position monitoring device and its bed necessaries
CN214149645U (en) Flexible wearable pressure sensor based on elastic cloth
US20210100480A1 (en) Apparatus and method for detecting posture using artificial intelligence
JP6886141B2 (en) Sitting posture monitoring system
CN107278286A (en) Determine the method and apparatus of the position of fingerprint prompting pattern in display screen
KR20180009925A (en) Carpet System using Smart Fabric
US8436820B2 (en) Touchpad using resistive electro-conductive fiber and input device having the same
Liu et al. Sitting posture recognition based on human body pressure and CNN
CN106446876B (en) A kind of sensing Activity recognition method and apparatus
Özdemir et al. Smart woven fabrics with portable and wearable vibrating electronics
US20210208691A1 (en) Pressure measuring device using textile sensor, and internet of things-based device control system using same
CN205729355U (en) A kind of human biological electricity and athletic posture intelligent monitoring clothing
CN208080632U (en) Trainer shoe and motion state monitor system
CN106226821B (en) A kind of physical activity detection method, device and sensor
CN110779143A (en) Control method, device and equipment of air conditioner and air conditioner
CN107454949A (en) A kind of motion sensor means, method and wearing module
CN113820049A (en) Fabric pressure sensor, preparation method thereof and fabric pressure sensor array
CN107169501B (en) Pressure and altitude data integration method and system
CN205512411U (en) Human biological electricity of back formula and motion gesture intelligent monitoring clothing
CN112535473A (en) Wearable nano sensor for measuring clothes and measuring system thereof
CN117770771B (en) Undisturbed sleep monitoring method and device
CN114089858A (en) Cloth base material, production method thereof and pressure detection method
CN219330762U (en) Wearable flexible fabric pressure sensor vest

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
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20230522

Address after: 518000 Building 7, Qianhai Youth Dream Workshop, Nanshan Street, Qianhai Shenzhen-Hong Kong Cooperation Zone, Shenzhen, Guangdong Province

Patentee after: Mianjie (Shenzhen) Network Technology Co.,Ltd.

Address before: 100010 room 1626, building 1, 17 zangjingguan Hutong, Dongcheng District, Beijing

Patentee before: Mianjie (Beijing) Network Technology Co.,Ltd.