Wrist-worn sports device with gesture recognition and power management

Abstract

A wrist-worn athletic performance monitoring system includes a gesture recognition processor configured to perform a gesture recognition process. Interaction with the performance monitoring system can be based at least in part on gestures performed by a user and provide an alternative to using physical buttons to make selections on the performance monitoring system, which can be cumbersome and / or inconvenient to use when performing athletic activities. In addition, the recognized gestures can be used to select one or more operating modes for the athletic performance monitoring system, so that a reduction in power consumption can be achieved.

Description

[0001] This application is a divisional application of the invention application with application date of August 7, 2014, application number 201480055168.0 and invention name “Wrist-worn sports device with gesture recognition and power management”.

[0002] CROSS-REFERENCE TO RELATED APPLICATIONS

[0003] This application claims the benefit of and priority to U.S. Provisional Patent Application No. 61 / 863,249, entitled “GESTURE RECOGNITION,” filed on August 7, 2013. The disclosure of said application is expressly incorporated herein by reference in its entirety and for any and all non-limiting purposes. Background Art

[0004] Modern technology has produced a variety of different electronic and / or communication devices that allow users to stay connected, entertained, and informed. A wide variety of portable electronic devices can be used for these purposes, such as: cellular phones; personal digital assistants ("PDAs"); pagers; pagers; MP3 or other audio playback devices; radios; portable televisions, DVD players, or other video playback devices; watches; GPS systems; and the like. Many people like to carry one or more of these types of devices with them when they exercise and / or participate in sports activities, for example, to keep in touch with others (e.g., to prevent bad weather, injuries; or emergencies; to contact coaches or trainers; and the like), to entertain them, and to provide information (time, directions, location, and the like).

[0005] Sports performance monitoring systems have also benefited from the latest developments in electronic devices and digital technology. Electronic performance monitoring devices allow monitoring of many physical or physiological characteristics related to exercise or other sports performance, including, for example: speed and distance data, altitude data, GPS data, heart rate, pulse rate, blood pressure data, body temperature, etc. Specifically, these sports performance monitoring systems have benefited from the latest developments in microprocessor design, allowing increasingly complex calculations and processes to be performed by microprocessors of increasingly smaller sizes. These modern microprocessors can be used to perform activity recognition processes so that the sports or activities being performed by athletes can be recognized, and information related to the sports or activities can be analyzed and / or stored. However, in some cases, interaction with these performance monitoring systems can be cumbersome and require athletes to use a series of buttons typical of conventional computer systems or portable electronic devices to make selections on the device. For athletes performing sports activities, interacting with performance monitoring systems in a traditional manner and making selections about system functions can be distracting, uncomfortable, or infeasible. In addition, these systems are typically powered by limited power sources such as rechargeable batteries so that the devices can be worn by athletes to allow portable activity monitoring and recognition. As the calculations performed by sports performance monitoring systems have become increasingly complex, the power consumption of integrated microprocessors performing calculations has also increased significantly. As a result, the usable time between battery charges has decreased.Therefore, there is a need for more efficient systems and methods for interacting with athletic performance monitoring devices and extending the battery life of athletic performance monitoring systems.

[0006] Aspects of the present disclosure are directed to novel systems and methods that address one or more of these deficiencies. Additional aspects relate to minimizing other shortcomings in the art. Summary of the invention

[0007] A simplified overview of the present disclosure is presented below to provide a basic understanding of some aspects of the present invention. This overview is not an extensive review of the present invention. It is not intended to identify the key and important elements of the present invention or to outline the scope of the present invention. The following overview only presents some concepts of the present invention in a simplified form as a prelude to a more detailed description provided later.

[0008] Various aspects of the systems and methods described herein relate to a non-transitory computer-readable medium having computer-executable instructions for receiving acceleration data into a gesture recognition processor in a device. The device can be placed on an appendage of a user and operated according to a first operating mode. The received acceleration data can represent movement of the user's appendage and can be classified as a gesture. After the classification is completed, the device can operate according to a second operating mode, wherein the second operating mode is selected based on the classified gesture.

[0009] In another aspect, the present disclosure relates to a device configured to be worn on an appendage of a user, comprising a sensor configured to collect acceleration data, a gesture recognition processor, and an activity processor. The device also includes a non-transitory computer-readable medium including computer-executable instructions for classifying the collected acceleration data into a gesture and selecting an operating mode for the activity processor based on the classified gesture.

[0010] In yet another aspect, the present invention relates to a non-transitory computer-readable medium having computer-executable instructions which, when executed by a processor, are configured to receive motion data from a sensor on a device, identify or select a gesture from the data, and adjust an operating mode of the device based on the identified gesture.

[0011] This Summary is provided to introduce selected concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 An exemplary system that may be configured to provide personal training and / or obtain data from a user's physical movements according to an exemplary embodiment is shown;

[0013] Figure 2 It shows that it can be Figure 1 An exemplary computer device that is part of or in communication with a system.

[0014] Figure 3 shows an exemplary sensor assembly that may be worn by a user according to an example embodiment;

[0015] Figure 4 Another exemplary sensor assembly that may be worn by a user according to an example embodiment is shown;

[0016] Figure 5 Illustrative locations for sensory input are shown, which may include physical sensors located on / in the user's clothing and / or be based on the recognition of a relationship between two moving body parts of the user;

[0017] Figure 6 is a schematic block diagram of an exemplary sensor device 600 that can be used for gesture recognition;

[0018] Figure 7 It is a schematic block diagram of the posture recognition training process.

[0019] Figure 8 It is a schematic block diagram of the gesture recognition process.

[0020] Fig. 9is a schematic block diagram of the operation mode selection process. DETAILED DESCRIPTION

[0021] Aspects of the present disclosure relate to identifying the gestures performed by the athlete, so as to call the specific functions of the relevant sports performance monitoring equipment. Except for the gesture information, the gesture can be identified from the motion data including one or more sports activities performed by the athlete / user as a representative. The motion data can be actively or passively sensed and / or stored in one or more non-temporary storage media, and used to generate output, for example, the calculated motion attribute, the feedback signal providing guidance, and / or other information. These and other aspects will be discussed in the context of the following illustrative embodiments of the personal training system.

[0022] In the following description of various embodiments, reference is made to the accompanying drawings, which form a part of this document and in which various embodiments are shown by way of illustration, and in which various aspects of the present disclosure may be practiced. However, it should be understood that other embodiments may be utilized and structural and functional modifications may be made without departing from the scope and spirit of the present disclosure. In addition, the headings within the scope of the present disclosure should not be considered as limiting aspects of the present disclosure, and the exemplary embodiments are not limited to the example headings.

[0023] I. Example Personal Training System

[0024] A. Illustrative Network

[0025] Various aspects of the present disclosure relate to systems and methods that can be utilized across multiple networks. In this regard, certain embodiments can be configured to adapt to dynamic network environments. Other embodiments can operate in different discontinuous network environments. Figure 1 An example of a personal training system 100 according to an example embodiment is shown. The example system 100 may include one or more interconnected networks, such as an illustrative body area network (BAN) 102, a local area network (LAN) 104, and a wide area network (WAN) 106. Figure 1As shown (and described throughout this disclosure), one or more networks (e.g., BAN 102, LAN 104, and / or WAN 106) may overlap or otherwise include each other. Those skilled in the art will appreciate that the exemplary networks 102-106 are logical networks that may each include one or more different communication protocols and / or network architectures, but may also be configured to have gateways to each other or other networks. For example, each of the BAN 102, LAN 104, and / or WAN 106 may be operably connected to the same physical network architecture, such as a cellular network architecture 108 and / or a wide area network architecture 110. For example, the portable electronic device 112, which may be considered to be a component of both the BAN 102 and the LAN 104, may include a network adapter or network interface card (NIC) that is configured to convert data and control signals to or from network information that traverses the one or more architectures 108 and / or 110 in accordance with one or more communication protocols, such as the Transmission Control Protocol (TCP), the Internet Protocol (IP), and the User Datagram Protocol (UDP), which are well known in the art and, therefore, will not be discussed in further detail.

[0026] The network architectures 108 and 110 may include one or more information distribution networks of any type or topology, alone or in combination, such as cable, fiber optic, satellite phone, cellular, wireless, etc., and thus may have a variety of configurations, such as having one or more wired or wireless communication channels (including but not limited to: Near Field Communication (NFC) and / or ANT technology). Thus, Figure 1 Any device in the network (eg, portable electronic device 112 or any other device described herein) may be considered to belong to one or more different logical networks 102-106. With the foregoing in mind, example components of an illustrative BAN and LAN (which may be coupled to WAN 106) are described.

[0027] 1. Sample LAN

[0028] The local area network 104 may include one or more electronic devices, such as a computer device 114. The computer device 114 or any other component of the system 100 may include a mobile terminal, such as a phone, a music player, a tablet, a netbook, or any portable device. In other embodiments, the computer device 114 may include a media player or recorder, a desktop computer, a server, a game console, such as a XBOX, Playstation, and / or Wii game console. Those skilled in the art will appreciate that these are merely example devices for description purposes and that the present disclosure is not limited to any console or computing device.

[0029] Those skilled in the art will appreciate that the design and configuration of the computer device 114 may vary depending on a variety of factors, such as its intended purpose. An exemplary implementation of the computer device 114 is provided in Figure 2 , which shows a block diagram of a computing device 200. Those skilled in the art will appreciate that Figure 2 The disclosure of can be applied to any device disclosed herein. Device 200 may include one or more processors, such as processors 202-1 and 202-2 (collectively referred to herein as "multiple processors 202" or "processor 202"). Processors 202 may communicate with each other or with other components via an interconnect network or bus 204. Processor 202 may include one or more processing cores, such as cores 206-1 and 206-2 (referred to herein as "multiple cores 206", or more generally as "multiple cores 206"), which may be implemented on a single integrated circuit (IC) chip.

[0030] The core 206 may include a shared cache 208 and / or a dedicated cache (e.g., including caches 210-1 and 210-2, respectively). One or more caches 208 / 210 may locally cache data stored in a system memory such as memory 212 for faster access by components of the processor 202. The memory 212 may communicate with the processor 202 via a chipset 216. In some embodiments, the cache 208 may be part of the system memory 212. The memory 212 may include, but is not limited to, a random access memory (RAM), a read-only memory (ROM), and may include one or more solid-state memory, optical or magnetic storage, and / or may be any other medium for storing electronic information. However, other embodiments may omit the system memory 212.

[0031] The system 200 may include one or more I / O devices (e.g., I / O devices 214-1 through 214-3, each collectively referred to as I / O device 214). I / O data from one or more I / O devices 214 may be stored in one or more caches 208, 210 and / or system memory 212. Each I / O device 214 may be permanently or temporarily configured to operatively communicate with components of the system 100 using any physical or wireless communication protocol.

[0032] Back to Figure 1, four example I / O devices (shown as elements 116-122) are shown in communication with the computer device 114. Those skilled in the art will appreciate that one or more of the devices 116-122 may be stand-alone devices, or may be associated with another device 114 other than the computer device. For example, one or more of the I / O devices may be associated with or interact with components of the BAN 102 and / or the WAN 106. The I / O devices 116-122 may include, but are not limited to, motion data acquisition units, such as sensors. One or more of the I / O devices may be configured to sense, detect, and / or measure motion parameters from a user, such as user 124. Examples include, but are not limited to, accelerometers, gyroscopes, location determination devices (e.g., GPS), light (including non-visible light) sensors, temperature sensors (including ambient temperature and / or body temperature), sleep mode sensors, heart monitors, image capture sensors, humidity sensors, force sensors, compasses, angular velocity sensors, and / or combinations thereof, and the like.

[0033] In other embodiments, the I / O devices 116-122 can be used to provide output (e.g., audible, visual, or tactile cues) and / or receive input, such as user input from the athlete 124. Example uses of these illustrative I / O devices are provided below, but those skilled in the art will appreciate that such discussion is merely a description of some of the many options within the scope of the present disclosure. In addition, reference to any data acquisition unit, I / O device, or sensor should be interpreted as disclosing embodiments that can have one or more I / O devices, data acquisition units, and / or sensors disclosed herein or known in the art (alone or in combination).

[0034] Information from one or more devices (across one or more networks) may use (or be available in form of) a variety of different parameters, metrics, or physiological characteristics, including but not limited to: motion parameters or motion data, such as speed, acceleration, distance, steps, direction, relative motion of certain body parts or objects relative to others, or other motion parameters that can be expressed as angular rate, linear rate, or combinations thereof, physiological parameters, such as calories, heart rate, sweat detection, energy, oxygen consumption, oxygen dynamics, and other metrics that may fall into one or more categories, such as: pressure, impact, information about the athlete, such as height, weight, age, demographic information, and combinations thereof.

[0035] System 100 may be configured to send and / or receive athletic data, including parameters, metrics, or physiological characteristics collected within system 100 or otherwise provided to system 100. As an example, WAN 106 may include server 111. Server 111 may have Figure 2One or more components of system 200. In one embodiment, server 111 includes at least a processor and a memory, such as processor 206 and memory 212. Server 111 can be configured to store computer executable instructions on a non-temporary computer readable medium. The instructions may include motion data, such as raw or processed data collected within system 100. System 100 can be configured to send data (such as energy consumption points) to a social networking website or host such a site. Server 111 can be used to allow one or more users to access and / or compare motion data. In this way, server 111 can be configured to send and / or receive notifications based on motion data or other information.

[0036] Returning to LAN 104, computer device 114 is shown in operative communication with display device 116, image acquisition device 118, sensor 120, and athletic device 122, which are discussed in turn below with reference to example embodiments. In one embodiment, display device 116 can provide audio-visual cues to athlete 124 to perform a particular athletic action. The audio-visual cues can be provided in response to computer-executable instructions executed on computer device 114 or any other device, including devices of BAN 102 and / or WAN. Display device 116 can be a touch screen device or otherwise configured to receive user input.

[0037] In one embodiment, data may be obtained from image acquisition device 118 and / or other sensors, such as sensor 120, which may be used to detect (and / or measure) athletic parameters, whether used alone or in combination with other devices, or stored information. Image acquisition device 118 and / or sensor 120 may include a transceiver device. In one embodiment, sensor 128 may include an infrared (IR), electromagnetic (EM) or acoustic transceiver. For example, image acquisition device 118, and / or sensor 120 may send a waveform including a direction toward athlete 124 to the environment, and receive a "reflection" or otherwise detect changes in these released waveforms. It will be readily understood by those skilled in the art that a variety of signals corresponding to different data spectra may be utilized according to various embodiments. In this regard, device 118 and / or 120 may detect a waveform emitted from an external source (e.g., not system 100). For example, device 118 and / or 120 may detect heat emitted by user 124 and / or the surrounding environment. Therefore, image acquisition device 126 and / or sensor 128 may include one or more thermal imaging devices. In one embodiment, image acquisition device 126 and / or sensor 128 may include an IR device configured to perform range phenomenology.

[0038] In one embodiment, exercise device 122 may be any device that may be configured to allow or facilitate athlete 124 to perform physical exercise, such as a treadmill, stepper, etc. The device need not be stationary. In this regard, wireless technology allows for the use of portable devices, whereby a bicycle or other movable exercise device may be used in accordance with certain embodiments. Those skilled in the art will recognize that device 122 may be or include an interface for receiving an electronic device containing exercise data that is performed remotely from computer device 114. For example, a user may use an exercise device (described below with respect to BAN 102) and upon returning home or to the location of device 122, download the exercise data to element 122 or any other device of system 100. Any I / O device disclosed herein may be configured to receive activity data.

[0039] 2. Body Area Network

[0040] BAN 102 may include two or more devices (including passive devices) configured to receive, transmit, or otherwise facilitate the collection of athletic data. Exemplary devices may include one or more data acquisition units, sensors, or devices known in the art or disclosed herein, including but not limited to I / O devices 116-122. Two or more components of BAN 102 may communicate directly, but in other embodiments, communication may be performed via a third device, which may be part of BAN 102, LAN 104, and / or WAN 106. One or more components of LAN 104 or WAN 106 may form part of BAN 102. In some implementations, whether a device such as portable device 112 is part of BAN 102, LAN 104, and / or WAN 106 may depend on the proximity of the athlete to an access point that allows access to mobile cellular network architecture 108 and / or WAN architecture 110. User activity and / or preferences may also affect whether one or more components are used as part of BAN 102. Example embodiments are provided below.

[0041] The user 124 may be associated with (e.g., hold, carry, wear, and / or interact with) any number of devices, such as a portable device 112, a shoe-mounted device 126, a wrist-mounted device 128, and / or associated with a sensing location, such as a sensing location 130, which may include a physical device or location for collecting information. One or more of the devices 112, 126, 128, and / or 130 may not be specifically designed for fitness or athletic purposes. In fact, aspects of the present disclosure relate to utilizing data from multiple devices, some of which are not fitness devices, to collect, detect, and / or measure athletic data. In some embodiments, one or more devices of the BAN 102 (or any other network) may include fitness or athletic equipment specifically designed for a particular athletic application. As used herein, the term "athletic equipment" includes any physical object that may be used or involved during a particular athletic or fitness activity. Exemplary sports equipment may include, but is not limited to: golf balls, basketballs, baseballs, soccer balls, footballs, powerballs, hockey pucks, weights, bats, clubs, sticks, paddles, mats, and combinations thereof. In further embodiments, exemplary fitness equipment may include objects in a sports environment in which a particular sport occurs, including the environment itself, such as goal nets, baskets, backboards, portions of a court, such as center lines, outer boundary markers, bases, and combinations thereof.

[0042] In this regard, it will be appreciated by those skilled in the art that one or more athletic devices may also be part of (or form a structure), and vice versa, a structure may include one or more athletic devices or be configured to interact with an interactive device. For example, a first structure may include a basketball hoop and backboard, which may be removable and replaced with goal posts. In this regard, one or more athletic devices may include one or more sensors that may provide information to be utilized, such as one or more of the sensors described above with respect to Figure 1-3 The sensors discussed, whether independently or in combination with other sensors, such as one or more sensors associated with one or more structures. For example, a backboard may include a first sensor configured to measure the force and direction of a basketball on the backboard, and the basket may include a second sensor for detecting the force. Similarly, a golf club may include a first sensor configured to detect grip force applied to the shaft, and a second sensor configured to measure impact with the golf ball.

[0043] Note the illustrative portable device 112, which may be a multi-function electronic device, i.e., including, for example, a telephone or a digital music player, including devices available from Apple Inc. of Cupertino, California. or or purchased from Microsoft in Redmond, Washington or Windows device. As is known in the art, a digital media player can function as an output device, an input device, and / or a storage device for a computer. Device 112 can be configured as an input device for receiving raw or processed data collected from one or more devices of BAN 102, LAN 104, or WAN 106. In one or more embodiments, portable device 112 can include one or more components of computer device 114. For example, portable device 112 can include display 116, image acquisition device 118, and / or one or more data acquisition devices, such as any of I / O devices 116-122 discussed above, with or without additional components, to constitute a mobile terminal.

[0044] a. Illustrative Clothing / Accessory Sensors

[0045] In some embodiments, the I / O devices may be formed into or otherwise associated with the user's 124 clothing or accessories, including watches, armbands, wristbands, necklaces, shirts, shoes, or the like. These devices may be configured to monitor the user's athletic movements. However, it should be understood that they may detect athletic movements during the user's 124 interaction with the computer device 114, and / or operate independently of the computer device 114 (or any other device disclosed herein). For example, one or more devices in BAN 102 may be configured to function as an all-day activity monitor that measures activity regardless of the user's proximity to or interaction with the computer device 114. It should be further understood that the devices shown in FIG. Figure 3 The sensing system 302 and the Figure 4 The device components 400 in FIG. 4 are merely illustrative examples, each of which is described in the following paragraphs.

[0046] i. Shoe installation equipment

[0047] In certain embodiments, Figure 1 The illustrated device 126 may include footwear, which may include one or more sensors including, but not limited to, those disclosed herein and / or known in the art. Figure 3An exemplary embodiment of a sensor system 302 is shown, which provides one or more sensor assemblies 304. Component 304 may include one or more sensors, such as accelerometers, gyroscopes, position determination components, force sensors, and / or any other sensors disclosed herein or known in the art. In the illustrated embodiment, component 304 includes multiple sensors, which may include force sensitive resistor (FSR) sensors 306; however, other sensors (multiple sensors) may be utilized. Port 308 may be located within a sole structure 309 of the shoe and is generally configured to communicate with one or more electronic devices. Port 308 may optionally be configured to communicate with an electronic module 310, and sole structure 309 may optionally include a housing 311, or other structure to receive module 310. Sensor system 302 may also include multiple leads 312 connecting FSR sensor 306 to port 308 to enable communication with module 310 and / or another electronic device through port 308. Module 310 may be contained within a recess or cavity of the sole structure of the shoe, and housing 311 may be positioned within the recess or cavity. In one embodiment, at least one gyroscope and at least one accelerometer are disposed within a single housing, such as module 310 and / or housing 311. In at least one further embodiment, when in operation, one or more sensors are disposed and configured to provide orientation information and angular velocity data. Port 308 and module 310 include complementary interfaces 314, 316 for connection and communication.

[0048] In certain embodiments, Figure 3 At least one force-sensitive resistor 306 in the sensor system 302 may include first and second electrodes or electrical contacts 318, 320, and a force-sensitive resistor material 322 disposed between the electrodes 318, 320 to electrically connect the electrodes 318, 320 together. When pressure is applied to the force-sensitive material 322, the resistivity and / or conductivity of the force-sensitive material 322 changes, which changes the electrical potential between the electrodes 318, 320. The change in resistance can be detected by the sensor system 302, thereby detecting the force applied to the sensor 316. The force-sensitive resistor material 322 can change its resistance under pressure in a variety of ways. For example, the force-sensitive material 322 can have an internal resistance that decreases when the material is compressed. Additional embodiments utilizing "volume-based resistance" can be measured, which can be implemented by "smart materials". As another example, the material 322 can change resistance by changing the degree of surface-to-surface contact, such as between two pieces of force-sensitive material 322, or between the force-sensitive material 322 and one or both electrodes 318, 320. In some cases, this type of force-sensitive resistive behavior may be described as "contact-based resistance."

[0049] ii. Wrist-worn devices

[0050] like Figure 4 As shown, the device 400 (which may be similar to or include Figure 1 The viewing device 128 shown may be configured to be worn by the user 124, such as around a wrist, arm, ankle, neck, or the like. The device 400 may include an input mechanism, such as a depressible input button 402 configured for use during operation of the device 400. The input button 402 may be operably connected to a controller 404 and / or any other electronic components, such as a controller 404, or a controller 404 that is configured to control the input of the device 400. Figure 1 114. The controller 404 may be embedded in the housing 406 or otherwise form a part of the housing 406. The housing 406 may be formed of one or more materials, including an elastomeric component and including one or more displays, such as a display 408. The display may be considered as an illuminable portion of the device 400. The display 408 may include a series of individual lighting elements or light-emitting components, such as LED lights 410. The lights may be formed in an array and operably connected to the controller 404. The device 400 may include an indicator system 412, which may also be considered as a part or component of the entire display 408. The indicator system 412 may be combined with the display 408 (which may have a pixel component 414) or operated and illuminated completely separately from the display 408. The indicator system 412 may also include a plurality of additional light-emitting elements or light-emitting components, which may also take the form of LED lights in the exemplary embodiment. In some embodiments, the indicator system may provide a visual indication of a goal, such as by lighting a portion of the lighting component of the indicator system 412 to indicate the completion of one or more goals. The device 400 may be configured to display data represented by activity points or currency earned by a user based on the user's activities, the display being through the display 408 and / or through the indicator system 412 .

[0051] The fastening mechanism 416 may be disengaged, wherein the device 400 may be positioned around a wrist or portion of the user 124, and the fastening mechanism 416 may then be placed in an engaged position. In one embodiment, the fastening mechanism 416 may include an interface for operably interacting with the computer device 114 and / or a device such as the device 120 and / or 112, including, but not limited to, a USB port. In certain embodiments, the fastening member may include one or more magnets. In one embodiment, the fastening member may contain no moving parts and rely entirely on magnetic force.

[0052] In some embodiments, the device 400 may include a sensor assembly ( Figure 4400 and / or its sensor assembly may be configured to receive data obtained from one or more external sensors.

[0053] iii. Clothing and / or body position sensing

[0054] Figure 1 Element 130 of shows an example sensing location that can be associated with a physical device, such as a sensor, a data acquisition unit, or other device. However, in other embodiments, it can be a specific location of a body part or region being monitored, such as monitored by an image acquisition device (e.g., image acquisition device 118). In some embodiments, element 130 may include a sensor, so that elements 130a and 130b can be sensors integrated into clothing, such as sports clothing. Such sensors can be placed at any desired location on the body of user 124. Sensor 130a / b can communicate (e.g., wirelessly) with one or more devices (including other sensors) of BAN 102, LAN104, and / or WAN 106. In some embodiments, a passive sensing surface can reflect waveforms emitted by image acquisition device 118 and / or sensor 120, such as infrared light. In one embodiment, a passive sensor located on user 124 clothing can include a generally spherical structure made of glass or other transparent or translucent surfaces that can reflect waveforms. Different categories of clothing may be utilized, wherein a given type of clothing has specific sensors that are configured to be positioned adjacent to specific parts of the body of user 124 when properly worn. For example, golf clothing may include one or more sensors positioned on the clothing in a first configuration, while soccer clothing may include one or more sensors positioned on the clothing in a second configuration.

[0055] Figure 5Illustrative locations for sensing input (see, e.g., sensor locations 130a-130o) are shown. In this regard, the sensor may be a physical sensor located on / on the user's clothing, but in other embodiments, the sensor locations 130a-130o may be based on the identification of a relationship between two moving body parts. For example, sensor location 130a may be determined by identifying the movement of user 124 with an image acquisition device (such as image acquisition device 118). Therefore, in some embodiments, the sensor may not be physically positioned at a specific location (such as one or more sensor locations 130a-130o), but rather may be configured to sense properties of that location, such as with image acquisition device 118, or other sensor data collected from other locations. In this regard, the overall shape or portion of the user's body may allow for the identification of certain body parts. Regardless of whether an image acquisition device and / or a physical sensor located on the user 124 is utilized, and / or data from other devices (such as the sensing system 302) is used, the device assembly 400 disclosed herein or known in the art and / or any other device or sensor is utilized, the sensor can sense the current position of the body part and / or track the movement of the body part. In one embodiment, the sensing data related to the position 130m can be used in determining the center of gravity (i.e., the center of mass) of the user. For example, the relationship between the position 130a and the position (multiple positions) 130f / 130l and one or more positions 130m-130o can be used to determine whether the user's center of gravity has risen along the vertical axis (e.g., when jumping), or whether the user is trying to "fake" jumping by bending and flexing the knees. In one embodiment, the sensor position 130N can be located near the sternum of the user 124. Similarly, the sensor position 130o can locate the navel of the user 124. In some embodiments, the data from the sensor positions 130m-130o can be used (alone or in combination with other data) to determine the center of gravity of the user 124. In other embodiments, the relationship between the positions of multiple sensors (such as sensors 130m-130o) can be used to determine the direction and / or rotational force of the user 124, such as the twisting of the torso of the user 124. In addition, one or more positions can be used to determine the position of the center of moment. For example, in one embodiment, one or more positions (multiple positions) 130m-130o can be used as a point for the center of moment of the user 124. In another embodiment, one or more positions can be used as the center of moment of a particular body part or region.

[0056] Figure 6An exemplary block diagram of a sensor device 600 configured to recognize one or more gestures in accordance with certain embodiments is depicted. As shown, the sensor device 600 is implemented as (and / or is in operational communication with) an element that can be configured to recognize one or more gestures from sensor data received / output by the sensor device 600. According to one embodiment, in addition to reducing power consumption by one or more components, the recognized gesture can execute one or more processes in accordance with one or more operating modes of the sensor device 600. The illustrative sensor device 600 is shown as having a sensor 602, a filter 604, an activity processor 606, a gesture recognition processor 608, a memory 610, a power supply 612, a transceiver 614, and an interface 616. However, those skilled in the art will recognize that Figure 6 This is merely an illustrative example of sensor device 600, and sensor device 600 may be implemented using a number of alternative configurations without departing from the scope of the processes and systems described herein. For example, it will be apparent to one of ordinary skill that activity processor 606 and gesture recognition processor 608 may be implemented as a single processor, or as one or more processing cores of a single multi-core processor, etc. In other embodiments, processors 606 and 608 may be implemented using dedicated hardware, or may be implemented using shared hardware that may be localized (on a common motherboard, within a common server, etc.) or distributed (on multiple network-connected servers, etc.).

[0057] In addition, the sensor device 600 may include Figure 2 The sensor device 600 may be considered as part of a larger computing device or may itself be a stand-alone computing device. Thus, in one embodiment, the sensor device 600 may be configured to partially or fully execute Figure 4 In such an embodiment, the sensor device 600 can be configured to, among other things, recognize one or more gestures performed by a user wearing the wrist-worn device 400. In response, the wrist-worn device 400 can perform one or more processes to, among other things, adjust one or more data analysis conditions or settings associated with one or more operating modes, identify one or more activities performed by the user, or result in a reduction in power consumption of the wrist-worn device 400, or a combination thereof.

[0058] In one embodiment, the power source 612 may include a battery. Alternatively, the power source 612 may be a single battery cell that draws power from stored chemical energy (a group of multiple such battery cells is generally referred to as a battery), or may be implemented using a combination of one or more other technologies, including solar cells, capacitors, which may be configured to store power harvested from the motion of the device 400 in which the sensor device 600 may be positioned, the supply of power via "wireless" induction, or via a wired supply of power from a main power outlet, such as a Universal Serial Bus (USB 1.0 / 1.1 / 2.0 / 3.0, etc.) outlet and the like. A skilled person will readily appreciate that the systems and methods described herein may be adapted to reduce power consumption from these and other power source 612 embodiments without departing from the scope of the present specification.

[0059] In one embodiment, the sensor 602 of the sensor device 600 may include one or more accelerometers, gyroscopes, location determination devices (GPS), light sensors, temperature sensors, heart rate monitors, image acquisition sensors, microphones, humidity sensors, force sensors, compasses, angular velocity sensors, and / or combinations thereof, etc. As an example embodiment including an accelerometer, the sensor 602 may be a three-axis (X, Y, and Z axis) accelerometer implemented as a single integrated circuit or "chip," wherein accelerations on one or more of the three axes are detected as changes in capacitance across a silicon structure in a microelectromechanical system (MEMS) device. Thus, a three-axis accelerometer may be used to resolve accelerations in any direction in three-dimensional space. In a specific embodiment, the sensor 602 may include an STMicroelectronics LIS3DH 3-axis accelerometer kit and output a digital signal corresponding to the acceleration amplitude of one or more of the three axes to which the accelerometer is aligned. It will be understood by those of ordinary skill that the sensor 602 may output a digital or pulse width modulated signal corresponding to the acceleration amplitude. The digital output of sensor 602 (e.g., one incorporating an accelerometer) may be received as a time-varying frequency signal, wherein the frequency of the output signal corresponds to the magnitude of acceleration on one or more of the three axes to which sensor 602 is sensitive. In an alternative embodiment, sensor 602 may output an analog signal as a time-varying voltage corresponding to the magnitude of acceleration on one or more of the three axes to which sensor 602 is sensitive. Furthermore, it should be understood that sensor 602 may be a single-axis, or dual-axis accelerometer without departing from the scope of the embodiments described herein. In yet another embodiment, sensor 602 may represent one or more sensors that output an analog or digital signal corresponding to a physical phenomenon / input to which sensor 602 responds.

[0060] Optionally, the sensor device 600 may include a filter 604, wherein the filter 604 may be configured to selectively remove certain frequencies of the output signal from the sensor 602. In one implementation, the filter 604 is an analog filter having low-pass, high-pass or band-pass filter characteristics, or the filter 604 is a digital filter, and / or a combination thereof. The output of the sensor 602 may be sent to the filter 604, wherein, in one implementation, the output of the analog sensor 602 will be in the form of a continuous time-varying voltage signal with varying frequency and amplitude. In one implementation, the amplitude of the voltage signal corresponds to the magnitude of the acceleration, and the frequency of the output signal corresponds to the number of changes in the acceleration per unit time. However, the output of the sensor 602 may also optionally be a time-varying voltage signal corresponding to one or more different sensor types. In addition, the output of the sensor 602 may be an analog or digital signal, which, among other things, represents an electric current, an optical signal, and a sound signal, or a combination thereof.

[0061] Filter 604 can be configured to remove those signals corresponding to frequencies outside of a frequency range of interest for gesture recognition and / or activity recognition by a gesture detection device, such as device 400. For example, filter 604 can be used to selectively remove high-frequency signals exceeding, for example, 100 Hz, which represent movement of sensor 602 at frequencies beyond human capabilities. In another implementation, filter 604 can be used to remove low-frequency signals from the output of sensor 602 so that those signals having frequencies below those associated with a user gesture are not further processed by sensor device 600.

[0062] Filter 604 may be referred to as a "pre-filter," where filter 604 may remove one or more frequencies from the signal output of sensor 602 so that activity processor 606 does not consume power processing data that does not represent a gesture or activity performed by a user. In this manner, pre-filter 604 may reduce the overall power consumption of sensor device 600 or a system of which sensor device 600 is a part.

[0063] In one implementation, the output of filter 604 is sent to both activity processor 606 and gesture recognition processor 608. When sensor device 600 is turned on in the first state, and power is supplied from power supply 612, both activity processor 606 and gesture recognition processor 608 may receive continuous-time output signals from sensor 602, wherein the output signals may be filtered by filter 604 before being received by activity processor 606 and gesture recognition processor 608. In another implementation, sensor data received by gesture recognition processor 608 is not filtered by filter 604, while sensor data received by activity processor 606 is filtered by filter 604. In yet another implementation, when sensor device 600 is turned on in the second state, activity processor 606 and gesture recognition processor 608 receive intermittent signals from sensor 602. It will be appreciated by those skilled in the art that one or more processors (e.g., processor 606 and / or 608) may analyze data obtained from sensors other than sensor 602.

[0064] Memory 610, which may be similar to Figure 2 The system memory 212 may be used to store computer executable instructions for executing one or more processes by the activity processor 606 and / or the gesture recognition processor 608. The memory 610 may include, but is not limited to, random access memory (RAM), read only memory (ROM), and may include one or more solid-state memories, optical memories, or magnetic memories, and / or any other medium that may be used to store electronic information. The memory 610 may be stored in Figure 6 600, but it should be understood that memory 610 can represent one or more types of memory that can be the same or different from each other. In addition, memory 610 can be omitted from sensor device 600 so that the executed instructions are stored on the same integrated circuit as one or more activity processors 606 and gesture recognition processor 608.

[0065] In one implementation, gesture recognition processor 608 may have a configuration similar to Figure 2 The structure of the processor 202 is such that the gesture recognition processor 608 can be implemented as part of a shared integrated circuit or as a microprocessor device. In another implementation, the gesture recognition processor 608 can be configured as an application-specific integrated circuit (ASIC), which can be shared with other processes or dedicated to a separate gesture recognition processor 608. In addition, it will be apparent to those skilled in the art that the gesture recognition processor 608 can be implemented using a variety of other configurations, such as using discrete analog and / or digital electronic components, and can be configured to perform the same processes as described herein without departing from the present invention. Figure 6 Similarly, the activity processor 606 can be constructed as an ASIC, or as Figure 2 The general-purpose processor 202 may be implemented such that both the activity processor 606 and the gesture recognition processor 608 may be implemented using physically separate hardware or may share part or all of their hardware.

[0066] Activity processor 606 can be configured to execute a process to identify one or more activities performed by a user, and classify the one or more activities into one or more activity categories. In one implementation, activity recognition can include measuring the number of steps of the user based on motion data, such as by detecting the peak and jump peak of the arm swing in the motion data. The measurement can be performed entirely based on the data collected by a single device worn on the user's arm (such as near the wrist). In one embodiment, the motion data is obtained from an accelerometer. The acceleration amplitude vector can be obtained for a time frame, and a value (such as the average value of the amplitude vector from the time frame) can be calculated. The average value (or any other value) can be used to determine whether the amplitude vector of the time frame meets the acceleration threshold to be eligible for use when calculating the number of steps for each time frame. Acceleration data that meets the threshold can be placed in an analysis buffer. A search range related to the acceleration frequency of the expected activity can be established. In some implementations, the frequency of the acceleration data within the search range can be analyzed to identify one or more peaks, such as jump peaks and arm swing peaks. In one embodiment, if it is within the estimated arm swing range and further meets the arm swing peak threshold, the first frequency peak can be identified as an arm swing peak. Similarly, a second frequency peak may be identified as a beating peak if it is within the estimated bounce range and further satisfies the beating peak threshold.

[0067] In addition, the system and method can determine whether to use the arm swing data, the jump data and / or other data or parts of the data to measure the number of steps or other movements. The number of peaks (such as arm swing peaks and / or jump peaks) can be used to determine which data to use. In one embodiment, the system and method can use the number of peaks (and the type of peaks) to select the stride and stride length for measuring the number of steps. In another embodiment, at least a portion of the activity data can be classified into activity categories based on step measurement.

[0068] In one embodiment, sensor signals (e.g., frequency of an accelerometer) and calculations based on the sensor signals (e.g., number of steps) can be utilized in the classification of activity categories, such as walking or running. In some embodiments, if the data cannot be classified as within a first category (e.g., walking) or within a group of categories (e.g., walking and running), a first method can analyze the collected data. For example, in one embodiment, if the detected parameters cannot be classified, the Euclidean norm equation can be used for further analysis. In another embodiment, the mean magnitude vector norm (square root of the sum of squares) of the obtained values ​​can be utilized. In another embodiment, different methods can analyze at least a portion of the data that is within the first category or group of categories after classification. In one embodiment, a step algorithm can also be utilized. Classified and unclassified data can be used to calculate energy expenditure values ​​in some embodiments.

[0069] Exemplary systems and methods that may be implemented to identify one or more activities are described in U.S. Patent Application No. 13 / 744,103, filed on January 17, 2013, the entire contents of which are hereby incorporated by reference in their entirety for any and all non-limiting purposes. In certain embodiments, activity processor 606 may be utilized in performing one or more of the processes described herein, including those methods described in the '103 application.

[0070] The process for classifying a user's activity may compare data received from sensor 602 to stored data samples that are specific to a particular activity, wherein one or more specific data samples may be stored in memory 610 .

[0071] Gesture recognition processor 608 may be configured to perform one or more processes to recognize or classify one or more gestures performed by a user, such as a user of device 400, of which sensor device 600 may be a component. In this manner, a user may perform one or more gestures in order to make selections related to actions of sensor device 600. Thus, a user may avoid interacting with sensor device 600 via one or more physical buttons, which may be cumbersome and / or impractical to use during physical activity.

[0072] The gesture recognition processor 608 receives data from the sensor 602 and recognizes one or more gestures through the received data, wherein the recognition is based on, among other things, a motion pattern of the sensor device 600, a touch pattern of the sensor device 600, an orientation of the sensor device 600, and a proximity of the sensor device 600 to the beacon, or a combination thereof. For example, the gesture recognition processor 608 can receive acceleration data from the sensor 602, wherein the sensor 602 is implemented as an accelerometer. In response to the reception of the acceleration data, the gesture recognition processor 608 can perform one or more processes to compare the received data with a database of motion patterns. The motion pattern can be a sequence of acceleration values ​​representing a specific motion by a user. In response to finding a motion pattern corresponding to the received sensor data, the gesture recognition processor 608 can perform one or more processes to change the operating mode of the activity processor 606 from a first operating mode to a second operating mode. The operating mode can be a group of one or more processes that generally define the operating mode of the sensor device 600. For example, the operating modes may include, among others, a sleep mode of activity processor 606, an activity recognition mode of activity processor 606, and a sensor selection mode of gesture recognition processor 608, or a combination thereof. In addition, it will be readily appreciated that a motion pattern may be a sequence of values ​​corresponding to a sensor type other than an accelerometer. For example, a motion pattern may be a sequence that includes, among others, gyroscope values, force values, light intensity values, volume / sound / tone values, or position values, or a combination thereof.

[0073] For an exemplary embodiment where the sensor 602 is an accelerometer, the motion pattern may be associated with, among other things, the movement of the user's arm in an intentional manner representing a gesture. For example, a gesture may invoke execution of one or more processes to display lap time to the user via the sensor device 600. The user may wear the wrist-worn device 400 on his / her left wrist, wherein the wrist-worn device 400 may be positioned on his / her left wrist with the display 408 located above the wrist. Thus, a "lap time gesture" may include a "flick," or shaking the user's left wrist at approximately 90° and returning to an initial position. The gesture recognition processor 608 may recognize such a flicking motion as a lap time gesture, and in response, display the lap time to the user on the display 408. An exemplary motion pattern associated with a lap time gesture includes, among other things, a first acceleration period with an associated acceleration value below a first acceleration threshold, a second acceleration period corresponding to a sudden increase in acceleration when the user begins to flick his / her wrist from an initial position, and a third acceleration period corresponding to a sudden change in acceleration when the user returns his / her wrist from an angle of approximately 90° to the initial position. It will be apparent to those skilled in the art that a motion pattern may include multiple discrete "cycles" or changes in sensor values ​​associated with a gesture. In addition, an action pattern may include values ​​from multiple sensors of the same or different types.

[0074] To associate the data from sensor 602 with one or more motion patterns, gesture recognition processor 608 may perform one or more processes to compare absolute sensor values ​​or changes in sensor values ​​with stored sensor values ​​associated with one or more motion patterns. Additionally, gesture recognition processor 608 may determine that a sequence of sensor data from sensor 602 corresponds to one or more motion patterns if one or more sensor values ​​in the received sensor data are: above / below one or more thresholds, within an acceptable range of one or more stored sensor values, or equal to one or more stored sensor values, or a combination thereof.

[0075] It will be apparent to those skilled in the art that motion patterns can be used to associate gestures performed by a user with many different types of processes performed by sensor device 600. For example, a gesture may include a movement of a user's left and right hands in a "T-shaped" position and holding both hands in that position for a predetermined length of time. Gesture recognition processor 608 may receive sensor data associated with this gesture and perform one or more processes to compare the received sensor data with one or more stored motion patterns. Gesture recognition processor 608 may determine that the received sensor data corresponds to a "pause" motion mode. In response, gesture recognition processor 608 may instruct activity processor 606 to perform one or more processes associated with a "pause" operating mode. For example, the "pause" operating mode may include reducing the power consumption of activity processor 606 by reducing the sampling rate at which activity processor 606 receives data from sensor 602. In another example, a gesture may include a user's arm moving to a position representing stretching the upper body after a sports exercise. Once again, gesture recognition processor 608 may receive sensor data associated with this gesture and perform one or more processes to compare the received data with one or more stored motion patterns. By comparing the received sensor data to one or more stored motion patterns, gesture recognition processor 608 may determine that the received sensor data corresponds to a "stretch" motion pattern. In response, gesture recognition processor 608 may instruct activity processor 606 to perform one or more processes associated with the "stretch" mode of operation. Such a "stretch" mode of operation may include a process for stopping activity recognition of one or more motion activities performed prior to the stretch gesture.

[0076] In one implementation, a gesture may be recognized by gesture recognition processor 608 after one or more "training mode" processes are performed by gesture recognition processor 608. During the training mode process, gesture recognition processor 608 may store one or more data sets corresponding to one or more motion patterns. In particular, gesture recognition processor 608 may instruct the user to perform a "training gesture" for a predetermined number of repetitions. For each repetition, gesture recognition processor 608 may receive data from one or more sensors 602. Gesture recognition processor 608 may compare the sensor data received for each training gesture and determine one or more characteristics common to the multiple gestures. These common characteristics may be stored as one or more sequences of thresholds of sensor values, or motion patterns. For example, during the training mode in which a "telling time" gesture is to be analyzed, gesture recognition processor 608 may instruct the user to perform a specific motion three times. Among other things, the specific motion may include positioning the user's left arm roughly beside his / her side and in a vertical direction, moving the left arm from a position roughly at the user's side to a substantially horizontal position and pointing straight out in front of the user, and then bending the user's left arm at the elbow so that the user's wrist is approximately in front of the user's chin. Gesture recognition processor 608 may execute one or more processes to identify sensor data common to the three "telling the time" training gestures performed by the user during the training mode and store these common characteristics as a motion pattern associated with the "telling the time" gesture. Gesture recognition processor 608 may also store one or more processes executed when the "telling the time" gesture is recognized, which may include displaying the current time to the user on display 408. In this way, if the user's motion corresponds to the "telling the time" gesture at a later time, the current time may be displayed to the user as determined by gesture recognition processor 608.

[0077] In another implementation, the gesture recognition processor 608 may recognize gestures from sensor data based on the pattern of touch of the sensor device 600. In one implementation, the pattern of touch may be generated by the user as a result of tapping the outer shell of the device 400. This tapping motion may be detected by one or more sensors 602. In one embodiment, the tapping may be detected as one or more spikes in the data output by the accelerometer. In this way, the gesture recognition processor 608 may associate the tapping pattern with one or more processes performed by the activity processor 606. For example, the gesture recognition processor 608 may receive sensor data representing one or more taps of the shell of the device 400 from the accelerometer. In response, the gesture recognition processor 608 may compare the received acceleration data with one or more tapping patterns stored in the memory 610, wherein the tapping pattern may include a threshold value of one or more acceleration count values. If, for example, the received sensor data contains multiple "spikes", or the values ​​in the acceleration data correspond to the peaks stored in the tapping pattern, and are within a predetermined time period of each other, the gesture recognition processor 608 may determine that the data received from the accelerometer corresponds to one or more tapping patterns. For example, if the received sensor data contains two acceleration value peaks with an average value exceeding a 2.0g threshold (g=gravitational acceleration) and are within 500ms of each other, gesture recognition processor 608 may determine that the data received from the accelerometer corresponds to a tapping pattern.

[0078] In another implementation, the touch pattern may be generated by a user swiping one or more capacitive sensors in operable communication with sensor device 600. In this manner, the touch pattern may include movement of one or more fingers of the user across the one or more capacitive sensors according to a predetermined pattern.

[0079] In yet another implementation, the gesture recognition processor 608 may recognize a gesture based on the orientation of the sensor device 600 within the device 400. The orientation of the sensor device 600 may be received from a sensor 602 implemented as an accelerometer, a gyroscope, or a magnetic field sensor, or a combination thereof, among others. In this way, the gesture recognition processor 608 may receive data representing the orientation of the sensor device 600 from the sensor 602, and associate the sensor orientation data with the gesture. In turn, this orientation gesture may call the gesture recognition processor 608 to perform one or more processes, thereby selecting an operating mode of the activity processor 606. In one example, the device 400 is positioned on the user's wrist. The device 400 may be oriented so that the display 408 is positioned on the top of the user's wrist. In this case, the "top" of the user's wrist may be defined as a side of the user's wrist that is roughly on the same plane as the back of the user's hand. In this example, the orientation gesture may be associated with the user rotating his / her wrist and therefore the device 400 so that the display 408 is substantially facing downward. In response to identifying the orientation gesture, gesture recognition processor 608 may perform one or more processes to, among other things, increase the sampling rate of activity processor 606 to prepare for periods of intense activity. In another example, the orientation gesture may be associated with the orientation of the user's hands on the handlebars of a road bicycle, wherein, among other things, the first grip orientation gesture may be associated with sprinting on a road bicycle and the second grip orientation gesture may be associated with uphill climbing on a road bicycle. Furthermore, it will be apparent to those of ordinary skill that fewer, more, or more orientation gestures may be defined without departing from the spirit of the disclosure described herein.

[0080] In another embodiment, the gesture recognition processor 608 can recognize a gesture associated with the sensor device 600 approaching a beacon. A beacon can be an electronic device, such as a transceiver, that is detectable when within a predetermined range of the sensor device 600. The beacon can transmit a short-range signal including information identifying one or more pieces of information associated with the beacon, wherein the beacon can represent, for example, a distance marker at the start of a marathon / long-distance race, along the length of a marathon, or at the end of a marathon. The signal associated with the beacon can be transmitted using wireless technology / protocols, including but not limited to: Wi-Fi, Bluetooth or cellular networks, or a combination thereof. The signal transmitted from the beacon can be received by the transceiver 614 of the sensor device 600. Upon receiving the beacon signal, the transceiver 614 can transmit data to the gesture recognition processor 608. In response, the gesture recognition processor 608 can recognize the received data as an approach gesture. In this example, the identified approach gesture can be associated with one or more processes that are configured to update the progress time associated with the user's marathon race.

[0081] In yet another embodiment, a proximity gesture may be associated with, among other things, sensor device 600 entering close proximity with another user or object. In this manner, a proximity gesture may be used, for example, to execute one or more processes based on multiple individuals competing as part of a sports team, or based on a runner entering close proximity with a starting block equipped with a beacon on a running track, and the like.

[0082] Figure 7 7 is a schematic block diagram of a gesture recognition training process 700. The gesture recognition training process 700 may be performed by the gesture recognition processor 608 as a "training mode," among other things. In particular, the process 700 begins at block 702, where the training mode is initiated by the gesture recognition processor 608. The training mode may be initiated for the first time in response to initialization of the sensor device 600, or at any time during use of the sensor device 600, in order to store new gesture patterns in the memory 610. Thus, these stored gesture patterns may be recognized by the gesture recognition processor 608 during "normal" operation of the device 600, where normal operation of the device 600 may be defined as any time when the device 600 is turned on and the training process 700 is not being performed.

[0083] In the gesture recognition training process 700, the gesture recognition processor 608 may instruct the user to perform multiple consecutive repetitions of the training gesture. In one embodiment, the action associated with the gesture may be defined by the user, while in another embodiment, the action may be specified by the gesture recognition processor 608 for the user to perform. Among other things, block 704 of the process 700 includes the user performing multiple consecutive repetitions of the training gesture. In one implementation, the number of consecutive repetitions of the training gesture may range from 1 to 10, but it will be apparent to those skilled in the art that any number of training gesture repetitions may be used in the training process 700.

[0084] The gesture recognition processor 608 may store one or more samples of the executed training gesture in the memory 610. The common characteristics of one or more training gestures may be identified by the gesture recognition processor 608 at the block 708 of the process 700. Specifically, block 708 represents one or more comparison processes performed by the gesture recognition processor 608 to identify sensor data points that characterize the executed training gesture. Among other things, these characteristics may be peaks in the acceleration data, or changes above a threshold in the gyroscope data points, and so on. Block 708 may also include a comparison of one or more training gestures sampled at different sampling rates. In this way, and for a given training gesture, the gesture recognition processor 608 may identify a sampling rate that is lower than the upsampling rate associated with the activity processor 606. At this lower sampling rate, if the data from the sensor 602 is sampled at the upsampling rate, the training gesture may still be recognized. The gesture recognition processor 608 may store the lower sampling rate in conjunction with the gesture samples. Subsequently, and when a gesture is recognized from received sensor data by gesture recognition processor 608 during normal operation of sensor device 600 , gesture recognition processor 608 may instruct activity processor 606 to sample data at a lower sampling rate, thereby reducing power consumption of activity processor 606 .

[0085] Box 710 represents the storage of one or more gesture samples in memory 610. During normal operation of sensor device 600, upon receiving data from sensor 602, gesture recognition processor 608 may poll a database storing gesture samples. Gesture samples may be stored as a sequence of data points corresponding to one or more sensor values ​​associated with one or more sensor types. In addition, gesture samples may be associated with one or more processes such that when a gesture is recognized from received sensor data by gesture recognition processor 608, gesture recognition processor 608 may instruct activity processor 606 to perform one or more related processes. These related processes may include, among other things, a process for transitioning sensor device 600 from a first operating mode to a second operating mode.

[0086] Figure 8800. In one embodiment, the gesture recognition process 800 may be performed by the gesture recognition processor 608. The process 800 is performed by the gesture recognition processor 608 and is responsive to receiving data from the sensor 602. Such sensor data reception is represented by the box 802. As previously disclosed, the data output from the sensor 602 may be analog or digital. In addition, the data output from the sensor 602 may be in the form of a data stream, such that the data output is continuous, or the data output may be intermittent. The data output from the sensor 602 may consist of one or more data points, wherein, among other things, the data point may include an identification of the sensor type from which it was generated, and one or more values ​​associated with the reading of the sensor type.

[0087] Process 800 may include buffering one or more data points received from sensor 602. This is represented by block 804, where a buffer circuit or one or more buffer processes may be used to temporarily store one or more received data points. In this manner, gesture recognition processor 608 or activity processor 606 may poll the buffer to analyze data received from sensor 602.

[0088] In one implementation, the gesture recognition processor 608 compares the days 1 received from the sensor 602 with one or more stored motion patterns. This is represented by block 806 of the process 800. In one embodiment, the gesture recognition processor 608 identifies the sensor type for which data has been received. In response, the gesture recognition processor 608 polls the memory 610 for stored motion patterns associated with the identified sensor type. Upon receiving a response from the polled memory 610 for one or more stored motion patterns associated with the identified sensor type, the gesture recognition processor 608 may iteratively search for a sequence of sensor values ​​corresponding to the received data from the stored motion patterns. If the received data is within the range of the stored sensor value sequence, the gesture recognition processor 608 may determine, among other things, that the received data corresponds to a stored sequence of sensor values ​​associated with the motion pattern. In another embodiment, the gesture recognition processor 608 does not poll the memory 610 for a motion pattern associated with the identified sensor type, and instead performs an iterative search for a stored motion pattern corresponding to the received sensor data.

[0089] In another implementation, the gesture recognition processor 608 may perform one or more processes to compare the data received from the sensor 602 with one or more stored touch patterns. This is represented by block 808 of process 800. Among other things, one or more stored touch patterns may be associated with a tapping sequence of the outer shell of the device 400, of which the sensor device 600 is a component of the device 400. These touch patterns may be stored in a database in the memory 610, so that the gesture recognition processor 608 can poll this database of touch patterns when receiving sensor data from the sensor 602. In one embodiment, the gesture recognition processor 608 may identify one or more peaks from the data output of the sensor 602, wherein the one or more peaks in the output data may represent one or more corresponding "taps" of the sensor device 600. In response, the gesture recognition processor 608 may poll the memory 610 for one or more touch patterns with one or more peaks corresponding to the output data received from the sensor 602.

[0090] In another implementation, and at block 810 of process 800, gesture recognition processor 608 may recognize a gesture based on an orientation of sensor device 600. Gesture recognition processor 608 may detect the orientation of sensor device 600 based on data received from sensor 602, where the orientation may be clear from the data received from sensor 602, which may be implemented as an accelerometer, a gyroscope, or a magnetic field sensor, or a combination thereof, among others.

[0091] In yet another implementation, gesture recognition processor 608 may recognize a gesture based on the detected proximity of sensor device 600 to a beacon. This is represented by block 812 of process 800. In one embodiment, sensor 602 may receive a signal via transceiver 614 representing proximity of sensor device 600 to a beacon.

[0092] The gesture recognition processor 608 may execute one or more processes to select an operating mode of the sensor device 600, and specifically an operating mode of the activity processor 606. This operating mode selection is represented by block 816 of process 800. In addition, the selection of the operating mode may be initiated in response to a gesture, and wherein the gesture may be recognized by the gesture recognition processor 608 based on one or more processes associated with blocks 806, 808, 810, and 812. In one embodiment, when the sensor device 600 is started, the activity processor 606 may execute one or more processes associated with the first operating mode. In another embodiment, the first operating mode may be passed to the activity processor 606 by the gesture recognition processor 608 as a default operating mode. Upon recognizing a gesture, the gesture recognition processor 608 may instruct the activity processor 606 to execute one or more processes associated with the second operating mode. It will be appreciated by those of ordinary skill that an operating mode may include many different types of processes to be performed by one or more components of the sensor device 600. In one example, an operating mode may include one or more processes to instruct the activity processor 606 to receive data from one or more additional / replacement sensors. In this way, when recognizing a gesture, activity processor 606 can be instructed to change the number or type of sensors from which data is received in order to recognize one or more activities. The operating mode can also include, among other things, a sampling rate or processes that specify the sampling rate at which activity processor 606 samples data from sensor 602. In this way, when recognizing a gesture, activity processor 606 can be instructed by gesture recognition processor 608 to sample data at a sampling rate associated with the second operating mode. This sampling rate can be lower than the possible upsampling rate of activity processor 606, so that a lower sampling rate can be associated with lower power consumption of activity processor 606.

[0093] Block 814 of process 800 represents one or more processes of filtering the data received from sensor 602. The data may be filtered by filter 604, where filter 604 may act as a "pre-filter." By pre-filtering, filter 604 may allow activity processor 606 to remain dormant or in a low-power state until the received data is above a threshold. Thus, upon receiving data corresponding to or above a threshold, filter 604 may transmit a "wake-up" signal to activity processor 606.

[0094] When the operating mode is selected, the activity processor 606 can analyze the data received from the sensor 602. The analysis is represented by block 818, where the activity processor 606 can perform one or more processes to identify one or more activities performed by the user. In addition, the data received by the analysis processor 606 from the sensor 602 can be received simultaneously to the gesture recognition processor 608, as represented by the parallel processing from block 814 to block 818.

[0095] Fig. 9 900 is a schematic block diagram of an operation mode selection process 900. Block 902 represents receiving data from sensor 602. In one implementation, as described by block 904, gesture recognition processor 608 may buffer the received data. Subsequently, as indicated by block 908, and as described with respect to Figure 8 As discussed above with respect to process 800 , gesture recognition processor 608 may perform one or more processes to recognize one or more gestures associated with the received data.

[0096] The data received at block 902 may be simultaneously transmitted to the activity processor 606, where the received data may be filtered at block 906 before being passed to the activity processor 606 at block 910. The activity processor 606 may perform one or more processes to identify one or more activities from the sensor data received at block 910, where such activity identification is performed in parallel with gesture identification by the gesture identification processor 608.

[0097] Block 912 of process 900 represents selecting an operating mode by gesture recognition processor 608. The selection of the operating mode may be based on the one or more gestures recognized from block 908, but additionally considers the one or more activities recognized from block 910, as described with respect to block 816 of process 800. In this manner, a second operating mode may be selected based on the one or more recognized gestures, and additionally accommodates one or more activities recognized by sensor device 600 as being performed by a user.

[0098] Exemplary embodiments allow a user to quickly and easily change the operating mode of a sensor device by performing a specific gesture, such as a device configured to be worn around a user's appendage. This can be, for example, flicking a wrist, tapping the device, orienting the device in a specific manner, or any combination thereof. In some embodiments, the operating mode can be a power saving mode, or a mode in which specific data is displayed or output. This can be particularly beneficial for users who are participating in a physical activity, in which, for example, a combination of pressing buttons or manipulating a touch screen can be difficult, dangerous, or otherwise undesirable. For example, if a user starts running a marathon, it is advantageous to enter a higher sampling rate operating mode by performing a gesture rather than pressing a start button, etc. In addition, since the operating mode can be changed by the user performing a gesture, it is not necessary to provide a sensor device with a variety of buttons or a complex touch screen display. This can reduce the complexity and / or cost and / or reliability and / durability and / or power consumption of the device.

[0099] In addition, in some embodiments, the sensor device can recognize that a physical activity has begun or ended. This can be recognized through recognition of gestures and / or activities. In response, this automatic recognition can result in a change in the operating mode. For example, if the sensor device recognizes or determines that the physical activity has ended, it can enter an operating mode in which power consumption is reduced. This can result in improved battery life, which can be particularly important for portable or wearable devices.

[0100] The sensor device 600 may include a classification module configured to classify the collected acceleration data into one of a plurality of postures. The sensor device 600 may also include an operation mode selection module configured to select an operation mode for the processor based at least on the classification posture. These modules may form part of the gesture recognition processor 608.

[0101] The sensor device 600 may include an activity recognition module configured to recognize an activity based on the acceleration data. This module may form part of the activity processor 606.

[0102] In any of the above aspects, the various features may be implemented in hardware, or as software modules running on one or more processors. Features of one aspect may be applicable to any other aspect.

[0103] In addition, a computer program or computer program product for performing any of the methods described herein, and a computer readable medium having stored thereon a program for performing any of the methods described herein, may also be provided. A computer program may be stored on a computer readable medium, or it may be, for example, in the form of a signal, such as a downloadable data signal provided on an Internet website, or it may be in any other form.

[0104] Further embodiments are provided below as exemplary entries:

[0105] Item 1. A computer-implemented method of operating a device, comprising:

[0106] (a) receiving acceleration data representing movement of a user's appendage at a processor included in a device operating in a first operating mode and configured to be worn by a person;

[0107] (b) classifying the acceleration data received at (a) into one of a plurality of postures on a processor;

[0108] (c) based at least on the classified gesture, entering a second operating mode of the device;

[0109] (d) receiving acceleration data representing movement of a user appendage at a processor included in the device operating in the second operating mode; and

[0110] (e) Classifying the acceleration data received at (d) into one of multiple postures on the processor.

[0111] Item 2. The computer-implemented method of Item 1, wherein the processor in (a), the processor in (b), the processor in (c), and the processor in (e) are a shared processor.

[0112] Item 3. The computer-implemented method of Item 1, wherein the posture is classified based on a motion pattern of the device.

[0113] Clause 4. The computer-implemented method of Clause 1, wherein the gesture is classified based on a touch pattern by the device through a user.

[0114] Clause 5. The computer-implemented method of Clause 4, wherein the touch pattern is a series of taps of the device by a user.

[0115] Clause 6. The computer-implemented method of Clause 1, wherein the posture is classified based on an orientation of the device.

[0116] Clause 7. The computer-implemented method of Clause 1, wherein the gesture is based on a proximity classification of the device to a beacon.

[0117] Clause 8. The computer-implemented method of Clause 7, wherein the device is a first sensor device and the beacon is associated with a second device on a second user.

[0118] Clause 9. The computer-implemented method of Clause 8, wherein the beacon is associated with a location and the device registers at the location based on the device's proximity to the beacon.

[0119] Clause 10. The computer-implemented method of clause 1, further comprising:

[0120] comparing a first value of acceleration data obtained from the accelerometer to a plurality of threshold values;

[0121] determining that a first value of the acceleration data corresponds to a first threshold value within a plurality of threshold values; and

[0122] The classification of the acceleration data into a gesture is based on a correspondence between a first value of the acceleration data and a first threshold.

[0123] Item 11. A single device configured to be worn around an appendage of a user, comprising:

[0124] a sensor configured to collect acceleration data from an appendage of the user;

[0125] processor;

[0126] A non-transitory computer-readable medium comprising computer-executable instructions, which, when executed, cause the processor to at least:

[0127] receiving, at the processor, the collected acceleration data;

[0128] Classifying the collected acceleration data into one of a plurality of postures by a processor;

[0129] An operating mode of a processor is selected based on the classified gesture, wherein the processor samples data from the accelerometer based on the operating mode.

[0130] Item 12. The single device of Item 11, wherein the processor selects a sampling rate for sampling data from the accelerometer based on the classified posture.

[0131] Item 13. The single device of Item 11, wherein the operating mode is a sleep mode such that the processor uses a low power level.

[0132] Item 14. The single device of Item 11, wherein the operating mode is further selected based on an activity identified by the processor.

[0133] Item 15. The single device of Item 11, wherein the processor selects a second sensor from which to receive motion data of the user based on the classified gesture.

[0134] Item 16. A non-transitory computer-readable medium comprising computer-executable instructions, which when executed cause a processor to at least:

[0135] a) receiving motion data of the user from a sensor of the device;

[0136] b) recognizing gestures from received motion data;

[0137] c) Adjusting the operating mode of the device based on the gesture identified in b).

[0138] Item 17. The non-transitory computer-readable medium of Item 16, wherein the sensor is one selected from the group consisting of an accelerometer, a gyroscope, a force sensor, a magnetic field sensor, a global positioning system sensor, and a capacitive sensor.

[0139] Clause 18. The non-transitory computer-readable medium of Clause 16, wherein the gesture is identified based on a motion pattern of the sensor device.

[0140] Clause 19. The non-transitory computer-readable medium of Clause 16, wherein the gesture is recognized based on a touch pattern of a user by a sensor device.

[0141] Clause 20. The non-transitory computer-readable medium of Clause 16, wherein the gesture is identified based on an orientation of the sensor device.

Claims

1. A computer-implemented method of operating a device configured to be worn by a user and comprising one or more sensors, the method comprising: causing the device to enter a training mode, and instructing a user to perform a plurality of consecutive repetitions of a training gesture while the device is in the training mode; While performing multiple consecutive repetitions of the training position: receiving, by the processor, from the accelerometer, first acceleration data associated with the performance of a plurality of consecutive repetitions of a training gesture; Collecting the first acceleration data at multiple sampling rates, the multiple sampling rates including a first sampling rate and a second sampling rate, the second sampling rate being lower than the first sampling rate; identifying one or more characteristics common to the one or more repetitions of the training gesture by comparing the collected first acceleration data associated with the performance of each of the one or more repetitions of the training gesture; comparing a plurality of consecutive repetitions of a training gesture acquired at a plurality of sampling rates, wherein the training gesture is recognizable at both the first sampling rate and the second sampling rate; storing the one or more characteristics and the second sampling rate; operating the device in a first operating mode in which acceleration data is collected at a first sampling rate; While operating the device at a first sampling rate: determining, based on a signal received from the beacon, that the device is in proximity to the beacon; identifying information associated with the received signal as a proximity gesture from among a plurality of proximity gestures; and One or more processes are performed based on identifying the proximity gesture.

2. The computer-implemented method of claim 1 , wherein: The beacon is associated with a second device worn by a second user.

3. The computer-implemented method of claim 1 or 2, wherein: The beacon is associated with a geographic location.

4. The computer-implemented method of claim 3, wherein: The one or more processes include registering the device at the geographic location.

5. The computer-implemented method of claim 1 or 2, wherein: The beacons are associated with points on the route.

6. The computer-implemented method of claim 5, wherein: The one or more processes include registering the device at a point on the route.

7. The computer-implemented method of claim 1 or 2, wherein: The one or more processes include updating a progress time associated with an activity performed by the user.

8. The computer-implemented method of claim 1 or 2, wherein: The one or more processes include causing the device to enter a second operating mode.

9. The computer-implemented method of claim 8, wherein: In the second operating mode, acceleration data is sampled at the second sampling rate.

10. The computer-implemented method of claim 8, wherein: Entering the second operating mode results in obtaining data from one or more additional sensors.

11. The computer-implemented method of claim 8, wherein: Entering the second operating mode causes specific data to be displayed on a display associated with the device.

12. The computer-implemented method of claim 8, wherein: The second operating mode is a sleep mode such that the processor uses a low power level.

13. The computer-implemented method of claim 10, wherein: The one or more sensors or the one or more additional sensors include: an accelerometer, a gyroscope, a force sensor, a magnetic field sensor, a global positioning system sensor and a capacitive sensor.

14. The computer-implemented method of claim 1 or 2, wherein: The device is a wristband.

15. A non-transitory computer readable medium comprising executable instructions which, when executed, cause a computer device to perform the method according to any one of claims 1 to 14.

16. A unitary device configured to be worn by a user, comprising: an acceleration sensor configured to collect acceleration data from an appendage of the user; a processor configured to receive the collected acceleration data; A non-transitory computer readable medium (610) comprising computer executable instructions which, when executed by the processor, perform the method of any one of claims 1 to 14.

17. A computer-implemented method of operating a device including a sensor, the method comprising: causing the device to enter a training mode, and instructing a user to perform a plurality of consecutive repetitions of a training gesture while the device is in the training mode; While performing multiple consecutive repetitions of the training position: receiving, by the processor, from the accelerometer, first acceleration data associated with the performance of a plurality of consecutive repetitions of a training gesture; collecting first acceleration data at a plurality of sampling rates during a plurality of consecutive repetitions of the training posture, the plurality of sampling rates comprising a first sampling rate and a second sampling rate, the second sampling rate being lower than the first sampling rate; identifying one or more characteristics common to the one or more repetitions of the training gesture by comparing the collected first acceleration data associated with the performance of each of the one or more repetitions of the training gesture; comparing a plurality of consecutive repetitions of a training gesture acquired at a plurality of sampling rates, wherein the training gesture is recognizable at both the first sampling rate and the second sampling rate; storing the one or more characteristics and the second sampling rate; receiving a signal from a beacon; identifying an approach gesture from the received signal; One or more gestures are performed based on the recognized proximity gesture, the one or more gestures comprising adjusting an operating mode of the device.

18. A non-transitory computer readable medium comprising executable instructions which, when executed, cause a computer device to perform the method of claim 17.

19. An all-in-one device configured to be worn by a user, comprising: an accelerometer configured to capture acceleration data from a user's limb; a processor for receiving the captured acceleration data; A non-transitory computer readable medium comprising computer executable instructions which, when executed by a processor, perform the method of claim 17.

Images