Performance metrology system and method

Abstract

A method of determining a performance indicator of an athlete, the method comprising the steps of, in a processing system: receiving data from at least one limb of the athlete; determining an orientation of the at least one limb and applying the orientation to the received data; and generating the performance indicator of the at least one limb based on the received data and the orientation of the at least one limb.

Description

Technical Field

[0001] The present invention relates to a performance measurement method and system. In a specific example, the present invention relates to measuring the performance of water sports such as swimming and rowing. Background Art

[0002] The following references and descriptions of prior art solutions or products are not intended to be, and should not be construed as, statements or admissions of common knowledge in the art. Specifically, the following descriptions of the prior art are not related to what is known or well-known to those skilled in the art, but are intended to help understand the creative steps of the present invention, of which the identification of the relevant prior art solutions is only a part.

[0003] Over time, certain performance metrics of athletes have been measured and captured to identify areas that require improvement and training. Using swimming as an example, coaches / trainers often look at certain performance metrics to see where athletes can improve to enhance their overall performance. This is often done by the coach observing the athlete and commenting on his or her stroke. So, for example, during freestyle, the coach might notice that the swimmer leans too far to one side when inhaling. This creates unnecessary drag and slows the swimmer down. Therefore, during training, the coach might recommend techniques to reduce the body lean.

[0004] However, these tips are often based on a coach's observation of his or her athletes and instinctual knowledge of where they can improve. They are not usually based on objective measurements of how a swimmer propels his or her body through the water.

[0005] The present invention is directed to a system and method for measuring one or more performance indicators that may ameliorate the above-mentioned shortcomings and deficiencies, or at least provide a useful alternative. Summary of the invention

[0006] According to one aspect of the present invention, a method for determining an athlete's performance indicator is provided, the method comprising the following steps: receiving data from at least one limb of the athlete; determining the orientation of the at least one limb and applying the orientation to the received data; and generating a performance indicator of the at least one limb based on the received data and the orientation of the at least one limb.

[0007] According to one example, the method may be performed by one or more processing systems, which may be part of a discrete or distributed / networked system.

[0008] In another example, the method includes receiving data including any one or a combination of pressure data from the at least one limb, acceleration data of the at least one limb, and time data.

[0009] In one embodiment, the at least one limb is a hand of an athlete, and the pressure data includes a palm pressure of the hand and a lateral pressure of the hand.

[0010] According to another example, the method includes determining a pressure difference, the pressure difference being a pressure difference between a palm pressure and a side pressure.

[0011] In yet another example, receiving pressure data includes receiving data from a left hand and a right hand of the athlete.

[0012] In one example, a method for determining an athlete performance indicator is provided, the method comprising the following steps, in a processing system: receiving data from at least one limb of the athlete; determining an orientation of the at least one limb and applying the orientation to the received data; and generating a performance indicator of the at least one limb based on the received data and the orientation of the at least one limb.

[0013] In another example, determining the orientation of the player includes applying at least a portion of the received data to a quaternion rotation. That is, applying the rotation function may include applying a quaternion rotation.

[0014] According to another embodiment, the method includes determining any one of three-dimensional pressure and three-dimensional acceleration or a combination thereof.

[0015] According to another example, determining the three-dimensional pressure includes determining a forward pressure of the limb, a lateral pressure of the limb, and a vertical pressure of the limb.

[0016] According to another example, determining the three-dimensional acceleration includes determining a forward acceleration of the limb, a lateral acceleration of the limb, and a vertical acceleration of the limb.

[0017] In another example, the method includes determining a velocity of the limb in one or more dimensions, the velocity including a forward velocity, a lateral velocity, and a vertical velocity.

[0018] In one example, a method of determining velocity includes: determining acceleration in one or more dimensions; integrating the acceleration in the one or more dimensions to determine velocity in the one or more dimensions.

[0019] In another example, the method includes determining displacement of the limb in one or more dimensions, including any one or a combination of forward displacement, lateral displacement, and vertical displacement.

[0020] In one example, determining the displacement in one or more dimensions includes integrating the velocity in one or more dimensions.

[0021] In one example, the athlete is a swimmer.

[0022] In yet another example, the method includes detecting a stroke event by identifying a point of entry of a hand into the water and a point of exit of the hand into the water.

[0023] According to another example, identifying the water entry point and the water exit point includes determining a pressure difference between a pressure measured on a side of the hand and a pressure measured on a palm, and a time period.

[0024] According to another example, the method includes detecting a lap event by identifying a change in forward direction.

[0025] In another example, identifying a forward change includes determining a forward pressure and a time period.

[0026] In another example, the method includes detecting a pull event.

[0027] According to another example, detecting a pull includes identifying one or more locations in a stroke where a forward velocity approaches zero, indicating a transition from a catch to a pull.

[0028] In another example, the method includes combining a stroke event, a pass event, and a pull event.

[0029] In yet another example, the method includes generating a graphical representation of stroke events, lap events, and / or pull events for one or more time periods for a swimmer.

[0030] In another embodiment, the method includes determining a stroke type or swimming style.

[0031] According to another example, the stroke type or swimming style may include any one of freestyle, backstroke, breaststroke, butterfly stroke and drill or a combination thereof.

[0032] In yet another example, the method includes generating a graphical representation of one or more performance indicators.

[0033] According to another example, the method includes: generating one or more graphical representations, the graphical representations including any one or a combination of the following: stroke rate and force over a period of time; force over a period of time, i.e., force applied by one or more limbs of an athlete over a specific period of time; stroke path of one or more limbs over a period of time; velocity of one or more limbs over a period of time; stroke paths of two or more limbs for comparison over a period of time; segmentation of stroke phases over a period of time; and angle of attack.

[0034] In one approach, stroke rate includes the number of strokes per minute over a period of time.

[0035] According to another example, the graphical representation of forces over a period of time includes any one or a combination of: forces per stroke, force fields of a limb, and forces versus time.

[0036] According to another aspect, the stroke path includes depth and outstroke motions of one or more limbs.

[0037] In yet another example, the comparing includes determining whether the limbs are consistent with respect to any one or a combination of the following: movement in the water, depth, and outstroke.

[0038] According to another example, segmenting the stroke phases includes generating a graphical representation showing percentages of the glide, pull, and recovery phases of a stroke.

[0039] In another embodiment, angle of attack includes determining the angle of the limb at a specific point in time, and the pressure applied at that time.

[0040] According to another aspect, the present invention provides a system for determining athlete performance indicators, the system comprising: a sensing system and a processing system, the processing system being configured to: receive data from a sensing system attached to at least one limb of the athlete; determine the orientation of the at least one limb and apply the orientation to the received data; and generate a performance indicator of the at least one limb based on the received data and the orientation of the at least one limb.

[0041] According to another aspect, the present invention provides a processing system for determining athlete performance indicators, wherein the processing system is configured to: receive data from a sensor system attached to at least one limb of the athlete; determine the orientation of the at least one limb and apply the orientation to the received data; and generate a performance indicator of the at least one limb based on the received data and the orientation of the at least one limb.

[0042] According to another aspect, the present invention provides a system for determining a performance indicator of a swimmer, the system being configured to: receive data from at least one limb of the swimmer; determine an orientation of the at least one limb and apply the orientation to the received data; and generate a performance indicator of the at least one limb based on the received data and the orientation of the at least one limb.

[0043] It will be understood that the aspects, schemes, and examples described herein may be formed in any combination. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The present invention may be better understood from the following non-limiting description of preferred embodiments, in which:

[0045] Figure 1A is a flow chart of an example aspect of the present invention;

[0046] Figure 1B is another flow chart of an exemplary aspect of the present invention;

[0047] Figure 2A and Figure 2B is a flow chart of another example aspect of the present invention;

[0048] FIG. 3A to FIG. 3F is a flow chart illustrating another example process of the present invention;

[0049] Figure 4 is a flowchart illustrating another example process of the present invention; and

[0050] Figures 5 to 36 is an illustration of an example graphical user interface showing various performance indicators generated by the systems and methods described herein. DETAILED DESCRIPTION

[0051] Figure 1A An example of a process for generating a user performance metric is shown. In one specific example, a system and method for generating a user or athlete performance metric is provided herein. It is understood that although the following example is directed to swimming, particularly freestyle swimming, the system / method described herein can be applied to any form of sports.

[0052] exist Figure 1A In the example of FIG. 1 , data is received from at least one limb or body part of a user at step 100. It will be appreciated that while the examples herein describe data received from a swimmer's hand, data may be received and analyzed from any suitable body part (e.g., the legs or head of any user during a sporting activity) according to the systems / methods described herein.

[0053] For example, the received data may include: data from one or more sensing systems (including one or more pressure sensors and one or more inertial measurement units (IMUs)) that form part of a device that is typically attached to at least one limb of a user (commonly referred to as a handheld system) and is configured to sense / generate various signals from one or more limbs of the user, such as pressure, acceleration, force, displacement, etc. at certain points of the limb. An example of a device is described in WO2019 / 204876 (“System and method for developing performance indicators for swimmers”), the entire contents of which are incorporated herein by reference.

[0054] It will be appreciated that performance metrics may include identification of stroke / swim type and therefore may include analysis of all strokes / drill breakdowns (e.g., stroke rate, force used per stroke, distance per stroke, number of strokes per lap, swim time, lap time, average speed, peak velocity, and efficiency (percent forward), and as further described herein, the path / trajectory that the limb is moving or any form of movement data).

[0055] Once the data is received, in step 110, the data is subjected to rotational orientation calibration to determine the orientation of the limb. According to a specific example, a rotation / orientation algorithm is applied. In a specific example, the algorithm is a quaternion rotation, although the user can understand that any form of rotation can be used to determine the user's orientation / position, such as a three-dimensional matrix, etc. Thus, at step 115, the limb movement is intuitively mapped, and / or various performance indicators are determined accordingly at step 120.

[0056] Understandably, Figure 1A The process may be applied to one or more systems including one or more processing systems, which may include networked or distributed systems. For example, a sensing system including one or more pressure sensors / IMUs may sense data as needed and transmit the data to a processing system for further processing. The processing system may be any one or a combination of a handheld device (such as a tablet or smartphone), a desktop or laptop computer, or a cloud-based system for storing and / or analyzing data and sharing data and / or performance metrics with other processing systems. Furthermore, the data generated may be stored in any data storage system, including a database, the cloud, or any distributed system.

[0057] Therefore, the present invention provides a method for determining an athlete's performance indicator, the method comprising the following steps: receiving data from at least one limb of the athlete; determining the orientation of the at least one limb and applying the orientation to the received data; and generating a performance indicator of the at least one limb based on the received data and the orientation of the at least one limb.

[0058] As described herein, the orientation of at least one limb or athlete may be initially determined by calibrating a sensing device that senses certain baseline performance indicators, such as pressure on at least one limb and acceleration of at least one limb to which the sensing device is coupled.

[0059] For example, if the athlete is a swimmer and the sensing device is attached to one or more of the swimmer's hands, the swimmer will typically stand facing the pool in which they will be swimming, with their palms facing up and towards the pool. Information / data about the position of their hands in relation to the pool can then be received, so the data from the sensing device can be modified / interpreted based on the position and orientation of the pool. In one example, a rotation algorithm (such as a quaternion algorithm) is applied to calibrate the position of the hands relative to the pool. This then determines the orientation of the athlete based on the athlete's position.

[0060] Thus, the system / method includes receiving data including any one or a combination of pressure data from the at least one limb, acceleration data of the at least one limb, and time data.

[0061] According to one example, the at least one limb is a hand of an athlete, and the pressure data includes a palm pressure of the hand and a side pressure of the hand. The method / system can then determine a pressure difference between the two sensed pressures of the palm and the side of the hand. It is worth noting that the pressure data can be received from one or more limbs. Thus, for example, the pressure data can include data from the left and right hands of an athlete.

[0062] Thus, the method / system can determine pressure and / or acceleration in one or more dimensions. Typically, they are determined in three dimensions - the forward, lateral and vertical (or x, y, z axis) directions of the limb. Thus, a rotation algorithm can be applied in three dimensions to calibrate the pressure and acceleration data relative to a positional reference system (e.g., the coordinate system of a pool).

[0063] Thus, the methods / systems described herein may include determining the velocity of the limb in one or more dimensions, including any one or a combination of forward velocity, lateral velocity, and vertical velocity. Typically, in order to determine the velocity in one or more directions, it is necessary to integrate the accelerations determined in one or more dimensions.

[0064] Further, the system / method may include determining the displacement of the limb in one or more dimensions, the displacement including any one or a combination of forward displacement, lateral displacement and vertical displacement. Typically, determining the displacement in one or more dimensions includes integrating each velocity in one or more dimensions.

[0065] It is worth noting that the method / system may also include applying trimming functions, resampling and / or noise filters as desired. Further examples are provided below.

[0066] Thus, the systems / methods described herein can provide certain baseline performance indicators that can be used to provide further performance analysis and graphical representation of the indicators. These baseline performance indicators include, but are not limited to: time and pressure differences at certain points or locations of a limb or body part, and one or more dimensions of pressure, acceleration, velocity, and displacement.

[0067] In the swimming example, the methods / systems described herein may also identify the entry and exit points of a swimmer's hand by determining the pressure difference between the pressure measured on one side of the hand and the pressure measured on the palm, and the time period. Additionally, the methods / systems may detect lap events by identifying a change in forward direction, typically including determining the forward pressure and the time period to that point.

[0068] Further, the system / method may detect a pull event, generally comprising: identifying one or more locations in a stroke where the forward velocity approaches zero, the forward velocity approaching zero indicating a transition from a catch to a pull. The method / system may then combine the stroke events, lap events, and pull events over a period of time, and may further generate a graphical representation of the swimmer's stroke events, lap events, and / or pull events over one or more time periods.

[0069] It is worth noting that for swimming, the method / system may include: determining a stroke type or a swimming style, wherein the stroke type or the swimming style may include any one or a combination of freestyle, backstroke, breaststroke, butterfly stroke, and split exercises.

[0070] As further described herein, the method / system may include: generating one or more graphical representations of one or more performance indicators. The graphical representations may include any one or a combination of the following: stroke rate and force over a period of time; force over a period of time, i.e., force applied by one or more limbs of the athlete over a particular period of time; stroke path of one or more limbs over a period of time; velocity of one or more limbs over a period of time; stroke paths of two or more limbs for comparison over a period of time; segmentation of stroke phases over a period of time; and angle of attack.

[0071] In these examples, the stroke rate includes the number of strokes per minute over a period of time, where the graphical representation of force over a period of time can include any one or a combination of the following: force per stroke, force field of a limb, and force versus time.

[0072] Additionally, the stroke path may include depth and outward stroke of one or more limbs; and the comparison includes determining whether the limbs are consistent in any one or a combination of: movement of the limb in the water, depth, and outward stroke of the limb of the swimmer's body.

[0073] The segmentation of the stroke phases may include generating a graphical representation showing the percentage of the glide, pull and recovery phases of a stroke. In addition, the angle of attack may include determining the angle of the limb at a particular point in time and the pressure applied at that time.

[0074] Further examples of graphical representations are provided below.

[0075] Figure 1B Another example of the process / system described herein is shown in which various performance metrics for swimming are calculated / displayed. In this example, in steps 125A and 125B, the time difference between the left and right hands is determined, respectively, in order to detect the stroke in step 130. In step 135, the starting point of each stroke is detected; in step 140, the stroke is divided into a number of strokes. In step 145, any filtering or calibration signals received (e.g., to compensate for gyroscope drift) are applied to the data received from the left and right hands in steps 150A and 150B, respectively. The data typically received from each hand while swimming includes, but is not limited to: time differences in the forward, lateral, and vertical directions; velocities in the forward, lateral, and vertical directions; and displacements in the forward, lateral, and vertical directions.

[0076] In step 160, various data measurements are extracted and may be graphed based on the data determined / received from each hand. This includes stroke phases, hand paths, forces per stroke, force fields, and forces versus time. For example, a graphical representation of a swimmer's hand path may be generated that may show the movement of the hand during the stroke. That is, the depth the hand travels through the water, and also the velocity and displacement of the hand as it moves through the water. Thus, data representing each stroke may be graphically mapped for viewing by a user. Examples of stroke mapping are discussed further below.

[0077] The user may also be provided with an analysis or swimming metric summary in step 165; and in step 170, the user may store the data in any digital storage means / device, such as on a local processing system (e.g., a mobile device or desktop device), or on a cloud system.

[0078] Figure 2A and Figure 2B An example of a process for generating performance metrics for a swimmer user is shown, where the one or more limbs are typically one or more hands of the swimmer.

[0079] In this example, the process includes: typically by the device as described above (referred to as a handheld device), in step 210, data for the user's left hand is generated / recorded; and in step 211, data for the user's right hand is generated / recorded. In step 212, the data is sent to a processing system (such as a mobile telecommunication device or a personal computer, etc.) via a communication system (such as Bluetooth or any wireless communication system, etc.). In steps 215 and 220, the processing system extracts the received data from the left hand and the right hand, respectively, and then unpacks the data in step 225 and presents it as raw data in step 230. In step 235, data conversion is performed. For example, the pressure data units received from the handheld device are typically converted to kilopascals, and the time units are typically converted to milliseconds.

[0080] The received data is typically trimmed in step 240. For example, this may include determining the first water entry point and deleting all data related to before the start of the swim, which is typically not necessary to determine the performance indicator.

[0081] In step 245, the received data is subjected to quaternion rotation to determine the direction of the hand. This is usually achieved by performing quaternion multiplication on the data with reference to the swimming pool orientation shown in step 242.

[0082] In step 250, the data may be resampled to generate data by taking any unevenly spaced raw data samples and resampling the data at uniform time intervals. Next, the process proceeds to step 255, which includes calculating the velocity and displacement of the hand, which includes an integration step in step 265. In step 260, the data is subjected to a smoothing function operation or a fast Fourier transform using a filter (e.g., a spectral filter) to smooth the data and remove any noise.

[0083] In step 270, the data is analyzed to determine one or more performance indicators and the process data may then be saved in step 275. Thus, in step 280, the data may be retrieved and an interactive chart / map may be generated in step 282 showing the limb in motion.

[0084] It is worth noting that in step 288 and step 285, the process settings and analysis settings can be set according to one or more users of the system, respectively.

[0085] Figures 3A to 3C A more detailed example of data that may be retrieved from one or more handheld devices that are typically attached to one or more hands of a swimmer in order to determine one or more performance metrics is shown.

[0086] In step 310, the system may receive raw data for the left and right hands. The raw data typically includes: time data, data from at least two pressure sensors (e.g., a palm sensor and a hand side sensor) at different locations of the limb, accelerometer data in one or more directions (typically in x, y, z dimensions), and may further include gyroscope data in one or more directions, magnetometer data in one or more directions, and quaternion baselines. It is noteworthy that in these examples, the directions are typically x, y, z directions based on the swimming direction (i.e., the direction the swimmer is facing in the pool).

[0087] In step 315, the data is converted to the metrics required for the process as described above, such as converting time to seconds and converting received pressure to kilopascals. In step 320, the data is trimmed to only the necessary data elements. It is worth noting that in this step, the pressure difference between palm and lateral pressure is also determined. That is, the depth-induced pressure can be balanced with the motion pressure to infer force data.

[0088] In step 325, the raw data is quaternion rotated. That is, the raw data is typically in the reference of the handheld device, and the rotation enables the data to be recalibrated relative to the (x, y, z) reference coordinate system (forward, lateral, vertical) of the pool. It will be appreciated that this rotation enables the performance indicator to be determined in the direction in which the swimmer is swimming.

[0089] Thus, for example, at this stage the orientation of the hand / palm relative to the pool can be determined, for example, and the magnitude of forces in different directions can also be determined. In step 330, applying quaternion rotations can generate pressures in the forward, lateral and vertical directions, and accelerations in the forward, lateral and vertical directions.

[0090] In step 335, a resampling algorithm may be applied, such as linear regression between the non-uniform data samples to interpolate at the desired time points to generate data at uniform time intervals. Thus, for example, the resampling algorithm may convert the non-uniform time intervals to uniform time intervals, which includes using linear interpolation between samples. This way, the size of all arrays is equal to the size of the time array output, thereby facilitating analysis of the generated data.

[0091] In step 340, a filtering algorithm is applied to remove any unnecessary noise from the data, such as high frequency noise and / or low frequency DC components. This may include applying a Fast Fourier Transform and / or a smoothing function. Typically, the smoothing function is a low pass notch filter with 3 functions, which can:

[0092] Acts as a low-pass filter, zeroing out any high-frequency "noise" in the sampled data;

[0093] Acts as a notch filter, zeroing out the lowest frequency (DC) component; and

[0094] As a smoothing function, it ensures that the filter's zeroing edges are smooth, which helps reduce the noise added to the data after the Fast Fourier Transform (FFT).

[0095] In addition, an inverse FFT can be applied to convert the time-based data into frequency domain data so that the high-frequency "noise" and low-frequency DC components can be separated, thereby eliminating any unwanted parasitic components in the smooth function. The inverse FFT converts the filtered data back to the time domain, at which point the noise has been removed.

[0096] Thus, for example, step 340 shows that the generated data, including pressure difference, forward pressure, lateral pressure, vertical pressure, three-dimensional (x, y, z) acceleration, forward acceleration, lateral acceleration, vertical acceleration, can all have filtering functions applied to them, including: applying a fast Fourier transform (FFT) to all data arrays; creating two smoothing functions (such as Figure 3B Notch_1 and Notch_2 shown); multiply each element of the FFT output by the corresponding smoothing element; and apply the inverse FFT (iFFT) to generate filtered data for each of the pressure difference, forward pressure, lateral pressure, vertical pressure, three-dimensional (x, y, z) acceleration, forward acceleration, lateral acceleration, and vertical acceleration. In step 345, various performance indicators of the hand, such as three-dimensional speed (including forward speed, lateral speed, and vertical speed) can be determined based on the data received by the handheld device. In this particular example, the forward hand speed, lateral hand speed, and vertical hand speed are all determined by taking the corresponding forward acceleration, lateral acceleration, and vertical acceleration and applying an integral function to each acceleration direction, and further applying a filtering function by applying FFT, multiplying by a smoothing function (Notch_3), and applying an inverse FFT.

[0097] Step 350 shows an example of determining the three-dimensional displacement of the hand. That is, in this example, the determined forward acceleration, lateral acceleration, and vertical acceleration are integrated and a filter function is applied thereto, which includes: applying FFT, multiplying with a smoothing function (Notch_4), and then applying iFFT to determine the corresponding forward, lateral, and vertical displacements.

[0098] Step 355 shows some examples of performance indicators that can be further derived based on the swimming style / stroke. In these examples, the swimmer is performing freestyle swimming, which has certain characteristics that can be determined to derive performance indicators. In step 356, the pull portion of the stroke is detected, for example, by identifying a location in the stroke where the forward velocity is zero or close to zero, which generally indicates a transition from the catch portion of the stroke to the pull portion.

[0099] The stroke itself can be determined in step 358, where it is determined at which point the swimmer's hand enters / exits the water. This is typically determined by pressure differential and time. For example, when the device exits the water, the pressure reading on both sensors on the hand is zero, because typically pressure increases with increasing depth and / or increasing force on the palm of the hand. So, for example, at the beginning of a swim, it is assumed that the swimmer is above the water surface when referenced to the "swimming direction". In addition, a reference atmospheric pressure is measured at this time. When the hand enters the water, the pressure on either sensor increases significantly due to the surrounding hydrostatic pressure. When the pressure on either sensor is above the nominal atmospheric pressure by a set threshold, the hand entry can be determined. In addition, when the pressure approaches atmospheric pressure, the hand exit can be determined.

[0100] In step 357, it can be determined that the swimmer has completed a lap (or is taking a breath or turning action) by determining the change in the swimmer's forward direction, which generally includes observing the forward pressure and time. For example, when the swimmer begins to swim forward, the pressure applied is toward the feet. When they complete a lap and reach the end point, they turn around and begin swimming in the opposite direction, and the detected main force is applied in the opposite direction. It can also be further determined by measuring the average time period of the swimmer swimming in a certain direction.

[0101] The stroke, pull, and pass trigger points may then be merged in step 359 and displayed at a specific point in time or time period in step 360. In one example, the system / method may receive a pass / stroke selection from a user in step 361; determine a target time period in step 362; extract processed data within the time period in step 363; and pass the data to a device for plotting or display the determined / generated plot to the user in step 364. Additional display examples are described below.

[0102] Figure 3D yes Figure 3A , 3B Another example of a noise / notch filter is shown in FIG. Figure 3DAs shown, the noise filter performs a fast Fourier transform (FFT) on the data set, generates a spectral filter, and superimposes the filter on the FFT data to suppress unwanted frequency bands. The process then applies an inverse FFT to restore the data to a time base.

[0103] Figure 3E Shows Figure 2B and Figure 3B Another example of resampling is shown in Figure 1. In this particular example, resampling takes a non-uniformly spaced input time array and generates uniformly spaced data points at a specified sampling rate. Therefore, when a new time point falls between measured samples, a linear fit can be performed between the two adjacent data points to interpolate the new data point. In general, the time_resampled output array may be a different size than the input array, however, all resampled output arrays are typically the same size to facilitate further data processing.

[0104] Figure 3F More details of quaternion rotation / transformation are shown. In one example, quaternion rotation is used to transform the reference coordinate system of the handheld device (x, y, z) to the pool reference coordinate system (horizontal, vertical, vertical). Typically, a swimmer's calibration begins before swimming, with the swimmer holding the handheld device out in the direction of the swim.

[0105] The quaternion function can convert the acceleration input in the reference coordinate system of the handheld device to the reference coordinate system of the swimming pool when the user is swimming. For example, based on the quaternion output of the IMU, the unit vector in each of the x, y, and z directions of the IMU chip can be projected onto the horizontal axis, vertical axis, and vertical axis of the swimming pool reference coordinate system.

[0106] It is worth noting that vectors in three-dimensional space can be represented as pure quaternions, that is, quaternions without real parts: q = 0 + xi + yj + zk. Usually a quaternion qR is used to represent rotation, and its modulus jqRj is additionally required to be equal to 1. The rotation from coordinate system A to coordinate system B can be achieved by the following conjugate operation: qB = qE qAqR*. Vector qB is also a vector.

[0107] So, for example, before a user starts swimming, they will typically position their hands with their palms facing up and towards the far end of the pool in order to calibrate the IMU. This starting position typically represents the user's quaternion baseline. So, as the user moves their hands while swimming, all position data determined by the sensors on the user's hands will be aligned with the pool by applying quaternion rotations.

[0108] Figure 4 An example is shown of how one or more users may interact with the systems and methods described herein.

[0109] In this example, the user is a swimmer who accesses the present system / method via a software application on their mobile communication device. In step 405, the user wears the handheld device on both hands and orients the device to determine the swimming direction in step 410. Typically, the swimmer's orientation is first determined as a baseline measurement that allows the system to assess the swimmer's forward / backward, up / down, left / right direction and generate a "zeroing" vector that can be used to track the direction the swimmer's palm is pointing.

[0110] Once the user completes the swim in step 415 (or during the swim), the device will upload the swim data to the user's mobile communication device in step 420, which can communicate with a central processing system for data processing and a central data storage system for data storage (in this example, a cloud application / server system). In step 425, the data is posted to the user's account using the unique SwimID in step 432.

[0111] In step 430, the system may extract data associated with the user's SwimID and process the data in step 435 by any of the methods described herein to provide performance metrics for the swimmer. For example, in step 440, metadata / data related to the user and their swim may be extracted from the processed data and displayed / stored in the swimmer's account in the system (typically based on the user ID). The metadata may include any one or combination of the following: SwimID, member type, location ID, swim date, duration, distance, stroke count (left and right), number of laps, distance per stroke (DPS), force per stroke (FPS), stroke rate, number of strokes per lap, average speed, peak speed, and efficiency. Notably, in step 442, the metadata is authenticated with the user and stored in the user profile / ID in step 443. The SwimIDs of steps 445, 446, and 448 are similar.

[0112] If the user requests data for a swim, the data may be obtained by requesting data for a specific SwimID in step 450. Typically, the data is stored / cached based on the user's SwimID. In step 455, the user may request to view a specific chart view or graphical representation of performance metrics. This may be requested and verified by the user in step 456, generated in step 458 and received by the user in step 460 for viewing.

[0113] More Examples

[0114] Figure 5 Figures 24 to 25 show example display images of some performance indicators generated in a graphical or visual format. Displaying sports performance indicators can allow users such as instructors or coaches (and athletes themselves) to intuitively see various performance indicators of one or more swimming movements through stroke images or charts, thereby helping users improve their techniques. It is understood that these generated displays can also allow coaches or teams to view / compare indicators in order to improve techniques accordingly.

[0115] Those skilled in the art will appreciate that the display may be applied to any processing system, such as a desktop computer system, a mobile communication device, a tablet computer, and the like.

[0116] also, Figure 5 An example of freestyle swimming is shown in Figure 22. However, it will be appreciated by those skilled in the art that the same / similar methods and systems may also be applied to other swimming strokes, and further to other water sports (such as rowing or kayaking, etc.), where a handheld device is attached to a paddle or oar.

[0117] Especially referring to Figures 5 to 10 , the system user can view a watch face of swimming metrics displayed in a graphical form and can switch between various metrics through a navigation bar or similar tool.

[0118] Figure 5 An example of stroke rate and force for the left and right hands is shown. In this example, stroke rate is mapped to the force applied by the swimmer. The number of laps swum by the swimmer is also selected in this figure. Therefore, a user of the present system / method can easily compare the performance of swimmers at different laps.

[0119] Fig. 6A An example of a force field for a right-hand stroke captured from above is shown. A specific time period is selected and the force field is segmented by the percentage or proportion of force applied in four different directions, namely forward, backward, left and right. Figure 6B is an example of mapping the force distribution of the left and right hands as part of the force field.

[0120] Fig. 7A , Fig.11 and Fig.12 An example of stroke path and hand speed is shown. In particular, the stroke path can reflect the depth and outstroke of the hand. This example is only for one hand - the right hand, and is shown at a specific time interval and number of strokes.

[0121] Figure 7Bis another example of stroke path and hand speed, showing three different perspectives - depth, outside and front. In this diagram, the stroke is broken down into the glide, pull and recovery phases so that the proportion of each phase of the stroke can be determined.

[0122] Figure 8 The depth and outstroke movements are shown, but the strokes for each hand are mapped to visually show consistency between the two hands. Fig.13 and Fig.14 Examples of graphical representations of two-hand consistency for depth and swiping motion views are shown, respectively.

[0123] Fig. 9 and Fig.15 An example of a graphical representation of the mapped forces over time for each hand is shown. It is worth noting that the forces can be broken down into total forces or forces in different directions, such as forward, lateral, and vertical forces.

[0124] Fig.10 , Fig.16 and Fig.17 is an example of another graphical representation that details the stroke phases for each hand, including the percentage of the pull phase, the pull phase, and the recovery phase. These segments can also include their respective times. Fig.17 Only the segmentation of the stroke phase for a single hand is shown.

[0125] Figures 18 to 22C Example functions that may be employed in the systems / methods described herein and may be used to generate graphical representations of various performance indicators are shown.

[0126] Fig.18 An example of stroke rate and force on a graphical representation is shown. In this figure, if a user assigns a unique identifier (such as a SwimID, etc.) to a swimmer and can select the number of strokes to be analyzed, the systems / methods described herein can generate a graphical representation in which the horizontal axis represents time, one vertical axis displays force ratio data (y1 axis), and another vertical axis displays stroke rate data (y2 axis). By entering the SwimID, the user can also see a graphical representation of the number of strokes, the force in each direction for each limb (such as the left and right hand), and the stroke rate.

[0127] Fig.19A An example of functions that can be used to generate a graphical representation of the force field for a hand during a stroke is shown. Typically, the user would provide / select a SwinID, a pass number, a hand, and a stroke, and the resulting graphical representation would show the forces plotted over time on the x- and y-axes, as well as the forces in different directions including forward, backward, left, right, up, down, and impulse. Fig.19B An example of generating a force field after swimming a lap is shown, wherein when the user selects a SwimID and the number of laps, a force field for each hand can be generated, showing the impulse and direction of the left and right hands respectively.

[0128] Fig. 20A An example graphical representation of the stroke path and hand speed depth generated by the user selected parameters SwimID, number of passes, hands and stroke action is shown. The generated path is a function of:

[0129] path = {[time], [x-axis], [depth], [color], [speed]}.

[0130] Fig. 20B An example graphical representation of a stroke path and speed is shown, showing the resulting outstroke motion by selecting parameters including SwimID, number of passes, hands, and stroke motion. The path generated in this example would typically be:

[0131] path = {[time], [x-axis], [outline], [color]}.

[0132] Fig.21A An example graphical representation of the consistency of depth across a stroke is shown, which typically does not require time and speed data. Fig. 21B An example graphical representation of the consistency of the outstroke of a water stroke without considering the time data is shown.

[0133] Fig.22A Example graphical representations of time and force for one or more limbs based on the SwimID and number of passes selected by the user are shown, and further indicate whether the user wants to view total force or force in a specific direction (e.g., forward, lateral, or vertical).

[0134] Fig. 22B An example graphical representation of the stroke phases is shown, where the stroke phases are segmented to determine the percentage or proportion of a stroke that is in a particular phase. So, for example, if the user provides / selects SwimID, Stroke Number, Hands, and Stroke, they can see the percentage of the left and right hand strokes that were in the glide, pull, and recovery modes, respectively (average and time accurate values ​​for specific strokes).

[0135] same, Fig. 22C An example graphical representation of the stroke phase segmentation in a stroke is shown. Thus, by selecting a SwimID and a stroke number, the system / method can provide a representation of the average glide time and percentage, average pull time and percentage, average recovery time and percentage for the left and right hands, and the stroke rate for the left and right limbs, respectively.

[0136] Figure 23 to Figure 33Further examples of how to analyze and compare the generated graphical representations of data are shown.

[0137] Fig.23 An example of a graphical representation of a stroke comparison between a good stroke (2301) and a poor stroke (2302) is shown, where in a freestyle stroke, a swimmer presses down on the water during the catch phase.

[0138] Fig.24 An example graphical representation of the breakdown of the total force measured by the sensor during a stroke is shown. In this example, the total force is broken down into six directions, with 2402 showing a good stroke and 2401 showing a poor stroke. In this stroke breakdown, 2404 shows the total downward force detected during each stroke. Note that the poor stroke has more downward force, while the magnitude of all other force directions are the same in both strokes. In particular, 2403 shows the forward propulsion force, 2405 shows the inward force, 2406 shows the drag force (palm forward), and 2407 shows the outward force. Notably, the upward force between 2416 and 2417 is almost negligible in this particular stroke.

[0139] Fig.25 An example of a graphical representation of the left and right hand paths from a top view and a side view, respectively, is shown. From the top view, it can be seen that the right hand stroke amplitude is obvious, which can be confirmed in the view (or video) representation of swimming (discussed further below).

[0140] Fig.26 and Fig. 27 A graphical representation of a trajectory indicating lateral pressure of the stroke is shown. In this example, if the trajectory is below zero, it indicates outward pressure. Above zero, it indicates inward pressure. Fig.26 In the figure, the shaded areas show the glide phase, which is the time the hand stays in front of the water after entering the water; the pull phase, which is the time from when the swimmer starts to pull the water back until the hand leaves the water; and the recovery phase, which is the time when the hand leaves the water. Fig.26 In the water, the pull phase begins when the hands begin to make a large outward stroke.

[0141] Fig.28 is a graphic representation of an example of a side view of a swimmer's hand path showing the hand entering the water, moving slightly downward, and then lifting upward before initiating the pull.

[0142] Fig.29is another example of a contrast between a good stroke (2901) and a bad stroke (2902). In this example, at 2902, the swimmer's hand enters the water too early (close to the ear) and then moves along a downward and forward path. In contrast, 2901 shows a pose where the swimmer reaches forward with the hand out of the water. The hand is in the water for a shorter period of time before the stroke phase begins.

[0143] Fig.30 and Fig.31 Examples of propulsion from the swimmer's right hand (3001) and left hand (3002) are shown. Area 3003 is a dead zone, where the swimmer is unable to generate forward propulsion. In these areas, the swimmer can hardly move forward. It is worth noting that Fig.31 Dead zone ratio for swimmers Fig.30 Thus, the current systems and methods enable comparisons between swimmers for any of the performance metrics described herein.

[0144] exist Fig.32 In the example graphical representation shown, the trace 3201 shows the amount of forward propulsion detected for the swimmer, while the shaded area 3202 is the glide phase, where the hand enters the water before the pull begins. Notably, when the trace 3201 becomes negative, this means that the palm is pointing forward, creating a lot of drag. Notably, from this illustration, for this particular swimmer, the drag created by the previous stroke was much less.

[0145] Now refer to Fig.33 , which is an example of a graphical representation of a swimmer where trace 3302 shows forward propulsion in a bad stroke, while trace 3301 shows the same swimmer swimming normally. In this example, both strokes are "breathing" strokes as the swimmer breathes. In the good stroke, forward propulsion begins sooner and the swimmer breathes faster, as shown in 3303. In contrast, the breathing in the bad stroke 3304 is late, delaying the time when the swimmer generates forward propulsion.

[0146] The following examples further illustrate how a coach / trainer or swimmer can use Figures 5 to 36 Improve your swimming technique with the following indicators:

[0147] Example: Hyperextension of the hands and the subsequent lateral tilt of the body - e.g. Fig.23 Example shown

[0148] The length of the forward reach is critical, but too much reach does not actually significantly increase the actual length of a swimmer’s stroke, but it can slow the stroke, disrupt rhythm, and cause the swimmer’s hands to lose coordination with the body. Overextending the arms and having the hands extended too far out and tilted slightly upward and forward can cause the swimmer to lose connection with the stroke and disrupt their rhythm. The hips often tilt excessively, so it is common to see swimmers over-rotate in an effort to achieve a longer stroke. This can cause the swimmer to lose balance. An unbalanced swimmer will not be able to exert power in any movement. This excessive tilt reduces power and depth in the second half of the stroke while delaying the propulsive phase of the first half. This lack of balance often manifests itself in a few ways – usually with the legs crossed in an attempt to rebalance the body. Another consequence of tilt and lack of balance is the hands pointing upward at the beginning of the stroke. The correct amount of body tilt is important for swimmers to position their body early in the catch phase.

[0149] More specifically, Figure 7 Figure 8 , Fig.11 , Fig.12 , Fig.13 , Fig.14 20 and 21 show the side profile of the hand moving in the water in the form of a stroke path diagram of the hand depth samples. In the initial stage of the stroke, the hand enters the water, moves upward to the surface of the water, and then begins to catch the water.

[0150] Therefore, in a graphical representation one can generate the forces broken down into the six directions and plot the forward thrust accordingly. For example, Fig. 9 Specifically, the following four view types are shown: total force measured for both the left and right hands; forward (positive) propulsion and rearward (negative) resistance; force applied downward (negative) or upward (positive); and force applied inward (positive) or outward (negative).

[0151] Additionally, a graph can be plotted showing where the hand enters the gliding phase and how the propulsion force becomes negative for a short period of time, reflecting the upward movement of the hand; in other words, the creation of resistance.

[0152] Example: Stroke Rate and Timing

[0153] In freestyle, the relationship between stroke rate and speed is critical. While an athlete may be "more efficient" in terms of distance and stroke length, there is usually a proper balance between stroke rate and stroke length. A common problem is when an athlete's hand waits too long before pulling out the water while the other arm is coming back, which creates a "dead spot" in the swimmer's stroke. Minimizing this "dead spot" is critical to finding the best timing for each athlete. Often, the right arm is extended during the gliding phase, waiting for the left arm to come in before starting the propulsive phase.

[0154] More specifically refer to Fig. 9 , Fig.15 and Fig.22A To help identify this problem, using the systems and methods described herein, coaches can measure the time between the propulsion phases of each arm. Each athlete has a time that works best for them. Generally, too much time between phases can cause momentum loss, disrupt rhythm, and reduce speed. Additionally, the time required for the glide phase from entry to catch can be measured and how it relates to stroke rate, as increasing stroke rate can increase speed.

[0155] The methods and systems described herein can provide an indication of stroke-by-stroke performance and can monitor how a swimmer's performance increases as their stroke cadence improves.

[0156] Example: Breathing and hip timing – e.g. Fig.33 As shown below:

[0157] Generally speaking, swimming fast means swimming fast. To swim faster, swimmers often need to maintain balance because maintaining balance during propulsion and a stable body generates more force. If swimmers breathe during the propulsion phase, their bodies often lie sideways, and it is difficult for the torso to stay aligned and connected to the core. The key is to get swimmers to change their breathing pattern. That is, breathing less can reduce the body's sway, allowing them to reach a balanced state faster and maintain it longer.

[0158] The systems and methods described herein can display or generate imaging that shows lower forces at the front of the stroke. Therefore, each breath stroke is shorter and has a shorter impulse—stroke after stroke is giving up some length. The cost in length is a cost in speed. Therefore, if this problem is solved, the swim time can be shorter.

[0159] Example: Pressing down the water level when catching (poor catch) - e.g. Fig.23 and 24 As shown, swimmers push the water down

[0160] The catch is key to swimming freestyle well because, when done correctly, it sets the stage for the swimmer's stroke during the underwater phase. It is important to master the feel of the water in an effortless manner so that after entry and forward extension, the swimmer's hands and forearms exert primarily backward pressure as they move toward the hips to exit the water. A common mistake is an improper catch, where the swimmer primarily uses the hands to press down (rather than back) toward the bottom of the pool.

[0161] So, visually, the data shows that there is a peak in the right hand downward force during the catch phase, and that this peak accounts for too large a proportion of the total force of each stroke. This reduces forward propulsion and reduces performance.

[0162] Example: Excessive outward strokes—e.g. Figure 25-27 As shown:

[0163] An effective free stroke requires not only maintaining the correct body position, but also ensuring that the swimmer's arms are moving along the correct path. A common problem for many swimmers is too much outward movement (or lateral stroke) during the catch phase. When a swimmer pulls too far to the outside of their body, it limits effective propulsion at the catch position, creating lateral force instead of propulsion. Proper catch position is essential to allowing the swimmer to smoothly move forward in a straight trajectory without placing the arms in a weak position with the hands positioned wider than the elbows. Having a stroke that is too wide affects how far a swimmer can move forward with each stroke, ultimately affecting their speed.

[0164] Fig. 7A , Figure 7B , Figure 8 , Fig.12 , Fig.14 Examples of outstrokes are shown in Figures 20 and 21. Mapping the hand and arm in this way can help identify excessive outstrokes, where the top of the graph is where the hand first starts to catch the water and the bottom is where the hand leaves the water. The data can also show the peak lateral force (outward) during the catch.

[0165] Example: No stretch phase - e.g. Figure 29-30 As shown, the unstretched state is displayed:

[0166] It is very important to have a proper extension of the stroke during propulsion. Generally speaking, there is a clear difference between those who enter the water with a deep downward motion and those who extend forward at shoulder depth. The latter ensure that their hands and forearms are in the correct position to start the stroke (catch). Deep downward motion during the extension phase of the stroke creates more resistance, which is usually the fastest and most efficient phase of the stroke, and misses the very important initial preparation for the catch.

[0167] Visually, the data can show that the hands are reaching far forward during the stroke, compared to swimmers reaching correctly to shoulder depth. The data shows that there is a large difference in the power phase between the left and right hands, which may increase stroke speed, but at the expense of reducing the effective power generated, meaning that the swimmer is getting less benefit from each stroke. Understandably, once the technique of reaching and catching is mastered, freestyle can become more fluid, powerful, and more importantly, much faster.

[0168] Example: Angle of Attack

[0169] The systems / methods described herein can determine the angle that a limb (e.g., a swimmer's hand) is facing at a particular point in time, and the pressure applied during the stroke at that time or moment. Thus, the systems / methods can determine the angle at which the hand is pointing when it is pointing toward the foot or to the side, and the amount of force generated at that particular angle.

[0170] Fig.34 A graphical example of the angle of attack is shown, and at that particular moment in time, a video of the swimmer is linked and superimposed onto the generated graphic. It can therefore be appreciated that a coach or any user can see the forces that a swimmer is generating at a particular angle of attack, and they may be able to determine what improvements the swimmer can make during their swim. For example, they may be able to tell that during their swim, the swimmer is beginning to fatigue, and can see that the angle of their hands when executing the stroke is not ideal, as too much force is being applied.

[0171] Visualization of the angle of attack in a graphical interface also means that rather than having to watch an entire video of a swimmer, a coach or user can quickly identify where problems occurred in a technique and jump to that section or time interval in the video.

[0172] It is worth noting that the video images may be overlaid and linked to any of the performance indicators described herein. Fig.35 An example of a video linked to a graph showing force versus time for a swimmer's left hand is shown. Fig.36 An example of a video relating to a swimmer's hand displacements is shown, wherein a graphical interface displays the hand displacements from the side, from above, and from the swimmer's head perspective.

[0173] Thus, the systems / methods described herein may allow athletes to further improve their technique by considering various performance metrics, which may be graphically displayed to the user and mapped into the user's swim log for easy reference.

[0174] The term "comprises" and variations of the term are used herein to mean the inclusion of one or more stated integers but not the exclusion of any other integer or integers, unless the context or usage requires an exclusive interpretation of the term.

[0175] Those skilled in the art will recognize that the invention described herein is susceptible to changes and modifications other than those specifically described. All such changes and modifications should be considered within the scope and spirit of the invention, the nature of which should be determined from the above description.

Claims

1. A method for determining an athlete performance indicator, the method comprising the following steps, in a processing system: receiving data from at least one limb of the athlete; determining an orientation of the at least one limb and applying the orientation to the received data; as well as The performance indicator of the at least one limb is generated based on the received data and the orientation of the at least one limb.

2. The method according to claim 1, comprising receiving data, wherein the data comprises any one or combination of the following: a. pressure data of at least one limb; b. acceleration data of at least one limb; and c. Time data.

3. The method according to claim 2, wherein: The at least one limb is a hand of the athlete, and the pressure data includes the pressure borne by the palm of the hand and the lateral pressure of the hand.

4. The method according to claim 3, wherein: The method includes determining a pressure differential, the pressure differential being a pressure difference between the palm pressure and the side pressure.

5. The method according to claim 3 or 4, wherein: The receiving pressure data includes receiving data from a left hand and a right hand of the athlete.

6. The method according to any one of claims 1 to 4, wherein: Determining the orientation of the player includes: a. receiving location data; and b. Applying a rotation function to at least part of the received data to locate the player according to the position.

7. The method according to claim 6, wherein: Applying the rotation function includes applying a quaternion rotation.

8. The method according to claim 2, comprising: Identify any one or a combination of the following: a. Three-dimensional pressure; and b. Three-dimensional acceleration.

9. The method according to claim 8, wherein: Determining the three-dimensional pressure involves determining: a. forward pressure of the limb; b. lateral pressure on the limb; and c. Vertical pressure on the limb.

10. The method according to claim 2, wherein: Determining the three-dimensional acceleration involves determining: a. forward acceleration of the limb; b. lateral acceleration of the limb; and c. The vertical acceleration of the limb.

11. The method according to claim 2, wherein: The method includes determining the velocity of the limb in one or more dimensions, including any one or a combination of forward velocity, lateral velocity, and vertical velocity.

12. The method according to claim 11, wherein: The method for determining the speed comprises: a. Determine acceleration in one or more dimensions; and b. Integrating the acceleration in one or more dimensions to determine velocity in one or more dimensions.

13. The method according to any one of claims 11 and 12, wherein: The method includes: determining the displacement of the limb in one or more dimensions, the displacement including any one or a combination of forward displacement, lateral displacement and vertical displacement.

14. The method according to claim 13, wherein: Determining the displacement in one or more dimensions includes integrating the velocity in one or more dimensions.

15. The method according to any one of claims 1 to 14, wherein: The athlete is a swimmer.

16. The method according to claim 15, wherein: The method includes detecting a stroke event by identifying a hand entry point and a hand exit point.

17. The method according to claim 16, wherein: Identifying the entry point and the exit point includes determining a pressure difference between a pressure measured on a side of the hand and a pressure measured on a palm, and a time period.

18. The method according to claim 15, wherein: The method includes detecting a pass event by identifying a change in forward direction.

19. The method according to claim 18, wherein: Identifying a change in forward direction includes determining the forward pressure and time period.

20. The method according to claim 15, wherein: The method comprises: detecting a water pulling action event.

21. The method according to claim 20, wherein: Detecting the pull includes identifying one or more locations in a stroke where forward velocity approaches zero, indicating a transition from a catch to a pull.

22. The method according to claims 16, 18 and 20, wherein: The method includes: combining the stroke event, the trip event and the pull event for a time period.

23. The method according to claim 22, wherein: The method includes generating a graphical representation of the stroke events, the lap events, and / or the pull events for one or more time periods of the swimmer.

24. The method according to any one of claims 15 to 23, wherein: The method includes determining a stroke type and a swimming style.

25. The method according to claim 24, wherein: The stroke type or the swimming style includes any one or a combination of freestyle, backstroke, breaststroke, butterfly stroke and split exercises.

26. The method according to any one of claims 1 to 25, wherein: The method includes generating a graphical representation of one or more performance indicators.

27. The method of claim 26 as appended to claim 15, wherein: The method includes generating one or more graphical representations, the graphical representations including any one or a combination of the following: a. stroke rate and force over a period of time; b. force over time, i.e. the force exerted by one or more limbs of the athlete over a specific period of time; c. the stroke path of one or more limbs over a period of time; d. The velocity of one or more limbs over a period of time; e. The stroke paths of two or more limbs used for comparison over a period of time; f. Segmentation of the stroke phase within a time period; and g. Angle of attack.

28. The method according to claim 27, wherein: The stroke rate includes the number of strokes per minute over a period of time.

29. The method according to claim 27, wherein: Graphical representations of forces over time include any one or a combination of the following: forces applied per stroke, force fields of the limb, and force versus time.

30. The method of claim 27, wherein: The stroke path includes depth and outstroke motions of the one or more limbs.

31. The method of claim 27, wherein: The comparison includes determining whether the limbs are consistent in any one or a combination of the following: water movement, depth, and outstroke.

32. The method of claim 27, wherein: Segmentation of the stroke phases involves generating a graphical representation showing the percentages of the glide, pull, and recovery phases of a stroke.

33. The method of claim 27, wherein: The angle of attack involves determining the angle of the limb at a specific point in time, and the pressure applied at that time.

34. A system for determining an athlete performance indicator, the system comprising: A sensing system and a processing system, wherein the processing system is configured to: a. receiving data from a sensor system attached to at least one limb of the athlete; b. determining the orientation of the at least one limb and applying the orientation to the received data; as well as c. Generating the performance indicator of the at least one limb based on the received data and the orientation of the at least one limb.

35. A processing system for determining an athlete performance indicator, the processing system being configured to: a. receiving data from a sensor system attached to at least one limb of the athlete; b. determining the orientation of the at least one limb and applying the orientation to the received data; and c. Generating the performance indicator of the at least one limb based on the received data and the orientation of the at least one limb.

Images