TENNIS TRAINING SYSTEM

Abstract

A body worn electronic device and method for training a player to improve upon the stroke of an article such as a racket in a sport wherein the device senses parameters of the player's strokes to create a stoke profile, compares the sensed parameters of the stroke profile with electronically stored comparative stroke profiles and wherein feedback may be provided to the player based on the comparison of the players stroke profile and the comparative stroke profile.

Description

FIELD OF THE INVENTION

The present invention is directed to electronic devices useful in training a tennis player in correct stroke technique. In particular, the devices are worn on the body of a player under training.

BACKGROUND TO THE INVENTION

The development of correct stroke technique in tennis is an important factor in mastering the game. There are a large number of strokes that may be used by a tennis player, with each being difficult to learn.

Prior art methods of teaching include the execution of drills which typically aim to concentrate the player's attention on achieving a particular result, such as placing the ball in a certain part of the court, or achieving top spin on the ball. While drills may be executed without the assistance of a coach, the player is not provided with any feedback on how to improve his or her stroke technique. Instead, a trial and error approach is common with the player altering various aspects of the stroke until a satisfactory result is achieved.

More successful methods of training include direct instruction from a coach. Typically, the coach observes the player's stroke technique, and suggests improvement in real time. The player may adjust his or her stroke according to the coach's suggestions and will hopefully note a direct improvement in an ability to strike the ball correctly.

Electronic devices may be used in tennis coaching. Some prior art methods include the use of video analysis whereby a player is recorded with a video camera during stroke execution, and deficiencies noted by a coach. The coach generally points out any stroke errors while reviewing the video with the player. As the player is viewing as a third person, he is more aware of his errors and how to correct them, under the guidance of a coach.

While coaching is undoubtedly of great assistance to a tennis player, there is a significant cost involved by way of professional fees charged. Accordingly, many players are only coached for short periods of time, and at long intervals.

Furthermore, there are undoubtedly differences in the ability of coaches to identify deficiencies in a player's stroke and to also suggest effective remedial action. Where a lesser or moderately skilled coach is employed, a player will typically blame himself or herself for any lack of improvement or for a slow improvement. This may lead to general dissatisfaction with the game, and possibly even lead to the player deciding to terminate training.

Even where a coach is very skilled, some players become nervous under direct observation and instruction, and may not relax sufficiently to allow for the required improvement in stroke execution.

It is an aspect of the present invention to overcome or alleviate a problem of the prior art by providing an electronic device that is capable of assisting in training a tennis player in correct stroke technique. It is a further aspect to provide an alternative to prior art devices used in tennis training.

The discussion of documents, acts, materials, devices, articles and the like is included in this specification solely for the purpose of providing a context for the present invention. It is not suggested or represented that any or all of these matters formed part of the prior art base or were common general knowledge in the field relevant to the present invention as it existed before the priority date of each provisional claim of this application.

SUMMARY OF THE INVENTION

In a first aspect, but not necessarily the broadest aspect, the present invention provides a system for improving stroke technique in tennis, the system comprising: (i) a limb-mountable device comprising one or more electronic sensors configured to collect data capable of defining a tennis stroke profile of a user, (ii) a processor device in operable connection with the sensor(s), (iii) a memory device comprising data defining a comparator tennis stroke profile, and optionally (iv) a user feedback device, wherein the processor device comprises software configured to compare the user tennis stroke profile with the comparator tennis stroke profile, and provide feedback to the user via the feedback device indentifying similarities and/or differences between the user tennis stroke and the comparator tennis stroke.

In one embodiment, the comparator stroke profile is superior to that of the user stroke profile.

In one embodiment the limb-mountable device is configured to be mountable on or about the wrist of the user.

In one embodiment one of the one or more sensors is an accelerometer and/or a rotation sensor and/or a magnetometer. The one or more sensors may be selected and/or combined to discern at least 6 degrees of freedom, or at least 9 degrees of freedom.

In one embodiment, the processor device and/or memory device and/or sensors is/are disposed in, on, or about the limb-mountable device.

In one embodiment, the feedback device is a mobile processor-based device, which may be a smart phone.

In a second aspect, the present invention provides a limb-mountable device configured to be operable in the system as described herein.

In one embodiment, the limb-mountable device comprises one or more sensors, a processor device and a memory device.

In one embodiment, the one or more sensors is an accelerometer and/or a gyroscope and/or a magnetometer. The one or more sensors may be selected and or combined to discern at least 6 degrees of freedom, or at least 9 degrees of freedom.

In a third aspect the present invention provides software configured to be operable in the system as described herein.

In a fourth aspect the present invention provides a method for improving the stroke of a user, the method comprising the steps of: electronically recording data capable of defining a user stroke profile, providing a comparator stroke profile, comparing the user stroke profile to the comparator stroke profile, and providing feedback to the user indentifying similarities and/or differences between the user stroke profile and the comparator stroke profile.

In one embodiment, the comparator stroke profile is superior to the user stroke profile.

In one embodiment, the step of electronically recording data capable of defining a user stroke profile comprises use of the limb-mountable device a described herein.

In one embodiment, the step of comparing the user stroke profile to the comparator stroke profile comprises use of the limb-mountable device as described herein.

In one embodiment, the step of providing feedback to the user comprises use of a mobile processor-based device.

BRIEF DESCRIPTION OF THE FIGURES

FIG. 1A is a diagram showing the spatial arrangement of components on printed circuit boards adapted to be included in a wrist band of the present invention.

FIG. 1B is a diagram showing the spatial arrangement of the components shown in FIG. 1A on the wrist of a user, demonstrating the orientation with respect to the hand and elbow of the user.

FIG. 2 is a flow diagram showing the data processing sequence, steps and dependencies. Each block can be considered to be a data processing function with specific data inputs and outputs.

DETAILED DESCRIPTION OF THE INVENTION

After considering this description it is apparent to one skilled in the art how the invention is implemented in various alternative embodiments and alternative applications. However, although various embodiments of the present invention is described herein, it is understood that these embodiments are presented by way of example only, and not limitation. As such, this description of various alternative embodiments should not be construed to limit the scope or breadth of the present invention. Furthermore, statements of advantages or other aspects apply to specific exemplary embodiments, and not necessarily to all embodiments covered by the claims.

Throughout the description and the claims of this specification the word “comprise” and variations of the word, such as “comprising” and “comprises” is not intended to exclude other additives, components, integers or steps.

Reference throughout this specification to “one embodiment” or “an embodiment” means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, appearances of the phrases “in one embodiment” or “in an embodiment” in various places throughout this specification are not necessarily all referring to the same embodiment, but may.

The present invention is predicated at least in part on the Applicant's finding that a player's tennis stroke may be improved by the use of an electronic device having sensors which (in real time) provide data allowing for the construction of a stroke profile, and to compare that stroke profile with that of a superior profile such as that of an accomplished tennis player. Feedback is provided to the player to identify aspects of their stroke profile which should be altered in order to more faithfully replicate the superior stroke profile. Accordingly, in a first aspect the present invention provides a system for improving stroke technique in tennis, the system comprising:

• • (i) a limb-mountable device comprising one or more electronic sensors configured to collect data capable of defining a tennis stroke profile of a user,
  • (ii) a processor device in operable connection with the sensor(s),
  • (iii) a memory device comprising data defining a comparator tennis stroke profile, and optionally
  • (iv) a user feedback device,
    wherein the processor device comprises software configured to compare the user tennis stroke profile with the comparator tennis stroke profile, and provide feedback to the user via the feedback device indentifying similarities and/or differences between the user tennis stroke and the comparator tennis stroke.

The present system is a significant departure from prior art approaches, which rely to a large extent on the observation of a player by a trained person (such as a coach) in order to identify and correct dysfunctional stroke technique. A player utilizing the present system may be presented with feedback based on a comparison of his or her stroke profile with that of an accomplished player (the comparator stroke) allowing aspect(s) of user's stroke profile to be altered to be closer to that of the accomplished player. The stroke profile of the accomplished player is typically superior to that of the user, and may be constructed from real data (for example, by the accomplished player executing a stroke while using the present system) or constructed by reference to video or photographic record of the accomplished player executing a stroke. It is anticipated that a user may wish to emulate the technique of a certain professional player, and may be enabled by the present system to upload that player's stroke profile into the memory device.

The profile of the comparator tennis stroke may not be constructed with reference to the stroke of any single player, and may be a composite of a number of players. Alternatively, the comparator stroke profile may be completely or partially artificially constructed based on sound biomechanical principles in tennis which are known to the skilled artisan.

In some embodiments, the comparator stroke profile is roughly equivalent or inferior to the user stroke profile. These circumstances are typically encountered in circumstances where the comparator stroke profile is constructed from a user tennis stroke. The ability for a user to compare their own stroke profiles over a period of time may be useful in some training strategies to identify an improvement, lack of improvement, or even a decline in stroke technique.

As used herein, the term “stroke profile” is intended to include a physical aspect of a tennis stroke which may be represented by a dataset, or constructed from a dataset, the dataset being provided by the sensor(s) of the limb-mountable device. For example, the stroke profile may comprise time-based positional information which describes the relative position of the device (and therefore the user's wrist). The sensor data may be translated into a real time estimate of sensor orientation (typically in quaternion or euler angle representation). This provides an indication of device/wrist orientation rather than position (which can in turn be interpreted). Thus, in that circumstance the profile comprises a spatial path along which the device travels in executing a stroke. Further information may be overlaid such as velocity, angular velocity, acceleration and the like to provide a more complete or substantially complete description of the stroke which is electronically storable in memory and processable.

The stroke profile may be constructed from a dataset covering (in a substantially continuous manner) the entirety of a tennis stroke. Alternatively, the stroke profile may be constructed from a dataset covering only a segment of a tennis stroke, or a number of discontinuous segments of a tennis stroke. As another alternative, the stroke profile may be constructed from data taken at only a single time point, or a number of discontinuous time points of a tennis stroke.

It is understood that a stroke profile having incomplete, or even minimal information may also be useful in certain embodiments of the present systems. For example, in some circumstances velocity information alone may be useful where a user's serve is acceptable, except for his or her propensity to briefly pause before the main swing. In that situation, a point in the stroke profile of zero velocity is sufficient information to indicate further improvement in the user's serve is necessary, and efforts made to avoid the halt in service action.

The terms “superior”, “inferior” and “equivalent” when used as descriptors for a stroke profile, in comparison with the user stroke profile. A stroke profile may be superior, inferior or equivalent with respect to any parameter of a stroke profile, or the result of striking a tennis ball with a physical stroke of the profile.

For example, an effective forehand stroke may have a spatial path which is substantially C-shaped, with a long follow through. The user's stroke profile may have a short follow through, which is suboptimal for power. Accordingly, the effective forehand stroke profile is considered superior to that of the users. As another example, the wrist in an effective forehand stroke rapidly accelerates around half way through the stroke to increase racket head speed. The user's stroke profile may have a consistent velocity throughout, and accordingly, the user's stroke profile is inferior to the effective stroke profile given the lower speed at which the ball is struck.

The limb-mounted device comprises a processor which is in operable connection with the sensors. The operable connection may be direct such that data output of the sensors is transmitted directly to the processor. Indirect connections are also contemplated, such as where the sensor output is communicated to a memory device, with the stored data subsequently transmitted to the processor.

The processor device comprises software configured to compares the user stroke profile with the comparator stroke profile. Typically, the comparison is undertaken using time-matched data from the user and comparator profile data streams. Matching of the data from the two profiles may first require analysis of one or both profiles to identify events or segments of the profile(s). It will be understood that in the comparison of user stroke profile and comparator stroke profile, raw datasets may be compared. Alternatively, the raw datasets are first processed into the segment(s) or time point(s).

For example, in the serve a first event in the stroke profile may be the first movement of the wrist which signifies commencement of the stroke, a second event may be the sharp reversal in direction which signifies the commencement of the main swing, and a third event may be the subsequent deceleration of the wrist signifying the end of the stroke. A similar analysis may be conducted on the comparator stroke profile such that the data from the two stroke profiles may be paired on a time-base with reference to the three events.

In one embodiment, the comparator stroke profile is not analysed in this way, but instead has embedded event data which has been independently validated.

The processor device may perform this pre-comparison analysis, or a second processor device may be implemented for that task.

The software may be configured to identity similarities and or differences in the stroke profiles under comparison. The differences may be output as qualitative information (for example short, long, high, low, fast, slow), or may be quantitative (for example, velocity, angular rotation, distance)

While the sensor data may be transmitted by wired or wireless transmission to a processor external to the limb-mountable device, it is preferable that the processor is integral with the device.

The feedback device may be integral with the limb-mountable device, or may be a separate device. The feedback device may provide feedback by way of audio and/or visual means including pre-recorded or synthesized speech, a graph, a photograph, a video, text, an animation, or a haptic stimulus.

A preferred feedback device is a mobile processor-enabled device, and particularly a smart phone or similar contrivance. In some embodiments of the system, the feedback is constructed by the software of the limb-mounted device, and transmitted to the feedback device for presentation thereon. In other embodiments, the feedback device constructs the feedback based on one or more of the sensor data, the user stroke profile, or a comparison of the user stroke profile and the comparator stroke profile.

The feedback may be generated and presented to the user in real time (i.e. during stroke execution), allowing the user to receive instant feedback while hitting a number of consecutive shots. This approach allows a user to continuously refine their stroke technique while playing in an attempt to more closely replicate the comparator stroke. As is understood, feedback in this circumstance may be limited to simple qualitative signals provided by audio tones, or short passages of synthesised speech.

Alternatively, the feedback may be presented after a training session, in which case more complex information may be presented. For example, graphics showing the spatial path of the wrist of the user overlaid with the path of the comparator stroke may be presented as feedback. Such graphics may be overlaid with velocity information or angular rotation information to provide a more complete comparative analysis for the user. The user can note where the two strokes diverge, and modify his or her stroke accordingly.

The system may be further configured to provide feedback on stroke consistency, typically as a rating. The stroke consistency may be defined by reference to the comparator stroke profile or the user's previous stroke profile(s).

Other types of feedback are further contemplated, including shot frequency, total shot count and breakdown, quality of shots and overall game, total play time plus effort expended on the court (in the form of calories burnt and distance travelled). This type of feedback is typically suited more so to an analysis conducted over the course of a game, a set, or a match.

A user may also be provided with feedback detailing achievements over a period of time, such as a playing season. The system may be configured to including feedback such as personal bests, improvement in a particular stroke, if the user has the best technique in their area, or at their club (this last feedback type requiring a number of users to deposit feedback into a shared server). Any achievements may be further shared on a social media platform such as Twitter™ or Facebook™.

The limb-mountable device of the present system may be configured to sit snugly on the player's wrist, preferably in a manner similar to a wrist watch, or a sweat band.

A number of advantages are provided by the sensors being mounted on the user, rather than on the racket. Good stroke technique is driven to a large extent by forearm (and particularly the wrist) movement, which in turn dictates racket movement. Thus, attempting to emulate a superior stroke profile based on comparative data from racket-based sensors will only assist the user in placing the racket in the same position as for the superior stroke. Instead, the present systems assist the user in placing their body in the same position as that required for a superior stroke.

Understanding biomechanical movements of the wrist is fundamental to stroke technique. The greater extent to which precise wrists movements are recorded and assessed, the better the user will understand whether or not their technique is consistent with a comparator technique.

It is particularly advantageous in comparative systems such as the present, that comparisons are made in the position and rotational movements of the wrist. These are the precise movements which should be isolated in order to understand technique. If these movements are correct, then the racket movement will more likely be correct.

As another advantage, reducing noise in the measurement system allows for greater accuracy of measurement. Applicant has found that embedding sensors away from the racket handle (such as about the wrist) reduces vibrational forces which occur through the racket when the ball is struck. These vibrational forces create noise in the data obtained by the sensors. While additional filtering and processing can minimise the noise, these processes have a detrimental impact on battery life of the device and in any event lead to a less precise understanding of the movement of the wrist.

The device comprises a sensor (and typically a number of sensors) which act to collect substantially real time data useful in the construction of a stroke profile. In one embodiment, sensors are selected such that information on the position and orientation of the device (and therefore the wrist) is obtainable. It is known in the art that the output of a combination accelerometer output and gyroscope output can be used to track the position and the orientation of an object. For example, inertial measurement units (IMUs) are known which can reliably sense and process multiple degrees of freedom (DoF), even in highly complex applications and under dynamic conditions. These units typically contain multi-axis combinations of precision gyroscopes, accelerometers, and magnetometers.

In one embodiment, the limb-mountable device comprises three accelerometers, three gyroscopes, and optionally three magnetometers. The accelerometers are typically disposed with their measuring axes are orthogonal to each other. These sensors measure inertial acceleration. The three gyroscopes are typically placed in a similar orthogonal pattern, measuring angular velocity. As the skilled person appreciates, position may be derived from the sensor data and the gyroscope only provides instantaneous rate of angular velocity which is a relative figure and not an absolute figure. Other sensor data are used to relate the output of the gyroscope back to a fixed frame of reference or coordinate system.

The optional inclusion of three magnetometers provides an absolute reference for yaw or heading. The gyroscope data may be used to provide granular data on yaw with the magnetometer data used to correct for drift that accumulates over time It is noted that the processor(s) and/or software of the present system are typically configured to execute any calculations required to provide useful information (such as the relative orientation of the limb-mountable device) from the accelerometer, gyroscope and optionally the magnetometer output.

Other information useful in the construction of a stroke profile may be provided by the sensors. For example, it is useful to identify the point in the stroke at which the ball is struck. A contemporaneous change in linear and angular momentum of the limb-mountable device may be reflective of a ball strike. Alternatively, the total acceleration data (square root of x̂2+ŷ2+ẑ2) may be used to identify ball impact. The moment of impact has a characteristic peak combined with vibration in this data.

Other calculations executed in the present system are directed to reference models which calculate the relative position of the racket face. The calculations may accept as input from the user information relating to the grip used to hold the racket for serves, forehands, backhands and volleys. For example, a semi western grip on the forehand. This allows for an accurate picture of how the movements of racket and wrist interact. Preferably, this process is applicable for all tennis strokes.

Some embodiments of the invention comprise two or more limb-mountable devices. For example, the system may comprise a first wrist-mountable device for the left limb, and a second wrist-mountable device for the right limb. Where the user is right-handed the second wrist-mountable device operates as discussed above, while the second wrist mountable device obtains positional data on the right hand. As is understood by the skilled person, the position of the non-playing hand can be important in maintaining balance, and correction to the position of that hand may lead to an improvement in the user's stroke technique.

In another embodiment, the system comprises a first wrist-mountable device for an upper limb, and a second ankle-mountable device for a lower limb, in tennis, the positioning of feet (and particularly the leading foot) can be important in improving stroke technique.

In a further embodiment, the system comprises two or more limb-mountable devices configured to be mounted on two or more regions of the dominant arm of the user. For example, there may be a wrist-mounted device, and an upper arm-mounted device. This system allows for a stroke profile to include information regarding an bend in the arm at the elbow joint. In some strokes a straight arm is necessary at some time during the stroke, and information on the relative positions of the upper and lower arms may be relevant in the improvement of stroke technique.

It is contemplated that the system may further comprise non-limb mountable devices capable of providing data relating to body orientation, hip rotation, head orientation position and the like. Accordingly, devices mountable on the head, neck, chest, waist, hips and buttocks may also be included in the system.

In another aspect, the present invention provides a limb-mountable device configured to be operable in the systems as described herein. The limb-mountable device may be constructed from elastomeric materials to ensure a snug fit on the limb. Movement of the device relative to the wrist is to be avoided, and so materials and surfaces which limit slippage a preferred especially in consideration of the lubricating effect of perspiration.

It is preferred that the limb-mountable device is light, so as to minimise any effect of the device on the user's stroke during data collection. Preferably, the device has a mass of less than about 5 g, 6 g, 7 g, 8 g, 9 g, 10 g, 11 g, 12 g, 13 g, 14 g, 15 g, 16 g, 17 g, 18 g, 19 g, 20 g. In one embodiment, the device has a mass of between about 10 g and about 15 g.

In another aspect the present invention provides software configured to be operable in the present systems. The software of part thereof may be embodied in the form of firmware in the processor device or memory device of the limb-mountable device. The software of part thereof may also be embodied in the form of an application executable on a mobile device (such as a smart phone), and therefore operable in an iOS or Android operating system environment for example.

In a further aspect, the present invention provides a method for improving the stroke of a user, the method comprising the steps of: electronically recording data capable of defining a user stroke profile, providing a comparator stroke profile, comparing the user stroke profile to the comparator stroke profile, and providing feedback to the user indentifying similarities and/or differences between the user stroke profile and the comparator stroke profile. The method may include the use of any system, any limb-mountable device, or any feedback device, or any software as described herein.

The present invention will now be further described by way of the following non-limiting preferred embodiments.

Preferred Embodiments of the Invention

An exemplary wristband captures and analyses the movements of the player by way of an array of onboard sensors, processors and micro controllers. The sensors are (i) a tri-axial accelerometer, (ii) a gyroscope and (iii) a magnetometer. Collectively these sensors have nine degrees of freedom (9DoF). Working together the sensors provide the ability to monitor an object's position, and the forces acting upon it, in time and space.

Reference is made to FIG. 1A, which shows a diagram of the components of a wrist-band of the present invention. The components are generally disposed in two layers, the lower layer comprising the battery 12 being a lithium polymer battery with 100-150 mAh capacity and dimensions of 35×25×3 mm., which is the upper layer 14 comprising two circuit boards 16. Disposed on the circuit board is a microcontroller being a EFM32WG390 Microprocessor (Silicon Wave Inc; RF Micro Devices Inc) 18. This microprocessor rate of up to 48 Mhz, which is sufficient to process the data output by the inertial sensors 20. The inertial sensors are ST LSM303D (a dual sensor triaxial magnetometer and accelerometer) and ST L3GD2OH (a triaxial gyroscope) (STMicroelectronics Inc).

These two inertial sensors 20 are disposed adjacent each other on the circuit board 16 with the orientation of the x-axis of each sensor pointing down towards the hand. The PCB is housed in the wristband with the sensors positioned on the top of the wrist. Each of the three sensors takes measurements through three axes, x, y and z. Combined together they represent 9 degrees of freedom (9DoF) with the output data being interpreted to provide information on the position of the wrist in space as a function of time. They also capture forces acting on the wrist such as momentum, angular rotation, acceleration and force. Again, the sensor outputs are not used directly to provide this information. The sensors provide vector linear acceleration, vector angular velocity and vector magnetic field strength data. Sensor fusion algorithms are then used to derive orientation data.

The memory 22 is in operable communication with the microprocessor 18 and inertial sensors 20. A Bluetooth module 24 being a dual mode Bluetooth transceiver-Bluetooth classic and Bluetooth low energy, is included to transmit feedback to a proximal smart phone of the user (not shown). The two circuit boards 16 are operably connected by a bus 26. The battery 12 is slightly curved to accommodate the curved surface of the wrist operably connected to the circuit board 16 by flexible wire 28.

In FIG. 1B the battery 12 and circuit boards 16 are shown layered, and positioned with reference to the wrist of a user. The battery 12 is curved, with the bus 26 forming a hinge between the two circuit boards 16. The ability of the circuit boards 16 to flex relative to each other allows them to conform to some extent to the curvature of the battery and the curve of the mechanics of the device.

The sensors are embedded in the wristband and capture the movement and orientation of the wrist holding the racket. The data output by the sensors is processed on board the device constantly, this includes analysing the data using a set of on board algorithms which determine shot type, and the characteristics of the shot. This data is then stored on the device using the inbuilt memory

The data processing functionality inside the wristband is responsible for translating raw sensor data into specific shot characteristic data and carrying out the associated analysis. While the sensor is in one of the normal active modes, it is continuously processing this raw data and looking for evidence that a shot has been played. On detecting such an event, it will analyse the shot to determine a wide range of characteristics related to that shot (including shot type) and log or stream the results of that shot. In addition, the system will keep track of the overall play data (shot frequency, total play time, etc.).

Turning to FIG. 2 there is shown a flow diagram detailing an exemplary scheme for processing raw data from wristband sensors. The sensors 50 output raw data in the form of accelerometer data, gyroscope data, magnetometer data and temperature data. The raw data is firstly adjusted by reference to a calibration standard 52, and output as calibrated data. Further processing 54 of the calibrated data provides orientation data which is used for stroke detection 56 either directly or after LP filtering 58. The orientation data is also co-processed with complementary data 60 before LP filtering 58.

The orientation data is directly processed for stroke characterisation extraction 60, and also indirectly after LP filtering 58. Stroke characterization extraction 60 followed by stroke evaluation involves analysis of the LP filtered orientation data to identify and characterize stroke events in the data in order to resolve what type of shot has been played (forehand, backhand, lob, serve etc), any relevant event characteristics which together form a stroke profile.

When a shot has been detected 56, play analysis 64 is triggered, involving the comparison of the stroke profile of the user with that of a superior stroke profile. The play analysis 64 is reliant on the identification of the shot type and event characteristics output by the shot evaluation step 62. The play analysis is presented to the user in the form of feedback on a smart phone (not shown).

Shot detection is based on carrying out peak detection of the low pass filtered total acceleration data. This peak detection is based on first identifying any occasion where the filtered total acceleration exceeds a predefined threshold. Once such an event has been detected, the peak itself is determined using a peak detection algorithm on the raw data itself.

With respect to characteristic extraction, a range of shot characteristic data is extracted at this stage. This data is used in turn to determine the shot type and other data in the Shot Evaluation stage. The type of data extracted in this processing stage includes:

• • Minimum and maximum peaks for yaw, pitch and roll.
  • Time of minimum and maximum peaks for yaw, pitch and roll.
  • Difference between minimum and maximum peaks for yaw, pitch and roll.
  • Maximum angular rate
  • Maximum angular rate at moment of ball impact

The characteristics extracted form an overall stroke profile of every shot played.

Each shot is broken down into a number of separate phases or stages. In this way, it is possible to identify and measure different characteristics related to shot technique more accurately. Each of these phases has a specific measurable duration (with the exception of the ball impact itself which is taken to occur at a specific point in time).

For some shots (and particularly non-serve shots), the following process and phases of movement are identified:

• • 1. Ready/waiting for the next shot.
  • 2. Backswing
  • 3. Swing (to impact)
  • 4. Ball impact
  • 5. Follow through
  • 6. Set-up for next shot
  • 7. Ready/waiting for the next shot.

With regard to shot evaluation, this processing step evaluates the specific shot type and characteristics related to that specific shot. The output from this step is the primary data that is presented to the player for each shot and is used in construction a summary of overall user performance.

Evaluating overall performance is undertaken by reference to the quality of each shot. To achieve this, the system uses a process of comparison against an extensive library of ideal stroke technique. The library contains characteristic information, data markers and limits against which the user's data is compared. Algorithms then identify differences between the user's data, and the library to determine the specific points of feedback to return to the player on their mobile device.

Examples include, but are not limited to; amount of wrist rotation during follow through of the forehand, momentum of racket head during serving motion. Depending on the size of the variance the device can determine against these characteristics the relative quality of a players game.

The algorithms determine the quality of a players shot and overall game by analysing the size of the variance in the data, relative to a set of ideal models.

With respect to play analysis, the output of this process step is a summary of the overall play session. This includes shot frequency, total shot count and breakdown, quality of shots and overall game, total play time plus effort expended on the court (in the form of calories burnt and distance travelled).

A key feature of play analysis is the consistency rating, which is combined with other data to provide an overall user score. The overall user score aggregates all shot evaluation data to determine how often the user is repeatedly achieving the correct technique. This applies to every shot hit by the user.

The data collected over time on the users overall performance and overall user score allows the user to monitor their improvement over time. This may be broken down further to relate to performance in each session, or to focus on one stroke in particular. The users overall score can also be used to compare with other players in the community. From mobile devices, a player can challenge another player nearby.

It should be appreciated that in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof, for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Furthermore, while some embodiments described herein include some but not other features included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention, and form different embodiments, as would be understood by those skilled in the art. For example, in the following claims, any of the claimed embodiments can be used in any combination.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In other instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Thus, while there has been described what are believed to be the preferred embodiments of the invention, those skilled in the art will recognize that other and further modifications may be made thereto without departing from the spirit of the invention, and it is intended to claim all such changes and modifications as falling within the scope of the invention. For example, components and functionality may be added or deleted from diagrams and operations may be interchanged among functional blocks. Steps may be added or deleted to methods described within the scope of the present invention.

Claims

1. A system for improving stroke technique in tennis, the system comprising: wherein the processor device comprises software configured to compare the user tennis stroke profile with the comparator tennis stroke profile, and provide feedback to the user via the feedback device identifying similarities and/or differences between the user tennis stroke and the comparator tennis stroke.

(i) a limb-mountable device comprising one or more electronic sensors configured to collect data capable of defining a tennis stroke profile of a user,

(ii) a processor device in operable connection with the sensor(s),

(iii) a memory device comprising data defining a comparator tennis stroke profile, and optionally

(iv) a user feedback device,

2. The system of claim 1 wherein the comparator stroke profile is superior to that of the user stroke profile.

3. The system of claim 1 or claim 2 wherein the limb-mountable device is configured to be mountable on or about the wrist of the user.

4. The system of claim 1 wherein one of the one or more sensors is an accelerometer and/or a rotation sensor and/or a magnetometer.

5. The system of claim 1 wherein the one or more sensors are selected and/or combined to discern at least 6 degrees of freedom.

6. The system of claim 1 wherein the one or more sensors are selected and/or combined to discern at least 9 degrees of freedom.

7. The system of claim 1 wherein the processor device and/or memory device is/are disposed in, on, or about the limb-mountable device.

8. The system of claim 1 wherein the feedback device is a mobile processor-based device.

9. The system of claim 1 wherein the mobile processor-based device is a smart phone.

10. A limb-mountable device configured to be operable in the system of claim 1.

11. The limb-mountable device of claim 10 comprising one or more sensors, a processor device and a memory device.

12. The limb-mountable device of claim 10 wherein one of the one or more sensors is an accelerometer and/or a rotation sensor and/or a magnetometer.

13. The limb-mountable device of claim 10 wherein the one or more sensors are selected and/or combined to discern at least 6 degrees of freedom.

14. The limb-mountable device of claim 10 wherein the one or more sensors are selected and/or combined to discern at least 9 degrees of freedom.

15. Software configured to be operable in the system of claim 1.

16. A method for improving the stroke of a user, the method comprising the steps of:

electronically recording data capable of defining a user stroke profile, providing a comparator stroke profile,

comparing the user stroke profile to the comparator stroke profile, and

providing feedback to the user indentifying similarities and/or differences between the user stroke profile and the comparator stroke profile.

17. The method of claim 16 wherein the comparator stroke profile is superior to the user stroke profile.

18. The method of claim 16 wherein the step of electronically recording data capable of defining a user stroke profile comprises use of the limb-mountable device.

19. The method of claim 16 wherein the step of comparing the user stroke profile to the comparator stroke profile comprises use of the limb-mountable device.

20. The method of claim 16 wherein the step of providing feedback to the user comprises use of a mobile processor-based device.