Developing IMU Sensors For Capturing Motion In Sports

IMU sensors are pretty useful because when strapped to the right location and given the right context they can provide very insightful information about an athlete’s (or anyone’s) movements. In this post, we are going to look at a couple of options in the market that allows us to skip the hardware development and jump right into the application development. Feel free to skip to the different sections that interest you:

[ Intro To IMUsmbientlabsNotch SensorNotch Mocap TestCustom Sensors]

Intro To IMUs

In case this is the first time you are hearing about IMU, here’s a brief intro. IMU stands for Inertial Measurement Unit; it is an electronic device that typically has accelerometers, gyroscopes and magnetometers, and it measures its own acceleration, angular rate (or spin rate) and surrounding magnetic field. IMUs are not only used in sports, in fact, it is used in many consumer electronic devices. Our smartphones for one has IMUs for detecting the orientation of the phone and changing the display to portrait or landscape. The IMUs also allows for functions such as undoing texting errors, a spirit level and motion sensor games. If a user carries the phone with them in their pockets most of their waking hours, it can act as a pedometer counting steps and detect when the user is sedentary. For runners who use running apps to track their runs, IMUs enable some apps to track indoor runs and cadence. Sports Engineering Researchers have used smartphones for tracking wheelchair rugby activities and classifying different sporting activities.

As great as the smartphones are with inbuilt IMU, GPS and processing power to give us real-time analysis, we don’t really want to strap an expensive smartphone onto a football player’s calf to monitor their kicking or tape an iPhone to a tennis racket to measure swing metrics. That’s why companies like Qlipp has developed sensors for tennis or Zepp which has sensors for a number of bat-and-ball or swing type sports. Then there are sensors for rowing, running, surfing, mountain biking and more. There are also different sports equipment that has in-built IMU sensors. Like smart balls (basketball, football, cricket ball etc), smart shoes, smart helmets, smart rackets etc, it could go on and on.

But sometimes we might still not find a sensor product on the market that is right for our sports or health application. So we explore the option of developing something on our own. Fortunately, we don’t necessarily have to start from scratch* because these days there are generic IMU sensor platforms that are designed and built for people who want to develop a sensor for a custom application. They often have the standard 9-DOF (degree of freedom) sensor setup and come with software SDK that allows developers to build their own applications for processing and analysing the data. Let’s look at a couple of options below.

[*when I say scratch, I mean getting sensor boards from SparkFun, Adafruit, Seeedstudio, Tindie etc]

mbientlab

mbientlab successfully launched their first Bluetooth IMU sensor on Kickstarter. They pitched it as a development and production platform for wearables with simple API for iOS and Android. There was some simple soldering required when people bought the first product. I didn’t get one from that campaign but I did get a later updated version which they called MetawearRG. What impressed me when I first got it was the size of it – it’s small and compact and I could use it to build/redesign a smart basketball prototype for a client. Then when I started testing it, I found that their API was really easy to use and I could use their sample iOS app to build a custom app for testing within a (reasonably) short time.

smart_ball_instagram_post
Smart Basketball Prototype and Watch app for tracking optimal shots

Since then, they have made many other versions of sensors with:

  • slightly different sensor configurations,
  • options of coin cell or rechargeable lithium battery,
  • accessories such as cases, clips or wristbands,
  • sensor fusion firmware,
  • cloud services, and
  • hubs to manage multiple sensors.
IMG_1624_edit
Metawear RG with custom 3d printed sleeve/case (L) and Metamotion (R)

I haven’t had the chance to try everything but I have to say, I have had a good experience using their Metawear and Metamotion sensors to build various proof of concepts and I am still using them for a number of projects. The sensor data can be streamed to your smartphone or logged on the device. In terms of API support, on top of iOS and Android, they have added Python, C, C# and Javascript, so developers can build stuff on various platforms.

IMG_1629

Sample/Template Metawear iOS app for testing

Looking at their new website revamp and some recent emails they sent out about new platform developments, they seem to be putting more focus into the allied health space, in particular, measuring range-of-motion (ROM). They are currently beta testing an app called the MetaClinic and it looks like they are using skeleton-tracking the likes of motion capture systems which would probably mean we need to use multiple sensors. That should be interesting.

mbientlab_metaclinic

MetaClinic App by mbientlab

Notch Sensors

Notch also launched on kickstarter, in fact slightly earlier than mbientlabs’ campaign. They had an interesting concept of integrating individual IMUs into custom designed clothing using pockets in discreet locations. Unfortunately, they weren’t successful at that instance. Their initial use case probably wasn’t strong enough. So I guess the founders went back to the drawing board, revamped it all and went with the “motion capture” approach for developers.

IMG_1627

Notch sensor with elastic band and clip

With the new design, the shape of the IMU sensor is essentially the same but they have ditched the micro-usb in each IMU for contact pins and made it water-resistant (IP67). They also designed elastic bands of varying lengths with a sensor clip and a user can secure each sensor up to 15 different locations on their body including head, chest, upper arms, wrists, hands, waist, thighs, ankles and feet. So instead of selling individual IMUs, they sell a kit of 6 IMUs with a set of elastic bands, and if a user wants to do a full (body) setup, they will need 3 kits.

IMG_1130

The Pioneer Kit: 6 IMUs with charging case and elastic bands with clips.

A quick test and review (for biomechanics)

I had the opportunity to run a short pilot test with one (the pioneer) kit in a biomechanics lab. I used the lower body setup which used all 6 IMUs strapped on my chest, waist, thighs and shins/ankles. In terms of setting up, it was pretty straightforward. After following an initial calibration procedure of all the IMUs in the case, I put on the bands and clipped each IMU to the right location according to the different colours as indicated on the app. The only thing is putting on the bands takes a bit of practice and I had to swing around to check that the bands are not too tight and restricting movement. Even though I don’t have muscly quads, I felt that the bands were somewhat tight and needed adjusting after a while.

WAOR1807

Setting up the Notch IMUs for lower body measurements

For testing, I did a simple protocol of walking, stopping and doing 3 squats of varying depths. Then I compared my knee angles measured on the notch and the motion capture system. A few quick things that I took out of the knee angle measurements were:

  • The angle measured by Notch is the exterior angle while the motion capture system looks at the interior angle. So it needs a quick recalculation before comparison.
  • Assuming the motion capture system is the more accurate measurement, Notch had a larger error as squats went deeper.
  • But for walking, the knee angles measured were quite close.

It’s wasn’t a very elaborate test but even from this simple outcome, I can safely say it’s probably not the best tool for accurate joint angle measurements. Although for a quick 3D visual feedback on movements, it might work. Here’s the clip of me doing the test described above (feel free to rotate the video to get different perspectives):



Further to that, I could only download angle data. If I wanted the raw sensor (acceleration and gyro) data, I would need to pay for an extended license that is renewed annually.

In terms of custom development support, they used to have support for iOS but they seem to have taken that off now and only have support for Android which I thought is a bummer. I am guessing they have some issues with getting it right on iOS. Hopefully, it is just temporal and they will resolve it soon. For Android developers, it looks like they have pretty good support and even provides a template app. I have to add that there is a fair bit of fine print I need to agree to before I can get access to their SDK. If I read it right, they basically want a licensing fee for using/commercialising their SDK.

Custom Sensors

Both of the above IMU sensors have similar specifications when it comes to measuring acceleration (using accelerometers) and angular velocity (using gyroscopes). The typical measurement range for accelerometers is +/-16g (that’s 16 times of gravitational acceleration), and for gyroscopes, it’s +/- 2000 degrees per sec. For many applications, this configuration is fine. But there might be some cases where higher acceleration needs to be measured and that goes beyond 16g, like shocks or high impact collisions. Or I might need high-speed rotations to be tracked and 2000 degrees per sec is too low, like measuring the spin of a cricket ball or gridiron football (which can come close to 3600 degrees per sec or 600rpm as demonstrated here by Drew Brees).

IMG_7657

Spin rates of a gridiron football during a throw test

As briefly mentioned earlier, hobby electronics stores like SparkFun, Adafruit, or Tindie would be a good place to start when looking for accelerometers and gyroscopes of different specifications. There are also lots of microcontrollers with Bluetooth Low Energy (BLE)  built-in that are Arduino compatible so we can program them with the Arduino software. One that I found pretty handy is this one called Blueduino which comes with a Lipo charger add-on (and add-ons are great) and that can be found on Tindie.

Football sensor

The gridiron football sensor prototype using the Blueduino

Final Word

For those who are in research and possibly need Matlab and software support for building custom Matlab programs, definitely check out Sabel Sense sensors (Australia). Else, I reckon the mbientlab sensors would be a great option for starting a custom development. If I get a chance to trial their Metaclinic platform, I will put up another post. Meanwhile, do drop me a message here if you need assistance or advice in any of the options above and feel free to leave a comment if you know of better/different solutions out there. With that, thanks for reading!

The challenges of making Smart Sports Garments

What is a Smart sports garment?

Smart sports garments or smart performance garments is a relatively new product segment in the consumer sports tech market. There are probably different views of what the definition should be, but for the purpose of this post, it is a sports garment with embedded sensors/electronics. The main functions of sports garments include providing covering, protection, comfort, ease of movement and some might say making the athlete more aesthetically pleasing. Then with the added sensors and electronics, there generally are two different types of secondary functions.

The more common one is the passive function where sensors monitor stuff on an athlete, either physiological measurements or physical movements. It can make smart evaluations based on the data and give real-time feedback suggesting to the athlete that they should push harder or rest or correct their technique etc. But the decision to act on that suggestion still lies with the athlete or coach. There is also the not-so-common active function where the garment does something to the user. For example giving electrical muscle stimulations (EMS) or possibly electric shocks. But so far the “electric shock” feature is only found on a wristband and hasn’t extended to any other wearables yet. I am not sure why that is the case. For EMS, it has been said that it helps with muscle strengthening which is good for rehab or as a complementary training tool. But I will not go into it since it’s beyond my area of expertise.

R&D in Melbourne

A while ago, I had the opportunity to be a lab rat for a mate’s PhD thesis. He has developed a patented novel technology to measure muscle activity and hopefully able to predict the risk of muscle and knee injuries in elite athletes. The experiment I took part in was basically collecting a bunch of data from this novel sensing technology, wireless electromyography (EMG) sensors, a motion capture system, and a bike trainer. Unfortunately, it also involved me pedalling for my life.

How is this relevant to smart garments? Well, the novel sensors and EMG sensors were all hidden under a compression garment with motion capture markers secured on the outside. The compression tights ensure that the sensors remain where they are (and reliably capture data) and they also (coincidentally) facilitate motion capture. Albeit it was a very crude way of combining the sensors and the 2XU tights, it was a functional prototype (of sorts), and the ultimate goal would be to have those novel sensors built into compression tights.

ppuy6097

Lab rat in action

As we discussed further on commercialising this novel sensing technology for smart sports garments or developing smart compression garments with any wireless sensors, it became apparent that there are a number of challenges. Here’s just a few:

Washing and durability :: A sports garment is going to get sweaty and smelly a lot more than everyday garments. So it definitely needs to get washed. Most smart garments in the market have an electronics module (IMU, BLE module, battery etc) that is removable because they will not survive a tumble in the washing machine. However, there are still conductive pads or conductive yarns (for electrical connections). Would long term washing affect their conductivity and so usefulness?  (A research has shown that most conductive threads will be affected although some hold up better.)

Sensor data accuracy :: In order to capture accurate & robust data, the sensors have to be positioned in the correct location each and every time the smart garment is put on. For measuring stuff like heart rate or EMG, it needs to maintain skin contact for proper measurements. If sensor positions are off (by a bit too much) or skin contact is not maintained, the data collected becomes meaningless and cannot be compared with previous data sets. Not to mention the effect of sweat on EMG electrodes.

Custom fitting :: This relates closely to the above point. Most sports compression wear are made in standard sizes. Sometimes one might find their compression garment being a bit too long at the legs or too short for the arms or too tight around a joint and too loose at a certain spot. It’s fine on a regular compression garment. But when sensors come into play, especially when there is fabric type of sensors (that measures compression or stretch), perhaps a custom-fit garment could be a more optimal solution.

Application :: This is possibly the most important challenge – designing a smart sports garment that solves a real need. It could be a very niche area or a wide-spread problem. But the starting point would be talking to athletes, coaches and sports scientists, to identify where the need is or what needs to be tracked. Then the smart garment that is developed would be a solution and not just a cool piece of technology.

What’s in the marketplace

Having said that, over the last 4-5 years, more than a handful of companies have taken up these challenges and developed their own smart sports garments. A quick search on google shows that there are at least 5-6 smart sports garments in the market.

Brands / Companies
Measured parameters
Heart rate Breathing frequency EMG Motion 3D motion (joints)
OmSignal
Hexoskin
Athos
Myontec
Heddoko

cvetfcjxgaa1ngv       hexoskin-6_v2

OmSignal and Hexoskin have smart garments that are an extension of heart rate monitors with an added IMU (Inertia measurement unit) which provides parameters such as breathing rhythm, running cadence, step count and more. While they both seem to be generic fitness trackers when they first came out, it looks like Omsignal has now dropped their original Omshirt and focused on a women-specific product (the Ombra) for running. This might have to do with a review like this: link.

       allsport_kit_600x680_01   1-ncipvwdjblutc7zvxalxaa

Myontec and Athos are smart compression garments with surface EMG sensors. The point of putting on these garments is for the user to know what’s going on with specific muscle groups during their run, cycle or gym workout. Myontec is focused on the lower body (quadriceps and hamstring) with an emphasis on running and biking, while Athos covers the whole body looking at general strength training. It is cool that their accompanying software/app provides feedback of which muscles should be activated more during a squat (or other exercises) but I think it might be better if they could correct a user’s posture/technique that is causing the wrong muscles to be activated.

aaeaaqaaaaaaaaymaaaajdflodaxnjuxltgwmzetngzmmc05owm3lti3mzmzythjowywmg

Heddoko is a full body compression suit that measures a user’s 3D motion much like the Xsens suit. The difference is that the Heddoko suit uses less number of IMU and has embedded stretch sensors, which makes it unique. Assuming the measurements are accurate and repeatable, it has lots of potential applications in sports biomechanics and injury prevention. But based on this video, they are still validating their sensors and trying to work out specific applications.

Some additional thoughts

On one hand, it is cool that there is all these performance tracking technology available to the average athlete – such as wireless EMG and 3D motion analysis (again, assuming the measurements are robust). On the other hand, I wonder if the benefits would outweigh the costs because they are mostly quite expensive and I am not sure if the average gym goer would need that much information about their workout. Perhaps they would be more useful to elite or professional athletes, especially where professional teams have coaches and sports scientists to analyse the data, and give custom feedback. They could also couple it with video playback and analysis so that there is more context to the data.

I think for the average athlete, a smart garment might be useful if they are going through physical rehab and need to monitor certain movements or muscle groups while under the guidance of a physical therapist. Or if they are trying to pick up a specific skill like throwing a football or baseball (In fact, there are sensor embedded sleeves that do just that, which I might discuss another time). Basically, there should really be a specific ‘pain’ to solve. A smart garment with a generic health and fitness application is probably not going to be of much use. Wristbands and smart watches already try to do that.

Do you already own a smart sports garment or are thinking of getting one? If yes, do leave a comment. I would love to hear your thoughts and what you would use it for. Thanks for reading!

Versus Fitness: Developing A Smart Gym

VersusOver a year ago, I wrote a post about developing with the Kinect and how I was working on a project that revolved around it. Fast forward to today, the project is now an officially launched gym that is also known as Versus Fitness.

What is Versus Fitness?

Versus is a system that has gamified fitness. By utilising different sensors and technologies, it is able to measure 3D motion, pressure, force, acceleration and power output of over 200 different gym exercises (and counting). With each proper repetition (or rep) that is executed, the user not only gets the rep counted by the system, a score is given based on the above measured parameters, and the score is scaled based on the user’s weight and height. In that way, 2 people of different weight and height doing the same workout can compete against each other on almost equal terms (Hence the name Versus). In case the term “wearable technology” comes to mind, no, there is nothing that the users need to wear to get their exercise tracked (maybe except a heart rate monitor, but that is purely optional). Just check out the video below.

How I got involved?

I started working on the Versus Fitness gym since late 2013 and it was purely by coincidence. Someone who knew Brad Bond (the founder of Versus Fitness) was at the RMIT Sports Engineering Lab on one of those Uni open days and he saw a novel sensor technology that would suit Versus. After a series of meetings and discussions, a research contract was set up to further develop that technology for Versus. This was partly funded by the Victorian Technology Development Voucher. At the same time, they were also looking for an additional team member to work on motion tracking algorithms. That’s where I came into the picture. Long story short I was offered a contract role on the Versus project which was partly funded by the Enterprise Connect – Researchers in Business grant (this has been replaced by the Entrepreneurs Infrastructure Programme). Kudos to Aaron Belbasis who was a key connector/initiator who brought everyone together and who was also one of the key researcher who helped develop the novel sensor tech. There’s a bit more details about the RMIT-Versus collaboration here.

What Tech are we talking about here?

One of the sensor technologies came from the research collaboration mentioned earlier. The team at RMIT calls it a “sensor-less sensing platform”. The closest thing would be Force Sensitive Resistors (FSR) like the ones from Tekscan. If you had a proper look at the video above, you will see the “sensor-less sensing platform” used in the floor exercises and some of the running exercises. Basically its a sensor that measures pressure.

There are other sensors that were developed or customised for tracking motion and a number of them are available off the shelf or at least purchasable online. In fact some of the sensors (like load cells and accelerometers) are similar ones typically used in the manufacturing, or automotive industry. A lot of custom fittings, enclosures and mechanisms were designed for the sensors before they could be installed in the gym. Majority of the design were done in-house and prototyped with the help of a MakerBot replicator.

But what really made the sensors (tracking system) worked effectively are the smart algorithms that processes all the sensor data and accurately identifies when each person is performing the exercise properly and evaluates how well he/she has done it. Initially when designing the algorithms for tracking each type of exercise, it all seemed pretty straightforward; but as things progressed, it turned out there were quite a few more considerations – e.g. filtering out “incorrect” movement data that resembled an actual rep, or profiling movement data from users of different abilities (or fitness level) etc.

Perception & Reality

Another important part of the system is the “gaming interface” or the “gaming control centre”. It is the personal trainer’s assistant. It relays to the users what exercises to do, records their performance, stores the performance data in a database, reminds the user how well they did previously (their Personal Best), manages the equipment (to some extent), and ensures that every exercise station is in sync so that the workout runs smoothly. That allows trainers to focus on one of the things they do best: scream at motivate people.

So with the combination of the sensors, smart algorithms and the gaming interface, this means: real-time tracking, with feedback of the users’ performance (score) or technique delivered right after each completed rep, and an overall quantified workout so users know how well they fare compared to their previous workouts (and with other users).

Future Developments?

The very first Versus Fitness gym is based in Moorabbin and that has seven different exercise stations (as seen in the video above). One could call that the full Versus experience. There are a number of possible developments in the pipeline. One is the development of new exercise stations to increase the type of exercises that can be tracked. Also, there are possible opportunities to customise the system for the elite or professional athletes, or even rehabilitation applications. Something that is definitely in the works is a “multi-station” concept – a single exercise station that has several sensor solutions allowing tracking of a few different types of exercises (e.g. dumbbell, kettlebell & floor exercises). This significantly reduces the footprint of the equipment and would suit small gym spaces. In fact this is currently on trial in a gym somewhere in Australia, and depending on how things go, you might start finding the VS logo in many more places!

A Look at Smart Balls

Tracking how fast a ball was kicked or thrown used to be done with an external device – it could be a speed radar or a high speed camera or maybe even a very trained (and experienced) eye. However, in the last 5-6 years, more and more engineers and scientists have tried to put some form of sensors inside the balls to measure linear velocity, spin velocity, spin axis. This has mostly been made possible with advanced developments in microelectromechanical sensors (MEMS), where accuracy and measurement range has increased significantly (while still keeping the small form factor). Another 2 tech contributions that helped keep the sensors (more permanently) in the balls are wireless connectivity (Bluetooth or Wifi) with the micro-controllers and wireless charging.

Smart Ball Construction

Although the electronics is key to measuring movement signals and processing, there is still the very important task of holding those components (sensors + micro-controller + wireless modules + battery) inside the ball. Let’s call all those components the core. So while designing a method to secure the core within the ball, one has to consider the weight and position of the core and how it affects the centre of mass of the ball. The method has to be robust enough since the ball will take lots of impacts as it’s kicked or thrown or bounced. The method of securing the core will also affect or determine how the ball is constructed. Here’s a look at some of the different type of “smart” balls and their construction:

Smart Basketball: 94Fifty

94Fifty

Image from their patent file

The way that the 9DOF sensor is built into the 94Fifty ball is rather unique (thus the patent). According to their patent application, there is an inner cavity on the surface of the inside of the ball, which is purposed for a casing to house the electronic components (core). The casing is built with a flexible material such that the walls can flex with the pressure difference between the inside of the bladder and the inside of the housing. The patent application also mentions providing access for battery charging but that was probably the early version. The new version is built with Bluetooth connectivity and wireless charging.

The ball is constructed according to the official size and weight which is 29.5 inches (749.3mm) and 22 ounces (623.7g). So with the extra weight added from the core, the designers made adjustments to the enclosure material so that the overall weight is close to the standard weight, and more importantly, the weight distribution is compensated so it spins like a standard ball. For example, if the core is positioned at the top of the ball (see image above), and the valve is placed 180 degrees from the core, the extra weight would be added around the valve until the balance is achieved.

Smart Soccer ball: adidas micoach

adidas miCoach Smartball

adidas’ smart ball is designed with its core positioned within the ball and held there by what looks like 12 sets of supports. The core is positioned or suspended right in the centre of the ball, and the supports are meant to be rigid so that the core is always in the dead centre. There doesn’t seem to be any patent related to the method of supporting the core but there was a patent with regards to the electrical wiring within the ball. The patent basically describes how the wiring is arranged along the bladder wall to interconnect two electronic devices. It also mentions that the electronic components are arranged in such as way that the ball is balanced and doesn’t affect playing properties of the ball. According to the adidas page, the core consists of only a tri-axial accelerometer. There is also wireless charging with their custom induction-charging stand. The induction coils would likely be placed along the bladder wall instead of in the core.

Smart Cricket ball

The Sportzedge group at RMIT developed an instrumented cricket ball for measuring the spin rate and calculating the position and movement of the spin axis (link to the conference paper). Due to the high spin rates of wrist spinners (up to 42 rps or 15,120 deg/s), typical off the shelf gyroscope sensors can’t manage that measurement range. What this smart cricket ball has are three high-speed gyros that can measure +/- 20,000 deg/s, one for each axis. This ball is not built in the typical manufacturing process. In order to house the electronics, meet weight requirements, and keep it balanced, 2 solid halves of the ball were designed and CNC machined from the material Ureol or RenShape® BM 5460 which had the right density and hardness. Eight holes within the ball allowed for additional masses to be inserted to balance the ball. According to the paper, this design is an initial prototype and it is still not robust enough to be hit by a cricket bat. But it is fully capable of measuring spin rates during fast bowling. Subsequent versions will be more sturdy and also include wireless charging.

Screen Shot 2015-02-15 at 8.17.23 pm

Instrumented cricket ball  (source: Fig 1 of the research paper)

Smart Oval Ball

Screen Shot 2015-02-15 at 2.37.05 pm

Smart AFL ball

The same team that built the smart cricket ball also developed a smart AFL ball to assess angular flight dynamics and precision of kick execution. The same electronics (high-speed gyros) that were built into the smart cricket ball was also incorporated into this smart oval ball. The main difference is, this oval ball is made with two bladders that sandwich the core electronics, keeping them right in the middle of the ball. The bladders were inflated simultaneously to ensure a more even distribution of pressure.  It was noted in their paper that the advantage of using an inflatable bladder (instead of replacing it with expanded polystyrene beads) is that it allows for realistic kicking whereas the foam beads will absorb too much energy thus dampening the performance. Other than the smart AFL ball, a recent patent search found another American style football that is built with an electronic circuit coupled to an inflatable bladder. Interestingly, the football in this patent is designed intentionally with the electronics causing imbalance, unlike the above designs where the creators made sure their balls are balanced. Even though Wilson Sporting Goods has been granted this patent, there has yet to be any news of them releasing an instrumented oval ball. This might be something to look out for?

Screen Shot 2015-02-22 at 9.57.14 pm

Ball Movement Measurements

No smart ball is complete if there are no “smarts” involved. The acceleration and/or angular velocity that is measured do not mean much if they are not processed and analysed. So firstly, the inertia sensors would require calibration – to ensure that the measurements are linear and accurate or at least corrected based on a benchmark device. Then mathematical models would be derived to determine the parameters for analysis; parameters such as spin rate, spin axis, speed, timing, ball flight path, angles, point of kick, bounces etc.

Also, to ensure that relevant data is processed accurately, certain “markers” or references are put in place to indicate when ball movement needs to be analysed and how it should be analysed. For the smart cricket and AFL ball developed by RMIT, as they are still in the research stage, a lot of the sensor measurements, signal processing, calculations and analysis are done manually. However for the commercial products like 94Fifty and the micoach smart ball, they have developed algorithms as well as guided user interface and instructions to make sure that each throw or bounce or kick is analysed accurately. In both cases, the interfaces and algorithms come in the form of an iPhone or iPad app. Here’s a breakdown of how each ball does it:

Screen Shot 2015-02-28 at 9.29.43 pm

Basically to analyse a kick with the adidas micoach ball, the micoach app needs to be turned on and connected to the ball via bluetooth. Then after the ball is positioned stationary on the ground, the user has to select his/her kicking foot and tap on the ‘Kick it’ screen before executing the kick. One condition for getting the parameters measured is to kick the ball at least a metre off the ground and for it to travel at least 10m. No bouncing or rolling kicks. 

Screen Shot 2015-02-28 at 7.16.33 pm

Similarly the 94Fifty ball requires its app to be turned on and connected via bluetooth for the shots to be measured. For measuring shots, the user’s height needs to be entered into the app as well as the distance where the user is shooting from. There are options in the app to utilise a shooting machine or a user can practice with a training partner who can pass the ball after each shot. The only condition is that the pass has to be a chest pass for the subsequent shot to be recognised by the app. There are also some workouts or skill trainings that allow users to practice on their own and ball handling tracking options.

Screen Shot 2015-03-01 at 10.42.39 pm

The Coaching Element

All these sensor-laden balls and their accompanying apps with smart algorithms aims to help users become better players – whether it is improved technique in kicking or shooting or training of muscle memory to perform proper mechanics over and over.

The 94Fifty app provides real-time audio feedback for each shot that a user makes, whether the focus is on shot arc angle or shot speed or shot backspin. Based on ideal stats (e.g. arc angle of 52 deg and backspin of 180rpm), the user can fine-tune his/her technique to achieve the right angle/speed/backspin. This user shows how by utilising the app’s feedback and capturing his practice on video at the same time, he could analyse his shot mechanics and identify how he could correct his shooting technique.

Likewise, the adidas micoach smart ball app not only measures each kick with ball speed, spin, spin angle, ball strike location & flight path, it also provides “Coach Notes” with recommendations on how the user can boost each specific parameter. A video option within the app allows a second person to capture the user’s kick using the iPhone/iPad’s camera so that the user not only gets the kick statistics but also visual playback of the kick.

Bottom Line

Designing a smart ball that analyses a player’s performance is definitely a complicated process. Not only must the instrumented ball behave like a normal standard ball with proper balance, but the electronics incorporated within the ball also have to be held robustly so that they don’t break under impact and the sensor data remains repeatable and reliable. Then there is the task of working out what parameters can be determined from the sensor data, if constraints/markers/references should be put in place to ensure accurate measurements, and how those parameters are helpful for improving an athlete’s skills and techniques.

Even with a properly designed ball that measures all the critical performance parameters accurately, it’s probably still not a complete coaching system. What the ball (and app) lacks is the ability to know (and break down) what exactly the athlete did in his kick or shot to achieve the numbers as calculated by the app. For example, in football, what affects a kick include foot speed, which part of the foot kicked the ball, and the amount of upper-body movement; and in basketball, a few things that influence a free throw include: the amount of trunk and knee flexion, shoulder flexion and elbow extension. These range of movements could be tracked with either video analysis (such as Kinovea which is markerless) or a 3D motion tracking system (such as Vicon which requires markers), or wearable sensors (such as SabelSenseXSens or this new sensor embedded compression suit).

In a nutshell, smart balls are definitely great coaching tools. But if combined with athlete movement tracking, it would give a lot more insight to improving the athlete’s shot performance.

Swimming with the times

InstabeatSwimming is one of the top priority sports in Australia and has been one of the most successful sports in the international arena. As such there’s a lot of attention put into improving the performance of athletes. In fact, for those who are new to this blog, research in swimming performance is one of the focus areas of Queensland Sports Technology Cluster (QSTC), and you will find some recent published work here and some related blog posts about them here. There has also been lots of work done in various research institutes in Australia and here are some notable ones in the last 4-5 years:

1110-swim-research-mm438534-044103

Mini-Traqua in action

The AIS itself has set up the Aquatic Testing, Training and Research Unit (ATTRU), where there has been even more research and testing done on swimming research, often working in tandem with research institutes mentioned earlier above. These and other similar type of research and innovation is what will give the Australian swimmers the edge to win on the international stage. Some of these research outcomes stay at the elite level of sport because they may not be relevant to the casual swimmers or do not have any commercial application or they are just ‘secret squirrel’ stuff. But some of the developed technology do get commercialized, though it may take a while before they get released into the public, but they do.

Commercialized Sports TechSo what kind of technologies/gadgets are available to everyday swimmers today?

1. Lap and stroke counting. How many times have you swam in a pool and lost track of the number of laps you covered? It can be pretty annoying. That’s why engineers developed swimming specific wrist watches that counts strokes and laps. These watches have motion sensors that enable them to count strokes, laps, and even estimate speeds and distances. Some of these include: the FINIS Swimsense, the Swimovate Poolmate, the Speedo Aquacoach, and the Garmin swim. The Garmin Swim particularly could even identify the type of stroke (front crawl, butterfly or breast stroke).

2. Music while swimming. One way to do it is to blast music at the swimming pool (assuming its your own pool, or everyone else at the pool likes your taste of music). The other option is to use waterproofed mp3 players. Some companies have developed swimming specific mp3 players, some applied waterproofing technology on existing devices, some made waterproof cases. Most of them did not stray far from the original mp3 player designed for land dwellers, all except the FINIS SwimP3 which used Bone conduction technology for audio transmission instead of earphones. If anyone is keen on swimming with music, they should check out DCrainmaker’s post comparing all (most of) the swimming mp3 players.

finis-aquapulse-in-depth-review-32-thumb

DCRainmaker with the AquaPulse

3. Heart Rate monitoring. For the more serious athletes who want to monitor their heart rates to keep track of how hard they are training (or if they are training in the correct zone), there are two options available in the market right now – Heart rate belts and Heart rate ear clips. Heart rate chest belts are a pretty common training accessory for most athletes, but not all heart rate monitoring (HRM) belts will work in the water. For example, HRM sensors that transmits via bluetooth (or any higher frequencies) will not work in water. So if you want to use a HRM chest belt for swimming, make sure they transmit in water (i.e. lower frequencies). As a guide, Polar sensors and the PoolMate HRM sensors will work. The alternative to chest belts is ear clips, and the only product in the market is the FINIS AquaPulse which uses infrared sensors to monitor capillary blood flow at your earlobes. The advantage of using the ear clip (I believe) is it is more secure than the chest belt which tends to slip while swimming thus losing heart rate readings. Although I can’t imagine the ear clip sensor being very comfortable during swimming.

4. GPS. This is mainly for open water swimming. Tracking where you have swam in the open ocean/sea/lake/river/pond. Many sports watches (targeted at runners and triathletes)  have a built-in GPS module. That’s your Garmin, Suunto, Timex, Polar, Magellan, Nike etc etc. But one GPS sports watch that stands out is the Leikr, because it actually puts the map on your wrist. Coloured maps! It’s not officially out in the market yet because it started as a Kickstarter project, but it has been successfully funded so it won’t be long. Would you really need the maps? It depends and I think it’s arguable.

5. Performance feedback. The traditional way of getting feedback is to have a coach scream at you. But with all these gadgets that count your stroke rate per lap, calculates how fast you swim and monitors how hard (heart rate) you are training, a swimmer can train without a coach yelling at him/her every session. These devices can tell you how you are performing. Since most of the mentioned devices are watches, the main feedback form is displaying all the calculated statistic on the screens. The one device that sets itself apart is the FINIS Aquapulse which used its Bone Conduction technology (what they used for their swimming mp3 player) to provide audio feedback of your heart rate. Saves you the trouble of trying to catch a glimpse of your watch face. Too bad it doesn’t work together  with their swimsense watch to also give you audio feedback of how many laps you swam and how fast you are swimming. Although that might make it worse than having a coach yelling…

So just when you think: that should be pretty much what swimmers need to help them train; along comes Instabeat – a heart rate sensor that is mounted on your goggles (and any other goggles), measures the laps, turns, breathing pattern, and gives you heads-up visual feedback of your training. Other than music and GPS, it does most of the things mentioned above. But how is it different from the rest?

  • For one, it measures heart rate from your temporal artery using optical sensors (which is patent-pending). 
  • Secondly, it becomes part of your goggles, so you are not wearing or clipping on an extra thing on your body.
  • Thirdly, it determines your breathing pattern. This is something new.
  • Lastly, it gives you real-time visual feedback of your heart rate training zone so you know if you are meeting your goals.

What led Hind Hobeika (Instabeat founder) to develop this was her deep dissatisfaction with existing heart rate monitors in the market. Utilising her swimming experience and engineering knowledge, she went through several designs, prototyping and testing them and the final result is this revolutionary heads-up display design.

Left: Initial designs of the Instabeat; Right: The final Instabeat design

Some of the challenges the Instabeat team faced included getting the right data from the sensors, coming up with a design that could fit all the different goggles, and not forgetting the challenge of making the sensor waterproof – the nemesis of all wearable technology. And now that they are past those product design challenges, they face the next challenge which is to bring it to market. They have decided to go through Indiegogo to crowdsource funds and you can support them here. The response looks positive so far and you know the Instabeat team is a bunch of forward thinkers because they have already planned a next version which includes wireless (bluetooth) data transfer and syncing with your smartphone. I even found out [Spoiler alert] that they would explore adding GPS for open water swimming and possibly make a version compatible with other eyewear, i.e. sunglasses. Sounds like the Sportiiiis could be having some competition in the near future.

In the meantime, I leave you with Instabeat’s pitch on Indiegogo:

Thanks for reading!

Wireless Power Technology and its application in Sports & Health

Tesla with his "Magnifying transmitter"

Tesla with his “Magnifying transmitter”

Wireless power isn’t an entirely new concept. The first person who tried to do it was none other than Nikola Tesla, and that was back in 1890s. Today, more than 100 years later, it is a reality.

I first saw it work on this Ted Talk by Eric Giler back in August 2009. He demonstrated a version of it that was developed in MIT between 2005 to 2007 and led to a spin-off company, WiTricity. Other than WiTricity, there are a couple of companies or organisations that developed versions of wireless power including: WiPowerPowerbyProxiQi (pronounced “Chee”) and the Alliance for Wireless Power (A4WP). Their technology are all largely based on electromagnetic induction principles, although WiTricity and PowerbyProxi are a bit more distinct in their technology and both have Intellectual Property. WiTricity uses magnetically coupled resonance, it does not depend on line of sight, and it covers a distance up to several meters. On the other hand, PowerbyProxi developed something they call Dynamic Harmonization Control which they claim to be the most efficient wireless power transmission and they also developed a wirelessly rechargeable double-A battery!

Although the most common application in the market now is charging mobile electronic devices (smart phones, media players, tablets or laptops), the real potential for wireless power transfer is huge. Since this is a sports & health technology blog, let’s look in those areas:

Firstly in the medical field, implantable medical devices like artificial (permanent) pacemakers will no longer need to be replaced when the batteries lose power, which means less surgeries required, less time spent on post-op recover and rehabilitation and also brings new meaning to “permanent pacemakers”; and not just pacemakers, lots of other implantable medical devices could take advantage of wireless power – ventricular assist devices, swallowable endoscopes, deep brain neurostimulators, cochlear implants, foot drop implants, gastric stimulators etc. In case you were wondering about the risks of wirelessly powering devices in the human body, engineers in Stanford have already proven it is safe and effective.

In sports engineering, wearable inertia sensors tracks and measures movements of athletes in the field using GPS, accelerometers, gyroscopes and magnetometers; with improved wireless tracking (indoor and outdoor) and increased data storage capabilities, the athletes can be monitored for as long as the devices’ battery has power. But if a stadium or a field or an indoor court can have wireless power, that limitation is gone, the sensors would be powered right in the field while being worn on the athletes. Also, this technology would enable sensors to be embedded into sports equipment permanently – solves the problem of designing an outlet for charging while keeping it water resistant. It could be balls, rackets, surfboards, snowboards, paddles, bicycle helmets, shoes, the list goes on. In fact, 94Fifty has already pushed this wireless power technology into their instrumented basketball using the Qi Specifications. You can read more in their Kickstarter  funding page here.

94fifty_wireless_pow

Instrumented basketball with wireless charging

Personally, what I think will be perfect is if we could combine an electricity generating equipment like the Soccket with wireless power transfer. So imagine running shoes generating electricity as you run and that is transferred wirelessly to power your heart rate monitor and GPS watch and MP3 player. That would be awesome.

Anyway. For developers who would like to incorporate wireless power into their products, just check out any of the companies or organisations mentioned above to find out about their licensing options or standards for wireless transmitters and receivers; and may the force (wireless) power be with you!

Thanks for reading!