Written by VAY
15th December 2020
It is nothing new to see more and more of what we traditionally did in person shift to an online environment, particularly with the experience and impact that the pandemic cursed year of 2020 has brought. One of the last frontiers to transition (or better complement its existing in person offering) a more digitally inclined service is the healthcare space and within it the fitness industry. Emerging technologies and the new normal that we have accustomed to have made virtual fitness and health a viable alternative and in many cases a more preferable one for people. This new operating space is ripe with opportunities that are still to be uncovered, creating exciting potential. One of these is motion analysis, which can act from anything from a personal coach/physician if supported with the right intelligence behind it.
What is motion analysis exactly?
Basically, motion analysis compares two or more consecutive images and return information on the motion in the images. Data is usually captured with sensors or cameras. Through this, motion can be tracked within an image, over time and in what direction.
What can you do with motion analysis technology?
The potential with motion analysis lies in what you do with it, how you use the data provided from analyzing specific movements. Real-time motion analysis opens the door the many applications, such as providing real-time feedback on movement, indicating if exercises are done correctly, or analyzing movements to check whether there is an imbalance that could lead to an injury. We at VAY have developed a motion analysis algorithm that can already do the former, with the latter being an application intended for the future. In essence, use cases for our application are plentiful. Virtual fitness solutions can provide their users with live-feedback on their exercise execution, enabling them to instantly correct them and avoid injuries, just as if training with a personal coach, seeing progress faster. Our solution can also be integrated into gym equipment, offering the same personal coach like feedback mechanism through it. Furthermore, physiotherapists can have their patients perform recovery exercises with our technology, ensuring that the rehabilitation process is done and also done effectively at home, with the physician being able to track it from afar. With many more applications in the works and out there.
Are you looking to elevate yourself and benefit from the revolution in virtual health?
While the virtual environment provides exceptional opportunities, it also has its drawbacks in certain aspects. The personal component is more difficult to incorporate, providing the users with a personalized experience. Virtual workouts and online group classes can show you what to do, but you have no feedback on how you are performing your exercises, as well as those offerings being highly interchangeable. Nothing prevents users from jumping ship and going to a very similar virtual workout offer from another provider. Offering something unique and personalized is the key to reduce such churn, while also creating a much more sophisticated workout experience.
Is the effort of implementing motion analysis worth the reward?
By now you are probably wondering why motion analysis is not yet ubiquitous in the virtual fitness and physiotherapy space and whether you can do it yourself. To answer the first point, new technology needs time to disperse through an industry, but more crucially, there has not been a B2B ready to use solution on the market until quite recently, so everyone had to develop it themselves, which required big investments and time. Fortunately, we at VAY have pivoted to becoming a technology provider, as our expertise lies in tech and movement science, providing you with an easy to implement and market ready product with an extensive existing exercise library. Developing a solution yourself is possible, though connected to prohibitively large investment in funds and time, so why not trust the experts who are solely dedicated to using motion analysis to its fullest extent.
Nobody wants to wear a sensor while exercising
We very much agree with this, which is why our solution is marker and sensor free. No cumbersome wearables are needed. Simply stand in front of any RGB camera (from any phone, tablet, laptop or machine with a camera) and perform your exercise freely and our algorithm magically does all the rest. It is easy to use and easy to implement, due to our hardware independent solution that is also highly scalable to millions of users.
Wait, so why have I not yet incorporated motion analysis tech into my product?
Well, that is a pretty good question, considering all the benefits it provides. Our biggest explanation is that the virtual fitness market has grown so massively in the recent months, causing a rising tide that lifts all ships. To stay ahead and dominate for the years to come though, a foundation of innovation is needed. Add an easily incorporable solution like VAY now and see the benefits immediately in higher user satisfaction and decreased churn.
You are ready to dig deeper into implementing such a solution, we have prepared a list of 6 questions, that should help you think about key considerations and how VAY can help you achieve them.
1) What is VAY's product?
VAY AG has developed a reliable and precise software for human pose estimation based on computer vision. The algorithms analyze human posture and motion in real-time with any camera. This way, we allow solution providers in the area of sports and health to create more immersive user experiences by tracking their users, understanding their movements and giving feedback based on movement science.
2) Who is your system designed for?
Our target audience is in the prevention sector, predominantly fitness apps that want to expand or improve their virtual fitness offering, as well as in the rehabilitation and physiotherapy sector, where we offer a compelling and cost-effective solution to track the form and repetition of exercises to get back to full health, without requiring in person sessions. Ideally, they already have a large existing customer base on their current application and want to take the user experience to the next level by including real-time feedback. Alternatively, they are corporations who see a huge potential in their customer segment using our technology and want to launch a new application enabled by computer vision.
3) What makes your product special?
Through our state-of-the-art motion capture technology and expert knowledge in biomechanics/movement science, we create a unique value for our clients. Our pose estimation has the unique qualities that can provide professional grade motion analysis in a hardware agnostic manner. The magic of our solution relies on capturing movements, that can be accessed with any device that has a RGB camera, no matter the system (iOS, Android, Windows, Linux) or device (phone, tablet, laptop, gym machine, etc.). We do not need intrusive sensors or markers to track a person and their movement, this is all done via computer vision. Our movement expertise then provides the analysis, based on the extensive exercise library we have built up, to provide real-time feedback on whether movements are performed with proper form and if not providing corrective feedback.
Our solution is further unique in the fact that we have an existing exercise library already that can be used in a plug and play fashion, while we also have the capability of adding up to 20 new exercises per week, tailored to a client’s specified needs. Our camera position is also flexible, allowing for it to work in any position. All in all, our solution is unintrusive and highly scalable and therefore is much more cost-effective to operate for our customers.
4) What data is VAY tracking?
Speed / Velocity
Up to 30 data points on the body and around the body
Range of Motion
This allows VAY to measure all data points that conventional trackers and high-profile camera systems were able to, just faster, cheaper and more scalable.
5) How precise is the VAY motion analysis algorithm?
Our human pose estimation already excels on benchmark data sets and is specifically trained for fitness exercises. We include prior knowledge about human anatomy and ensure temporal consistency.
Any remaining inconsistencies are made up for by our motion analysis neural networks, which are specifically trained on different exercises also on imperfect human pose models during each exercise.
Our computer vision algorithms are designed to resemble human vision. Therefore, precision is reduced in very dark environments.
6) What does the client need to provide for potential cooperation? How much work is involved?
Integration is straightforward (1-2h). The VAY Motion Analysis Kits can be directly integrated into any application and is well documented. It is important to mention that we do not offer GUIs or audio-visual feedback systems, as this relates directly to user experience and we know that you know your users best. However, we like to know as much as possible about your product to perfectly support you with integration and building a good user experience.
Have more questions or want a demo? Get in touch via the contact form!