A Look Beneath the Hood: How Driveline Sport Science Collects, Processes, and Analyzes Hundreds of Athletes’ Biomechanics Information6 min read
Driveline Baseball has lengthy been baseball’s utilized biomechanics chief. Since 2008, when founder Kyle Boddy began constructing his first movement seize lab within the aisles of Dwelling Depot, Driveline has leveraged the worth of objectively quantifying human motion.
The lab has improved by leaps and bounds since then. Driveline R&D has iteratively refined the know-how and underlying programs in our movement seize ecosystem. Our present setup, The Launchpad, options simultaneous markered and markerless movement seize knowledge in addition to a wealth of extra monitoring applied sciences like Rapsodo, Trackman, HitTrax, and Pulse. Gone are the times of utilizing hacked Wiimotes to measure biomechanics (true story).
And that lab has enabled us to be taught loads of issues. We’ve studied the results of weighted baseballs on pitching mechanics, validated biomechanics applied sciences, and leveraged biomechanics to drive our coaching protocols for each hitters and pitchers.
Our Biomechanics Group has written and talked extensively on each the Driveline Weblog and Driveline R&D podcast on what we do with biomechanics and accent knowledge as soon as we get it. Some wonderful examples embody our ahead dynamics and computed muscle management simulations. Much less generally talked about is how we get to the purpose the place we’re prepared to investigate our knowledge. How will we go from uncooked 3D coordinates to kinematic and kinetic knowledge that analysts, coaches, and different R&D employees can use? Moreover, how will we mix knowledge from so many sources to boost our insights with out overtaxing employees??
Within the lab, we’re all the time operating a handful of various applied sciences. So how will we handle all of it? As anybody who’s interfaced with a number of baseball applied sciences earlier than is aware of all too effectively, every extra device is one other job for the coaches or participant growth employees. Because the tech stacks up, the workload shortly turns into overwhelming.
Every extra toy is one other job except you construct the underlying programs to cut back the quantity of human oversight wanted. How will we effectively course of biomechanics knowledge and stream it into our broader participant growth ecosystem?
That’s what we’ll discuss right here.
Much less Time Accumulating; Extra Time Growing
Despite the fact that a number of applied sciences could also be operating for any given particular person movement seize evaluation, customized software program options permit the Launchpad to be run by one individual – although we nonetheless want one other set of palms to feed the pitching machine for hitting assessments.
Proprietary Driveline software program syncs our Edgertronic cameras to any Stalker radar gun enabling automated triggering when a pitch is thrown. This eliminates the necessity for handbook Edgertronic operation. Edgertronic clips are then synched to athletes’ TRAQ profiles and fed into our inner markerless movement seize pipeline.
Rapsodo and Trackman ball monitoring knowledge are mechanically uploaded to our inner databases. Visual3D and Python processing pipelines add each pitch/swing (markered or markerless) to the identical knowledge warehouse. Joint kinetics, kinematics, energetics, and pressure plate knowledge are matched on a per-pitch stage whereas session and player-level tables present the mandatory metadata for customized knowledge choice and filtering as wanted. Customized knowledge constancy checks filter out any troublesome inconsistencies that bumped into points alongside the way in which.
Ball monitoring and full sign biomechanics knowledge get paired on a per-pitch stage. This whole course of, from inserting markers to producing customized reporting that populates in an athlete’s Traq profile, happens inside 24 hours of preliminary knowledge assortment. If we now have a excessive precedence evaluation that requires an expedited turnaround time, we will manually run our processing pipelines to generate the mandatory deliverables forward of the next-day turnaround.
All of those automations unlock R&D workers to do what they do finest: assist coaches and gamers, drive additional insights, and frequently enhance the underlying programs.
Markerless and Markered Movement Seize Processing
Since Driveline’s first movement seize processing pipeline over a decade in the past, we now have been engaged on making biomechanics knowledge processing as clean as attainable. Immediately, we’re on the sixth iteration of our processing pipeline (v6) and the quantity of human oversight wanted to take knowledge from evaluation to relevant perception has by no means been decrease.
We began making an attempt to maintain monitor of what number of labor hours go right into a single mocap session again in 2019. Again then, we had been turning round experiences in ~7 days and it was taking 5+ mixed labor hours per movement seize session. Immediately, we do extra with that biomechanics knowledge than we ever have and through peak volumes it takes us lower than 90 minutes of labor per session from finish to finish. This summer season, there have been over 500 movement seize classes within the Launchpad and it solely value us ~600 labor hours.
However what will get us enthusiastic about V6?
with out giving freely the key sauce…
Up to date Pose Estimation & Skeleton Mannequin
Visual3D has been the main research-grade biomechanics processing platform for a number of many years. We really feel no different platform gives comparable choices relating to pose estimation and linked-segment modeling. It’s for these causes that we funnel all of our markered and markerless movement seize knowledge via Visual3D for foundational pose estimation, inverse kinematics, and inverse dynamics calculations earlier than shifting to Python and R for extra intensive and application-specific sign processing.
With V6, we now have used Visual3D to additional superb tune our linked-segment mannequin in order that it extra intently captures how our athletes transfer. Our up to date mannequin is much less constrained, permitting segments on the distal finish of enormous vary of movement joints, such because the shoulders and hips, to maneuver freely relative to their neighboring section. Beforehand, constraining segments on opposing sides of those joints generally prompted pose estimation issues and fewer correct kinematic and kinetic profiles.
Power Stream + Drive Plates
V6 homes two new knowledge courses along with the normal kinematic and kinetic knowledge: energetics and pressure plates. Energy flow analyses permit us to see when, the place, and the way a lot kinetic vitality is shifting between physique segments. Drive plates inform us how our athletes are interfacing with the bottom. Each of those knowledge sources assist present a extra full image of how athletes transfer throughout every pitch/swing.
Uncooked & Processed Information
V6 homes all our unfiltered, unprocessed movement seize knowledge separate from the processed knowledge. Any worker or shopper can entry it and carry out customized analyses for their very own tasks. If we need to take a look at completely different filtering settings? Cool. If we need to check out a unique set of mannequin assumptions? No drawback. If we need to discover a brand new metric derived from world kinematic/kinetic knowledge as an alternative of counting on typical coordinate system and rotation sequence conventions? We will.
The place We’re Going
Much less invasive knowledge assortment means bigger samples. With these bigger samples, we will begin to establish, on a person and group stage, what actually issues. Paired markerless knowledge with live-AB outcomes drill proper right down to what get’s hitters out. Markerless knowledge paired with ball monitoring and per-play outcomes permits us to investigate baseball at a stage that nearly didn’t appear attainable only a few years in the past. Wish to quantify how a pitcher’s deception influences an anticipated run worth of a pitch? We will. Wish to measure how a batter adjusts to an off-speed pitch thrown in a hitter’s rely? That’s attainable, too.
Much less labor intensive knowledge assortment additionally means extra consideration to different applied sciences to proceed constructing our paired databases. Essentially the most highly effective insights usually come on the intersection of sport science sub-disciplines. Much less labor intensive permits us to reside there, focusing extra on the interaction of method and efficiency.
Higher programs automation and group tightens the suggestions loop between movement seize and actionable perception. No extra dedicating observe time to getting markered up and transported to some separate biomechanics lab to get a baseline or a retest mocap carried out. Now we will do it with minimal disruption to the observe plan, and with out killing R&D employees with labor-heavy knowledge cleansing or processing. All so we will preserve digging into the way to enhance on-field efficiency.
Written by Dr. Kyle Wasserberger – Sports activities Scientist
We may help you together with your biomechanics knowledge. Study extra about our Biomechanics Companies right here