Pose Estimation for Sprinter Form Comparisons

Our study aims to discover what joints and other factors play the most important role in developing faster sprinters. Using data from both high schoolers and professional athletes, we compared differences in each athlete's top speed position at their MVP stance, which is the maximal height of vertical projection as defined by the ALTOS Kinogram Method. With TensorFlow's MoveNet Thunder pose estimation model, we investigated each athlete's limb angles in the legs and arms. Alongside these angle key points, we measured the ground-to-air ratios (number of frames with foot on the ground divided by number of frames with foot in the air) of each athlete at their top speed. Comparing the angles, we discovered that professional athletes tend to have a more constricted range of movement at their maximal height projection while high school athletes tended to swing wider in the same position. With speed data of the high school athletes, we also discovered that a shorter ground-to-air ratio also meant a typically faster time. Paired with this data, we also found that the front hip and elbows tend to determine speed in athletes. However, while these findings may serve as benchmarks for success, performance will vary among athletes, so individualized training will most benefit a sprinter.