Mining Automatically Estimated Poses from Video Recordings of Top Athletes

Abstract Human pose detection systems based on state-of-the-art DNNs are about to be extended, adapted and re-trained to fit the application domain of specific sports. Therefore, plenty of noisy pose data will soon be available from videos recorded at a regular and frequent basis. This work is among the first to develop mining algorithms that can mine the expected abundance of noisy and annotation-free pose data from video recordings in individual sports. Using swimming as an example of a sport with dominant cyclic motion, we show how to determine unsupervised time-continuous cycle speeds and temporally striking poses as well as measure unsupervised cycle stability over time. The average error in cycle length estimation across all strokes is 0.43 frames at 50 fps compared to manual annotations. Additionally, we use long jump as an example of a sport with a rigid phase-based motion to present a technique to automatically partition the temporally estimated pose sequences into their respective phases with a mAP of 0.89. This enables the extraction of performance relevant, pose-based metrics currently used by national professional sports associations. Experimental results prove the effectiveness of our mining algorithms, which can also be applied to other cycle-based or phase-based types of sport.