Activity-conditioned continuous human pose estimation for performance analysis of athletes using the example of swimming

TL;DR

This paper enhances human pose estimation in swimming videos by integrating activity information and continuous video data, significantly improving joint detection accuracy for athletic performance analysis.

Contribution

It introduces activity-conditioned and continuous pose estimation extensions to CNN architectures, tailored for aquatic environments, with demonstrated accuracy improvements.

Findings

Up to 16% increase in correct joint detections

Effective integration of swimming style information

Successful adaptation of pose estimation to aquatic videos

Abstract

In this paper we consider the problem of human pose estimation in real-world videos of swimmers. Swimming channels allow filming swimmers simultaneously above and below the water surface with a single stationary camera. These recordings can be used to quantitatively assess the athletes' performance. The quantitative evaluation, so far, requires manual annotations of body parts in each video frame. We therefore apply the concept of CNNs in order to automatically infer the required pose information. Starting with an off-the-shelf architecture, we develop extensions to leverage activity information - in our case the swimming style of an athlete - and the continuous nature of the video recordings. Our main contributions are threefold: (a) We apply and evaluate a fine-tuned Convolutional Pose Machine architecture as a baseline in our very challenging aquatic environment and discuss its error modes, (b) we propose an extension to input swimming style information into the fully convolutional architecture and (c) modify the architecture for continuous pose estimation in videos. With these additions we achieve reliable pose estimates with up to +16% more correct body joint detections compared to the baseline architecture.