Analyzing Swimming Performance Using Drone Captured Aerial Videos

TL;DR

This work addresses the challenge of robustly tracking swimmer performance without multiple cameras by using a moving UAV to capture aerial footage. It combines an end-to-end pipeline with Data Acquisition via a DJI drone, Landmark Detection with MediaPipe Pose, and Performance Analysis to extract limb angles, stroke duration, and velocity. The approach achieves accurate metrics, reporting maximum errors of $0.3$ s for stroke duration and $0.35$ m/s for velocity across training and competition data, while highlighting limitations due to splashes and water refraction. The method offers comprehensive pool coverage with a single camera, enabling coaches to diagnose technique, symmetry, and pacing, and sets the stage for robust, real-time performance analytics in competitive swimming.

Abstract

Monitoring swimmer performance is crucial for improving training and enhancing athletic techniques. Traditional methods for tracking swimmers, such as above-water and underwater cameras, face limitations due to the need for multiple cameras and obstructions from water splashes. This paper presents a novel approach for tracking swimmers using a moving UAV. The proposed system employs a UAV equipped with a high-resolution camera to capture aerial footage of the swimmers. The footage is then processed using computer vision algorithms to extract the swimmers' positions and movements. This approach offers several advantages, including single camera use and comprehensive coverage. The system's accuracy is evaluated with both training and in competition videos. The results demonstrate the system's ability to accurately track swimmers' movements, limb angles, stroke duration and velocity with the maximum error of 0.3 seconds and 0.35~m/s for stroke duration and velocity, respectively.

Figures (9)

• Figure 1: Capturing swimmer footage using a moving UAV
• Figure 2: System overview
• Figure 3: UVA and its demonstration for aerial footage collection
• Figure 4: Angles between two arms and the reference line
• Figure 5: Left and right arm angle in front crawl