Development of a climbing performance analysis tool using computer vision

Indoor bouldering, a rapidly growing sport in the UK and globally, has seen a significant rise in participation, paralleled by an increase in the use of fitness apps and wearable trackers. Despite this growth, tracking and recording metrics for indoor climbing remains a challenge. This paper proposes an automated tool utilising computer vision and a gym-wide camera system to collect data on routes climbed and attempts made, without the need for manual logging. This tool aims to provide climbers with detailed performance analysis and support climbing gyms in optimising route setting and member engagement. Initial market research and discussions with climbing coaches highlight the complexity of quantifying climbing performance and the potential benefits of the proposed system. The system employs modern computer vision techniques, pose estimation and object detection to identify climbers and climbing holds. It captures footage from multiple cameras, processes it using Python, and stores keypoint data from climbers’ poses and holds. This stored data enables the calculation of various performance metrics, including the outcomes of attempts on routes. Yolov7 was selected for pose estimation, for its multi-person tracking capabilities. While existing tools focus on individual movement analysis, the proposed system emphasises broader quantitative metrics, offering a unique approach to enhancing the climbing experience. The system performs well, with high accuracy for climbers and holds, but further research and development are required to refine the system and fully realise its potential benefits.