Recent advances in deep learning have led to more studies to enhance golfers' shot precision. However, these existing studies have not quantitatively established the relationship between swing posture and ball trajectory, limiting their ability to provide golfers with the necessary insights for swing improvement. In this paper, we propose a new dataset called CaddieSet, which includes joint information and various ball information from a single shot. CaddieSet extracts joint information from a single swing video by segmenting it into eight swing phases using a computer vision-based approach. Furthermore, based on expert golf domain knowledge, we define 15 key metrics that influence a golf swing, enabling the interpretation of swing outcomes through swing-related features. Through experiments, we demonstrated the feasibility of CaddieSet for predicting ball trajectories using various benchmarks. In particular, we focus on interpretable models among several benchmarks and verify that swing feedback using our joint features is quantitatively consistent with established domain knowledge. This work is expected to offer new insight into golf swing analysis for both academia and the sports industry.

The first golf major of the year is in the books, and we all know what that means. Yes, over the next couple of weeks, across the globe, countless amateur players are dusting down their clubs and hitting up their local course. And while this trend usually fizzles out (at least until the next major) once players are reminded of their own golfing limitations, the rise of shot trackers and swing analysers now mean it's easier than ever to actually break this seemingly never-ending cycle of mediocrity and improve into a solid regular. Whether it's through GPS watches or trackers from the likes of Garmin, or more dedicated club sensors from companies such as Game Golf and Arccos, receiving insights into your round has never been easier. But despite there being plenty of devices to choose from, few put together a complete tracking experience.