Visualizing Skiers' Trajectories in Monocular Videos
arXiv:2304.02994 · doi:10.1109/CVPRW59228.2023.00547
Abstract
Trajectories are fundamental to winning in alpine skiing. Tools enabling the analysis of such curves can enhance the training activity and enrich broadcasting content. In this paper, we propose SkiTraVis, an algorithm to visualize the sequence of points traversed by a skier during its performance. SkiTraVis works on monocular videos and constitutes a pipeline of a visual tracker to model the skier's motion and of a frame correspondence module to estimate the camera's motion. The separation of the two motions enables the visualization of the trajectory according to the moving camera's perspective. We performed experiments on videos of real-world professional competitions to quantify the visualization error, the computational efficiency, as well as the applicability. Overall, the results achieved demonstrate the potential of our solution for broadcasting media enhancement and coach assistance.
arXiv comment2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), CVsports workshop
References in corpus (6)
- Visual Object Tracking in First Person Vision
- Visual Tracking by means of Deep Reinforcement Learning and an Expert Demonstrator
- Intra-frame Object Tracking by Deblatting
- Weakly-Supervised Domain Adaptation of Deep Regression Trackers via Reinforced Knowledge Distillation
- CoCoLoT: Combining Complementary Trackers in Long-Term Visual Tracking
- Spatiotemporal Motion Synchronization for Snowboard Big Air