Abstract
AbstractCompetitive figure skaters perform successful jumps with critical parameters, which are valuable for jump analysis in athlete training. Driven by recent computer vision applications, recovering 3D pose of figure skater to obtain the meaningful variables has become increasingly important. However, conventional works have suffered from getting 3D information based on the corresponding 2D information directly or leaving the specificity of sports out of consideration. Issues such as self-occlusion, abnormal pose, limitation of venue and so on will result in poor results. Motivated by these problems, this paper proposes a multi-task architecture based on a calibrated multi-camera system to facilitate jointly 3D jump pose of figure skater. The proposed methods consist of three key components: Likelihood distribution and temporal smoothness- based discrete probability points selection filter out the most valuable 2D information; Multi-perspective and combinations unification-based large-scale venue 3D reconstruction is proposed to deal with the multi-camera; multi-constraint-based human skeleton estimation decides the final 3D coordinate from the candidates. This work is proved can be applied to 3D animated display and motion capture of the figure skating competition. The success rate of the independent joint is: 93.38% of 70 mm error range, 92.57% of 50 mm error range and 91.55% of 30 mm error range.
Publisher
Springer Science and Business Media LLC
Subject
Computational Mathematics,Engineering (miscellaneous),Information Systems,Artificial Intelligence
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献