Ski jumping is an expert sport that requires fine motor skills to guarantee the safe conduct of training and competition. In this paper, we therefore employed multiple inertial sensors to build and evaluate a framework for the assessment of jump errors and motion style. First, a large set of inertial ski jump motion captures were augmented, segmented, and transformed into multiple statistic and time-serial motion feature representations. All features were next used to learn and retrieve style error information from the jump segments under two classification strategies in a cross-validation cycle. Average accuracies of the error recognition indicated the applicability of the proposed system with error recognition rates between 60% and 75%, which should be considered sufficiently good under the present size and quality of the real life training data. Furthermore, the chosen signal-based motion features appeared to be better suited to extract and recognize style errors than the chosen kinematic induced features obtained using expensive postprocessing. This assumption could constitute important information for many related application systems. Therefore, it should be investigated whether such result can be generalized under different extracted features or further feature set compositions in the future.
ASJC Scopus subject areas