Signal Processing Methods in Human Motion Path Analysis: A Use Case for Karate Kata
Toamasz Hachaj, Marcin Piekarczyk, Marek R. Ogiela · 2018 2nd European Conference on Electrical Engineering and Computer Science (EECS) · 2018
In this paper we will propose and evaluate a novel DTW-based method that allows to align and compare motion trajectories of relatively long (than 30 seconds or longer) and complex human motion paths. In contrary to other human motion analysis techniques we do not have restriction on motion direction, we use only kinematic data and we are able to compare any foot trajectory no matter how many rotations take place during the motion. The output of our algorithm are vectors defined along motion trajectory that corresponds to beginning and end positions of steps. The left and right foot is analyzed separately. The difference of two motion paths can be expressed in any DTW-based feature, for example DTW normalized distance. The dataset we use in evaluation procedure is consisted of four types of karate kata performed by two black belt Shorin-Ryu karate masters with more than 20 years of experience. The method proposed in this paper can be easily applied also for aligning and comparison of any other motion class described by two - dimensional motion trajectories. It can successfully evaluate motion paths that were generated by people with different body proportion done with different speed.