The influence of labeling techniques in classifying human manipulation movement of different speed

TL;DR

This study examines how different labeling techniques affect the accuracy of classifying human arm movements at various speeds using machine learning, highlighting the superiority of trajectory-based labeling.

Contribution

It compares the impact of video-based versus trajectory-based labeling methods on classification accuracy across multiple machine learning models.

Findings

Trajectory-based labeling improves accuracy by nearly 20%.

Models trained on normal-speed data generalize better to fast movements.

All tested models perform better with trajectory-labeled data.

Abstract

In this work, we investigate the influence of labeling methods on the classification of human movements on data recorded using a marker-based motion capture system. The dataset is labeled using two different approaches, one based on video data of the movements, the other based on the movement trajectories recorded using the motion capture system. The dataset is labeled using two different approaches, one based on video data of the movements, the other based on the movement trajectories recorded using the motion capture system. The data was recorded from one participant performing a stacking scenario comprising simple arm movements at three different speeds (slow, normal, fast). Machine learning algorithms that include k-Nearest Neighbor, Random Forest, Extreme Gradient Boosting classifier, Convolutional Neural networks (CNN), Long Short-Term Memory networks (LSTM), and a combination of CNN-LSTM networks are compared on their performance in recognition of these arm movements. The models were trained on actions performed on slow and normal speed movements segments and generalized on actions consisting of fast-paced human movement. It was observed that all the models trained on normal-paced data labeled using trajectories have almost 20% improvement in accuracy on test data in comparison to the models trained on data labeled using videos of the performed experiments.