Human Motion Capture Data Segmentation Based on ST-GCN

Human motion sequence segmentation plays a crucial role in understanding and applying human motion capture(MoCap) sequences. However, most of the traditional segmentation methods are designed to find the locations where the motion features have changed significantly. When dealing with complex motion scenes, such methods often lead to inefficiency, inaccuracy, and limitations. To address these challenges, we propose an end-to-end sequence segmentation method based on the Spatial Temporal Graph Convolutional Networks(ST-GCN). Our network effectively extracts motion features from MoCap sequences, reduces dimensions through convolutional operations, and identifies segmentation points between different motions. Under the constraints of excessive segmentation and clip length, the optimal segmentation is achieved by combining three carefully designed loss functions. The proposed framework was evaluated on two benchmark datasets, CMU MoCap database and HDM05 dataset, and achieved better accuracy and robustness compared with existing methods.

1. INTRODUCTION

Human motion analysis[1] is a challenging area in computer vision that includes tasks such as motion recognition and object detection. It has a wide range of applications in many fields, such as medical diagnosis, movie animation, and security inspection. Long motion sequences are usually segmented before motion analysis[2], since the segmented motion fragments contain only a single type of motion, such as running, jumping, or clapping. The segmented motion segments are further used for action synthesis[3], recognition[4], retrieval and prediction[5]. As a result, the computer vision community has devoted considerable effort to the research and development of action segmentation techniques.