Describing Local Reference Frames for 3-D Motion Trajectory Recognition

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

1 Scopus Citations
View graph of relations



Original languageEnglish
Pages (from-to)36115-36121
Journal / PublicationIEEE Access
Online published22 Jun 2018
Publication statusPublished - 2018


Motion trajectories tracked from points of interest can provide key relevant features for characterizing motion patterns in video. As increasing number of 3D vision sensors arise, 3D motion trajectories that serve as motion representations have been applied successfully to video retrieval and analysis, scene understanding, motion recognition, and so on, in existing works. Most of these works use raw data of motion trajectories directly or draw simple geometric quantities to describe motion trajectories, whereas these simple descriptions are not intrinsically complete as they cannot feature the orientation changes of moving points along 3D motion trajectories. In principle, orientation changes of a single moving point in 3D space have to been obtained by resorting to high-order derivatives, but the high-order derivatives would result in high sensitivity to noise. This paper tackles the problem by describing local reference frames along 3D motion trajectories, while we consider a motion trajectory as a temporal sequence of local reference frames. The maximal blurred segment of noisy discrete curves is employed to estimate local reference frames without high-order derivatives involved, and the local reference frame contains complete information of positions and orientations in 3D Euclidean space. To describe such local reference frames, we use the rotations and local square-root velocities of local reference frames as the proposed descriptor to characterize the position and orientation changes of moving points along motion trajectories. In the experiments, we evaluate the effectiveness of the proposed descriptor by applying it to gesture recognition on two large benchmark datasets which contain hand motion trajectories. The results show our proposed descriptor can achieve superior performance compared to existing descriptors and state-of-the-art methods in 3D motion trajectory recognition.

Research Area(s)

  • Estimation, gesture and activity recognition, local reference frame, maximal blurred segment, Motion segmentation, Motion trajectory, Noise measurement, Sensitivity, Three-dimensional displays, Tracking, Trajectory

Citation Format(s)