A high level trajectory indexing method for real time 3D motion recognition

Author

Yang, Jianyu ; Li, Y.F. ; Wang, Keyi

Author_Institution

Dept. of Manuf. Eng. & Eng. Manage., Univ. of Sci. & Technol. of China, Suzhou, China

fYear

2011

Firstpage

2061

Lastpage

2066

Abstract

Motion trajectory description plays an important role in motion recognition for many robotic tasks. The previous methods are too high in computational cost for real time recognition. In this paper, we propose a novel indexing method for motion trajectories as a high level descriptor for real time 3D motion recognition. Trajectories are segmented into basic segments and represented in segment level rather than point level. We index the trajectories by their segment sequences to recognize them. The computational cost is significantly decreased and the experimental results show that this method is effective and it can be used for real time motion recognition.

Keywords

image motion analysis; image recognition; image segmentation; image sequences; robot vision; solid modelling; computational cost; high level descriptor; high level motion trajectory indexing method; real time 3D motion recognition; robotic tasks; segment level representation; segment sequence; trajectory segmentation; Indexing; Motion segmentation; Real time systems; Tracking; Trajectory;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Biomimetics (ROBIO), 2011 IEEE International Conference on

Conference_Location

Karon Beach, Phuket

Print_ISBN

978-1-4577-2136-6

Type

conf

DOI

10.1109/ROBIO.2011.6181595

Filename

6181595