Annotation of Human Gesture using 3D Skeleton Controls

The manual transcription of human gesture behavior from video for linguistic analysis is a work-intensive process that results in a rather coarse description of the original motion. We present a novel approach for transcribing gestural movements: by overlaying an articulated 3D skeleton onto the video frame(s) the human coder can replicate original motions on a pose-by-pose basis by manipulating the skeleton. Our tool is integrated in the ANVIL tool so that both symbolic interval data and 3D pose data can be entered in a single tool. Our method allows a relatively quick annotation of human poses which has been validated in a user study. The resulting data are precise enough to create animations that match the original speaker's motion which can be validated with a realtime viewer. The tool can be applied for a variety of research topics in the areas of conversational analysis, gesture studies and intelligent virtual agents.


This tool was developed by Quan Nguyen as his Master project in the EMBOTS group. It won the GALA 2009 Award for the best tool related to intelligent virtual agent development.

ANVIL Website: www.anvil-software.de

Poster presented at LREC 2010, Malta


Nguyen, Q., Kipp, M. (2010) Annotation of Human Gesture using 3D Skeleton Controls. In: Proceedings of the 7th International Conference on Language Resources and Evaluation (LREC-2010), ELDA, Paris.

Nguyen, Q. and Kipp, M. (2009) A Gesture Analysis and Modeling Tool for Interactive Embodied Agents. In: Proceedings of the 9th International Conference on Intelligent Virtual Agents (IVA-09), Springer, pp. 566-568.


GALA submission video HD Quality (139 MB)  Quicktime (59 MB)  AVI (35 MB)

Back to projects