Motion Icon
1. Overview

Motion capture has been widely used in digital entertainment industry, and large motion capture databases have been built.
Motion data retrieval and browsing have been an issue. In this project, we will propose methods to visualize motion capture
 data in a single image, and thus provide a convenient way to browse the motion retrieval result as well as the database. 
Specifically, we visualize motion capture data in three different ways: stroboscopic pose sequences, photographic blur and 
action lines. Using stroboscopic pose sequences, we render multiple key poses, conveying motion, in a single image. 
Using photographic blur, we convey motion through simulating motion blur by rendering selected poses in a single image 
with varying transparency. Using action lines, we convey motion by adding curves indicating an action. The two major 
challenges of this project are to extract concise motion representations and to visualize them in an effective way.

The final goal of this project can be achieved by taking the following 3 steps:
Step 1: Build a system framework, and implement a preliminary approach to visualizing motion using action lines.
Step 2: Propose and implement effective approaches to visualizing motion using action lines and photographic blur.
Step 3: Propose and implement effective approaches to visualizing motion using stroboscopic pose sequences.

2. Project 1

The goal for Project 1 is to build a system framework, and implement a preliminary approach to visualizing motion 
using action lines. Specifically, the following work will be finished:
a. Implement a motion player.
b. Analyze motion capture data and extract a key frame, which, together with the corresponding action lines, 
convey most information.
c. Visualize the key frame and its action lines in an effective way.
 
3. References
[1]James E Cutting. Representing motion in a static image: constraints and parallels in art, science, and popular culture. 
Perception. Vol. 31, 2002: 1165-1193.
[2] Assa, J., Caspi, Y., and Cohen-Or, D. Action synopsis: pose selection and illustration. ACM Trans. Graph. 24 (3), 2005: 667-676.
[3] Feng Liu , Yueting Zhuang , Fei Wu , Yunhe Pan, 3D motion retrieval with motion index tree, Computer Vision and Image Understanding, 
Vol.92 (2-3), 2003: 265-284. 
[4] Sam T. Roweis and Lawrence K. Saul. Nonlinear Dimensionality Reduction by Locally Linear Embedding. Science. Vol. 290, 2000: 2323-2326.
[5] Bongwon Suh, Haibin Ling, Benjamin B. Bederson, and David W. Jacobs. Automatic thumbnail cropping and its effectiveness. 
In Proceedings UIST'03, pages 95-104, 2003.
[6] Feng Liu and Michael Gleicher. Automatic Image Retargeting with Fisheye-View Warping. ACM UIST 2005, Seattle, USA, October 2005. pp.153-162.
[7] Liu, G., Zhang, J., Wang, W., and McMillan, L. 2005. A system for analyzing and indexing human-motion databases. SIGMOD '05. 
ACM Press, New York, NY, 924-926.