Using Synthetic Data for Planning, Development and Evaluation of Shape-from-Silhouette Based Human Motion Capture Methods

The shape-from-silhouette approach has been popular in computer vision-based human motion analysis. For the results to be accurate, a certain number of cameras are required and they must be properly synchronised. Several datasets containing multiview image sequences of human motion are publically accessible, but the number of available actions is relatively limited. Furthermore, the ground truth for the location of joints is unknown for most of the datasets, making them less suitable for evaluating and comparing different methods. In this paper a toolset for generating synthetic silhouette data applicable for use in 3D reconstruction is presented. Arbitrary camera configurations are supported, and a set of 2605 motion capture sequences can be used to generate the data. The synthetic data produced by this toolset is intended as a supplement to real data in planning and development, and to fascilitate comparative evaluation of shape-from-silhouette-based motion analysis methods.

[1]  Christos Faloutsos,et al.  Laziness is a Virtue: Motion Stitching Using Effort Minimization , 2008, Eurographics.

[2]  Stefano Corazza,et al.  Most favorable camera configuration for a shape-from-silhouette markerless motion capture system for biomechanical analysis , 2005 .

[3]  Ralph Gross,et al.  The CMU Motion of Body (MoBo) Database , 2001 .

[4]  Montse Pardàs,et al.  Shape from inconsistent silhouette , 2008, Comput. Vis. Image Underst..

[5]  Hossein Ragheb,et al.  MuHAVi: A Multicamera Human Action Video Dataset for the Evaluation of Action Recognition Methods , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[6]  Hélène Laurent,et al.  Comparative study of background subtraction algorithms , 2010, J. Electronic Imaging.

[7]  Bruno Raffin,et al.  A Distributed Approach for Real Time 3D Modeling , 2004, 2004 Conference on Computer Vision and Pattern Recognition Workshop.

[8]  Adrian Hilton,et al.  Surface Capture for Performance-Based Animation , 2007, IEEE Computer Graphics and Applications.

[9]  Ioannis Pitas,et al.  The i3DPost Multi-View and 3D Human Action/Interaction Database , 2009, 2009 Conference for Visual Media Production.

[10]  A. Laurentini,et al.  The Visual Hull Concept for Silhouette-Based Image Understanding , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Rémi Ronfard,et al.  Free viewpoint action recognition using motion history volumes , 2006, Comput. Vis. Image Underst..

[12]  Adrian Hilton,et al.  Real-time Pose Estimation using Tree Structures Built from Skeletonised Volume Sequences , 2012, VISAPP.

[13]  Long Quan,et al.  Image deblurring with blurred/noisy image pairs , 2007, SIGGRAPH 2007.

[14]  Adrian Hilton,et al.  A survey of advances in vision-based human motion capture and analysis , 2006, Comput. Vis. Image Underst..

[15]  Simone Re,et al.  Ideas and methods for modeling 3D human figures: the principal algorithms used by MakeHuman and their implementation in a new approach to parametric modeling , 2008, Bangalore Compute Conf..

[16]  Marc Van Droogenbroeck,et al.  A technique for building databases of annotated and realistic human silhouettes based on an avatar , 2009 .

[17]  Takeo Kanade,et al.  Shape-From-Silhouette Across Time Part II: Applications to Human Modeling and Markerless Motion Tracking , 2005, International Journal of Computer Vision.

[18]  Ilya Baran,et al.  Automatic rigging and animation of 3D characters , 2007, SIGGRAPH 2007.

[19]  Tim J. Ellis,et al.  ViHASi: Virtual human action silhouette data for the performance evaluation of silhouette-based action recognition methods , 2008, 2008 Second ACM/IEEE International Conference on Distributed Smart Cameras.

[20]  Anastasios Tefas,et al.  Combining Fuzzy Vector Quantization With Linear Discriminant Analysis for Continuous Human Movement Recognition , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[21]  Michael J. Black,et al.  HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion , 2010, International Journal of Computer Vision.