Motion Capture of Interacting Characters

We present a markerless motion capture approach that reconstructs the skeletal motion and detailed time-varying surface geometry of two closely interacting people from multi-view video. Due to ambiguities in feature-to-person assignments and frequent occlusions, it is not feasible to directly apply single-person capture approaches to the multiperson case. We therefore propose a combined image segmentation and tracking approach to overcome these difficulties. A new probabilistic shape and appearance model is employed to segment the input images and to assign each pixel uniquely to one person. Thereafter, a single-person markerless motion and surface capture approach can be applied to each individual, either one-by-one or in parallel, even under strong occlusions. We demonstrate the performance of our approach on several challenging multi-person motions, including dance and martial arts, and also provide a reference dataset for multi-person motion capture with ground truth.

Crash	Fall	Jump	Marker
Calib File	Calib File	Calib File	Calib File
Model Templates	Model Templates	Model Templates	Model Templates
Images	Images	Images	Images
Silhouette	Silhouette	Silhouette	Silhouette
Result Meshes	Result Meshes	Result Meshes	Result Meshes
			Marker Data


	Broadband Network & Digital Media Lab