Motion capture apparatus and method
AssigneeElectronics and Telecommunications Research Institute
InventorsHan-Byul Joo, Seong-Jae Lim, Ji-Hyung Lee, Bon-Ki Koo
Life of this patent
Estimating the term…
Abstract
Disclosed herein is a motion capture apparatus and method. The motion capture apparatus includes a three-dimensional (3D) appearance reconstruction unit for reconstructing a 3D appearance of an entity using a multi-view image obtained by capturing the entity at a T+1-th frame. A 3D skeleton generation unit generates a 3D skeleton of the T+1-th frame using the 3D appearance and a model of the entity having a motion of a T-th frame. A motion reconstruction unit reconstructs a motion of the T+1-th frame of the model by changing the motion of the model based on the 3D skeleton of the T+1-th frame.
Claims16
A motion capture apparatus, comprising:
- a three-dimensional (3D) appearance reconstruction unit for reconstructing a 3D appearance of an entity using a multi-view image obtained by capturing the entity at a T+1-th frame;
- a 3D skeleton generation unit for generating a 3D skeleton of the T+1-th frame using the 3D appearance and a model of the entity having a motion of a T-th frame;
- and
- a motion reconstruction unit for reconstructing a motion of the T+1-th frame of the model by changing the motion of the model based on the 3D skeleton of the T+1-th frame,
- wherein the 3D skeleton generation unit comprises:
- a cross-section generation unit for generating a cross-section of the model of the entity having the motion of the T-th frame and a cross-section of the 3D appearance of the entity in a direction of a normal line relative to a longitudinal direction of a skeleton of the model of the entity;
- an ellipse fitting unit for generating an ellipse by elliptically fitting the cross-section of the model;
- and
- a skeleton location estimation unit for searching for an optimal location of the ellipse based on the cross-section of the 3D appearance, thus estimating a location of the skeleton of the model.
A motion capture method, comprising:
- reconstructing a three-dimensional (3D) appearance of an entity using a multi-view image obtained by capturing the entity at a T+1-th frame;
- generating a 3D skeleton of the T+1-th frame using the 3D appearance and a model of the entity having a motion of a T-th frame;
- and
- reconstructing a motion of the T+1-th frame of the model by changing the motion of the model based on the 3D skeleton of the T+1-th frame,
- wherein the generating the 3D skeleton comprises:
- generating a cross-section of the model of the entity having the motion of the T-th frame and a cross-section of the 3D appearance of the entity in a direction of a normal line relative to a longitudinal direction of a skeleton of the model of the entity;
- generating an ellipse by elliptically fitting the cross-section of the model;
- and
- searching for an optimal location of the ellipse based on the cross-section of the 3D appearance, thus estimating a location of the skeleton of the model.
Dependencies are inferred from the claim text.