Patent
Motion reconstruction method from inter-frame feature correspondences of a singular video stream using a motion library
TLDR
In this paper, the authors proposed a method for motion reconstruction from inter-frame feature correspondences of a singular video stream using a motion library, which comprises the detailed information on the whole processes from images to motions.Abstract:
The present invention relates to the motion reconstruction method from inter-frame feature correspondences of a singular video stream using a motion library. The motion library is constructed through a motion capture system which is becoming more actively used or skilled animators. The present invention comprises the detailed information on the whole processes from images to motions. These processes are very simple to implement and straight forward. The total movement of a motion can be effectively inferenced and this technology can directly used for various fields in which human motions are produced from the images.read more
Citations
More filters
Patent
Apparatus and method for high-speed marker-free motion capture
TL;DR: In this article, a high-speed marker-free motion capture system is proposed to detect a body's feature points corresponding to body's end portions such as a head, hands, feet, trunk, arms and legs.
Patent
3d textured objects for virtual viewpoint animations
James R. Gloudemans,Walter Hsiao +1 more
TL;DR: In this paper, a 3D model of an object is combined with a textured model of the event to depict a virtual viewpoint which differs from a viewpoint of the camera, in order to simulate a sports event.
Patent
Fading techniques for virtual viewpoint animations
James R. Gloudemans,Felicia Yue +1 more
TL;DR: In this paper, an image of an event is obtained from a camera and an object is detected in the image, and the object is at least partially faded out at a virtual viewpoint which meets a specified criterion, such as a specified angular offset, or exceeding a specified difference from the viewpoint of the camera.
Patent
Movement correction in MRI using a camera
Jeff Duyn,Lei Qin +1 more
TL;DR: In this paper, the authors provided a system and methods for movement correction in an MRI environment, comprising receiving a first plurality of images from a first scan of a subject with a first camera, receiving magnetic resonance imaging (MRI) images obtained concurrently with the first scan, correlating the first plurality with the MRI images, resulting in motion correction data.
Patent
Image repair interface for providing virtual viewpoints
TL;DR: In this article, an image of an event is obtained from a camera, and an object is detected in the image, and a user may perform the repair via a user interface by selecting part of an image from an image library and positioning the selected portion relative to the object.
References
More filters
Patent
A system for reconstructing the 3-dimensional motions of a human figure from a monocularly-viewed image sequence
TL;DR: In this paper, a system is provided for reconstruction the 3D motions of a human figure from a monocularly viewed image sequence in which a statistical approach is used coupled with the use of a set of motion capture examples to build a gaussian probability model for short human motion sequences.
Patent
Sample refinement method of multiple mode probability density estimation
Tat-Jen Cham,James M. Rehg +1 more
TL;DR: In this paper, a multimodal likelihood function is proposed to find the maxima of the likelihood function starting from each seed point in state-space, and kernel functions are fitted to these peaks.
Patent
System and method for determining structure and motion from two-dimensional images for multi-resolution object modeling
Abstract: The present invention is embodied in systems and methods for determining structure and motion of a three-dimensional (3D) object using two-dimensional (2D) images of the object obtained from multiple sets of views with different projection models, such as from a full perspective view and a weak perspective views. A novel fundamental matrix is derived that embodies the epipolar geometry between a full perspective view and a weak perspective view. The systems and methods of the present invention preferably uses the derived fundamental matrix together with the 2D image information of the full and weak perspective views to digitally reconstruct the 3D object and produce results with multi-resolution processing techniques. These techniques include recovering and refining motion parameters and recovering and refining structure parameters of the fundamental matrix. The results can include, for example, 3D positions of points, camera position between different views, texture maps, and the like.