Browsing by Subject "motion capture"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item 3D Facial Performance Capture From A Single RGBD Camera(2013-05-28) Chen, Yen-LinRealistic facial animation remains one of the most challenging problems in computer graphics, where facial performance capture of real people has been a key component. The current state-of-the-art technologies used to capture facial performances are far too expensive and cumbersome for general users, which limits the potential applications of performance capture. The primary contribution of this dissertation is to propose two systems that are suitable for common users to capture facial performance using a single low-cost device. Our first system focuses on large-scale facial performance reconstruction from a single RGBD image. Our goal is to accurately reconstruct global transformation, as well as large-scale deformations from the images provided by a single shot of a Microsoft Kinect camera. With the combination of a robust facial feature detector and an image-based registration method, our system is automatic, robust and accurate to reconstruct facial movements. The result face meshes are topology consistent and with dense correspondences. Since people are natural experts of native human expressions and can distinguish subtle differences, e.g. dynamic facial wrinkles, we propose a second system combining our performance capture with a 3D scanning system to add person-specific high-resolution details in an efficient and effective way. We demonstrate the power of our proposed systems by testing on both real and synthetic data, as well as a commercially available motion capture system. Results show that the proposed systems generate believable and comparable results. We believe the proposed systems should be useful and applicable for general as well as professional users.Item An Extensible System For Physically-based Virtual Camera Control Using Rotational Motion Capture(2014-04-24) Huebel, Robert ShelbyAn important characteristic of any well-designed system is user interface design. Even in extremely complex systems with high learning curves, a designer?s goal is to create an interface that is simple to use and that feels natural, while at the same time allowing the user full access to all of the system?s functionality. In the field of visual effects and computer animation, effective manipulation of the virtual camera is essential to any successful production. In most cases, the virtual camera is manipulated with standard input devices such as the mouse and keyboard. This thesis presents an alternative user interface design for virtual cameras using physical controls. This thesis describes an extensible system which offers physically-based, real-time virtual camera control in a commercial 3D software package by means of rotational motion capture. The system described is composed of both programmed physical hardware and a software application. The physical hardware consists of multiple analog sensors programmed to work in conjunction to detect rotation about the de- vice?s three axes. The software application interprets the data sent from the physical hardware into a form a 3D software package can use to manipulate a virtual cam- era, while also providing additional functionality for the motion capture and camera manipulation processes. This thesis constructs the physical motion-sensing device using only affordable, commercially-available parts. The software components of the system use freely available programming languages and development environments. The system possesses the ability to be expanded upon to add additional functionality or modify existing components, in order for it to be flexible enough for numerous applications. The result of this research is a working prototype system that captures pitch, roll, and yaw motions that mimic actual physical motions performed by the user. The workflow provided by the system allows for quick iterations and facilitates an inter- active control scheme for the virtual camera that traditional mouse-and-keyboard techniques cannot.Item Video looping of human cyclic motion(Texas A&M University, 2004-09-30) Choi, Hye MeeIn this thesis, a system called Video Looping is developed to analyze human cyclic motions. Video Looping allows users to extract human cyclic motion from a given video sequence. This system analyzes similarities from a large amount of live footage to find the point of smooth transition. The final cyclic loop is created using only a few output images. Video Looping is useful not only to learn and understand human movements, but also to apply the cyclic loop to various artistic applications. To provide practical animation references, the output images are presented as photo plate sequences to visualize human cyclic motion similar to Eadweard Muybridge's image sequences. The final output images can be used to create experimental projects such as composited multiple video loops or small size of web animations. Furthermore, they can be imported into animation packages, and animators can create keyframe animations by tracing them in 3D software.