Please use this identifier to cite or link to this item:
Title: Sketch animation based on sketch-annotated key-frame in normal video
Authors: Lee, Tian Hui.
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Computer graphics
Issue Date: 2009
Abstract: Animation has been widely popular around the world with numerous movies and TV series today had animation incorporated into them for special effects. To many animators, animation is time consuming and expensive to develop. The more realistic the object is, the more difficult it is to create the motion and the details of it. In this project, a software program is proposed to investigate how sketches can be animated through motion transfer from a video of the actual scene to aid animators in making better and more realistic animation. In order to develop the program, intensive research has been done on various motion estimation techniques like optical flow, box matching and pel-recursion algorithm. The strengths and weaknesses of various techniques were noted and taken into consideration in the design of the system. With the knowledge and keeping the objective in mind, the program is designed using optical flow technique to estimate the motion vectors of multiple frames from a key frame. The program allows the user to sketch an object and use the motion vectors obtain from a video of the actual scene to animate the motion and orientation of the sketched object. Lastly, the program also provides a user-friendly GUI and the capability to save the sketches into a video file. Although the program requirements were met, additional features could be added to extend the capabilities of the program. Some recommendations include adding paint function, incorporating other motion estimation techniques and animation on selected part of the object.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
Lee Tian Hui 09.pdf
  Restricted Access
1.2 MBAdobe PDFView/Open

Page view(s) 20

checked on Oct 28, 2020

Download(s) 20

checked on Oct 28, 2020

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.