05-07-2010, 03:42 PM
HIGH RESOLUTION ANIMATED SCENES FROM STILLS
Abstract
Current techniques for generating animated scenes involve either videos (whose resolution is limited) or a single image (which requires a significant amount of user interaction). In this project, we describe a system that allows the user to quickly and easily produce a compelling-looking animation from a small collection of high resolution stills. Our system has two unique features. First, it applies an automatic partial temporal order recovery algorithm to the stills in order to approximate the original scene dynamics. The output sequence is subsequently extracted using a second-order Markov Chain model. Second, a region with large motion variation can be automatically decomposed into semiautonomous regions such that their temporal orderings are softly constrained. This is to ensure motion smoothness throughout the original region. The final animation is obtained by frame interpolation and feathering. Our system also provides a simple-to-use interface to help the user to fine-tune the motion of the animated scene. Using our system, an animated scene can be generated in minutes. We show results for a variety of scenes.
Existing System:
 The existing system has garnered a lot of attention is video texture, which reuses frames to generate a seamless video of arbitrary length.
 Video textures work by figuring out frames in the original video that are temporally apart but visually close enough, so that jumping between such frames appears seamless.
 This work was extended to produce video sprites, which permit high-level control of moving objects in the synthesized video. Unlike videos, the ordering of our input stills may not be 1D. Thus, we can only use partial orders as reference dynamics.
Drawbacks:
Fully manual in traction.
Each and every process should be done by manually.
Ex. Flash player.
Proposed System:
 The proposed system is a scene animation system that can easily generate a video or video texture from a small collection of stills.
 Our system first builds a graph that links similar images. It then recovers partial temporal orders among the input images and uses a second-order Markov Chain model to generate an image sequence of the video or video texture. Our system is designed to allow the user to easily fine-tune the animation.
Merits:
¢ Reduce the user interaction
¢ Time complexity
¢ User can give only collections of jpeg images. Based on the images we will get movie file for 1 or more than 2 minutes.
¢ Simply conversion of Jpeg to Mpeg/AVI
Modules
The modules of the system are
¢ Preprocessing
¢ Building a Graph
¢ Motion creation
¢ Scene making
¢ Manual editing
Module Description
Preprocessing
Color Enhancement, Improve the image quality, Size corrections, and noise removal.
Algorithm: Morphological Filters, Automatic Color Enhancement technique [ACE]
Input:
Collections of related stills/ images.
Output:
Quality stills.
1. Color Enhancement - improve the Contrast & Brightness, Improve the quality based on the saturation Adjustment
In first module we first set same pixels for all images. Bcoz it will compare the images for find the difference b/w the same objects.
After that we will set the same brightness and contrast for all images. Bcoz based on the brightness and contrast the output will be show with same bright n contrast.
Morphology - Removing Noise
If we improve the quality of an image it will affect the original pixels. Some pixels may be affect that time noise will occur. Her we are using noise removal process.
2. Convolution and correlation - Smoothing, Sharpness
Building a Graph
¢ Image comparison.
¢ Algorithm: Floyd™s algorithm, Partial Temporal order recovery algorithm.
¢ Input: Unordered stills
¢ Output: Ordered, distance computed.
1. Edge Detection - Detect the object Edges
Using canny edge detection process we will detect the edges of the images. Here we will show layout of the objects.
2. Difference calculation “ Calculate the Difference b/w the two images based on the pixel difference.
3. Make a Graph “ Make a Graph based on difference
Motion Creation
¢ Based on distance low resolution optical flow is created between two adjacent images. Sampling the graph
¢ Algorithm: Statistical approach, Markov Chain Model.
¢ Fine tuning
¢ Input: Stills with no tuning
¢ Output: Fine tuned video texture.
Scene Making
¢ Video texture creations
¢ AVI File conversion based on time sequence
¢ Frame interpolation
¢ Algorithm :AVI format
¢ Input: Stills
¢ Output: Video or video texture.
Manual Editing
¢ Manual reorders
¢ Editing the image
¢ Motion smoothness
¢ Measuring motion irregularity.
Software Requirements
Operating system: Windows XP Professional/Vista
Front End : Microsoft Visual Studio .Net 2008
Coding Language : Visual C# .Net
Hardware Requirements
System : Pentium IV
Hard disk : 40 GB
RAM : 1 GB