Friday, 20 November 2015

Automatic Generation of Action Sequence Images from Burst Shots

Abstract

Many sports enthusiasts, from novice photographers to professional publishers, rely on manual image segmentation with tools like Photoshop to combine multiple images of a bike trick or basketball dunk into a single image by cutting out the foreground of each image and overlaying it onto the background of one image. The goal of this project is to develop an algorithm that can automatically combine multiple images generated from burst shots of an action into a single image that clearly shows the full action. This requires three main tasks for each set of images, including background alignment between images in the cases when the camera is moving (using feature detection and matching), segmentation of the foreground and background components of each image even in cases when portions of the background might be moving, and finally cleanly combining the foreground image segments all of the images onto a single background image. The algorithm described in this paper successfully compiles a variety of image sets, including those where the foreground object overlaps between images or sets with multiple objects, but fails to compile sets where multiple objects cross paths during the action.





Domain: Image Processing

Language: MATLAB

Contact Detail

Ph.no: 7200555526

e-mail: info.nanosoftwares@gmail.com

No comments:

Post a Comment