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

High Dynamic Range Image Compression by Optimizing Tone Mapped Image Quality Index

Abstract

Tone mapping operators (TMOs) aim to compress high dynamic range (HDR) images to low dynamic range (LDR) ones so as to visualize HDR images on standard displays. Most existing TMOs were demonstrated on specific examples without being thoroughly evaluated using well-designed and subject validated image quality assessment models. A recently proposed tone mapped image quality index (TMQI) made one of the first attempts on objective quality assessment of tone mapped images. Here, we propose a substantially different approach to design TMO. Instead of using any predefined systematic computational structure for tone mapping (such as analytic image transformations and/or explicit contrast/edge enhancement), we directly navigate in the space of all images, searching for the image that optimizes an improved TMQI. In particular, we first improve the two building blocks in TMQI—structural fidelity and statistical naturalness components—leading to a TMQI-II metric. We then propose an iterative algorithm that alternatively improves the structural fidelity and statistical naturalness of the resulting image. Numerical and subjective experiments demonstrate that the proposed algorithm consistently produces better quality tone mapped images even when the initial images of the iteration are created by the most competitive TMOs. Meanwhile, these results also validate the superiority of TMQI-II over TMQI.

Domain: Image Processing

Language: MATLAB

Contact Detail

Ph.no: 7200555526

e-mail: info.nanosoftwares@gmail.com