Benbrook Chen Leckie Lopez: Difference between revisions
imported>Student221 Created page with '== Introduction == == Background == == Methods == == Results == == Conclusions == == Appendix == You can write math equations as follows: <math>y = x + 5 </math> You ca…' |
imported>Student221 No edit summary |
||
| Line 1: | Line 1: | ||
== Introduction == | == Introduction == | ||
Image alignment is the process of matching one image called template with another image. It is a crucial step in many image systems engineering applications such as video stabilization, summarization, and the creation of panoramic mosaics. | |||
== Background == | == Background == | ||
Previous work on image alignment algorithms fall into two categories: intensity-based and feature-based. Intensity-based algorithms compare the spatial intensity in sets of images, while feature-based algorithms detect image features like objects or lines. Image alignment algorithms can alternatively be sorted according to the transformation on the target image space to the reference image space. Some models use linear transformations, while other models use non-linear transformations that are elastic or non-rigid. There are many existing algorithms to accomplish image alignment, but to our knowledge, one does not exist in Matlab format, particularly one that is integrated into ISETcam. | |||
== Methods == | == Methods == | ||
The main goal of this project is to experiment with existing image alignment algorithms and adapt one of them to be implemented within the ISETcam framework. We will develop a metric to analyze the performance of several algorithms, and compare the data from the algorithms to data from a perfect sensor. We will focus on comparing algorithms that utilize feature-based, linear transformation models. The instructors will provide data from the ISET3D software on simulated images taken by various cameras and sensors, and images where the object is moving as well as the global scene. Once we align images, we can use mean squared error or SSIM (structural similarity) as metrics to compare between algorithms, and baseline the algorithm’s performance against algorithms reported in previous literature. Whichever algorithm performs the image alignment the best, according to the metrics, will be integrated into ISETcam. | |||
== Results == | == Results == | ||
Revision as of 22:07, 7 December 2019
Introduction
Image alignment is the process of matching one image called template with another image. It is a crucial step in many image systems engineering applications such as video stabilization, summarization, and the creation of panoramic mosaics.
Background
Previous work on image alignment algorithms fall into two categories: intensity-based and feature-based. Intensity-based algorithms compare the spatial intensity in sets of images, while feature-based algorithms detect image features like objects or lines. Image alignment algorithms can alternatively be sorted according to the transformation on the target image space to the reference image space. Some models use linear transformations, while other models use non-linear transformations that are elastic or non-rigid. There are many existing algorithms to accomplish image alignment, but to our knowledge, one does not exist in Matlab format, particularly one that is integrated into ISETcam.
Methods
The main goal of this project is to experiment with existing image alignment algorithms and adapt one of them to be implemented within the ISETcam framework. We will develop a metric to analyze the performance of several algorithms, and compare the data from the algorithms to data from a perfect sensor. We will focus on comparing algorithms that utilize feature-based, linear transformation models. The instructors will provide data from the ISET3D software on simulated images taken by various cameras and sensors, and images where the object is moving as well as the global scene. Once we align images, we can use mean squared error or SSIM (structural similarity) as metrics to compare between algorithms, and baseline the algorithm’s performance against algorithms reported in previous literature. Whichever algorithm performs the image alignment the best, according to the metrics, will be integrated into ISETcam.
Results
Conclusions
Appendix
You can write math equations as follows:
You can include images as follows (you will need to upload the image first using the toolbox on the left bar, using the "Upload file" link).
