3 results
12 - Gradient descent approaches to image registration
- from PART III - Feature Matching and Strategies for Image Registration
-
- By Arlene A. Cole-Rhodes, Morgan State University, Maryland, Roger D. Eastman, Loyola University, Maryland
- Edited by Jacqueline Le Moigne, NASA-Goddard Space Flight Center, Nathan S. Netanyahu, Roger D. Eastman, Loyola University Maryland
-
- Book:
- Image Registration for Remote Sensing
- Published online:
- 03 May 2011
- Print publication:
- 24 March 2011, pp 265-275
-
- Chapter
- Export citation
-
Summary
Abstract
This chapter covers a general class of image registration algorithms that apply numerical optimization to similarity measures relating to cumulative functions of image intensities. An example of these algorithms is an algorithm minimizing the least-squares difference in image intensities due to an iterative gradient-descent approach. Algorithms in this class, which work well in 2D and 3D, can be applied simultaneously to multiple bands in an image pair and images with significant radiometric differences to accurately recover subpixel transformations. The algorithms discussed differ in the specific similarity measure, the numerical method used for optimization, and the actual computation used. The similarity measure can vary from a measure that uses a radiometric function to account for nonlinear image intensity differences in the least-squares equations, to one that is based on mutual information, which accounts for image intensity differences not accounted for by a standard functional model. The numerical methods considered are basic recursive descent, a method based on Levenberg-Marquardt's technique, and Spall's algorithm. This chapter relates to the above registration algorithms and classifies them by their various elements. It also analyzes the image classes for which variants of these algorithms apply best.
Introduction
We consider in this chapter a class of image registration algorithms that apply numerical techniques for optimizing some similarity measures that relate only to the image intensities (or a function of the image intensities) of an image pair.
14 - Multitemporal and multisensor image registration
- from PART IV - Applications and Operational Systems
-
- By Jacqueline Le Moigne, NASA Goddard Space Flight Center, Maryland, Arlene A. Cole-Rhodes, Morgan State University, Maryland, Roger D. Eastman, Loyola University, Maryland, Nathan S. Netanyahu, University of Maryland, Maryland, Harold S. Stone, NEC Research Laboratory Retiree, New Jersey, Ilya Zavorin, University of Maryland, Maryland, Jeffrey T. Morisette, NASA Goddard Space Flight Center, Maryland
- Edited by Jacqueline Le Moigne, NASA-Goddard Space Flight Center, Nathan S. Netanyahu, Roger D. Eastman, Loyola University Maryland
-
- Book:
- Image Registration for Remote Sensing
- Published online:
- 03 May 2011
- Print publication:
- 24 March 2011, pp 293-338
-
- Chapter
- Export citation
-
Summary
Abstract
Registration of multiple source imagery is one of the most important issues when dealing with Earth science remote sensing data where information from multiple sensors exhibiting various resolutions must be integrated. Issues ranging from different sensor geometries, different spectral responses, to various illumination conditions, various seasons and various amounts of noise, need to be dealt with when designing a new image registration algorithm. This chapter represents a first attempt at characterizing a framework that addresses these issues, in which possible choices for the three components of any registration algorithm are validated and combined to provide different registration algorithms. A few of these algorithms were tested on three different types of datasets – synthetic, multitemporal and multispectral. This chapter presents the results of these experiments and introduces a prototype registration toolbox.
Introduction
In Chapter 1, we showed how the analysis of Earth science data for applications, such as the study of global environmental changes, involves the comparison, fusion, and integration of multiple types of remotely sensed data at various temporal, spectral, and spatial resolutions. For such applications, the first required step is fast and automatic image registration which can provide precision correction of satellite imagery, band-to-band calibration, and data reduction for ease of transmission. Furthermore, future decision support systems, intelligent sensors and adaptive constellations will rely on real- or near-real-time interpretation of Earth observation data, performed both onboard and at ground-based stations.
6 - Image registration using mutual information
- from PART II - Similarity Metrics for Image Registration
-
- By Arlene A. Cole-Rhodes, Morgan State University, Maryland, Pramod K. Varshney, Syracuse University, New York
- Edited by Jacqueline Le Moigne, NASA-Goddard Space Flight Center, Nathan S. Netanyahu, Roger D. Eastman, Loyola University Maryland
-
- Book:
- Image Registration for Remote Sensing
- Published online:
- 03 May 2011
- Print publication:
- 24 March 2011, pp 131-150
-
- Chapter
- Export citation
-
Summary
Abstract
This chapter provides an overview of the use of mutual information (MI) as a similarity measure for the registration of multisensor remote sensing images. MI has been known for some time to be effective for the registration of monomodal, as well as multimodal images in medical applications. However, its use in remote sensing applications has only been explored more recently. Like correlation, MI-based registration is an area-based method. It does not require any preprocessing, which allows the registration to be fully automated. The MI approach is based on principles of information theory. Specifically, it provides a measure of the amount of information that one variable contains about the other. In registration, we are concerned with maximizing the dependency of a pair of images. In this context, we discuss the computation of mutual information and various key issues concerning its evaluation and implementation. These issues include the estimation of the probability density function and computation of the joint histogram, normalization of MI, and use of different types of interpolation, search and optimization techniques for finding the parameters of the registration transformation (including multiresolution approaches).
Introduction
In this chapter, we discuss the application of mutual information (MI) as a similarity metric for cross-registering images produced by different imaging sensors. These images may be from different sources taken at different times and may be produced at different spectral frequencies and/or at different spatial resolutions.