J
Jacqueline Le Moigne
Researcher at Goddard Space Flight Center
Publications - 66
Citations - 1173
Jacqueline Le Moigne is an academic researcher from Goddard Space Flight Center. The author has contributed to research in topics: Image registration & Wavelet. The author has an hindex of 15, co-authored 66 publications receiving 1049 citations. Previous affiliations of Jacqueline Le Moigne include Universities Space Research Association & National Institute of Advanced Industrial Science and Technology.
Papers
More filters
Journal ArticleDOI
A fast implementation of the isodata clustering algorithm
Nargess Memarsadeghi,Nargess Memarsadeghi,David M. Mount,Nathan S. Netanyahu,Nathan S. Netanyahu,Jacqueline Le Moigne +5 more
TL;DR: A more efficient approach to ISODATA clustering is presented, which achieves better running times by storing the points in a kd-tree and through a modification of the way in which the algorithm estimates the dispersion of each cluster.
Journal ArticleDOI
Efficient algorithms for robust feature matching
TL;DR: This paper presents two algorithmic approaches to the point matching problem, in an attempt to reduce its computational complexity, while still providing a guarantee of the quality of the final match.
BookDOI
Image registration for remote sensing
TL;DR: A survey of image registration methods for remote sensing can be found in this article, where the authors discuss the importance of registration in remote sensing and their application in the field of image validation.
Proceedings ArticleDOI
Parallel registration of multisensor remotely sensed imagery using wavelet coefficients
TL;DR: In this article, a parallel implementation of decomposition and reconstruction by wavelet transforms has been developed on a single-instruction multiple-data (SIMD) massively parallel computer, the MasPar MP-1.
Journal ArticleDOI
Automatic Image Registration of Multimodal Remotely Sensed Data With Global Shearlet Features
TL;DR: This work integrates the recently developed mathematical construction of shearlets, which is more effective at identifying sparse anisotropic edges, with an existing automatic wavelet-based registration algorithm, and shows an improved robustness to initial conditions, when compared with wavelet features alone.