2011
DOI: 10.1109/tgrs.2010.2076288
|View full text |Cite
|
Sign up to set email alerts
|

Improvement of Target-Detection Algorithms Based on Adaptive Three-Dimensional Filtering

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
8
0

Year Published

2013
2013
2021
2021

Publication Types

Select...
6
3

Relationship

1
8

Authors

Journals

citations
Cited by 41 publications
(8 citation statements)
references
References 57 publications
0
8
0
Order By: Relevance
“…Akçay and Aksoy [12] presented a geospatial object detection method by using hierarchical segmentation which combined spectral and structural information. Recently, there are also some methods concentrating on detecting objects in synthetic aperture radar (SAR) image [13, 14] and hyperspectral image [15, 16]. …”
Section: Introductionmentioning
confidence: 99%
“…Akçay and Aksoy [12] presented a geospatial object detection method by using hierarchical segmentation which combined spectral and structural information. Recently, there are also some methods concentrating on detecting objects in synthetic aperture radar (SAR) image [13, 14] and hyperspectral image [15, 16]. …”
Section: Introductionmentioning
confidence: 99%
“…The noise variance in each band of HSI is not constant, in particular, there exist some bands at which the atmosphere absorbs so much light that the signal received from the surface is unreliable. Although the SD noise has become as dominant as the SI noise in HSI data collected by new-generation hyperspectral sensors due to the improved sensitivity in the electronic components [2,3,4,5,6,7]. For this the denoising methods for those two types of noise are not the same.…”
Section: Introductionmentioning
confidence: 99%
“…Instead of processing the HSI in a band-by-band manner, researchers have paid much attention to consider the HSI as a whole entity and develop various multidimensional image restoration techniques [15]- [17]. Typically, multidimensional Wiener filtering (MWF) extends the classical 2-D Wiener filtering to the tensor model by using multilinear algebra tools [15].…”
Section: Introductionmentioning
confidence: 99%
“…However, annoying artifacts and oversmooth effects will be introduced by the MWF method in the case that signal subspace and noise subspace are difficult to be distinguished [18]. In addition, there are some more advanced multidimensional methods, including the genetic kernel Tucker decomposition [16] and adaptive 3-D filtering [17]. Since all the abundant signals (containing a large number of relative pixels) and the rare signals (containing only a few relative pixels) are processed together, these multidimensional methods easily lead the rare signals to be unexpectedly removed [19].…”
Section: Introductionmentioning
confidence: 99%