Target detection in hyperspectral imaging combining replacement and additive models

Vincent, François; Besson, Olivier

doi:10.1016/j.sigpro.2021.108212

Cited by 6 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to notice that this problem is not a classical detection one, as the background power is different under the two hypotheses (background-only versus target-plus-background). Recent efforts for the development of detectors based on the replacement model can be found in [12], [13]. In [12], the analogous of Kelly's Generalized Likelihood Ratio Test (GLRT) [14] for the replacement model, namely the Adaptive Cell Under Test Estimator (ACUTE), is derived, allowing for the detection of small targets with adaptivity with respect to the background abundance estimated in the PUT.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multiple Sub-Pixel Target Detection for Hyperspectral Imaging Systems

Addabbo

Fiscante

Giunta

et al. 2023

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

Hyperspectral target detection is a task of primary importance in remote sensing since it allows for location and discrimination of target features. To this end, the reflectance maps, which contain the spectral signatures and related abundances of the materials in the observed scene, are often used. However, due to the low spatial resolution of most hyperspectral sensors, targets occupy a fraction of the pixel and, hence, the spectra of different sub-pixel targets (including the background spectrum) are mixed together within the same pixel. To solve this issue, in this paper, we adopt a generalized replacement model accounting for multiple sub-pixel target spectra and formulate the detection problem at hand as a binary hypothesis test where under the alternative hypothesis the target is modeled in terms of a linear combination of endmembers whose coefficients also account for the presence of the background. Then, we devise detection architectures based upon the generalized likelihood ratio test where the unknown parameters are suitably estimated through procedures inspired by the maximum likelihood approach. The performances of the proposed decision schemes are evaluated by means of both synthetic as well as real data and compared with an analogous counterpart by showing the effectiveness of the proposed procedure.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multiple Sub-Pixel Target Detection for Hyperspectral Imaging Systems

Addabbo

Fiscante

Giunta

et al. 2023

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

show abstract

“…It is important to notice that this problem is not a classical detection one, as the background power is different under the two hypotheses (background-only versus target-plusbackground). Recent efforts for the development of detectors based on the replacement model can be found in [12], [13]. In [12], the analogous of Kelly's Generalized Likelihood Ratio Test (GLRT) [14] for the replacement model, namely the Adaptive Cell Under Test Estimator (ACUTE), is derived, allowing for the detection of small targets with adaptivity with respect to the background abundance estimated in the PUT.…”

Section: Introductionmentioning

confidence: 99%

“…In [12], the analogous of Kelly's Generalized Likelihood Ratio Test (GLRT) [14] for the replacement model, namely the Adaptive Cell Under Test Estimator (ACUTE), is derived, allowing for the detection of small targets with adaptivity with respect to the background abundance estimated in the PUT. A modified version of the replacement model is developed in [13], where the GLRT is derived in the presence of a residual additive noise. However, since in the hyperspectral sensors the spectra of different sub-pixel targets are mixed together with the background spectrum, a generalized replacement model is proposed in this paper, where the sum of the total amount of both multiple sub-pixel targets and background spectra is equal to one, as explained ahead.…”

Section: Introductionmentioning

confidence: 99%

Multiple Sub-Pixel Target Detection for Hyperspectral Imaging Systems

Addabbo¹,

Fiscante²,

Guerra³

et al. 2023

Preprint

View full text Add to dashboard Cite

Hyperspectral target detection is a task of primary importance in remote sensing since it allows identification, location, and discrimination of target features. To this end, the reflectance maps, which contain the spectral signatures and related abundances of the materials in the observed scene, are often used. However, due to the low spatial resolution of most hyperspectral sensors, targets occupy a fraction of the pixel and, hence, the spectra of different sub-pixel targets (including the background spectrum) are mixed together within the same pixel. To solve this issue, in this paper, we adopt a generalized replacement model accounting for multiple sub-pixel target spectra and formulate the detection problem at hand as a binary hypothesis test where under the alternative hypothesis the target is modeled in terms of a linear combination of endmembers whose coefficients also account for the presence of the background. Then, we devise detection architectures based upon the generalized likelihood ratio test where the unknown parameters are suitably estimated through procedures inspired by the maximum likelihood approach. The performances of the proposed decision schemes are evaluated by means of both synthetic as well as real data and compared with an analogous counterpart by showing the effectiveness of the proposed procedure.

show abstract