Automatic spectral target recognition in hyperspectral imagery

By Hsuan Ren, Chein-I. Chang. 2003

471 citations recorded by the source corpus.

Subfields: Atmospheric Science, Media Technology

View Paper: https://www.semanticscholar.org/paper/d8a3681f4eb1730ddc22c8f22ca44ef80c647d8a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Media Technology

Citations in the corpus

The Why and How of Nonnegative Matrix Factorization (2014, methodology): “SPA is closely related to several endmember extraction algorithms; in particular N-FINDR [108] and its variants, the automatic target generation process (ATGP) [99], and the successive volume maximization algorithm (SVMAX) [21]; see the discussion in [90] for more details.”
Similarity-Based Unsupervised Band Selection for Hyperspectral Image Analysis (2008, methodology): “The OSP-based band selection is the same as the one for endmember extraction algorithm in [11].”
A Signal Processing Perspective on Hyperspectral Unmixing: Insights from Remote Sensing (2014, methodology): “Later, a very similar algorithm, called the automatic target generation process (ATGP), was proposed by Ren and Chang in 2003 in remote sensing [19].”
A fast iterative algorithm for implementation of pixel purity index (2006, methodology): “3 shows the final 22 endmember pixels extracted by the PPI and the 17 endmember pixels extracted by the FIPPI where “ ” rather than “ ” was used to indicate that the ATGP-generated pixels were target pixels, not necessarily endmember pixels.”
Sparse Unmixing of Hyperspectral Data (2011, methodology): “Among the endmember extraction algorithms working under this regime, we can list some popular approaches such as the pixel purity index [11], N-FINDR [12], orthogonal subspace projection technique in [13], and vertex component analysis (VCA) [14].”
Constrained band selection for hyperspectral imagery (2006, methodology): “Since it must be performed unsupervisedly, an unsupervised algorithm which was proved to be effective, the automatic target generation process (ATGP) developed in [6], [17] was used to generate nine target pixels directly from the original image with full bands shown in Fig.”
Estimation of number of spectrally distinct signal sources in hyperspectral imagery (2004, methodology): “So, if we further applied the automatic target detection and classification (ATDCA) proposed in [26] to the AVIRIS scene, it required nine target signatures to separate the rhyolite from cinders.”
Independent component analysis-based dimensionality reduction with applications in hyperspectral image analysis (2006, methodology): “An algorithm proposed to be used in the ICA-DR3 to generate a set of initial projector unit vectors is called automatic target generation process (ATGP) which is derived from the automatic target detection and classification algorithm in [4] and [17].”
GETNET: A General End-to-End 2-D CNN Framework for Hyperspectral Image Change Detection (2019, methodology): “In this work, automatic target generation process (ATGP) [29] is adopted to ﬁnd potential target endmembers.”
Hyperspectral and LiDAR Data Fusion: Outcome of the 2013 GRSS Data Fusion Contest (2014, methodology): “The " FE " module applies blind unmixing using Automatic Target Generation Procedure [46] to extract endmembers.”