Anomaly detection and classification for hyperspectral imagery

By Chein-I. Chang, Shao-Shan Chiang. IEEE Transactions on Geoscience and Remote Sensing, 2002

530 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Atmospheric Science, Media Technology

View Paper: https://www.semanticscholar.org/paper/d000e714aba108ee6d4572d4e4013ad4364053ba

How researchers see this paper

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

In Artificial Intelligence

1. Qian Du
2. Wei Li
3. Nasser M. Nasrabadi
4. James E. Fowler
5. Heesung Kwon
6. Chein-I. Chang
7. Antonio J. Plaza

In Atmospheric Science

1. Qian Du
2. Wei Li
3. Nasser M. Nasrabadi
4. Heesung Kwon
5. James E. Fowler
6. Chein-I. Chang
7. Antonio J. Plaza
8. José M. Bioucas-Dias

In Media Technology

1. Qian Du
2. Wei Li
3. Chein-I. Chang
4. Nasser M. Nasrabadi
5. Heesung Kwon
6. James E. Fowler
7. Antonio J. Plaza
8. Thomas L. Ainsworth

Citations in the corpus

• Kernel RX-algorithm: a nonlinear anomaly detector for hyperspectral imagery (2005, methodology): “This algorithm is now commonly referred to as the RX anomaly detector which has been successfully applied to many hyperspectral target detection applications [8], [12], [14].”
• Hyperspectral Imaging (2003, methodology): “Unfortunately, as shown in Chang et al. (1998b), the TSP classifier created an additional bias, which requires the complete knowledge of target signatures in the undesired target signature matrix U.”
• Exploiting manifold geometry in hyperspectral imagery (2005, background): “Therefore, one other commonly used metric, the Mahalanobis distance, which is frequently applied in classification and detection problems in hyperspectral imagery analysis [16], cannot be applied in the context that is often used.”
• Hyperspectral Image Compression Using JPEG2000 and Principal Component Analysis (2007, methodology): “The well-known RX algorithm is employed for anomaly detection [7].”
• Hyperspectral Anomaly Detection With Attribute and Edge-Preserving Filters (2017, unknown): “importance in military and civilian applications [4]–[6].”
• An Effective Evaluation Tool for Hyperspectral Target Detection: 3D Receiver Operating Characteristic Curve Analysis (2021, methodology): “by Reed and Yu [33], referred to as RX-AD in this article and R-AD in [29] which was originally referred to as R-RXD in [34].”
• Collaborative Representation for Hyperspectral Anomaly Detection (2015, methodology): “The representation-based methods (and their acronyms) investigated in the experiments are summarized as follows: 1) representation without 1-norm or 2-norm minimization as RD; 2) representation with 2-norm minimization as CRD; 3) representation with 2-norm minimization and distance- weighted…”