Algorithms for Multispectral and Hyperspectral Image Analysis
1US Army Research Laboratory, Adelphi, MD, USA
2Wake Forest University, Winston-Salem, NC, USA
3Space and Remote Sensing Sciences Group, Los Alamos National Laboratory, Los Alamos, NM, USA
4University of Missouri, Columbia, MO, USA
Algorithms for Multispectral and Hyperspectral Image Analysis
Description
Recent advances in multispectral and hyperspectral sensing technologies coupled with rapid growth in computing power have led to new opportunities in remote sensing—higher spatial and/or spectral resolution over broader areas leads to more accurate and comprehensive land cover mapping and more sensitive target detection. But these large volumes of data provide new challenges as well. The need for timely processing of this data creates a tension between simplicity and sophistication of algorithms and motivates the development of parallel algorithms and specialized hardware. Critical issues in the analysis of multispectral and hyperspectral data include sensor noise and nonlinearities, atmospheric distortion and interference, characterization of target signatures and variability of background clutter, combination of spatial and spectral features, and the balance of statistical and physical modeling.
Despite a plethora of hyperspectral algorithms developed over the last decade, most of these issues still remain. Accordingly, the development of robust and accurate modeling and analysis of multispectral and hyperspectral imagery are essential for advancing the quality of information retrieval from a remote sensor or suite of sensors. This special issue aims to advance the capabilities of algorithms and analysis technologies for this imagery by addressing these critical issues.
Investigators are invited to submit their original contributions that can address the current multispectral and hyperspectral signal processing issues. Timely review papers will also be considered. Potential topics include, but are not limited to:
- Novel algorithms for supervised classification
- Semisupervised classification and rare category detection
- Anomaly detection, unsupervised classification, segmentation, and clustering
- Dimensionality reduction
- Material detection, identification, and quantitation
- Physics-based modeling
- Sensor fusion
- Spectral unmixing, endmember extraction
- Spatiospectral feature extraction
- Fast implementation of multispectral and hyperspectral algorithms
- Compressive sensing (and reconstruction) of multispectral/hyperspectral data
- Signal processing directly on compressively sensed hyperspectral data
Before submission authors should carefully read over the journal's Author Guidelines, which are located at http://www.hindawi.com/journals/jece/guidelines/. Prospective authors should submit an electronic copy of their complete manuscript through the journal Manuscript Tracking System at http://mts.hindawi.com/ according to the following timetable: