We investigate the relationship among several popular end-member extraction algorithms, including N-FINDR, the simplex growing algorithm (SGA), vertex component analysis (VCA), automatic target generation process (ATGP), and fully constrained least squares linear unmixing (FCLSLU). We analyze the fundamental equivalence in the searching criteria of the simplex volume maximization and pixel spectral signature similarity employed by these algorithms. We point out that their performance discrepancy comes mainly from the use of a dimensionality reduction process, a parallel or sequential implementation mode, or the imposition of certain constraints. Instructive recommendations in algorithm selection for practical applications are provided.

No abstract

This paper investigates RGB color composition schemes for hyperspectral imagery display. A three-channel composite inevitably loses a significant amount of information contained in the original high-dimensional data. The objective here is to display the useful information as distinctively as possible for high-class separability. To achieve this objective, it is important to find an effective data processing step prior to color display. A series of supervised and unsupervised data transformation and classification algorithms are reviewed, implemented, and compared for this purpose. The resulting color displays are evaluated in terms of class separability using a statistical detector and perceptual color distance. We demonstrate that the use of the data processing step can significantly improve the quality of color display, whereas data classification generally outperforms data transformation, although the implementation is more complicated. Several instructive suggestions for practitioners are provided.

Airborne remote sensing has important applications in agriculture monitoring because of the flexibility of system deployment. The major obstacle in practical use is its high cost. To reduce the cost, a multispectral system can be assembled by using individual cameras onboard a small aerial platform, such as a miniature unmanned aerial vehicle (mini-UAV). In such a case, the cameras may have shifting and rotational misalignment, even after careful adjustment. Contiguous frames are captured as the platform flies. So multi-band registration within a single frame and frame-toframe mosaicking are necessary to obtain a co-registered multispectral image for the entire monitoring area before any commercial product can be generated to support practical decision-making. In this paper, we present automatic algorithms to achieve this goal. These algorithms are particularly useful to the image scenes where no distinctive features are available. Both automatic and manual evaluations confirm the effectiveness of the developed algorithms in multi-sensor data fusion for overall flat terrain without distinctive features.

No abstract