Torres Madroñero, Maria C.
Loading...
2 results
Publication Search Results
Now showing 1 - 2 of 2
Publication Development of the hyperspectral coastal image analysis toolbox (hyciat) with a focus on hyperspectral and lidar data fusion(2008) Torres Madroñero, Maria C.; Vélez Reyes, Miguel; College of Engineering; Hunt, Shawn D.; Goodman, James; Department of Electrical and Computer Engineering; González Quevedo, Antonio A.The Hyperspectral Coastal Image Analysis Toolbox integrates algorithms for the estimation of water optical properties, bathymetry and fractional abundances of bottom composition in a graphical interface using Matlab to perform analysis of hyperspectral images of shallow waters. The primary algorithms included in the toolbox were previously developed by students and faculty at LARSIP at University of Puerto Rico at Mayagu ̈ez. Work was also performed to add new capabilities to these existing algorithms by incorporating the capacity to fuse lidar data into the hyperspectral processing. The HyCIAT algorithms are fundamentally based on the Lee et al. [1] semi-analytical inversion model combined with linear unmixing techniques developed by Goodman [2] and Castrodad [3]. The Lee algorithm is one of the more commonly used models for the estimation of water optical properties and bathymetry from passive hyperspectral imagery. Goodman integrated the Lee model with unmixing algorithms (LIGU) to first independently derive estimates of water properties and bathymetry, and then derive the habitat composition. Castrodad similarly combined the Lee model with an unmixing algorithm (CIUB), but this derives the water properties, bathymetry and habitat composition simultaneously. Both these techniques are included in HyCIAT as well as new capabilities for both models that allow lidar bathymetry to be used as input. This work presents the HyCIAT toolbox, and evaluates model performance using both simulated data and actual airborne hyperspectral imagery. Results indicate that accuracy in parameter retrieval is increased when the lidar data is included in the models.Publication Unsupervised unmixing analysis based on multiscale representation(2013) Torres Madroñero, Maria C.; Hunt, Shawn D.; College of Engineering; Velez Reyes, Miguel; Santiago, Nayda G.; Goodman, James; Department of Electrical and Computer Engineering; Pares Matos, Elsie I.Unsupervised unmixing analysis aims to extract the basic materials, the so called endmembers, and their abundances from a hyperspectral image. Unmixing is usually performed by pixels-only techniques that do not take into account the spatial information and generally require a priori estimate of the number of endmembers. Recently, several spatial-spectral unmixing techniques have been developed. However, most of these techniques depend of spatial kernels or windows to include the spatial information in the unmixing analysis. In this work, a new unmixing approach based on multiscale representation is developed. The proposed technique extracts spectral signatures and spectral endmember classes from hyperspectral imagery in an unsupervised fashion. A multiscale representation of the hyperspectral images is obtained using nonlinear diffusion. Then, spectral endmembers are automatically identified using multigrids methods to solve the diffusion partial differential equation. The multiscale representation and multigrids allows to avoid the use of spatial kernels. Once the spectral endmembers are identified, similar spectra are clustered to build spectral endmember classes thus accounting for the spectral variability of the materials along the unmixing analysis. A comparison with other unmixing methods shows that the proposed unsupersived unmixing approach outperforms traditional spectral techniques. Capabilities of the proposed approach were validated and assessed using simulated imagery and real imagery collected with the AVIRIS and AISA sensors over different landscapes.