Abstract: Context-based unmixing has been studied by several researchers. Recent techniques, such as piece-wise convex unmixing using fuzzy and possibilistic clustering or Bayesian methods proposed in [11] attempt to form contexts via clustering. It is assumed that the linear mixing… Read More
Conference PapersConference Papers
Extended functions of multiple instances for target characterization
Abstract: An extension of the Function of Multiple Instances (FUMI) algorithm for target characterization is presented. FUMI is a generalization of Multiple Instance Learning (MIL). However, FUMI differs significantly from standard MIL and supervised learning approaches because only data points… Read More
Unmixing using a combined microscopic and macroscopic mixture model with distinct endmembers
Abstract: Much work in the study of hyperspectral imagery has focused on macroscopic mixtures and unmixing via the linear mixing model. A substantially different approach seeks to model hyperspectral data non-linearly in order to accurately describe intimate or microscopic relationships… Read More
Sand ripple characterization using an extended synthetic aperture sonar model and MCMC sampling methods
Abstract: Side-look synthetic aperture sonar (SAS) can produce very high quality images of the sea-floor. The aim of this work is to develop a hierarchical Bayesian framework for estimating sand ripple characteristics from SAS imagery that can make use of… Read More
Subpixel target detection in hyperspectral imagery using piece-wise convex spatial-spectral unmixing, possibilistic and fuzzy clustering, and co-registered LiDAR
Abstract: A new algorithm for subpixel target detection in hyperspectral imagery is proposed which uses the PFCM-FLICM-PCE algorithm to model and estimate the parameters of the image background. This method uses the piece-wise convex mixing model with spatial-spectral constraints, and… Read More
Simultaneous band-weighting and spectral unmixing for multiple endmember sets
Abstract: In this paper, the SimUltaneous Band-weighting and Spectral Unmixing for Multiple Endmember Sets (SUBSUME) which performs endmember extraction for multiple sets of endmembers, estimates proportion values, and assigns partition-specific band weights is presented. By incorporating simultaneous band weighting, input… Read More
Multi-Image texton selection for sonar image seabed co-segmentation
Abstract: In this paper we describe an unsupervised approach to seabed co-segmentation over the multiple sonar images collected in sonar surveys. We adapt a traditional single image segmentation texton-based approach to the sonar survey task by modifying the texture extraction… Read More
Landmine classification using possibilistic K-nearest neighbors with wideband electromagnetic induction data
Abstract: A possibilistic K-Nearest Neighbors classifier is presented to classify mine and non-mine objects using data collected from a wideband electromagnetic induction (WEMI) sensor. The proposed classifier is motivated by the observation that buried objects often have consistent signatures depending… Read More
Spectral unmixing using the beta compositional model
Abstract: This paper introduces a beta compositional model as a mixing model for hyperspectral images. Endmembers are represented via beta distributions, hereafter referred to as betas, to constrain endmembers to a physically-meaningful range. Two associated spectral unmixing algorithms are described… Read More
A framework for computing crowd emotions using agent based modeling
Abstract: We present a computational framework for modeling geospatial dynamics of crowd emotions as part of anticipatory analysis. The framework is based on agent based modeling (ABM) and evaluation-activation space for emotion representation. ABM is a simulation technique that uses… Read More