Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Signal Processing
Learning Set Representations For Lwir In-Scene Atmospheric Compensation, Nicholas M. Westing [*], Kevin C. Gross, Brett J. Borghetti, Jacob A. Martin, Joseph Meola
Learning Set Representations For Lwir In-Scene Atmospheric Compensation, Nicholas M. Westing [*], Kevin C. Gross, Brett J. Borghetti, Jacob A. Martin, Joseph Meola
Faculty Publications
Atmospheric compensation of long-wave infrared (LWIR) hyperspectral imagery is investigated in this article using set representations learned by a neural network. This approach relies on synthetic at-sensor radiance data derived from collected radiosondes and a diverse database of measured emissivity spectra sampled at a range of surface temperatures. The network loss function relies on LWIR radiative transfer equations to update model parameters. Atmospheric predictions are made on a set of diverse pixels extracted from the scene, without knowledge of blackbody pixels or pixel temperatures. The network architecture utilizes permutation-invariant layers to predict a set representation, similar to the work performed …
Non-Gnss Smartphone Pedestrian Navigation Using Barometric Elevation And Digital Map-Matching, Daniel Broyles, Kyle J. Kauffman, John F. Raquet, Piotr Smagowski
Non-Gnss Smartphone Pedestrian Navigation Using Barometric Elevation And Digital Map-Matching, Daniel Broyles, Kyle J. Kauffman, John F. Raquet, Piotr Smagowski
Faculty Publications
Pedestrian navigation in outdoor environments where global navigation satellite systems (GNSS) are unavailable is a challenging problem. Existing technologies that have attempted to address this problemoften require external reference signals or specialized hardware, the extra size,weight, power, and cost of which are unsuitable for many applications. This article presents a real-time, self-contained outdoor navigation application that uses only the existing sensors on a smartphone in conjunction with a preloaded digital elevation map. The core algorithm implements a particle filter, which fuses sensor data with a stochastic pedestrian motion model to predict the user’s position. The smartphone’s barometric elevation is then …