While deep learning technologies for computer vision have developed rapidly since 2012, modeling of remote sensing systems has remained focused around human vision. In particular, remote sensing systems are usually constructed to optimize sensing cost-quality tradeoffs with respect to human image interpretability. While some recent studies have explored remote sensing system design as a function of simple computer vision algorithm performance, there has been little work relating this design to the state of the art in computer vision: deep learning with convolutional neural networks. We develop experimental systems to conduct this analysis, showing results with modern deep learning algorithms and recent overhead image data. Our results are compared to standard image quality measurements based on human visual perception, and we conclude not only that machine and human interpretability differ significantly but also that computer vision performance is largely self-consistent across a range of disparate conditions. This paper is presented as a cornerstone for a new generation of sensor design systems that focus on computer algorithm performance instead of human visual perception.

An underground nuclear explosion (UNE) can generate a shock wave that lofts surface material, resulting in surface changes that might be detectable. The Comprehensive Nuclear Test-Ban Treaty (CTBT) allows ground and airborne spectral and thermal imaging to help locate such events. Landsat 5 data on the 1998 Indian and Pakistani tests are used here to demonstrate that there are detectable changes in surface features which might be used to localize an underground nuclear test and to develop change detection techniques specific to the use of satellite data to support a CTBT on-site inspection. Landsat 5 has been active for over 20 years providing repeat coverage of the Earth's surface every 16 days. Most locations have Landsat data available for a variety of dates, allowing for statistical analysis of the data to understand temporal trends and data variability on a pixel-by-pixel basis. Given the right conditions, these usual patterns of change (such as seasonal changes or weathering) can be discerned from unusual patterns of change, such as features relating to a UNE. This paper extends known change detection techniques to a temporal series of data and shows that multispectral change detection can be used to help localize a UNE.

No abstract

No abstract

Multispectral imaging can offer many benefits in cost, complexity, resolution, size, weight, and power, relative to hyperspectral imaging. When designing a multispectral system, spectral bandpasses can be selected using optimization algorithms configured to maximally separate target detection scores between target and background regions. A hyperspectral image (HSI) can serve as the source of data from which band groupings can be tested for optimality. The output of an adaptive cosine estimator target detection algorithm is used in an objective function. Three optimization algorithms are compared: particle swarm, dual annealing, and differential evolution. A global optimum is also found using a brute force approach on the Livermore Computing Syrah supercomputer. Three materials are investigated: calcite, gypsum, and limestone. This is done for 3-, 4-, and 5-band systems. The data originate from a longwave infrared HSI of a material display board. The optimization algorithms were run 30 times for every scenario. Performance statistics (maximum, minimum, mean, standard deviation, and median) based on the separation values are given. Additional characterization was performed using receiver operator characteristic (ROC) curves and the area under the ROC curve. While good performance was obtained for the three optimization algorithms, the dual annealing algorithm produced the highest and most consistent detection separation scores on average. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.