Kent, United Kingdom
Kent, United Kingdom
SEARCH FILTERS
Time filter
Source Type

Braun T.R.,Drive Intelligence
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2010

Image processing applications typically parallelize well. This gives a developer interested in data throughput several different implementation options, including multiprocessor machines, general purpose computation on the graphics processor, and custom gate-array designs. Herein, we will investigate these first two options for dictionary learning and sparse reconstruction, specifically focusing on the K-SVD algorithm for dictionary learning and the Batch Orthogonal Matching Pursuit for sparse reconstruction. These methods have been shown to provide state of the art results for image denoising, classification, and object recognition. We'll explore the GPU implementation and show that GPUs are not significantly better or worse than CPUs for this application. © 2010 SPIE.


Hwangbo J.,Drive Intelligence
American Society for Photogrammetry and Remote Sensing Annual Conference 2012, ASPRS 2012 | Year: 2012

We present Visual Intelligence Iris One™ Stereo System designed to achieve the performance of the film aerial cameras. The patented ARCA™ design uses synchronously operating camera module heads to form a single virtual central-perspective image. The geometric accuracy of ARCA system is achieved from laboratory calibration as well as calibration flight. First, each camera module head is calibrated to define the camera module model. Then, the entire ARCA arrays are calibrated to obtain the relative position and orientation of the camera modules. After the laboratory calibration, a single Virtual Frame image is formed. The residual of calibration of a single camera module head and the Virtual Frame is less than 1 μm. One of the coveted advantages of the film camera is the ability to achieve 0.6 B/H ratio for engineering-quality precision mapping. Designed with the long along-track footprint, the Iris One Stereo system can achieve the B/H ratio of about 0.6. The geometric accuracy of Iris One Stereo System is obtained by examining the image residuals from aerial triangulation of a test flight.


Greer J.B.,Drive Intelligence | Flake J.C.,Booz Allen Hamilton
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2013

The emerging field of Compressive Sensing (CS) provides a new way to capture data by shifting the heaviest burden of data collection from the sensor to the computer on the user-end. This new means of sensing requires fewer measurements for a given amount of information than traditional sensors. We investigate the efficacy of CS for capturing HyperSpectral Imagery (HSI) remotely. We also introduce a new family of algorithms for constructing HSI from CS measurements with Split Bregman Iteration [Goldstein and Osher,2009]. These algorithms combine spatial Total Variation (TV) with smoothing in the spectral dimension. We examine models for three different CS sensors: The Coded Aperture Snapshot Spectral Imager-Single Disperser (CASSI-SD) [Wagadarikar et al.,2008] and Dual Disperser (CASSI-DD) [Gehm et al.,2007] cameras, and a hypothetical random sensing model closer to CS theory, but not necessarily implementable with existing technology. We simulate the capture of remotely sensed images by applying the sensor forward models to well-known HSI scenes - An AVIRIS image of Cuprite, Nevada and the HYMAP Urban image. To measure accuracy of the CS models, we compare the scenes constructed with our new algorithm to the original AVIRIS and HYMAP cubes. The results demonstrate the possibility of accurately sensing HSI remotely with significantly fewer measurements than standard hyperspectral cameras. © 2013 SPIE.


Tang J.,Drive Intelligence
Current Genomics | Year: 2011

Microbial metabolomics constitutes an integrated component of systems biology. By studying the complete set of metabolites within a microorganism and monitoring the global outcome of interactions between its development processes and the environment, metabolomics can potentially provide a more accurate snap shot of the actual physiological state of the cell. Recent advancement of technologies and post-genomic developments enable the study and analysis of metabolome. This unique contribution resulted in many scientific disciplines incorporating metabolomics as one of their "omics" platforms. This review focuses on metabolomics in microorganisms and utilizes selected topics to illustrate its impact on the understanding of systems microbiology. © 2011 Bentham Science Publishers.


Kalukin A.,Drive Intelligence
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2015

Factors that degrade image quality in video and other sensor collections, such as noise, blurring, and poor resolution, also affect the spatial power spectrum of imagery. Prior research in human vision and image science from the last few decades has shown that the image power spectrum can be useful for assessing the quality of static images. The research in this article explores the possibility of using the image power spectrum to automatically evaluate full-motion video (FMV) imagery frame by frame. This procedure makes it possible to identify anomalous images and scene changes, and to keep track of gradual changes in quality as collection progresses. This article will describe a method to apply power spectral image quality metrics for images subjected to simulated blurring, blocking, and noise. As a preliminary test on videos from multiple sources, image quality measurements for image frames from 185 videos are compared to analyst ratings based on ground sampling distance. The goal of the research is to develop an automated system for tracking image quality during real-time collection, and to assign ratings to video clips for long-term storage, calibrated to standards such as the National Imagery Interpretability Rating System (NIIRS). © 2015 SPIE.


Grossman S.,Drive Intelligence
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2015

Since the events of September 11, 2001, the intelligence focus has moved from large order-of-battle targets to small targets of opportunity. Additionally, the business community has discovered the use of remotely sensed data to anticipate demand and derive data on their competition. This requires the finer spectral and spatial fidelity now available to recognize those targets. This work hypothesizes that directed searches using calibrated data perform at least as well as inscene manually intensive target detection searches. It uses calibrated Worldview-2 multispectral images with NEF generated signatures and standard detection algorithms to compare bespoke directed search capabilities against ENVI™ in-scene search capabilities. Multiple execution runs are performed at increasing thresholds to generate detection rates. These rates are plotted and statistically analyzed. While individual head-to-head comparison results vary, 88% of the directed searches performed at least as well as in-scene searches with 50% clearly outperforming in-scene methods. The results strongly support the premise that directed searches perform at least as well as comparable in-scene searches. © 2015 SPIE.


Defibaugh y Chavez J.,Drive Intelligence | Tullis J.A.,University of Arkansas
Remote Sensing | Year: 2013

Coverage and frequency of remotely sensed forest structural information would benefit from single orbital platforms designed to collect sufficient data. We evaluated forest structural information content using single-date Hyperion hyperspectral imagery collected over full-canopy oak-hickory forests in the Ozark National Forest, Arkansas, USA. Hyperion spectral derivatives were used to develop machine learning regression tree rule sets for predicting forest neighborhood percentile heights generated from near-coincident Leica Geosystems ALS50 small footprint light detection and ranging (LIDAR). The most successful spectral predictors of LIDAR-derived forest structure were also tested with basal area measured in situ. Based on the machine learning regression trees developed, Hyperion spectral derivatives were utilized to predict LIDAR forest neighborhood percentile heights with accuracies between 2.1 and 3.7 m RMSE. Understory predictions consistently resulted in the highest accuracy of 2.1 m RMSE. In contrast, hyperspectral prediction of basal area measured in situ was only found to be 6.5m2/ha RMSE when the average basal area across the study area was ~12m2/ha. The results suggest, at a spatial resolution of 30 × 30 m, that orbital hyperspectral imagery alone can provide useful structural information related to vegetation height. Rapidly calibrated biophysical remote sensing techniques will facilitate timely assessment of regional forest conditions. © 2013 by the authors.


Grossman S.,Drive Intelligence
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2015

Target detection is the act of isolating objects of interest from the surrounding clutter, generally using some form of test to include objects in the found class. However, the method of determining the threshold is overlooked relying on manual determination either through empirical observation or guesswork. The question remains: how does an analyst identify the detection threshold that will produce the optimum results? This work proposes the concept of a target detection sweet spot where the missed detection probability curve crosses the false detection curve; this represents the point at which missed detects are traded for false detects in order to effect positive or negative changes in the detection probability. ROC curves are used to characterize detection probabilities and false alarm rates based on empirically derived data. It identifies the relationship between the empirically derived results and the first moment statistic of the histogram of the pixel target value data and then proposes a new method of applying the histogram results in an automated fashion to predict the target detection sweet spot at which to begin automated target detection. © 2015 SPIE.


Rice K.E.,Drive Intelligence
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2013

This paper describes the role that the National Geospatial Intelligence Agency (NGA) has in motion imagery research and development (R&D). Motion imagery R&D is ubiquitous. Commercial technology is strongly leveraged by the Department of Defense (DoD) and each component in DoD has unique needs that they invest R&D dollars against. DoD Directive 5106.601 gives NGA full responsibility for geospatial intelligence (GEOINT), including a wide range of R&D functions. InnoVision, NGA's R&D component has specific areas of focus for motion imagery R&D that are designed to complement and enhance service and industry efforts. © 2013 SPIE.


Loading Drive Intelligence collaborators
Loading Drive Intelligence collaborators