The purpose of this research is to jointly learn multiple classification tasks by appropriately sharing information between
similar tasks. In this setting, examples of different tasks include the discrimination of targets from non-targets by
different sonars or by the same sonar operating in sufficiently different environments. This is known as multi-task
learning (MTL) and is accomplished via a Bayesian approach whereby the learned parameters for classifiers of similar
tasks are drawn from a common prior. To learn which tasks are similar and the appropriate priors a Dirichlet process is
employed and solved using mean field variational Bayesian inference. The result is that for many real-world instances
where training data is limited MTL exhibits a significant improvement over both learning individual classifiers for each
task as well as pooling all data and training one overall classifier. The performance of this method is demonstrated on
simulated data and experimental data from multiple imaging sonars operating over multiple environments.
A constant false alarm rate (CFAR) detection algorithm and a threshold selection algorithm are adapted and developed for use in multiband-image small-target detection. While it is often difficult to predict the spectral signatures of targets, the shape of the target may be known. This detection algorithm exploits geometric target features and spectral differences between the target and the surrounding area. The detection algorithm is derived from a general statistical model of the data with most emphasis on the background. The utility of CFAR algorithms is that the selection of a detection threshold can be made independently of image intensity. However, varied applications of the algorithms show that detection values are dependent on the scene adherence to the model. Achieving a CFAR in applications is very difficult. The threshold for a desired number of false alarms fluctuates with differing backgrounds. By appropriately mapping observations to the model, an automatic threshold selection algorithm is shown. Combining the CFAR-detection algorithm with the threshold selection algorithm produces a reliable constant false alarm rate.
The Airborne Littoral Reconnaissance Technology (ALRT) program has successfully demonstrated the Wide-Field Airborne Laser Diode Array Illuminator (ALDAI-W). This illuminator is designed to illuminate a large area from the air with limited power, weight, and volume. A detection system, of which the ALDAI-W is a central portion, is capable of detecting surface-laid minefields in absolute darkness, extending the allowed mission times to night operations. This will be an overview report, giving processing results and suggested paths for additional development.
The Airborne Littoral Reconnaissance Technologies (ALRT) project has developed and tested a nighttime operational minefield detection capability using commercial off-the-shelf high-power Laser Diode Arrays (LDAs). The Coastal System Station’s ALRT project, under funding from the Office of Naval Research (ONR), has been designing, developing, integrating, and testing commercial arrays using a Cessna airborne platform over the last several years. This has led to the development of the Airborne Laser Diode Array Illuminator wide field-of-view (ALDAI-W) imaging test bed system. The ALRT project tested ALDAI-W at the Army’s Night Vision Lab’s Airborne Mine Detection Arid Test. By participating in Night Vision’s test, ALRT was able to collect initial prototype nighttime operational data using ALDAI-W, showing impressive results and pioneering the way for final test bed demonstration conducted in September 2003. This paper describes the ALDAI-W Arid Test and results, along with processing steps used to generate imagery.
This paper analyzes the performance of a fast, low complexity, integer-to-integer compression scheme that is designed to give greater importance to small targets. Practical real-time operation of unmanned aerial vehicle mine/minefield detection systems has two difficult constraints. One is limited data-link bandwidth and the other is limited on-board processing power. Standard compression techniques are usually complex and tend to remove small objects from the imagery. In the imagery used for airborne mine/minefield detection, the targets are small, usually on the order of a few pixels. The region-of-interest (ROI) Wavelet Difference Reduction (WDR) compression scheme satisfies both of these con-straints and is shown to preserve detection rates of small targets. Results are compared for block-based (BB)-WDR compressed and ROI-WDR compressed and uncompressed images. The ROI -WDR process is shown to be superior to other compression conditions.
KEYWORDS: Image registration, Video, Multispectral imaging, Simulation of CCA and DLA aggregates, Image processing, Algorithm development, Vegetation, Video processing, Cameras, Fourier transforms
Registering video imagery in real-time is a demanding process. Multispectral imagery adds complexity due to the variances between different bands. This paper demonstrates a process that registers airborne multispectral imagery at a rate of thirty frames per second. It can create both mosaics and multispectral sets from a camera that captures a cycle of spectral bands with each spectral band in a separate video frame. A series of phase correlation measurements provides subpixel accuracy. Roll, pitch and yaw variances are corrected with complex polynomial interpolation.
The Airborne Littoral Reconnaissance Technologies (ALRT) project has developed and successfully demonstrated a nighttime operational minefield detection capability using commercial off-the-shelf high-power Laser Diode Arrays (LDAs). The Coastal System Station's ALRT project, under funding from the Office of Naval Research (ONR), has been designing, developing, integrating, and testing commercial arrays using a Cessna airborne platform over the last several years. This has led to the development of three test bed variants, as reported on last year: the Airborne Laser Diode Array Illuminator prototype (ALDAI-P), the original commercial array version (ALDAI-C), and the most recent wide field-of-view commercial version (ALDAI-W). Using the ALDAI-W variant because of its increased operational capabilities with higher altitudes and wider field of views, ALRT recently demonstrated nighttime operation by detecting minefields over several background variations, expanding Naval reconnaissance capabilities that had been previously limited to daytime operation. This paper describes the demonstration and shows results of the ALDAI-W test.
Polarization based detection is often accomplished by using two separate components, reflectivity/emissivity and polarization, as detection algorithm inputs. These are Stokes vector components and are derived from elementary factors that represent energy collected with different polarizers. The elementary factors are added to produce the reflectivity/emissivity component and subtracted to produce the polarization component. Using the reflectivity/emissivity and polarization clearly addresses the advantage of using polarization as an added discriminant. However, depending on the detection algorithm, it may be better to use the elementary factors as input into a detection algorithm. A constant false alarm rate detection algorithm derived from a maximum likelihood is used as a foundation for judging target detection with these two different inputs. The results are presented for detecting man-made objects on natural backgrounds. The data cover two incident light sources: natural light, which is unpolarized and a linearly polarized laser. Detection using the elementary factors is shown to be consistent with detection using the Stokes vector components and is shown to decrease the false alarm rate.
The utility of Constant False Alarm Rate (CFAR) algorithms is that the selection of a detection threshold may be made independently of image intensity. However, wide application of the algorithms shows that detection values are highly dependent on scene characteristics. A threshold selection algorithm is presented for a CFAR detection algorithm. Fitting the output of the detection algorithm with a model of a portion of the theoretical results allows for background independent threshold selection.
The Airborne Littoral Reconnaissance Technologies (ALRT) Project has demonstrated a nighttime operational minefield detection capability using commercial off-the-shelf high-power Laser Diode Arrays (LDAs). Historically, optical aerial detection of minefields has primarily been limited to daytime operations but LDAs promise compact and efficient lighting to allow for enhanced reconnaissance operations for future mine detection systems. When combined with high-resolution intensified imaging systems, LDAs can illuminate otherwise unseen areas. Future wavelength options will open the way for active multispectral imaging with LDAs. The Coastal Systems Station working for the Office of Naval Research on the ALRT project has designed, developed, integrated, and tested both prototype and commercial arrays from a Cessna airborne platform. Detailed test results show the ability to detect several targets of interest in a variety of background conditions. Initial testing of the prototype arrays, reported on last year, was completed and further investigations of the commercial versions were performed. Polarization-state detection studies were performed, and advantageous properties of the source-target-sensor geometry noted. Current project plans are to expand the field-of-view coverage for Naval exercises in the summer of 2003. This paper describes the test collection, data library products, array information, on-going test analysis results, and future planned testing of the LDAs.
An automated band selection algorithm suitable for real-time application with fixed filter multispectral cameras is presented for multispectral target detection. Fixed filter multispectral cameras collect all bands regardless of the background. Background adaptive band is the selection of a subset of the bands for target detection processing. Fixed filter systems typically include a small number of general-purpose bands. The bands are chosen to enhance target-background contrast but are not keyed to specific target features. In some situations it is unlikely that all bands contribute to target discrimination. Using only a subset of the available bands can decrease false alarms while maintaining target detection performance and reduced processing requirements. The advantages are demonstrated using six band multispectral data and two distinct background categories.
A tactical unmanned aerial vehicle-size illumination system for enhanced mine detection capabilities has been designed, developed, integrated, and tested at the Coastal Systems Station. Airborne test flights were performed from June 12, 2001 to February 1, 2002. The Airborne Laser Diode Array Illuminator uses a single-wavelength compact laser diode array stack to provide illumination and is coupled with a pair of intensified CCD video cameras. The cameras were outfitted with various lenses and polarization filters to determine the benefits of each of the configurations. The first airborne demonstration of a laser diode illumination system is described and its effectiveness to perform nighttime mine detection operations is shown.
The Joint Mine Detection Technology (JMDT) project, following successful field-based testing of its new Tunable Filter Multispectral Camera (TFMC) has now completed initial Airborne Testing of the TFMC at both the Coastal Systems Station and Eglin Air Force Base sites. An overview of the testing is presented along with the investigations into the advantages of a system utilizing the TFMC in airborne operational scenarios. The TFMC-like tuning flexibility was flight-tested using optimized wavelength combinations, which were found using field test data, over a variety of backgrounds and altitudes. The data revealed the suitability of background tuning, polarization, and mechanically co-registered channels as benefits to multispectral target detection. The data were also compared to that collected with an IMC-201 camera, using the six filters of the Coastal Battlefield Reconnaissance and Analysis (COBRA) Advanced Technology Demonstration (ATD) system, in order to determine improvements over existing capabilities.
The signal adaptive target detection algorithm developed by Crosby and Riley uses target geometry to discern anomalies in local backgrounds. Detection is not restricted based on specific target signatures. The robustness of the algorithm is limited by an increased false alarm potential. The base algorithm is extended to eliminate one common source of false alarms in a littoral environment. This common source is glint reflected on the surface of water. The spectral and spatial transience of glint prevent straightforward characterization and complicate exclusion. However, the statistical basis of the detection algorithm and its inherent computations allow for glint discernment and the removal of its influence.
KEYWORDS: Distortion, 3D image processing, Magnetism, Image storage, Medical imaging, Head, Image processing, Imaging systems, Magnetic resonance imaging, Data storage
This paper presents a new and comprehensive approach for correcting magnetic-resonance images that are subject to three-dimensional geometric distortion. Distortion in such images is typically caused by variations in the magnetic- field gradient in each of the three spatial dimensions. The new approach sequentially applies one-dimensional and two- dimensional correction techniques to achieve a complete three-dimensional geometric correction. It thus avoids many theoretical complications and computational inefficiencies that are inherently associated with direct (non-sequential) three-dimensional correction techniques.
A constant false alarm rate algorithm has been developed for use in multi-band mine detection. While it is often difficult to predict the spectral signatures of targets, the shape of the target may be known. This test exploits geometric target features and spectral differences between the target and the surrounding area. The algorithm is derived from a general statistical model of the data, which allows it to adapt to changing backgrounds and variable signatures.
AN initial automated band selection algorithm suitable for real-time application with tunable multispectral cameras is presented for multispectral target detection. The method and algorithm were developed from analyses of several background and target signatures collected from a field test using the prototype Tunable Filter Multispectral Camera (TFMC). Target and background data from TFMC imagery were analyzed to determine the detection performance of 32,768 unique 3-band channel combinations in the visible through and near IR spectral regions. This tuning knowledge base was analyzed to develop rules for an initial dynamic tuning algorithm. The performance data was sorted by conventional means to determine the best 3-band combinations. Methods were then developed to determine performance enhancing band sets for particular backgrounds and a variety of targets. This knowledge is then used in an algorithm to affect a real-time 3-band tuning capability. Additional band sets for real-time background categorization are chosen by both the ability to spectrally detect of one background from another. This work will illustrate an example of the performance results form the analysis for three targets on various backgrounds.
KEYWORDS: Unmanned aerial vehicles, Video, Video surveillance, Land mines, Global Positioning System, Surveillance, Multispectral imaging, Target detection, Reconnaissance, Reconnaissance systems
The Coastal Battlefield Reconnaissance and Analysis)COBRA) system described here was a Marine Corps Advanced Technology Demonstration (ATD) development consisting of an unmanned aerial vehicle (UAV) airborne multispectral video sensor system and ground station which processes the multispectral video data to automatically detect minefields along the flight path. After successful completion of the ATD, the residual COBRA ATD system participated in the Joint Countermine (JCM) Advanced Concept Technology Demonstration (ACTD) Demo I held at Camp Lejeune, North Carolina in conjunction with JTFX97 and Demo II held in Stephenville, Newfoundland in conjunction with MARCOT98. These exercises demonstrated the COBRA ATD system in an operational environment, detecting minefields that included several different mine types in widely varying backgrounds. The COBRA system performed superbly during these demonstrations, detecting mines under water, in the surf zone, on the beach, and inland, and has transitioned to an acquisition program. This paper describes the COBRA operation and performance results for these demonstrations, which represent the first demonstrated capability for remote tactical minefield detection from a UAV. The successful COBRA technologies and techniques demonstrated for tactical UAV minefield detection in the Joint Countermine Advanced Concept Technology Demonstrations have formed the technical foundation for future developments in Marine Corps, Navy, and Army tactical remote airborne mine detection systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.