This Pdf file contains the Front Matter associated with SPIE Proceedings Volume 7694, including Title page, Copyright information, Table of Contents, Conference Committee listing, and Introduction, if any.

Ultimately, the success of any persistent ISR system will be judged by the quality (timeliness, accuracy and provenance) of the intelligence products that it delivers. In deploying multiple sensors to gather intelligence there is frequently a tripartite trade-off to be made between the physical constraints imposed by the sensor and platform performance both against the requirements of that mission and against the information needs of other users. Thus there is a need when working with constrained resources to optimise deployment through intelligent tasking to maximise the information quality without contradictory or over-constraining requirements and whilst maintaining mission efficiency. This paper considers recent advancements in defining mission specifications to better facilitate the optimum deployment of sensors against competing requirements and the needs of different missions. Considerations will be based against a scenario of a number of airborne vehicles carrying heterogeneous imaging sensors tasked for mine detection missions.

Within the context of C4ISTAR information "systems of systems", we discuss sensor data fusion aspects that are aiming at the generation of higher-level in-formation according to the JDL model of data fusion. In particular, two issues are addressed: (1) Tracking-derived Situation Elements: Standard target tracking applications gain information related to 'Level 1 Fusion' according to the well-established terminology of the JDL model. Kinematic data of this type, however, are by no means the only information to be derived from tar-get tracks. In many cases, reliable and quantitative higher level information according to the JDL terminology can be obtained. (2) Anomaly Detection in Tracking Data Bases: Anomaly detection can be regarded as a process of information fusion that aims at focusing the attention of human decision makers or decision making systems is focused on particular events that are "irregular" or may cause harm and thus require special actions.

Within a coalition environment, ad hoc Communities of Interest (CoI's) come together, perhaps for only a short time, with different sensors, sensor platforms, data fusion elements, and networks to conduct a task (or set of tasks) with different coalition members taking different roles. In such a coalition, each organization will have its own inherent restrictions on how it will interact with the others. These are usually stated as a set of policies, including security and privacy policies. The capability that we want to enable for a coalition operation is to provide access to information from any coalition partner in conformance with the policies of all. One of the challenges in supporting such ad-hoc coalition operations is that of providing efficient access to distributed sources of data, where the applications requiring the data do not have knowledge of the location of the data within the network. To address this challenge the International Technology Alliance (ITA) program has been developing the concept of a Dynamic Distributed Federated Database (DDFD), also know as a Gaian Database. This type of database provides a means for accessing data across a network of distributed heterogeneous data sources where access to the information is controlled by a mixture of local and global policies. We describe how a network of disparate ISR elements can be expressed as a DDFD and how this approach enables sensor and other information sources to be discovered autonomously or semi-autonomously and/or combined, fused formally defined local and global policies.

The management of sensor networks in coalition settings has been treated in a piecemeal fashion in the current literature without taking a comprehensive look at the complete life cycle of coalition networks, and determining the different aspects of network management that need to be taken into account for the management of sensor networks in those contexts. In this paper, we provide a holistic approach towards managing sensor networks encountered in the context of coalition operations. We describe how the sensor networks in a coalition ought to be managed at various stages of the life cycle, and the different operations that need to be taken into account for managing various aspects of the networks. In particular, we look at the FCAPS model for network management, and assess the applicability of the FCAPS model to the different aspects of sensor network management in a coalition setting.

Recent experience has demonstrated that adversary activities are difficult to distinguish from background activity. In order to see hidden activities, it is proposed that a combination of new sensing modalities and better ways of processing existing modalities is required. We have applied a robust methodology to analyse the strengths and weaknesses of sensor types at detecting and characterising adversary activities. This has revealed both complementary and synergistic relationships between sensor types, supporting the hypothesis that judicious combining of data from multiple sensors will result in a sensing capability significantly greater than that achievable by individual sensors. The challenge to making this capability a reality is to develop and integrate automatic processing techniques to self-cue sensors and fuse their information, whilst avoiding additional burden on the users. To facilitate evolution and wide exploitation of this capability, we are developing an open, scalable architecture in which to integrate the sensors and processing. All of this work is now being taken forward in the UK's PWAS (Persistent Wide Area Surveillance) S2O demonstrator project which is working towards a rapid demonstration of the capability benefits of an integrated multiple sensor system. The immediate goal is to integrate mature equipment into a demonstrator system, as a test-bed for current and developing cueing/fusion processing algorithms. The near-term goal is to evolve the capability through technology updates which exploit new sensors and improved sensor processing.

In this paper we present a Generic Vehicle Architecture (GVA), developed as part of the UK MOD GVA programme that addresses the issues of dynamic platform re-role through modular capability integration and behaviour orchestration. The proposed architecture addresses the need for: a) easy integration with legacy and future systems, and architectures; b) scalability from individual sensors, individual human users, vehicles and patrols to battle groups and brigades; c) rapid introduction of new capabilities in response to a changing operational scenario; d) be agnostic of communications systems, devices, operating systems and computer platforms. The GVA leverages the use of research output and tools developed by the International Technology Alliance (ITA) in Network and Information Science¹ programme, in particular the ITA Sensor Fabric^2-4 developed to address the challenges in the areas of sensor identification, classification, interoperability and sensor data sharing, dissemination and consumability, commonly present in tactical ISR/ISTAR,⁵ and the Gaian Dynamic Distributed Federated Database (DDFD)^6-8 developed the challenges of accessing distributed sources of data in an ad-hoc environment where the consumers do not have the knowledge of the location of the data within the network. The GVA also promotes the use of off-the-shelf hardware, and software which is advantageous from the aspect of easy of upgrading, lower cost of support and replacement, and speed of re-deploying platforms through a "fitted for but not with" approach. The GVA exploits the services orientated architecture (SOA) environment provided by the ITA Sensor Fabric to enhance the capability of legacy solutions and applications by enabling information exchange between them by, for example, providing direct near real-time communication between legacy systems. The GVA, a prototype implementation demonstrator of this architecture has demonstrated its utility to fusing, exploiting and sharing situational awareness information for force protection, and platform and device health and usage information for logistics and deployment management.

We consider the problem of deploying mobile robots to create a mutually-visible formation between stationary and mobile targets in a known environment. A mutually-visible formation is a placement where each agent or target is connected to all others through a sequence of visibility pairings. Mutual visibility enhances radio communications links, and enables other modalities such as optical communications. We discretize the environment in a manner conducive to visibility calculations, and, as targets shift, we use dynamic programming to find formations that preserve the visibility topology and minimize movement.

Substantial research has addressed the problems of automatic search, routing, and sensor tasking for UAVs, producing many good algorithms for each task. But UAV surveillance missions typically include combinations of these tasks, so an algorithm that can manage and control UAVs through multiple tasks is desired. The algorithm in this paper employs a cooperative graph-based search when target states are unknown. If target states become more localized, the algorithm switches to route UAV(s) for target intercept. If a UAV is close to a target, waypoints and sensor commands are optimized over short horizons to maintain the best sensor-to-target viewing geometry.

In future military missions, there will be many sensor assets collecting much important information about the environment. User control over surveillance assets is important to ensure that the specific data collected is appropriate for the current mission. Unfortunately, previous work has shown that individual users cannot effectively control more than about four assets, even if the assets have significant autonomy. In the ACCAST project, we hypothesized that by including autonomous teamwork between the assets and allowing users to interact by describing what the team as a whole and specific sub-teams should do, we could dramatically scale up the number of assets an individual user could effectively control. In this paper, we present the results of an experiment where users controlled up to 30 autonomous assets performing a complex mission. The assets autonomously worked together using sophisticated teamwork and the user could tell sub-teams to execute team oriented plans which described the steps required to achieve a team objective without describing exactly which asset performed which role and without having to specify how the team should handle routine information sharing, communications and failure circumstances. The users, soldiers from Fort Benning, were surprisingly good at managing the assets and were all able to complete the complex mission with extremely low friendly and civilian casualties.

Environmental Awareness for Sensor and Emitter Employment (EASEE) is a flexible, object-oriented software design for predicting environmental effects on the performance of battlefield sensors and detectability of signal emitters. Its decision-support framework facilitates many sensor and emitter modalities and can be incorporated into battlespace command and control (C2) systems. Other potential applications include immersive simulation, force-on-force simulation, and virtual prototyping of sensor systems and signal-processing algorithms. By identifying and encoding common characteristics of Army problems involving multimodal signal transmission and sensing into a flexible software architecture in the Java programming language, EASEE seeks to provide an application interface enabling rapid integration of diverse signal-generation, propagation, and sensor models that can be implemented in many client-server environments. Its explicit probabilistic modeling of signals, systematic consideration of many complex environmental and mission-related factors affecting signal generation and propagation, and computation of statistical metrics characterizing sensor performance facilitate a highly flexible approach to signal modeling and simulation. EASEE aims to integrate many disparate statistical formulations for modeling and processing many types of signals, including infrared, acoustic, seismic, radiofrequency, and chemical/biological. EASEE includes objects for representing sensor data, inferences for target detection and/or direction, signal transmission and processing, and state information (such as time and place). Various transmission and processing objects are further grouped into platform objects, which fuse data to make various probabilistic predictions of interest. Objects representing atmospheric and terrain environments with varying degrees of fidelity enable modeling of signal generation and propagation in diverse and complex environments.

The purpose of the CityBeat @ Tec^Edge program is to improve urban situation awareness through the integration, visualization and exploitation of geospatial imagery and products with sociocultural information in a layered sensing architecture. CityBeat applies persistent surveillance from multiple sensors to include wide area airborne and ground level cameras to learn normal behavior patterns based on object motion. Publicly available GIS and sociocultural datasets are integrated to provide context for the direct sensor measurements. Anomaly detection algorithms incorporating normalcy models with observed behavior are being developed to automatically alert an analyst of unusual behavior for objects of interest.

The Department of Defense (DoD) has established an Unattended Ground Sensor (UGS) Standards Working Group to address the interoperability of UGS, promote competition, provide enhanced capabilities, and support UGS missions.

Unattended Ground Sensor (UGS) systems have special requirements for long-duration, low-power operation, exfiltration of sensor reports and imagery over intermittent terrestrial or satellite communications channels, sensor description, management, discovery, configuration and command-and-control. This paper surveys a number existing and proposed software architectures for networked sensors, to include publish/subscribe brokered frameworks, with respect to the specific features needed for standards and protocols for UGS interoperability.

The combination of changing technology in the marketplace and new requirements for UGS will provide a continuing force for improving the performance of UGS systems in the future. The characterization of UGS as a System has already transformed UGS from an individual sensor reporting a target detection to a user in proximity to the sensor into the current paradigm of many UGS units interacting over a network to provide much more target information. As the technology continues to move forward, the amount of target information and the precision of the information are going to advance. This paper will provide examples of research underway to meet these future UGS needs and estimates of when these advances will become deployable systems.

Unattended Ground Sensors (UGS) from a wide range of manufacturers have difficulty interoperating with each other and common control and dissemination points. Typically, sensor data is transmitted via RF or wired connections to a central location where the data can be fused together and transmitted further via satellite to a Processing, Exploitation and Dissemination (PED) system. These PED's are charged with analyzing the data to create real time actionable intelligence for the war fighter. However, when several disparate sensors from different manufacturers are used, interoperability problems arise. Therefore, a central UGS controller that accepts data from a wide range of sensors and helps them interoperate is essential. This paper addresses benefits derived from using the Open Geospatial Consortium's (OGC) Sensor Model Language (SensorML) sensor descriptions for an UGS controller. SensorML 1.0 is an approved OGC standard and is one of the major components within the OGC Sensor Web Enablement (SWE) suite of standards. SensorML provides standard models and an XML encoding for describing any process, including the process of measurement by sensors. By incorporating SensorML, an UGS controller can accept data from various sensors from different manufacturers, and interpret that data with the SensorML descriptions to allow the controller to take programmed actions and interoperate between sensors. Furthermore, SensorML can be used to translate the native sensor formats once the original data has been transmitted to the PED. Therefore, this makes a SensorML enabled UGS controller an extremely powerful tool that provides situational awareness by combining multiple sensors to form a single common operational picture (COP).

We present an architecture for layered sensing which is constructed on open source and government off-the-shelf software. This architecture shows how leveraging existing open-source software allows for practical graphical user interfaces along with the underlying database and messaging architecture to be rapidly assimilated and utilized in real-world applications. As an example of how this works, we present a system composed of a database and a graphical user interface which can display wide area motion imagery, ground-based sensor data and overlays from narrow field of view sensors in one composite image composed of sensor data and other metadata in separate layers on the display. We further show how the development time is greatly reduced by utilizing open-source software and integrating it into the final system design. The paper describes the architecture, the pros and cons of the open-source approach with results for a layered sensing application with data from multiple disparate sensors.

"The foundation for integrating ISR planning and direction is the information network, including the appropriate ISR services and applications oriented toward the [commanders] needs. By combining global visibility of available information and intelligence needs with the tools to maximize platform/sensor/target management, the network will improve efficiency and maximize persistence. Inherent within this concept is the idea of integrating and synchronizing a mix of sensing systems and platforms rather than relying on a single system. The second concept embedded within this concept is the ability to capture the activity/information as it occurs rather than forensically reconstructing after the fact. This requires the ability for the [commander] to adjust collection priorities of the entire collection suite to a level appropriate to the activity of interest. Individual sensors, platforms and exploitation nodes will become more efficient as part of an integrated system. Implementing this fully integrated ISR Enterprise will result in improved persistence, and ultimately better ISR for the warfighter."[3] Over the last 6 years, SAIC has been working with CERDEC and AMRDEC to introduce Battle Command aids supporting (semi) autonomous execution and collaboration of unmanned assets. This paper presents an operational context and a distributed command and control architecture aiming to reduce workload and increase Persistent ISR effectiveness. This architecture has been implemented and demonstrated in field tests and as part of FY'09 C4ISR OTM testbed.

Teledyne Scientific Company, the University of California at Santa Barbara (UCSB) and the Army Research Lab are developing technologies for automated data exfiltration from heterogeneous sensor networks through the Institute for Collaborative Biotechnologies (ICB). Unmanned air vehicles (UAV) provide an effective means to autonomously collect data from unattended ground sensors (UGSs) that cannot communicate with each other. UAVs are used to reduce the system reaction time by generating autonomous data-driven collection routes. Bio-inspired techniques for search provide a novel strategy to detect, capture and fuse data across heterogeneous sensors. A fast and accurate method has been developed for routing UAVs and localizing an event by fusing data from a sparse number of UGSs; it leverages a bio-inspired technique based on chemotaxis or the motion of bacteria seeking nutrients in their environment. The system was implemented and successfully tested using a high level simulation environment using a flight simulator to emulate a UAV. A field test was also conducted in November 2009 at Camp Roberts, CA using a UAV provided by AeroMech Engineering. The field test results showed that the system can detect and locate the source of an acoustic event with an accuracy of about 3 meters average circular error.

Determination of an optimal configuration (numbers, types, and locations) of a sensor network is an important practical problem. In most applications, complex signal propagation effects and inhomogeneous coverage preferences lead to an optimal solution that is highly irregular and nonintuitive. The general optimization problem can be strictly formulated as a binary linear programming problem. Due to the combinatorial nature of this problem, however, its strict solution requires significant computational resources (NP-complete class of complexity) and is unobtainable for large spatial grids of candidate sensor locations. For this reason, a greedy algorithm for approximate solution was recently introduced [S. N. Vecherin, D. K. Wilson, and C. L. Pettit, "Optimal sensor placement with terrain-based constraints and signal propagation effects," Unattended Ground, Sea, and Air Sensor Technologies and Applications XI, SPIE Proc. Vol. 7333, paper 73330S (2009)]. Here further extensions to the developed algorithm are presented to include such practical needs and constraints as sensor availability, coverage by multiple sensors, and wireless communication of the sensor information. Both communication and detection are considered in a probabilistic framework. Communication signal and signature propagation effects are taken into account when calculating probabilities of communication and detection. Comparison of approximate and strict solutions on reduced-size problems suggests that the approximate algorithm yields quick and good solutions, which thus justifies using that algorithm for full-size problems. Examples of three-dimensional outdoor sensor placement are provided using a terrain-based software analysis tool.

We discuss the development, design, implementation, and demonstration of a robotic UGV (Unmanned Ground Vehicle) system for networked and non-line-of-sight sensing applications. Our development team is comprised of AFRL Summer Interns, University Faculty, and Personnel from AFRL. The system concept is based on a previously published technique known as "Dual-UAV Tandems for Indirect Operator-Assisted Control" [1]. This architecture is based on simulating a Mini-UAV Helicopter with a building-mounted camera and simulating a low-flying QuadRotor Helicopter with a Robotics UGV. The Robotics UGV is fitted with a custom-designed sensor boom and a surrogate chem/bio (Carbon Monoxide) PCB sensor extracted from a COTS (Commercial-Off-The-Shelf) product. The CO Sensor apparatus is co-designed with the sensor boom and is fitted with a transparent covering for protection and to promote CO (surrogate chem/bio) flow onto the sensor. The philosophy behind this non-line-of-sight system is to relay video of the UGV to an Operator station for purposes of investigating "Indirect Operator-Assisted Control" of the UGV via observation of the relayed EO video at the operator station. This would serve as a sensor fusion, giving the operator visual cues of the chemical under detection, enabling him to position the UGV in areas of higher concentration. We recorded this data, and analyzed the best approach given a test matrix of multiple scenarios, with the goal of determining the feasibility of using this layered sensing approach and the system accuracy in open field tests. For purposes of collecting scientific data with this system, we developed a Test (data collection) Matrix with following three parameters: 1. Chem/Bio detection level with side-looking sensor boom and slowly traversing UGV; 2. Chem/Bio detection level with panning sensor boom and slowly traversing UGV; 3. Chem/Bio detection level with forward-looking sensor boom and operator-assisted steering based on onboard wind vane readings of UGV display that is overlayed onto relayed video. In addition to reporting the trends and results of analysis with regard to data collected with this Test Matrix, we discuss potential approaches to upgrading our networked robotics UGV system and also introduce the concept of "swapping sensors" with this low-cost networked sensor concept.

L-3 Nova's mNet family of miniature networked transceivers provides high data rate (500 kbps) networked connectivity. The mNet provides coverage from 300 MHz to 2.48 GHz, covering frequencies ideally suited for ground propagation. mNet offers low power sleep modes and full software control of data rates, modulation settings and RF power levels. The on-board LNA and PA can be enabled to increase range or disabled to conserve power. The mNet utilizes ad-hoc mesh networking to form a collaborative sensor network for distributed processing. L-3 Nova offers a variety of mNet implementation options; some units are no larger than a coin.

The detection and localization of weapon firing on the battlefield is envisaged by means of acoustic waves. The main objective of this work is to compare various sensing elements that can be integrated in acoustic arrays. Experimental measurements of sound waves obtained by using some of these elements in Unattended Ground Sensors are presented for snipers, mortars or artillery guns. The emphasis will be put on the characteristics of the sensing elements needed to detect and classify the Mach wave generated by a supersonic projectile and the muzzle wave generated by the combustion of the propulsion powder. Examples of preliminary prototypes are presented to illustrate our topic. We will concentrate on a wearable system considered to improve the soldier's awareness of the surrounding threats: this realization consists of a network of three helmets integrating an acoustic array for the detection and localization of snipers.

There exists a current need to rapidly and accurately identify the presence and location of optical imaging devices used in counter-surveillance activities against U. S. troops deployed abroad. The locations of devices employed in counter-surveillance activities can be identified through detection of the optically augmented reflection from these devices. To address this need, we have developed a novel optical augmentation sensor, the Mobile Optical Detection System (MODS), which is uniquely designed to identify the presence of optical systems of interest. The essential components of the sensor are three, spectrally diverse diode lasers (1 ultraviolet/2 near-infrared) which are integrated to produce a single multi-wavelength interrogation beam and a charge-coupled-device (CCD) receiver which is used to detect the retroreflected, optical beam returned from a target of interest. The multi-spectral diode laser illuminator and digital receiver are configured in a pseudo-monostatic arrangement and are controlled through a customized computer interface. By comparison, MODS is unique among OA sensors since it employs a collection of wavelength-diverse, continuous-wave (CW) diode laser sources which facilitate the identification of optical imaging devices used for counter-surveillance activities. In addition, digital image processing techniques are leveraged to facilitate improved clutter rejection concomitant with highly-specific target location (e.g., azimuth and elevation). More, the digital output format makes the sensor amenable to a wide range of interface options including computer networks, eyepieces and remotely-located displays linked through wireless nodes.

Utility-based cross-layer optimization is a valuable tool for resource management in mission-oriented wireless sensor networks (WSN). The benefits of this technique include the ability to take application- or mission-level utilities into account and to dynamically adapt to the highly variable environment of tactical WSNs. Recently, we developed a family of distributed protocols which adapts the bandwidth and energy usage in mission-oriented WSN in order to optimally allocate resources among multiple missions, that may have specific demands depending on their priority, and also variable schedules, entering and leaving the network at different times.^9-12 In this paper, we illustrate the practical applicability of this family of protocols in tactical networks by implementing one of the protocols, which ensures optimal rate adaptation for congestion control in mission-oriented networks,9 on a real-time 802.11b network using the ITA Sensor Fabric.¹³ The ITA Sensor Fabric is a middleware infrastructure, developed as part of the International Technology Alliance (ITA) in Network and Information Science,¹⁴ to address the challenges in the areas of sensor identification, classification, interoperability and sensor data sharing, dissemination and consumability, commonly present in tactical WSNs.¹⁵ Through this implementation, we (i) study the practical challenges arising from the implementation and (ii) provide a proof of concept regarding the applicability of this family of protocols for efficient resource management in tactical WSNs amidst the heterogeneous and dynamic sets of sensors, missions and middle-ware.

The Army Research Laboratory is in partnership with the University of Florida - Electronics Communications Laboratory to develop compact radar technology and demonstrate that it is scalable to a variety of ultra-lightweight platforms (<10 lbs.) to meet Army mission needs in persistent surveillance, unattended ground sensor (UGS), unmanned systems, and man-portable sensor applications. The advantage of this compact radar is its steerable beam technology and relatively long-range capability compared to other small, battery-powered radar concepts. This paper will review the ongoing development of the sensor and presents a sample of the collected data thus far.

This paper details the continued development of a modularized system level model of a sparse detector sensor system. The assumptions used to simplify the equations describing the effects of individual system components and characteristics such as target to background properties, collection optics, detectors, and classifiers will be detailed and modeled. These individual effects will then be combined to provide an overall system performance model and used to compare two sensor node designs. The model will facilitate design trade offs for Unattended Ground Sensors. The size and power restrictions of these sensors often preclude these sensors from being effective in high-resolution applications such as target identification. However, these systems are well suited for applications such as broad scale classifications or differentiations between targets such as humans, animals or small vehicles. Therefore, the demand for these sensors is increasing for both the military and homeland security.

This paper provides a feasibility analysis and details of implementing a classification algorithm on an embedded controller for use with a profiling sensor. Such a profiling sensor has been shown to be a feasible approach to a low-cost persistent surveillance sensor for classifying moving objects such as humans, animals, or vehicles. The sensor produces data that can be used to generate object profiles as crude images or silhouettes, and/or the data can be subsequently automatically classified. This paper provides a feasibility analysis of a classification algorithm implemented on an embedded controller, which is packaged with a prototype version of a profiling sensor. Implementation of the embedded controller is a necessary extension of previous work for fielded profiling sensors and their appropriate applications. Field data is used to confirm accurate automated classification.

This paper describes ongoing research by Georgia Tech into the challenges of tasking and controlling heterogonous teams of unmanned vehicles in mixed indoor/outdoor reconnaissance scenarios. We outline the tools and techniques necessary for an operator to specify, execute, and monitor such missions. The mission specification framework used for the purposes of intelligence gathering during mission execution are first demonstrated in simulations involving a team of a single autonomous rotorcraft and three ground-based robotic platforms. Preliminary results including robotic hardware in the loop are also provided.

In order to anticipate the constantly changing landscape of global warfare, the United States Air Force must acquire new capabilities in the field of Intelligence, Surveillance, and Reconnaissance (ISR). To meet this challenge, the Air Force Research Laboratory (AFRL) is developing a unifying construct of "Layered Sensing" which will provide military decision-makers at all levels with the timely, actionable, and trusted information necessary for complete battlespace awareness. Layered Sensing is characterized by the appropriate combination of sensors and platforms (including those for persistent sensing), infrastructure, and exploitation capabilities to enable this synergistic awareness. To achieve the Layered Sensing vision, AFRL is pursuing a Modeling & Simulation (M&S) strategy through the Layered Sensing Operations Center (LSOC). An experimental ISR system-of-systems test-bed, the LSOC integrates DoD standard simulation tools with commercial, off-the-shelf video game technology for rapid scenario development and visualization. These tools will help facilitate sensor management performance characterization, system development, and operator behavioral analysis. Flexible and cost-effective, the LSOC will implement a non-proprietary, open-architecture framework with well-defined interfaces. This framework will incentivize the transition of current ISR performance models to service-oriented software design for maximum re-use and consistency. This paper will present the LSOC's development and implementation thus far as well as a summary of lessons learned and future plans for the LSOC.

A current trend that is gaining strength in the wireless sensor network area is the use of heterogeneous sensor nodes in one coordinated overall network, needed to fulfill the requirements of sophisticated emerging applications, such as area surveillance systems. One of the main concerns when developing such sensor networks is how to provide coordination among the heterogeneous nodes, in order to enable them to efficiently respond the user needs. This study presents an investigation of strategies to coordinate a set of static sensor nodes on the ground cooperating with wirelessly connected Unmanned Aerial Vehicles (UAVs) carrying a variety of sensors, in order to provide efficient surveillance over an area of interest. The sensor nodes on the ground are set to issue alarms on the occurrence of a given event of interest, e.g. entrance of a non-authorized vehicle in the area, while the UAVs receive the issued alarms and have to decide which of them is the most suitable to handle the issued alarm. A bio-inspired coordination strategy based on the concept of pheromones is presented. As a complement of this strategy, a utility-based decision making approach is proposed.

In this paper we present a new approach to the real-time generation and dissemination of steerable video chips from large volume motion imagery streams. Traditional large frame motion imagery streaming and dissemination systems employ JPEG 2000 (J2K) compression and associated JPEG 2000 Interactive Protocol (JPIP) streaming to encode and deliver images over varying bandwidth communication channels. While J2K and JPIP technologies are suitable for many large frame motion imagery applications, they often struggle to satisfy the needs of certain low power, low bandwidth users. The J2K format does not currently support inter-frame compression and, therefore, cannot target the lowest bandwidth motion imagery users. Additionally, J2K decompression and JPIP processing both consume more computational resources than low-end client systems often have available. This is especially true for handheld and thin-client devices. We address these issues by integrating region-of-interest J2K compression and JPIP streaming with MPEG-2 and H.264 video compression technology, taking advantage of the ubiquitous hardware acceleration and client ingest support for these full motion video product formats. The proposed architecture maintains all the benefits of incorporating a J2K archival format, while also boasting the ability to disseminate J2K regions-of-interest and low resolution overviews to an even greater number of simultaneous clients. We illustrate a real-time integration and implementation of these technologies and show how they can be used to enable interactive and automated tracking and dissemination of multiple moving objects from wide area persistent surveillance motion imagery.

As the number of sensing assets and tactical command and control (C2) systems grow, the need for a centralized means of collecting and disseminating the crucial information grows as well. Over the past 5 years, Honeywell has created a software application known as the Network-Enabled Operator Station (NEOS) to answer this need. NEOS has been developed from the ground up to be an open-architecture solution which integrates a variety of assets, communications systems and protocols, and data sharing techniques. The ultimate goals are to increase friendly situational awareness and increase the effectiveness of field operators.

Multiple sensors with multiple modalities are being routinely deployed in forward areas to gain the situational awareness. Some of the sensors are activity detection sensors such as acoustic, seismic, passive infrared (PIR), and magnetic sensors which normally consume low power. These sensors often cue or wake up more power hungry sensors such as imaging sensors, namely visible camera and infrared camera, and radar to either capture a picture or to track a target of interest. Several airborne sensors routinely gather information on an area of interest using radar, imaging sensors for intelligence, surveillance and reconnaissance (ISR) purposes. Recently, Empire Challenge has brought a new concept: that is, harvesting the ISR data from the remotely distributed unattended ground sensors. Here aerial vehicle flies by the area occasionally and queries if the sensors have any data to be harvested. Harvesting large amounts of data is unnecessary and impractical - so some amount of fusion of the sensor data is essential.

In the modern networked battlefield, network centric warfare (NCW) scenarios need to interoperate between shared resources and data assets such as sensors, UAVs, satellites, ground vehicles, and command and control (C2/C4I) systems. By linking and fusing platform routing information, sensor exploitation results, and databases (e.g. Geospatial Information Systems [GIS]), the shared situation awareness and mission effectiveness will be improved. Within the information fusion community, various research efforts are looking at open standard approaches to composing the heterogeneous network components under one framework for future modeling and simulation applications. By utilizing the open source services oriented architecture (SOA) based sensor web services, and GIS visualization services, we propose a framework that ensures the fast prototyping of intelligence, surveillance, and reconnaissance (ISR) system simulations to determine an asset mix for a desired mission effectiveness, performance modeling for sensor management and prediction, and user testing of various scenarios.

Unattended Ground Sensors have found widespread usefulness in force and asset protection, border patrol and, drug enforcement. In recent years their application has extended into ground and air surveillance providing additional data from disparate networked Intelligence, Surveillance, and Reconnaissance resources. The consolidation of this data and effective presentation through software applications efficiently communicates critical information that helps the analyst support persistent surveillance missions. This paper presents the interface such flexible applications with an emphasis on their presentation elements and information content.

The current bottleneck in wide area persistent surveillance missions is slow exploitation and analysis (real-time and forensic)by human analysts. We are currently developing an automated data exploitation system that can detect, track, and recognize targets and threats using computer vision. Here we present results from a newly developed target detection process. Depanding on target size, target detection can be divided in three detection classes: unresolved targets, small extended targets, and large extended targets. The Matched Filter (MF) method is currently a popular approach for unresolved target detection using IR focal plane arrays and EO (CCD) cameras and sensor detectors. The MF method is much more difficult to apply to to the extended target classes, since many different matched filters are needed to match the different target shapes and intensity profiles that can exist. The MF method does not adequately address non-fixed target shapes (e.g. walking or running human). We have developed an approach for robust target detection that can detect targets of different sizes and shapes (fixed/non-fixed) using a combination of image frame time-differencing, deep-thresholding, and target shape and size analysis with non-linear morphologial operations. Applications for gound vehicle detection under heavy urban background clutter will be presented.

We present a novel method to quickly detect and track objects of low resolution within an image frame by comparing dense, oriented gradient features at multiple scales within an object chip. The proposed method uses vector correlation between sets of oriented Haar filter responses from within a local window and an object library to create similarity measures, where peaks indicate high object probability. Interest points are chosen based on object shape and size so that each point represents both a distinct spatial location and the shape segment of the object. Each interest point is then independently searched in subsequent frames, where multiple similarity maps are fused to create a single object probability map. This method executes in real time by reducing feature calculations and approximations using box filters and integral images. We achieve invariance to rotation and illumination, because we calculate interest point orientation and normalize the feature vector scale. The method creates a feature set from a small and localized area, allowing for accurate detections in low resolution scenarios. This approach can also be extended to include the detection of partially occluded objects through calculating individual interest point feature vector correlations and clustering points together. We have tested the method on a subset of the Columbus Large Image Format (CLIF) 2007 dataset, which provides various low-pixel-on-object moving and stationary vehicles with varying operating conditions. This method provides accurate results with minimal parameter tuning for robust implementation on aerial, low pixel-on-object data sets for automated classification applications.

Optical flow-based tracking methods offer the promise of precise, accurate, and reliable analysis of motion, but they suffer from several challenges such as elimination of background movement, estimation of flow velocity, and optimal feature selection. Wavelet approximations can offer similar benefits and retain spatial information at coarser scales, while optical flow estimation increases with the reduction of finer details of moving objects. Optical flow methods often suffer from significant computational overload. In this study, we have investigated the necessary processing steps to increase detection and estimation accuracy, while effectively reducing computation time through the reduction of the image frame size. We have implemented an object tracking algorithm using the optical flow calculated from a phase change between representative coarse wavelet coefficients in subsequent image frames. We have also compared phasebased optical flow with two versions of intensity-based optical flow to determine which method produces superior results under specific operational conditions. The investigation demonstrates the feasibility of using phase-based optical flow with wavelet approximations for object detection and tracking of low resolution aerial vehicles. We also demonstrate that this method can work in tandem with feature-based tracking methods to increase tracking accuracy.

This paper presents object profile classification results using range and speed independent features from an infrared profiling sensor. The passive infrared profiling sensor was simulated using a LWIR camera. Field data collected near the US-Mexico border to yield profiles of humans and animals is reported. Range and speed independent features based on height and width of the objects were extracted from profiles. The profile features were then used to train and test three classification algorithms to classify objects as humans or animals. The performance of Naïve Bayesian (NB), K-Nearest Neighbors (K-NN), and Support Vector Machines (SVM) are compared based on their classification accuracy. Results indicate that for our data set all three algorithms achieve classification rates of over 98%. The field data is also used to validate our prior data collections from more controlled environments.