This PDF file contains the front matter associated with SPIE Proceedings Volume 7668, including the Title Page, Copyright information, Table of Contents, Introduction, and the Conference Committee listing.

Three-dimensional (3D) imaging technologies have considerable potential for aiding military operations in areas such as reconnaissance, mission planning and situational awareness through improved visualisation and user-interaction. This paper describes the development of fast 3D imaging capabilities from low-cost, passive sensors. The two systems discussed here are capable of passive depth perception and recovering 3D structure from a single electro-optic sensor attached to an aerial vehicle that is, for example, circling a target. Based on this example, the proposed method has been shown to produce high quality results when positional data of the sensor is known, and also in the more challenging case when the sensor geometry must be estimated from the input imagery alone. The methods described exploit prior knowledge concerning the type of sensor that is used to produce a more robust output.

Lock-in imaging enables high contrast imaging in adverse conditions by exploiting a modulated light source and homodyne detection. We report results on a patent pending lock-in imaging system fabricated from commercial-off-theshelf parts utilizing standard cameras and a spatial light modulator. By leveraging the capabilities of standard parts we are able to present a low cost, high resolution, high sensitivity camera with applications in search and rescue, friend or foe identification (IFF), and covert surveillance. Different operating modes allow the same instrument to be utilized for dual band multispectral imaging or high dynamic range imaging, increasing the flexibility in different operational settings.

A field deployable hyperspectral imager utilizing chromotomography (CT), with a direct vision prism (DVP) as the dispersive element, has been constructed at the Air Force Institute of Technology (AFIT). A "shift and add" reconstruction algorithm was used to resolve spectral and spatial content of the collected data. The AFIT instrument is currently the fastest known imaging DVP based hyperspectral CT instrument of its type and is a prototype for a space-based system. The imager captured images at rates up to 900 frames per second (fps) and acquired data cube information in 55 ms, during testing. This instrument has the ability to capture spatial and spectral data of static and transient scenes. During testing, the imager captured spectral data of a rapidly evolving scene (a firecracker detonation) lasting approximately 0.12 s. Spectral results included potassium and sodium emission lines present during the explosion and an absorption feature as the fireball extinguishes. Spatial and spectral reconstruction of a scene in which an explosion occurs during the middle of the collection period is also presented in this paper. The instrument is capable of acquiring data required to identify, classify and characterize transient battlespace events, such as explosions.

VTT Technical Research Centre of Finland has developed a new miniaturized staring hyperspectral imager with a weight of 350 g making the system compatible with lightweight UAS platforms. The instrument is able to record 2D spatial images at the selected wavelength bands simultaneously. The concept of the hyperspectral imager has been published in the SPIE Proc. 7474¹. The operational wavelength range of the imager can be tuned in the range 400 - 1100 nm and spectral resolution is in the range 5 - 10 nm @ FWHM. Presently the spatial resolution is 480 × 750 pixels but it can be increased simply by changing the image sensor. The field of view of the system is 20 × 30 degrees and ground pixel size at 100 m flying altitude is around 7.5 cm. The system contains batteries, image acquisition control system and memory for the image data. It can operate autonomously recording hyperspectral data cubes continuously or controlled by the autopilot system of the UAS. The new hyperspectral imager prototype was first tried in co-operation with the Flemish Institute for Technological Research (VITO) on their UAS helicopter. The instrument was configured for the spectral range 500 - 900 nm selected for the vegetation and natural water monitoring applications. The design of the UAS hyperspectral imager and its characterization results together with the analysis of the spectral data from first test flights will be presented.

FEATHAR (Fusion, Exploitation, Algorithms, and Targeting for High-Altitude Reconnaissance) is an ONR funded effort to develop and test new tactical sensor systems specifically designed for small manned and unmanned platforms (payload weight < 50 lbs). This program is being directed and executed by the Naval Research Laboratory (NRL) in conjunction with the Space Dynamics Laboratory (SDL). FEATHAR has developed and integrated EyePod, a combined long-wave infrared (LWIR) and visible to near infrared (VNIR) optical survey & inspection system, with NuSAR, a combined dual band synthetic aperture radar (SAR) system. These sensors are being tested in conjunction with other ground and airborne sensor systems to demonstrate intelligent real-time cross-sensor cueing and in-air data fusion. Results from test flights of the EyePod and NuSAR sensors will be presented.

NuSAR (Naval Research Laboratory Unmanned Synthetic Aperture Radar) is a sensor developed under the ONRfunded FEATHAR (Fusion, Exploitation, Algorithms, and Targeting for High-Altitude Reconnaissance) program. FEATHAR is being directed and executed by the Naval Research Laboratory (NRL) in conjunction with the Space Dynamics Laboratory (SDL). FEATHAR's goal is to develop and test new tactical sensor systems specifically designed for small manned and unmanned platforms (payload weight < 50 lbs). NuSAR is a novel dual-band (L- and X-band) SAR capable of a variety of tactically relevant operating modes and detection capabilities. Flight test results will be described for narrow and wide bandwidth and narrow and wide azimuth aperture operating modes.

EyePod is a compact survey and inspection day/night imaging sensor suite for small unmanned aircraft systems (UAS). EyePod generates georeferenced image products in real-time from visible near infrared (VNIR) and long wave infrared (LWIR) imaging sensors and was developed under the ONR funded FEATHAR (Fusion, Exploitation, Algorithms, and Targeting for High-Altitude Reconnaissance) program. FEATHAR is being directed and executed by the Naval Research Laboratory (NRL) in conjunction with the Space Dynamics Laboratory (SDL) and FEATHAR's goal is to develop and test new tactical sensor systems specifically designed for small manned and unmanned platforms (payload weight < 50 lbs). The EyePod suite consists of two VNIR/LWIR (day/night) gimbaled sensors that, combined, provide broad area survey and focused inspection capabilities. Each EyePod sensor pairs an HD visible EO sensor with a LWIR bolometric imager providing precision geo-referenced and fully digital EO/IR NITFS output imagery. The LWIR sensor is mounted to a patent-pending jitter-reduction stage to correct for the high-frequency motion typically found on small aircraft and unmanned systems. Details will be presented on both the wide-area and inspection EyePod sensor systems, their modes of operation, and results from recent flight demonstrations.

With the advances in focal plane, electronics and memory storage technologies, wide area and persistence surveillance capabilities have become a reality in airborne ISR. A WAS system offers many benefits in comparison with the traditional airborne image capturing systems that provide little data overlap, both in terms of space and time. Unlike a fix-mount surveillance camera, a persistence WAS system can be deployed anywhere as desired, although the platform typically has to be in motion, say circling above an area of interest. Therefore, WAS is a perfect choice for surveillance that can provide near real time capabilities such as change detection and target tracking. However, the performance of a WAS system is still limited by the available technologies: the optics that control the field-of-view, the electronics and mechanical subsystems that control the scanning, the focal plane data throughput, and the dynamics of the platform all play key roles in the success of the system. It is therefore beneficial to develop a simulated version that can capture the essence of the system, in order to help provide insights into the design of an optimized system. We describe an approach to the simulation of a generic WAS system that allows focal plane layouts, scanning patterns, flight paths and platform dynamics to be defined by a user. The system generates simulated image data of the area ground coverage from reference databases (e.g. aerial imagery, and elevation data), based on the sensor model. The simulated data provides a basis for further algorithm development, such as image stitching/mosaic, registration, and geolocation. We also discuss an algorithm to extract the terrain elevation from the simulated data, and to compare that with the original DEM data.

In this paper we present an approach to integrate sensors to meet the demanding requirements of Quick Reaction Capability (QRC) airborne programs. Traditional airborne sensors are generally highly integrated and incorporate custom sensor technologies and interfaces. Custom solutions and new technologies often require significant engineering to achieve a high technology readiness level (TRL) and to meet the overall mission objective. Our approach differs from traditional approaches in that we strive to achieve an integrated solution through regular review, assessment, and identification of relevant industry "best athlete" technologies. Attention is focused on solution providers that adhere to standard interfaces and formats, incorporate non-proprietary techniques, are deemed highly-reliable/repeatable, and enable assembly production. Processes and engineering tools/methods have traditionally been applied to dozens of longer-acquisition space-based ISR programs over 50 years. We have recently leveraged these techniques to solve airborne Intelligence, Surveillance and Reconnaissance (ISR) mission challenges. This presentation describes and illustrates key aspects and examples of these techniques, solving real-world airborne mission needs.

Continuum emission is predominant in fireball spectral phenomena and in some demonstrated cases, fine detail in the temporal evolution of infrared spectral emissions can be used to estimate size and chemical composition of the device. Recent work indicates that a few narrow radiometric bands may reveal forensic information needed for the explosive discrimination and classification problem, representing an essential step in moving from "laboratory" measurements to a rugged, fieldable system. To explore phenomena not observable in previous experiments, a high speed (10μs resolution) radiometer with four channels spanning the infrared spectrum observed the detonation of nine home made explosive (HME) devices in the < 100lb class. Radiometric measurements indicate that the detonation fireball is well approximated as a single temperature blackbody at early time (0 < t ⪅ 3ms). The effective radius obtained from absolute intensity indicates fireball growth at supersonic velocity during this time. Peak fireball temperatures during this initial detonation range between 3000.3500K. The initial temperature decay with time (t ⪅ 10ms) can be described by a simple phenomenological model based on radiative cooling. After this rapid decay, temperature exhibits a small, steady increase with time (10 ⪅ t ⪅ 50ms) and peaking somewhere between 1000.1500K-likely the result of post-detonation combustion-before subsequent cooling back to ambient conditions . Radius derived from radiometric measurements can be described well (R² > 0.98) using blast model functional forms, suggesting that energy release could be estimated from single-pixel radiometric detectors. Comparison of radiometer-derived fireball size with FLIR infrared imagery indicate the Planckian intensity size estimates are about a factor of two smaller than the physical extent of the fireball.

Military test centers require detailed site descriptions. Test agencies demand significant written and visual information of test sites in order to facilitate successful test preparation and execution. New terrestrial imaging techniques (360 degree FOV collection) have recently become feasible to collect in the field. Combined with GIS and mapping applications, image and video data is now provided to test agencies for their use. Test sites for this study include locations in Alaska and Panama with planned image data collection in Arizona and Maryland.

An overview of a high performance zoom camera will be presented. Performance achievements including zoom (magnification range), mass, bore sight, space envelope and environment will be discussed. Optical mounting techniques and flexural decoupling of components for large temperature ranges will be presented. Precision trajectory and positioning of multiple moving lens groups will be reviewed and lead screw decoupling methods providing axial stiffness with radial compliance will be illustrated. A mechanical system interface with high stiffness and thermal compliance for azimuth and elevation adjustments will be given. Finally, the paper will conclude with a review of lessons learned, including lead screw decoupling and aligning multiple static and moving lens groups.

A pushbroom MSI sensor collects image data from the ground, parallel to the flight path, at a specific point angle. Images taken at two instances of time while the scanner moves with the platform usually have a spatial offset, and need to be registered before they can be compared for any changes between the two images. Moving target detection is a special case of change detection that requires the time between frames be small enough that a moving vehicle remains in close proximity on the two frames. We propose an algorithm for the detection of moving targets in a multi-band line scanning pushbroom sensor. Ideally, change detection works best when images have the same spectral bandwidth and are perfectly registered to one another, since differencing the two images automatically removes most of the common background signal. However, this is not always the case. For example, the sensor considered here has different bandwidths for its component bands, and since it is a line-scanner it is much more challenging regarding image registration than a framed-based scanner. In this study, we will use simulated data of the same bandwidth to demonstrate the fundamental algorithm of detection and velocity calculation. The velocity calculation is that of distance divided by time; but, depending on the focal plane layout and other operating considerations and conversion between image space to physical units, this calculation is not as simple as it seems. We will also discuss our effort in applying our algorithm to real line-scan imagery, of different bandwidths in the two channels. We will show the extra image processing efforts needed to make it work, and show some of the test results.

We propose a feature-based approach for vehicle detection in aerial imagery with 11.2 cm/pixel resolution. The approach is free of all constraints related to the vehicles appearance. The scale-invariant feature transform (SIFT) is used to extract keypoints in the image. The local structure in the neighbouring of the SIFT keypoints is described by 128 gradient orientation based features. A Support Vector Machine is used to create a model which is able to predict if the SIFT keypoints belong to or not to car structures in the image. The collection of SIFT keypoints with car label are clustered in the geometric space into subsets and each subset is associated to one car. This clustering is based on the Affinity Propagation algorithm modified to take into account specific spatial constraint related to geometry of cars at the given resolution.

In the aerial images of 11.2 cm/pixel resolution the car components that can be seen are only large parts of the car such as car bodies, windshields, doors and shadows. Furthermore, these components are distorted by low spatial resolution, low color contrast, specular reflection and viewpoint variation. We use the mean shift procedure for robust segmentation of the car parts in the geometric and color joint space. This approach is robust, efficient, repeatable and independent of the threshold parameters. We introduce a hierarchical segmentation algorithm with three consecutive mean-shift procedures. Each is designed with a specific bandwidth to segment a specific car part, whose size is estimated a priori, and is followed by a support vector machine in order to detect this car part, based on the color features and the geometrical moment based features. The procedure starts with the largest car parts, which are then removed from the segmented region lists after the detection to avoid over-segmentation of large regions with the mean-shift using smaller bandwidth values. Finally we detect and count the cars in the image by combining the detected car parts according to the spatial relations. Experiment results show a good performance.

This paper presents a relational graph based approach to track thousands of vehicles from persistent wide area airborne surveillance (WAAS) videos. Due to the low ground sampling distance and low frame rate, vehicles usually have small size and may travel a long distance between consecutive frames, WAAS videos pose great challenges to correct associate existing tracks with targets. In this paper, we explore road structure information to regulate both object based vertex matching and pair-wise edge matching schemes in a relational graph. The proposed relational graph approach then unifies these two matching schemes into a single cost minimization framework to produce a quadratic optimized association result. The experiments on hours of real WAAS videos demonstrate the relational graph matching framework effectively improves vehicle tracking performance in large scale dense traffic scenarios.

In this paper, a novel system is presented to detect and track multiple targets in Unmanned Air Vehicles (UAV) video sequences. Since the output of the system is based on target motion, we first segment foreground moving areas from the background in each video frame using background subtraction. To stabilize the video, a multi-point-descriptor-based image registration method is performed where a projective model is employed to describe the global transformation between frames. For each detected foreground blob, an object model is used to describe its appearance and motion information. Rather than immediately classifying the detected objects as targets, we track them for a certain period of time and only those with qualified motion patterns are labeled as targets. In the subsequent tracking process, a Kalman filter is assigned to each tracked target to dynamically estimate its position in each frame. Blobs detected at a later time are used as observations to update the state of the tracked targets to which they are associated. The proposed overlap-rate-based data association method considers the splitting and merging of the observations, and therefore is able to maintain tracks more consistently. Experimental results demonstrate that the system performs well on real-world UAV video sequences. Moreover, careful consideration given to each component in the system has made the proposed system feasible for real-time applications.

In recent years, we see an increase of interest for intelligent and efficient tracking systems in surveillance applications. Many of the proposed techniques are designed for static cameras environments. When the camera is moving, tracking moving objects becomes more difficult and many techniques fail to detect and track the desired targets. The problem becomes more complex when we want to track a specific object in real-time using a Pan and Tilt camera system (PTU). Tracking a target using a PTU in order to keep the target within the image is important in surveillance applications. When a target is detected, the possibility of automatically tracking it and keeping it within the image until action is taken is very important for security personnel working in sensitive areas. This work presents a real-time tracking system based on particle filters. The proposed system permits the detection and continuous tracking of a selected target using a Pan and Tilt camera platform. A novel simple and efficient approach for dealing with occlusions is presented. Also a new intelligent forget factor is introduced in order to take into account target shape variations and avoid learning non desired objects. Tests conducted in outdoor operational scenarios show the efficiency and robustness of the proposed approach.

Volitional search systems that assist the analyst by searching for specific targets or objects such as vehicles, factories, airports, etc in wide area overhead imagery need to overcome multiple problems present in current manual and automatic approaches. These problems include finding targets hidden in terabytes of information, relatively few pixels on targets, long intervals between interesting regions, time consuming analysis requiring many analysts, no a priori representative examples or templates of interest, detecting multiple classes of objects, and the need for very high detection rates and very low false alarm rates. This paper describes a conceptual analyst-centric framework that utilizes existing technology modules to search and locate occurrences of targets of interest (e.g., buildings, mobile targets of military significance, factories, nuclear plants, etc.), from video imagery of large areas. Our framework takes simple queries from the analyst and finds the queried targets with relatively minimum interaction from the analyst. It uses a hybrid approach that combines biologically inspired bottom up attention, socio-biologically inspired object recognition for volitionally recognizing targets, and hierarchical Bayesian networks for modeling and representing the domain knowledge. This approach has the benefits of high accuracy, low false alarm rate and can handle both low-level visual information and high-level domain knowledge in a single framework. Such a system would be of immense help for search and rescue efforts, intelligence gathering, change detection systems, and other surveillance systems.

We present four new change detection methods that create an automated change map from a probability map. In this case, the probability map was derived from a 3D model. The primary application of interest is aerial photographic applications, where the appearance, disappearance or change in position of small objects of a selectable class (e.g., cars) must be detected at a high success rate in spite of variations in magnification, lighting and background across the image. The methods rely on an earlier derivation of a probability map. We describe the theory of the four methods, namely Bernoulli variables, Markov Random Fields, connected change, and relaxation-based segmentation, evaluate and compare their performance experimentally on a set probability maps derived from aerial photographs.

The following material is given to address the effect of low slant angle on video interpretability: 1) an equation for the minimum slant angle as a function of field-of-view to prevent no more than a &sqrt2; change in GSD across the scene; 2) evidence for reduced situational awareness due to errors in perceived depth at low slant angle converting to position errors; 3) an equation for optimum slant angle and target orientation with respect to maximizing exposed target area; 4) the impact of the increased probability of occlusion as a function of slant angle; 5) a derivation for the loss of resolution due to atmospheric turbulence and scattering. In addition, modifications to Video-NIIRS for low slant angle are suggested. The recommended modifications for low-slant angle Video-NIIRS are: 1) to rate at or near the center of the scene; and 2) include target orientations in the Video-NIIRS criteria.

Advances have been made in short wave infrared (SWIR) imaging technology to address the most demanding imaging and surveillance applications. Multiple techniques have been developed and deployed in Goodrich's SWIR indium gallium arsenide (InGaAs) cameras to optimize the dynamic range performance of standard, commercial off-the-shelf (COTS) products. New developments have been implemented on multiple levels to give these cameras the unique ability to automatically compensate for changes in light levels over more than 5 orders of magnitude, while improving intra-scenic dynamic range. Features recently developed and implemented include a new Automatic Gain Control (AGC) algorithm, image flash suppression, and a proprietary image-enhancement algorithm with a simplified but powerful user command structure.

Image mosaicking is the process of piecing together multiple video frames or still images from a moving camera to form a wide-area or panoramic view of the scene being imaged. Mosaics have widespread applications in many areas such as security surveillance, remote sensing, geographical exploration, agricultural field surveillance, virtual reality, digital video, and medical image analysis, among others. When mosaicking a large number of still images or video frames, the quality of the resulting mosaic is compromised by projective distortion. That is, during the mosaicking process, the image frames that are transformed and pasted to the mosaic become significantly scaled down and appear out of proportion with respect to the mosaic. As more frames continue to be transformed, important target information in the frames can be lost since the transformed frames become too small, which eventually leads to the inability to continue further. Some projective distortion correction techniques make use of prior information such as GPS information embedded within the image, or camera internal and external parameters. Alternatively, this paper proposes a new algorithm to reduce the projective distortion without using any prior information whatsoever. Based on the analysis of the projective distortion, we approximate the projective matrix that describes the transformation between image frames using an affine model. Using singular value decomposition, we can deduce the affine model scaling factor that is usually very close to 1. By resetting the image scale of the affine model to 1, the transformed image size remains unchanged. Even though the proposed correction introduces some error in the image matching, this error is typically acceptable and more importantly, the final mosaic preserves the original image size after transformation. We demonstrate the effectiveness of this new correction algorithm on two real-world unmanned air vehicle (UAV) sequences. The proposed method is shown to be effective and suitable for real-time implementation.

Remote sensing is widely applied to provide information of areas with limited ground access with applications such as to assess the destruction from natural disasters and to plan relief and recovery operations. However, the data collection of aerial digital images is constrained by bad weather, atmospheric conditions, and unstable camera or camcorder. Therefore, how to recover the information from the low-quality remote sensing images and how to enhance the image quality becomes very important for many visual understanding tasks, such like feature detection, object segmentation, and object recognition. The quality of remote sensing imagery can be improved through meaningful combination of the employed images captured from different sensors or from different conditions through information fusion. Here we particularly address information fusion to remote sensing images under multi-resolution analysis in the employed image sequences. The image fusion is to recover complete information by integrating multiple images captured from the same scene. Through image fusion, a new image with high-resolution or more perceptive for human and machine is created from a time series of low-quality images based on image registration between different video frames.

Digital video mosaicking from Unmanned Aircraft Systems (UAS) is being used for many military and civilian applications, including surveillance, target recognition, border protection, forest fire monitoring, traffic control on highways, monitoring of transmission lines, among others. Additionally, NASA is using digital video mosaicking to explore the moon and planets such as Mars. In order to compute a "good" mosaic from video captured by a UAS, the algorithm must deal with motion blur, frame-to-frame jitter associated with an imperfectly stabilized platform, perspective changes as the camera tilts in flight, as well as a number of other factors. The most suitable algorithms use SIFT (Scale-Invariant Feature Transform) to detect the features consistent between video frames. Utilizing these features, the next step is to estimate the homography between two consecutives video frames, perform warping to properly register the image data, and finally blend the video frames resulting in a seamless video mosaick. All this processing takes a great deal of resources of resources from the CPU, so it is almost impossible to compute a real time video mosaic on a single processor. Modern graphics processing units (GPUs) offer computational performance that far exceeds current CPU technology, allowing for real-time operation. This paper presents the development of a GPU-accelerated digital video mosaicking implementation and compares it with CPU performance. Our tests are based on two sets of real video captured by a small UAS aircraft; one video comes from Infrared (IR) and Electro-Optical (EO) cameras. Our results show that we can obtain a speed-up of more than 50 times using GPU technology, so real-time operation at a video capture of 30 frames per second is feasible.

UAV have a growing importance for reconnaissance and surveillance. Due to improved technical capability also small UAVs have an endurance of about 6 hours, but less sophisticated sensors due to strong weight limitations. This puts a high strain and workload on the small teams usually deployed with such systems. To lessen the strain for photo interpreters and to improve the capability of such systems we have developed and integrated automatic image exploitation algorithms. An import aspect is the detection of moving objects to give the photo interpreter (PI) hints were such objects are. Mosaiking of imagery helps to gain better oversight over the scene. By computing stereo-mosaics from mono-ocular video-data also 3-d-models can be derived from tactical UAV-data in a further processing step. A special instrument of gaining oversight is to use multi-temporal and multifocal images of video-sensors with different resolution of the platform and to fusion them into one image. This results in a good situation awareness of the scene with a light-weight sensor-platform and a standard video link.

Monitoring video data sources received from UAVs is especially challenging because of the quality of the video received. Due to the individual characteristics of the unmanned platform and the changing environment, the important elements in the scene are not always observable or easily identified. In addition to typical sensor noise, significant image degradation can occur during transmission of the video from an airborne platform. Interference from other transmitters, analog noise in the embedded avionics, and multi-path effects can corrupt the video signal during transmission, introducing distortion in the video received at the ground. In some cases, the loss of signal is so severe; no information is received in portions of an image frame. To improve the corrupt video, we capitalize on the oversampling in the temporal domain (across video frames), applying a data fusion approach to de-noise the video. The resulting video retains the significant scene content and dynamics, without distracting artifacts from noise. This allows humans to easily ingest the information from the video, and make it possible to utilize further video exploitation algorithms such as object detection and tracking.

We describe the Materials and Components for Missile (MCM) Innovation and Technology Partnership (ITP) programme. The MCM - ITP is an Anglo-French research programme started in 2007 to encourage early stage research in future weapons technology. SELEX Galileo leads the domain related to the Electro-Optic Sensor within future guided weapons. Our objective is to capture cutting edge ideas in the research community and develop them for exploitation in future missile generations. We provide a view of two areas where we believe development of enhanced seeker capability should be focussed. Examples of current research within and outside the ITP that may be harnessed to deliver these capabilities are provided.

This paper details and evaluates a system that aims to provide continuous robust localisation ('tracking') of vehicles throughout the scenes of aerial video footage captured by Unmanned Aerial Vehicles (UAVs). The scientific field of UAV object tracking is well studied in the field of computer vision, with a variety of solutions offered. However, rigorous evaluation is infrequent, and further novelty lies here in our exploration of the benefits of combined modality processing, in conjunction with a proposed adaptive feature weighting technique. Building on our previously reported framework for object-tracking in multi-spectral video¹, moving vehicles are initially located by exploiting their intrascene displacement within a camera-motion compensated video-image domain. For each detected vehicle, a spatiogram²-based representation is then extracted, which is a representative form that aims to bridge the gap between the 'coarseness' of histograms and the 'rigidity' of pixel templates. Spatiogram-based region matching then ensues for each vehicle, towards determining their new locations throughout the subsequent frames of the video sequence. The framework is flexible in that, in addition to the exploitation of traditional visible spectrum features, it can accommodate the inclusion of additional feature sources, demonstrated here via the attachment of an infrared channel. Furthermore, the system provides the option of enabling an adaptive feature weighting mechanism, whereby the transient ability of certain features to occasionally outperform others is exploited in an adaptive manner, to the envisaged benefit of increased tracking robustness. The system was developed and tested using the DARPA VIVID2 video dataset³, which is a suite of multi-spectral (visible and thermal infrared) video files captured from an airborne platform flying at various altitudes. Evaluation of the system is quantitative, which differentiates it from a large portion of the existing literature, whilst the results observed serve to further reveal the challenging nature of this problem.

Since actual application of Target Recognition is often under outdoor natural circumstances, existence and variance of illumination can not be obviously neglected. Common-used target recognition algorithm having been applied to images under diverse illumination, the effect seems undesirable. Thus, the authors have applied Retinex Theory to amend the target recognition algorithm based on wavelet moment. Applying the amended algorithm to marine images, experimental results have shown a notably optimizing effect.

In recent decades, hyperspectral Images (HSI) have been widely exploited in many fields for rich information containing in them. Many algorithms have been brought out for endmember extracting, among which, VCA algorithm performs a better precision and lower complexity. However, endmembers of the same HIS extracted with traditional VCA algorithm are not always the same in different runs. After deeply analyzing, the authors have proposed an improved VCA algorithm to resolve that shortcoming. For verification, experiment and comparative study have been performed. On conclusion, the improved VCA algorithm has manifested higher efficiency and accuracy than the traditional one.

There exists a wealth of information in the scientific literature on the physical properties and device characterization procedures for complementary metal oxide semiconductor (CMOS), charge coupled device (CCD) and avalanche photodiode (APD) format detectors. Numerous papers and books have also treated photocathode operation in the context of photomultiplier tube (PMT) operation for either non imaging applications or limited night vision capability. However, much less information has been reported in the literature about the characterization procedures and properties of photocathode detectors with novel cross delay line (XDL) anode structures. These allow one to detect single photons and create images by recording space and time coordinate (X, Y & T) information. In this paper, we report on the physical characteristics and performance of a cross delay line anode sensor with an enhanced near infrared wavelength response photocathode and high dynamic range micro channel plate (MCP) gain (> 10⁶ ) multiplier stage. Measurement procedures and results including the device dark event rate (DER), pulse height distribution, quantum and electronic device efficiency (QE & DQE) and spatial resolution per effective pixel region in a 25 mm sensor array are presented. The overall knowledge and information obtained from XDL sensor characterization allow us to optimize device performance and assess capability. These device performance properties and capabilities make XDL detectors ideal for remote sensing field applications that require single photon detection, imaging, sub nano-second timing response, high spatial resolution (10's of microns) and large effective image format.ÿ

Monitoring the soil composition of agricultural land is important for maximizing crop-yields. Carinthian Tech Research, Schiebel GmbH and Quest Innovations B.V. have developed a multi-spectral imaging system that is able to simultaneously capture three visible and two near infrared channels. The system was mounted on a Schiebel CAMCOPTER^® S-100 UAV for data acquisition. Results show that the system is able to classify different land types and calculate vegetation indices.