Juan R. Vasquez

Feature Aided Tracking with Hyperspectral Imagery

Target tracking in an urban environment presents a wealth of ambiguous tracking scenarios that cause a kinematic-only tracker to fail. Partial or full occlusions in areas of tall buildings are particularly problematic as there is often no way to correctly identify the target with only kinematic information. Feature aided tracking attempts to resolve problems with a kinematic-only tracker by extracting features from the data. In the case of panchromatic video, the features are often histograms, the same is true for color video data. In the case where tracks are uniquely different colors, more typical feature aided trackers may perform well. However, a typical urban setting has similar size, shape, and color tracks, and more typical feature aided trackers have no hopes in resolving many of the ambiguities we face. We present a novel feature aided tracking algorithm combining two-sensor modes: panchromatic video data and hyperspectral imagery. The hyperspectral data is used to provide a unique fingerprint for each target of interest where that fingerprint is the set of features used in our feature aided tracker. Results indicate an impressive 19% gain in correct track ID with our hyperspectral feature aided tracker compared to the baseline performance with a kinematic-only tracker.

Enhanced motion and sizing of bank in moving-bank MMAE

The focus of this research is to provide methods for generating precise parameter estimates in the face of potentially significant parameter variations such as system component failures. The standard multiple model adaptive estimation (MMAE) algorithm uses a bank of Kalman filters, each based on a different model of the system. Parameter discretization within the MMAE refers to selection of the parameter values assumed by the elemental Kalman filters, and dynamically redeclaring such discretization yields a moving-bank MMAE. A new online parameter discretization method is developed based on the probabilities associated with the generalized chi-squared random variables formed by residual information from the elemental Kalman filters within the MMAE. This new algorithm is validated through computer simulation of an aircraft navigation system subjected to interference/jamming while attempting a successful precision landing of the aircraft.

Sensor modeling and demonstration of a multi-object spectrometer for performance-driven sensing

A novel multi-object spectrometer (MOS) is being explored for use as an adaptive performance-driven sensor that tracks moving targets. Developed originally for astronomical applications, the instrument utilizes an array of micromirrors to reflect light to a panchromatic imaging array. When an object of interest is detected the individual micromirrors imaging the object are tilted to reflect the light to a spectrometer to collect a full spectrum. This paper will present example sensor performance from empirical data collected in laboratory experiments, as well as our approach in designing optical and radiometric models of the MOS channels and the micromirror array. Simulation of moving vehicles in a highfidelity, hyperspectral scene is used to generate a dynamic video input for the adaptive sensor. Performance-driven algorithms for feature-aided target tracking and modality selection exploit multiple electromagnetic observables to track moving vehicle targets.

Persistent hyperspectral adaptive multi-modal feature-aided tracking

An architecture and implementation is presented regarding persistent, hyperspectral, adaptive, multi-modal, feature-aided tracking within the urban context. A novel remote-sensing imager has been designed which employs a micro-mirror array at the focal plane for per-pixel adaptation. A suite of end-to-end synthetic experiments have been conducted, which include high-fidelity moving-target urban vignettes, DIRSIG hyperspectral rendering, and full image-chain treatment of the prototype adaptive sensor. Corresponding algorithm development has focused on: motion segmentation, spectral feature modeling, classification, fused kinematic/spectral association, and adaptive sensor feedback/control.

Improved hypothesis selection for multiple hypothesis tracking

The need to track closely-spaced targets in clutter is essential in support of military operations. This paper presents a Multiple Hypothesis Tracking (MHT) algorithm which uses an efficient structure to represent the dependency which naturally arises between targets due to the joint observation process, and an Integral Square Error (ISE) mixture reduction algorithm for hypothesis control. The resulting algorithm, denoted MHT with ISE Reduction (MISER), is tested against performance metrics including track life, coalescence and track swap. The results demonstrate track life performance similar to that of ISE-based methods in the single-target case, and a significant improvement in track swap metric due to the preservation of correlation between targets. The result that correlation reduces the track life performance for formation targets requires further investigation, although it appears to demonstrate that the inherent coupling of dynamics noises for such problems eliminates much of the benefit of representing correlation only due to the joint observation process.

Feature-aided tracking via synthetic hyperspectral imagery

Hyperspectral imaging (HSI) feature-aided tracking (FAT) is an emerging area of research, employing HSI instruments and exploitation techniques with the goal to track moving objects within challenging environments and across frequent ambiguities. A series of studies have been conducted to demonstrate HSI-FAT with contemporary and novel HSI instruments. Synthesized HSI data have been the key enabler to this effort. Capabilities have been evaluated with synthetic models of low-cost, off-the-shelf sensors such as a video-rate liquid crystal tunable filter, as well as sophisticated emerging sensor concepts such as microelectromechanical-adapted systems. A suite of end-to-end synthetic experiments have been conducted, which include high-fidelity moving-target urban vignettes, synthetic hyperspectral rendering, and full image-chain treatment of the various sensor models. Corresponding algorithm development has focused on motion segmentation, spectral feature modeling, classification, fused kinematic/spectral association, and adaptive sensor feedback/ control.

A genetic algorithm approach to optimal spatial sampling of hyperspectral data for target tracking

Hyperspectral imagery (HSI) data has proven useful for discriminating targets, however the relatively slow speed at which HSI data is gathered for an entire frame reduces the usefulness of fusing this information with grayscale video. A new sensor under development has the ability to provide HSI data for a limited number of pixels while providing grayscale video for the remainder of the pixels. The HSI data is co-registered with the grayscale video and is available for each frame. This paper explores the exploitation of this new sensor for target tracking. The primary challenge of exploiting this new sensor is to determine where the gathering of HSI data will be the most useful. We wish to optimize the selection of pixels for which we will gather HSI data. We refer to this as spatial sampling. It is proposed that spatial sampling be solved using a utility function where pixels receive a value based on their nearness to a target of interest (TOI). The TOIs are determined from the tracking algorithm providing a close coupling of the tracking and the sensor control. The relative importance or weighting of the different types of TOI will be accomplished by a genetic algorithm. Tracking performance of the spatially sampled tracker is compared to both tracking with no HSI data and although physically unrealizable, tracking with complete HSI data to demonstrate its effectiveness within the upper and lower bounds.

Bio-Inspired Navigation of Chemical Plumes

The ability of many insects, especially moths, to locate either food or a member of the opposite sex is an amazing achievement. There are numerous scenarios where having this ability embedded into ground-based or aerial vehicles would be invaluable. This paper presents results from a 3-D computer simulation of an unmanned aerial vehicle (UAV) autonomously tracking a chemical plume to its source. The simulation study includes a simulated dynamic chemical plume, 6-degree of freedom, nonlinear aircraft model, and a bio-inspired navigation algorithm. The emphasis of this paper is the development and analysis of the navigation algorithm. The foundation of this algorithm is a fuzzy controller designed to categorize where in the plume the aircraft is located: coming into the plume, in the plume, exiting the plume, or out of the plume

Optimal spatial sampling of hyperspectral imagery for fusion with panchromatic video in multitarget tracking

Hyperspectral imagery (HSI) data has proven useful for discriminating targets, however the relatively slow speed at which HSI data is gathered for an entire frame reduces the usefulness of fusing this information with panchromatic video. Additionally, the volume of HSI information collected affects the computational performance of software exploiting the information. Paradoxically, it is too much information and we cannot get enough of it. A new sensor under development has the potential of overcoming this problem. It has the ability to provide HSI data for a limited number of pixels while providing panchromatic video for the remainder of the pixels. The HSI data is co-registered with the panchromatic video and is available at each frame. This paper investigates the exploitation of this new sensor for target tracking. The first challenge of exploiting this sensor is to determine where the gathering of HSI data will be the most useful as compared to collecting panchromatic. We optimize the selection of pixels for which we will gather HSI data. We refer to this as spatial sampling. Spatial sampling is solved using a utility function where pixels receive a value based on their nearness to a target of interest (TOI). The TOIs are determined from the tracking algorithm providing a close coupling of the tracking and the sensor control. The weighting of the different types of TOIs is accomplished by a multiobjective genetic algorithm. Experiments compare fused versus non-fused tracking performance.

Estimating Queue Size in a Computer Network Using an Extended Kalman Filter

An extended Kalman filter is used to estimate queue size in a network. This paper presents the derivation of the transient queue behavior for a system with Poisson traffic and exponential service times. This result is then validated for ideal traffic using a network simulated in OPNET A more complex OPNET model is then used to test the adequacy of the transient queue size model when non-Poisson traffic is combined. The extended Kalman filter theory is presented and a network state estimator is designed using the transient queue behavior model. The behavior of the network state estimator is than investigated.