abstract: The tracking of multiple targets becomes more challenging in complex environments due to the additional degrees of nonlinearity in the measurement model. In urban terrain, for example, there are multiple reflection path measurements that need to be exploited since line-of-sight observations are not always available. Multiple target tracking in urban terrain environments is traditionally implemented using sequential Monte Carlo filtering algorithms and data association techniques. However, data association techniques can be computationally intensive and require very strict conditions for efficient performance. This thesis investigates the probability hypothesis density (PHD) method for tracking multiple targets in urban environments. The PHD is based on the theory of random finite sets and it is implemented using the particle filter. Unlike data association methods, it can be used to estimate the number of targets as well as their corresponding tracks. A modified maximum-likelihood version of the PHD (MPHD) is proposed to automatically and adaptively estimate the measurement types available at each time step. Specifically, the MPHD allows measurement-to-nonlinearity associations such that the best matched measurement can be used at each time step, resulting in improved radar coverage and scene visibility. Numerical simulations demonstrate the effectiveness of the MPHD in improving tracking performance, both for tracking multiple targets and targets in clutter. / Dissertation/Thesis / M.S. Electrical Engineering 2011

International Telemetering Conference Proceedings / October 28-31, 1985 / Riviera Hotel, Las Vegas, Nevada / Military aerospace test ranges are increasingly being called upon to conduct missions utilizing large numbers of participating units, or targets. Precision, position and trajectory data must be recorded on all participants. In addition, weapon/target engagements must be scored and real-time range safety considerations must be accommodated. This requires precision metric data be available in real-time on all participating targets. One solution to these problems, is utilization of multiple target tracking radars which incorporate electronic beam steering to quickly move from one target to another in sequence. This paper briefly recounts the history of range instrumentation radars, points out some of the advantages of using multi-target radars, and highlights the specifications and design of a multiple target instrumentation radar now being acquired by the U.S. Army for use at White Sands Missile Range and the Kwajalein Missile Range.

When hostile missile raids are launched, protecting allied assets requires that many targets be tracked simultaneously. In these raids, it is possible that the number of missiles could outnumber the sensors available to measure them. In these situations, communication between sensors can be utilized along with dynamic task planning to increase the amount of knowledge available concerning these missiles. Since any allied decisions must depend on the knowledge available from the sensors, it follows that improving the overall knowledge will improve the ability of allies to protect their assets through improved decision making. The goal of the this research effort is to create a Sensor Resource Management (SRM) algorithm to optimize the information available during these missile raids, as well as strengthening the simulation framework required to evaluate the performance of the SRM. The SRM must be capable of near-real-time run time so that it could potentially be deployed in a real-world system. The SRM must be capable of providing time-varying assignments to sensors, allowing more than one target to be observed by a single sensor. The SRM must predict measurements based on sensor models to assess the potential information gain by each assignment. Using these predictions, an optimal allocation of all sensors must be constructed. The initial simulation, upon which this work was built, was capable of simulating a set number of missiles launched simultaneously, providing appropriate charts to display the accuracy of knowledge on each target as well as their predicted impact locations. Communication delays are implemented within the simulation, and sensor models are refined. In refining the sensor models, they are given geometric limitations such as range and viewing angles. Additionally, simulated measurements incorporate geometric considerations to provide more realistic values. The SRM is also improved to account for the details added to the simulation. These improvements include creating assignment schedules and allowing a time-varying numbers of targets. The resulting simulation and SRM are presented, and potential future work is discussed. / text

Reliable track continuity is an important characteristic of multiple target tracking (MTT) algorithms. In the specific case of visually tracking multiple ground targets from an aerial platform, challenges arise due to realistic operating environments such as video compression artifacts, unmodeled camera vibration, and general imperfections in the target detection algorithm. Some popular visual detection techniques include Kanade-Lucas-Tomasi (KLT)-based motion detection, difference imaging, and object feature matching. Each of these algorithmic detectors has fundamental limitations in regard to providing consistent measurements. In this thesis we present a scalable detection framework that simultaneously leverages multiple measurement sources. We present the recursive random sample consensus (R-RANSAC) algorithm in a data fusion architecture that accommodates multiple measurement sources. Robust track continuity and real-time performance are demonstrated with post-processed flight data and a hardware demonstration in which the aircraft performs automated target following. Applications involving autonomous tracking of ground targets occasionally encounter situations where semantic information about targets would improve performance. This thesis also presents an autonomous target labeling framework that leverages cloud-based image classification services to classify targets that are tracked by the R-RANSAC MTT algorithm. The communication is managed by a Python robot operating system (ROS) node that accounts for latency and filters the results over time. This thesis articulates the feasibility of this approach and suggests hardware improvements that would yield reliable results. Finally, this thesis presents a framework for image-based target recognition to address the problem of tracking targets that become occluded for extended periods of time. This is done by collecting descriptors of targets tracked by R-RANSAC. Before new tracks are assigned an ID, an attempt to match visual information with historical tracks is triggered. The concept is demonstrated in a simulation environment with a single target, using template-based target descriptors. This contribution provides a framework for improving track reliability when faced with target occlusions.

<p>This thesis considers the problem of tracking multiple static or moving targets with one single pan/tilt-camera with a limited field of view. The objective is to minimize both the time needed to pan and tilt the camera's view between the targets and the total position uncertainty of all targets. To solve this problem, several planning methods have been developed and evaluated by Monte Carlo simulations and real world experiments. If the targets are moving and their true positions are unknown, both their current and future positions need to be estimated in order to calculate the best sensor trajectory. When dealing with static and known targets the problem is reduced to a deterministic optimization problem.</p><p>The planners have been tested through experiments using a real camera mounted above a car track using toy cars as targets. An algorithm has been developed to detect the cars and associate the detections with the correct target.</p><p>The Monte Carlo simulations show that, in the case of static targets, there is a huge advantage to arrange the targets into groups to be able to view more than one target at the time. In the case of moving targets with estimated positions it can be concluded that if the objective is to minimize the error in the position estimation the best planning choice is to always move to the target with the highest position uncertainty.</p>

No description available.

This thesis considers the problem of tracking multiple static or moving targets with one single pan/tilt-camera with a limited field of view. The objective is to minimize both the time needed to pan and tilt the camera's view between the targets and the total position uncertainty of all targets. To solve this problem, several planning methods have been developed and evaluated by Monte Carlo simulations and real world experiments. If the targets are moving and their true positions are unknown, both their current and future positions need to be estimated in order to calculate the best sensor trajectory. When dealing with static and known targets the problem is reduced to a deterministic optimization problem. The planners have been tested through experiments using a real camera mounted above a car track using toy cars as targets. An algorithm has been developed to detect the cars and associate the detections with the correct target. The Monte Carlo simulations show that, in the case of static targets, there is a huge advantage to arrange the targets into groups to be able to view more than one target at the time. In the case of moving targets with estimated positions it can be concluded that if the objective is to minimize the error in the position estimation the best planning choice is to always move to the target with the highest position uncertainty.

In recent years, ultra-wideband (UWB) radars are gaining popularity in the radar field mainly inindustrial and commercial areas. The UWB radar has the potential of dramatically improving thecontrol and surveillance of industrial processes in confined areas.The report provides an introduction to radar systems and detail working principle of M-sequenceUWB radar and methodology of how detection of targets is carried out. First two chapters of thereport describes the working of radar systems and M-sequence radar whereas in the later part ofthe report, different detection algorithms are discussed which has been implemented in thepresent radar simulations. In conventional radar the main detection algorithm is matched filteringwhere the transmitted signal is correlated with the received signal. Whereas UWB signal is nonsinusoidalthat is vulnerable to change in its shape during entire radar operation. This is thereason, the traditional signal processing methods like matched filtering or correlation process arenot advisable for UWB signals. Therefore, a different detection scheme known as Inter-periodcorrelation process (IPCP) has been studied.IPCP technique had been implemented and a comparison was made with the conventional targetdetection algorithm. On the basis of comparison made in this project, it has been observed thatthe conventional target detection methods are not effective in case of M-sequence UWB radar.The simulation results shows that by implementing IPCP method, performance close to 8-bitADC can be achievable with 1-bit comparator, also with IPCP implementation system resolutioncan be enhance effectively.Main focus was to analyze how close the system can detect two targets, therefore in all themeasurements i.e. practical and simulated measurements, only two targets were used.

Understanding the content of a video sequence is not a particularly difficult problem for humans. We can easily identify objects, such as people, and track their position and pose within the 3D world. A computer system that could understand the world through videos would be extremely beneficial in applications such as surveillance, robotics, biology. Despite significant advances in areas like tracking and, more recently, 3D static scene understanding, such a vision system does not yet exist. In this work, I present progress on this problem, restricted to videos of objects that move in smoothly and which are relatively easily detected, such as people. Our goal is to identify all the moving objects in the scene and track their physical state (e.g., their 3D position or pose) in the world throughout the video. We develop a Bayesian generative model of a temporal scene, where we separately model data association, the 3D scene and imaging system, and the likelihood function. Under this model, the video data is the result of capturing the scene with the imaging system, and noisily detecting video features. This formulation is very general, and can be used to model a wide variety of scenarios, including videos of people walking, and time-lapse images of pollen tubes growing in vitro. Importantly, we model the scene in world coordinates and units, as opposed to pixels, allowing us to reason about the world in a natural way, e.g., explaining occlusion and perspective distortion. We use Gaussian processes to model motion, and propose that it is a general and effective way to characterize smooth, but otherwise arbitrary, trajectories. We perform inference using MCMC sampling, where we fit our model of the temporal scene to data extracted from the videos. We address the problem of variable dimensionality by estimating data association and integrating out all scene variables. Our experiments show our approach is competitive, producing results which are comparable to state-of-the-art methods.

abstract: Neural activity tracking using electroencephalography (EEG) and magnetoencephalography (MEG) brain scanning methods has been widely used in the field of neuroscience to provide insight into the nervous system. However, the tracking accuracy depends on the presence of artifacts in the EEG/MEG recordings. Artifacts include any signals that do not originate from neural activity, including physiological artifacts such as eye movement and non-physiological activity caused by the environment. This work proposes an integrated method for simultaneously tracking multiple neural sources using the probability hypothesis density particle filter (PPHDF) and reducing the effect of artifacts using feature extraction and stochastic modeling. Unique time-frequency features are first extracted using matching pursuit decomposition for both neural activity and artifact signals. The features are used to model probability density functions for each signal type using Gaussian mixture modeling for use in the PPHDF neural tracking algorithm. The probability density function of the artifacts provides information to the tracking algorithm that can help reduce the probability of incorrectly estimating the dynamically varying number of current dipole sources and their corresponding neural activity localization parameters. Simulation results demonstrate the effectiveness of the proposed algorithm in increasing the tracking accuracy performance for multiple dipole sources using recordings that have been contaminated by artifacts. / Dissertation/Thesis / Masters Thesis Electrical Engineering 2014