Download Free Cooperative Multi Sensor Data Fusion To Geo Localize Ground Moving Targets Using An Aerial Sensor And A Human As An Additional Sensor Book in PDF and EPUB Free Download. You can read online Cooperative Multi Sensor Data Fusion To Geo Localize Ground Moving Targets Using An Aerial Sensor And A Human As An Additional Sensor and write the review.

The ability to track targets using Unmanned Aerial Vehicles (UAVs) has a wide range of civilian and military applications. For example, for military personnel, it is critical to track and locate a variety of objects, including the movement of enemy vehicles. For civilian applications, we can easily find UAVs performing tasks related to land survey, weather forecasting, search and rescue missions, and monitoring farm crops. This study presents a novel method for determining the locations of moving ground-based targets using UAVs and human operators. In previous research, Sharma et al. [1] developed a vision-based target tracking algorithm. They used a Kalman-filter to estimate the target's position and velocity. An information-filter was used to control the sensor. Targets were geo-localized using the pixel locations of the targets in an image. The measurements of the UAV position, altitude, and camera pose angle along with the information embedded in the image provide the required input to an estimator to geo-locate ground targets. Using the highly sophisticated skills of humans for sensing environments, we are interested in integrating the abilities of human operators as a part of sensor network. The main contribution of this thesis is a cyber-physical system developed for reducing the localization errors of targets observed by either UAVs or humans working cooperatively. In particular, in the process of developing the system, we developed (1) an Extended Kalman Filter (EKF) based algorithm to estimate the positions of multiple targets, (2) a human sensor model using neural networks, and (3) a weighted filter to fuse local target estimations from multiple UAVs. Human sensor inputs were utilized to improve the geo localization accuracy of target position estimates. This technique requires operators to be equipped with an Android device; providing operators an easy access to Google map and Global Positioning System (GPS); such that they can specify a target's position on the map. Each sensor, UAVs or human operators, exchanges data through a Wi-Fi sensor network. A central station is used to collect the information observed by independent sensors for data fusion and combines them to generate more accurate estimates that would not be available from any single UAV or a human operator. The capability of the system was demonstrated using simulation results and Android hardware.
The purpose of this tutorial paper is to present an application example for the MultiUAV cooperative control simulation. MultiUAV has been used to simulate a Cooperative Moving Target Engagement (CMTE) scenario, with a team of UAVs acting as a sensor and communication network to cooperatively track and attack moving ground targets. This scenario illustrates the utility of MultiUAV for cooperative control applications requiring heterogeneous vehicles with varied sensor, communication, dynamic, and weapon capabilities. A human supervisor designates one or more moving ground targets for the vehicles to attack. The vehicle agents must then autonomously and cooperatively determine which vehicles will perform the required tasks, when the tasks will be performed, and what flight paths will be used. This requires assigning time-dependent cooperative and joint tasks, where multiple sub-elements of the primary task must be accomplished by different vehicles, for any of the tasks to have value. This tutorial focuses on the unique requirements of the CMTE scenario and how they are addressed in the MultiUAV simulation.
Proceedings of the NATO Advanced Study Institute on Multisensor Data Fusion, held in Pitlochry, Perthshire, Scotland, June 25-July 7, 2000
The emerging technology of multisensor data fusion has a wide range of applications, both in Department of Defense (DoD) areas and in the civilian arena. The techniques of multisensor data fusion draw from an equally broad range of disciplines, including artificial intelligence, pattern recognition, and statistical estimation. With the rapid evolut
Multisensor data fusion combines data from multiple sensor systems to achieve improved performance and provide more inferences than could be achieved using a single sensor system. One of the most important aspects of data fusion is data association. This dissertation develops new algorithms for data association, including measurement to track association, track to track association and track fusion, in distributed multisensor multitarget environment with overlapping sensor coverage. The performance of the proposed algorithms is compared to that of existing techniques. Computational complexity analysis is also presented. Numerical results based on Monte Carlo simulations and real data collected from the United States Coast Guard Vessel Traffic Services system are presented. The results show that the proposed algorithms reduce the computational complexity and achieve considerable performance improvement over those previously reported in the literature.
Network-Centric Naval Forces: A Transition Strategy for Enhancing Operational Capabilities is a study to advise the Department of the Navy regarding its transition strategy to achieve a network-centric naval force through technology application. This report discusses the technical underpinnings needed for a transition to networkcentric forces and capabilities.
Explains numeric and symbolic approaches to data association, tracking combination, classification, and situation assessment, and provides an overview of data fusion theory and mathematical formalisms.
This dissertation considers the geolocation of a point of interest (POI), i.e., determining the location of a POI in the world, using multiple cooperating uninhabited aerial vehicles (UAVs) with gimballing camera sensors. A square root sigma point information filter (SR-SPIF) is developed to provide a probabilistic estimate of the POI location. The SR-SPIF utilizes the UAV's onboard navigation system to save computation and also takes important properties for numerical accuracy (square root), tracking accuracy (sigma points), and fusion ability (information). The SR-SPIF is general and scales well to any tracking problem with multiple, moving sensors. In the development of the SR-SPIF, the errors in the navigation system output are assumed to be zero mean. However, in the practical application, there are non zero mean errors (biases), which degrade geolocation accuracy. Therefore, a decentralized approach to simultaneously estimate the biases on each UAV and the unknown POI location is developed. The new decentralized bias estimation approach provides accurate geolocation in spite of sensor biases and further scales well with the number of UAVs. Communication is an important part of a cooperative geolocation mission and in practice communication losses and delays are inevitable. Therefore, a new method for cooperative geolocation in the presence of communication loss, termed the predicted information method, is developed from a separable formulation of the extended information filter. The predicted information method is shown to give the exact solution for linear systems when the measurement dynamics are constant or known by all UAVs. In addition to theoretical developments, extensive experimental flight tests with ScanEagle UAVs have been performed. The experimental flight tests serve two purposes: 1) to develop practical guidelines for geolocation 2) to validate all of the new approaches presented in this dissertation. In addition to the flight tests, a high fidelity, distributed, hardware in the loop simulation test bed was developed and used as further validation of all new approaches.