We propose and demonstrate a novel architecture for on-the-fly inference while collecting data from sparse sensor networks. In particular, we consider source localization using acoustic sensors dispersed over a large area, with the individual sensors located too far apart for direct connectivity. An Unmanned Aerial Vehicle (UAV) is employed for collecting sensor data, with the UAV route adaptively adjusted based on data from sensors already visited, in order to minimize the time to localize events of interest. The UAV therefore acts as a information-seeking data mule, not only providing connectivity, but also making Bayesian inferences from the data gathered in order to guide its future actions. The system we demonstrate has a modular architecture, comprising efficient algorithms for acoustic signal processing, routing the UAV to the sensors, and source localization. We report on extensive field tests which not only demonstrate the effectiveness of our general approach, but also yield specific practical insights into GPS time synchronization and localization accuracy, acoustic signal and channel characteristics, and the effects of environmental phenomena.
Abstract-We report on a field demonstration of autonomous detection, localization, and verification of multiple acoustic events using sparsely deployed unattended ground sensors, unmanned aerial vehicles (UAV) as data mules, and a ground control interface. A novel algorithm is demonstrated to address the problem of multiple event acoustic source localization in the presence of false and missed detections. We also demonstrate an algorithm to route a UAV equipped with a radio to collect data from sparsely deployed ground sensors that takes advantage of the communication range of the aircraft while adhering to kinematic constraints of the UAV. A second UAV was utilized to provide video verification of localized events to a human operator at a ground control station.
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.
Flyperspectral image sets are three dimensional data volumes that are difficult to exploit by manual means because they are comprised of multiple bands of image data that are not easily visualized or assessed. GTE Government Systems Corporation has developed a system that utilizes Evolutionary Computing techniques to automatically identify materials in terrain hyperspectral imagery. The system employs sophisticated signature preprocessing and a unique combination of non-parametric search algorithms guided by a model based cost function to achieve rapid convergence and pattern recognition. The system is scaleable and is capable of discriminating and identifying pertinent materials that comprise a specific object of interest in the terrain and estimating the percentage of materials present within a pixel of interest (spectral unmixing). The method has been applied and evaluated agamst real hyperspectral imagery data from the AVIRIS sensor. In addition, the process has been applied to remotely sensed infrared spectra collected at the microscopic level to assess the amounts of DNA. RNA and protein present in human tissue samples as an aid to the early detection of cancer.1. BACKGROUND Current multispectral sensors that collect images of the terrain (Landsat, SPOT) provide a handful of spectral bands of imagery that are registered and span the visible to short wave infrared portion of the electromagnetic spectrum. Hyperspectral sensors typically provide hundreds of spectral bands of spatially registered imagery that span a specific portion of the electromagnetic spectrum and provide greater spectral discrimination versus multispectral systems. Figure 1-1 shows an example of a hyperspectral image cube.Figure 1-1: Example of a hyperspectral image cube of Cuprite, Nevada; three bands were selected for red. green and blue for pseudo-coloring the face of the cube. Color coding on edges corresponds to edge pixel spectral signatures. The image was collected by the Jet Propulsion Laboratory using the AVIRIS sensor. Downloaded From: http://proceedings.spiedigitallibrary.org/ on 06/16/2016 Terms of Use: http://spiedigitallibrary.org/ss/TermsOfUse.aspxPrior techniques for hyperspectral imagery exploitation use model based or least squares approaches to detect and classify materials present in the data. Some of the disadvantages of these techniques are:. Notrobust across different sets of imagery collected from the same sensor at separate times and spatial locations . Cannot accurately determine the presence of other materials (spectral unmixing) in a pixel spectral signature . They are computationally complex . They do not easily conform to non-linear sensor, atmospheric and mixing models . Some of the existing approaches do not easily scale as the number of endmembers is expanded.The technique described in this paper was presented in a prior SPIE conference [22] and is designed to minimize some of the drawbacks [6,7,8,9, 10, 1 1 , 12,13, 14, 15, 16] observed with existing methods for hyperspectral imagery exploitation. Specif...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.