Transportation, Logistics, and Finance

Permanent URI for this collectionhdl:10365/32213

Browse

Browsing Transportation, Logistics, and Finance by Subject "Autonomous vehicles."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Performance of Hyperspectral Imaging with Drone Swarms
    (2018) Bridgelall, Raj; Upper Great Plains Transportation Institute
    The ongoing proliferation and diversification of remote sensing platforms offers greater flexibility to select from a range of hyperspectral imagers as payloads. The emergence of low-cost unmanned aircraft systems (drones) and their launch flexibility presents an opportunity to maximize spectral resolution while scaling both daily spatial coverage and spatial resolution simultaneously by operating synchronized swarms. This article presents a model to compare the performance of hyperspectral-imaging platforms in terms of their spatial coverage and spatial resolution envelope. The authors develop a data acquisition framework and use the model to compare the achievable performance among existing airborne and spaceborne hyperspectral imaging vehicles and drone swarms. The results show that, subject to cost and operational limitations, a platform implemented with drone swarms has the potential to provide greater spatial resolution for the same daily ground coverage compared to existing airborne platforms.
  • No Thumbnail Available
    Item
    Rapid Hyperspectral Image Classification to Enable Autonomous Search Systems
    (2016) Bridgelall, Raj; Rafert, J. Bruce; Tolliver, Denver D.; Lee, EunSu; Upper Great Plains Transportation Institute
    The emergence of lightweight full-frame hyperspectral cameras is destined to enable autonomous search vehicles in the air, on the ground, and in water. Self-contained and long-endurance systems will yield important new applications, for example, in emergency response and the timely identification of environmental hazards. One missing capability is rapid classification of hyperspectral scenes so that search vehicles can immediately take actions to verify potential targets. Onsite verifications minimize false positives and preclude the expense of repeat missions. Verifications will require enhanced image quality, which is achievable by either moving closer to the potential target or by adjusting the optical system. Such a solution, however, is currently impractical for small mobile platforms with finite energy sources. Rapid classifications with current methods demand large computing capacity that will quickly deplete the on-board battery or fuel. To develop the missing capability, the authors propose a low-complexity hyperspectral image classifier that approaches the performance of prevalent classifiers. This research determines that the new method will require at least 19-fold less computing capacity than the prevalent classifier. To assess relative performances, the authors developed a benchmark that compares a statistic of library endmember separability in their respective feature spaces.