|Title:||Remote Sensing of Multimodal Transportation Systems|
|Authors:||Raj Bridgelall, James B. Rafert, and Denver D. Tolliver|
|Publication Date:||Sep 2016|
|Type:||Research Report – MPC Publications|
Hyperspectral remote sensing is an emerging field with many potential applications in the observation, management, and maintenance of the global transportation infrastructure. This report describes the development of an affordable framework to capture hyperspectral images and models to classify the images. The framework and models enable new approaches to plan, analyze, and assess the performance of multimodal transportation systems. Every hyperspectral image frame contains information in wavelengths that extend well beyond those that humans are capable of seeing or perceiving. The rapid size and cost reduction of both unmanned aircraft systems and hyperspectral image sensors enable easy scaling of the framework. Scaling is achieved simply by conducting multiple parallel missions to achieve broad area coverage at affordable prices. The authors showcase the general utility of the framework to enhance models used for roadway congestion forecasting, railway condition monitoring, and pipeline risk management. The authors offer additional insights by demonstrating a specific utility of the framework and models for the rapid detection of hazardous spills. Practitioners who utilize the framework and models to implement hyperspectral remote sensing platforms will benefit from greater situational awareness to make informed decisions in transportation systems development, operations, and maintenance.
Bridgelall, Raj, James B. Rafert, and Denver D. Tolliver. Remote Sensing of Multimodal Transportation Systems, MPC-16-313. North Dakota State University - Upper Great Plains Transportation Institute, Fargo: Mountain-Plains Consortium, 2016.