Small unmanned vertical take off and landing vehicles are used to provide the eye-in-the-sky alternative to monitoring and regulating traffic dynamically. Spatial-temporal visual data are collected in real time and they are used to generate traffic-related statistical profiles, serving as inputs to traffic simulation models. Generated profiles, which are continuously updated, are used to calibrate traffic model parameters, to obtain more accurate and reliable simulation models, and for model modifications. This method overcomes limitations of existing traffic simulation models, which suffer from outdated data, poorly calibrated parameters because of outdated data, questionable accuracy and poor predictions of traffic patterns.

This paper presents a low cost, high powered onboard processing system for miniature unmanned vehicles (UVs), especially unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs). Such vehicles have shown great potential due to their compact size, high maneuverability and high payload-to-size ratio. The proposed on-board processing system differs from other existing designs by utilizing developed commercial off the shelf (COTS) hardware and a full, nongraphical, operating system (OS). The hardware allows for quick development and deployment of the on-board processing system as well as easy integration with new hardware. The full OS allows for simplified software development and testing as well as the use of commercial and open source software. The physical configuration of the system, necessary drivers, and field tests on both aerial and ground vehicles are presented

Alternative designs of a simple, low cost, effective vision system suitable for small, portable, unmanned vertical take off and landing (VTOL) vehicle based surveillance and landmark recognition are presented. Designs depend mainly on two critical constraints: aerial vehicle payload limitations and power supply limitations; both constraints affect on-board vision system configuration, processing power and flexibility. Hardware and software components are described for both designs. Advantages and disadvantages of both alternatives are compared and an implementation of the chosen system is presented along with experimental results.

A two module fuzzy logic controller that also includes a separate error calculating box is derived for autonomous navigation and control of small manned- unmanned aerial vehicles demonstrating ability to fly through specified waypoints in a 3-D environment repeatedly, perform trajectory tracking, and, duplicate/follow another vehicle's trajectory. A MATLAB standard configuration environment and the Aerosim Aeronautical Simulation Block Set are utilized for simulation studies, presented through a visualization interface; results illustrate controller performance and potential.

The paper presents a machine vision system for aerial surveillance that can interpret and process data acquired by a UAV on-board infrared camera. System components include noise reduction, feature extraction, classification and decision-making. Decision-making is performed in terms of an alarm signal. The system has been configured for automatic fire detection applications where the alarm is set off in case of fire identification. Real time tests have been performed and the system has been tested producing sets of real images. Finally, a genetic algorithm was used to automatically define some of the system's parameters.