Methods of analyzing traffic imagery collected from aerial platforms

A limitation of most traditional methods of traffic data collection is that they rely on techniques that are strictly local in nature. Aerial imagery sensors can provide sufficient resolution to sense vehicle locations and movements across broader spatial and temporal scales. Digital imagery, global positioning systems, and automated image processing can be used to improve the spatial coverage, accuracy and cost-effectiveness of the data collection and reduction. In this paper, an approach for collecting and analyzing aerial imagery is given. To illustrate the value of the imagery, the paper outlines methods to generate estimates of speeds, travel times, densities, and queueing delays.

I. Introduction

Research in the use of aerial imagery for transportation has been conducted for over 75 years. In 1927, aerial photography was used to estimate traffic densities on a highway between Baltimore and Washington [1]. In 1947, Greenshields published a paper that dealt with the potential use of aerial photographs in traffic analysis [2]. Other researchers continued to work with aerial photography during the 1950s, 1960s, and early 1970s for traffic operations analysis. Although the data was found to be very useful, this research slowed in the mid-to-late 1970s because of the cost of data collection and the large time and money required to manually reduce the data. Although some of the limitations faced by researchers three decades ago still exist, the technology available today and the understanding gained on remote sensing allow researchers to overcome many of them.