Publications

The Federal Highway Administration (FHWA) has had a focused program to improve the integration of weather decision support systems into surface transportation operations since 1999. Clarus (Latin for clear) is the FHWA's most recent surface transportation weather initiative. The Clarus concept is to develop and demonstrate an integrated surface transportation weather observing, forecasting and data management system (Pisano, 2006a). As part of this effort, the FHWA is also promoting research into methods for applying new and existing sensor or probe data. These efforts include utilizing new in-vehicle sensor data that will be part of the vehicle infrastructure initiative (VII) (Pisano, 2006b), and finding innovative ways to use existing camera imagery. MIT Lincoln Laboratory (MIT/LL) was tasked to evaluate the usefulness of camera imagery for sensing ambient and road weather conditions and the feasibility for creating a portable visibility estimation algorithm. This paper gives a general background on the current utilization of camera imagery, including past and ongoing research of automated weather/condition algorithms. This is followed by a description of the MIT/LL camera test site, the analyses performed and the resultant prototype visibility estimation algorithm. In addition, the paper details application of the prototype algorithm to existing state DOT cameras in Utah. The final section discusses the future possibilities of camera-based weather and road condition algorithms.

Thousands of traffic and safety monitoring cameras are deployed or are being deployed all across the country and throughout the world. These cameras serve a wide range of uses from monitoring building access to adjusting timing cycles of traffic lights at clogged intersections. Currently, these images are typically viewed on a wall of monitors in a traffic operations or security center where observers manually monitor potentially hazardous or congested conditions and notify the appropriate authorities. However, the proliferation of camera imagery taxes the ability of the manual observer to track and respond to all incidents. In addition, the images contain a wealth of information, including visibility, precipitation type, road conditions, camera outages, etc., that often goes unreported because these variables are not always critical or go undetected. Camera deployments continue to expand and the corresponding rapid increases in both the volume and complexity of camera imagery demand that automated algorithms be developed to condense the discernable information into a form that can be easily used operationally by users. MIT Lincoln Laboratory (MIT/LL) under funding from the Federal Highway Administration (FHWA) is investigating new techniques to extract weather and road condition parameters from standard traffic camera imagery. To date, work has focused on developing an algorithm to measure atmospheric visibility and prove the algorithm concept. The initial algorithm examines the natural edges within the image (the horizon, tree lines, roadways, permanent buildings, etc) and performs a comparison of each image with a historical composite image. This comparison enables the system to determine the visibility in the direction of the sensor by detecting which edges are visible and which are not. A primary goal of the automated camera imagery feature extraction system is to ingest digital imagery with limited specific site information such as location, height, angle, and visual extent, thereby making the system easier for users to implement. There are, of course, many challenges in providing a reliable automated estimate of the visibility under all conditions (camera blockage/movement, dirt/raindrops on lens, etc) and the system attempts to compensate for these situations. This paper details the work-to-date on the visibility algorithm and defines a path for further development of the overall system.