An Onboard Virtual Rumble-Strip Based Operation for Road Departure Warning Phase II - FY12 NATSRL

Principal Investigator:

Jiann-Shiou Yang, Professor, UMD-Electrical Engineering

Project Summary:

Techniques such as lane departure warning (LDW) systems can improve traffic safety significantly. An LDW system should be able to detect when a driver is in danger of departing the road, then trigger an alarm to warn the driver early enough to take corrective action. This work developed a new prototype LDW system. The system is primarily an image-based approach that finds a vehicle's lateral characteristics and then uses that information to establish an operation algorithm to determine whether a warning signal should be issued based on the status of the vehicle deviating from its heading lane. The system developed takes a mixed approach by integrating the Lucas-Kanade (L-K) optical flow and the Hough transform-based lane detection methods in its implementation. The L-K point tracking is used when lane boundaries cannot be detected, while the lane detection technique is used when they become available. Although both techniques are used in the system, only one method is activated at any given time because each technique has its own advantages and disadvantages. The developed LDW system was road tested on I-35, US-53, Rice Lake Road, Martin Road, and Jean Duluth Road. Overall, the system operated correctly as expected, with a false alarm occurring only about 1.18 percent of the operation time. This research explored the system implementation, findings, and factors that could affect system performance.

Sponsor:

Project Details: