Browse Publications Technical Papers 2014-01-0167

Development of Lens Condition Diagnosis for Lane Departure Warning by Using Outside Camera 2014-01-0167

Driver safety continues to be improved by advances in active safety technologies. One important example is Lane Departure Warning (LDW). European regulators soon will require LDW in big cars to reduce traffic accidents and New Car Assessment Programs in various countries will include LDW in a few years. Our focus is on rear cameras as sensing devices to recognize lane markers. Rear cameras are the most prevalent cameras for outside monitoring, and new Kids and Cars legislation will make them obligatory in the United States from 2014.
As an affordable sensing system, we envision a rear camera which will function both as a rear-view monitoring device for drivers and as an LDW sensing device. However, there is a great difficulty involved in using the rear camera: water-droplets and dirt are directly attached to the lens surface, creating bad lens condition.
The purpose of this study is to improve the durability of lane recognition systems when water-droplets and dirt are deposited on the lens surface. First, we developed various diagnostic logics under various lens conditions. We then analyzed the results of various diagnosis and expressed the lens conditions by using two evaluation axes. After that, we improve the durability of the lane recognition system including a judgment function that determines whether to stop the LDW system under heavy dirt and water-droplets.
We conducted driving tests and captured evaluation movies in the United States, Europe, and Japan. We evaluated the lane recognition rate for a total of 8 hours of evaluation movies under various weather conditions. We achieved a lane recognition rate of 95% and improved the durability of the lane recognition system.


Subscribers can view annotate, and download all of SAE's content. Learn More »


Members save up to 17% off list price.
Login to see discount.
Special Offer: Download multiple Technical Papers each year? TechSelect is a cost-effective subscription option to select and download 12-100 full-text Technical Papers per year. Find more information here.
We also recommend:

Clustering and Scaling of Naturalistic Forward Collision Warning Events Based on Expert Judgments


View Details


Intelligent Lighting


View Details


A Systematic Scenario Typology for Automated Vehicles Based on China-FOT


View Details