Search Results

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.

A new automotive vision platform has been developed for practical applications. The vision platform simultaneously realizes high-performance computing power and reliability for automotive use by using a newly developed dedicated image processor. The developed processor has specialized and novel hardware allowing it to process a large amount of image data at high speed under a moderate clock frequency. The vision platform has enough capability to process multiple applications at the same time. In this paper, we describe the unified memory architecture in the vision platform. We introduce specific functional units for various applications such as the edge analysis unit. We report results from experiments with a real-time on-board lane recognition system.