Estimation of Vehicle’s Lateral Position via the Lucas-Kanade Optical Flow Method

The use of rumble strips on roads has proven to be an effective means of providing drivers lane departure warning (LDW). However, rumble strips require an infrastructure and do not exist on a majority of roadways. Therefore, it is desired to develop an effective virtual rumble-strip LDW system. However, before developing such a system, it is essential that we know the vehicle’s lateral characteristics; in particular, the vehicle’s lateral position and speed. In this paper, we focus on using image processing via an in-vehicle camera to estimate the vehicle’s lateral position and speed. The lateral position is determined by finding the vehicle’s heading angle via a homography and the Lucas-Kanade optical flow techniques; while the lateral speed is determined via the heading angle and the vehicle’s On Board Diagnostic (OBD) System forward speed data. This paper describes our approach and findings in some detail together with suggested improvements. The advantage of our approach is that only the minimal set of information to characterize the vehicle lateral characteristics is needed and thus, making it more feasible in a vehicle application. Key-Words: Heading angle, homography, histogram equalization, Harris corner, feature selection and tracking, optical flow.