Vehicle Road Lane Extraction Using Millimeter-Wave Radar Imagery for Self-Driving Applications

Abstract

Millimeter-wave (MMW) radar imaging technology has advanced significantly, providing high-resolution images crucial for various self-driving applications. This letter presents a novel approach for extracting road surfaces within a vehicle's lane using MMW radar imagery. First, the zonal connected area detection algorithm with sliding windows effectively detects feature points in the radar images. Second, the feature point classification algorithm, utilizing horizontal offset values, preliminarily identifies the feature points for the vehicle's lane boundary. Finally, the feature points are refined based on horizontal density, followed by boundary fitting to extract the road surface accurately. Experiments were conducted on three different scenarios and three distinct datasets to verify the effectiveness and generalization ability of the algorithm.