Robust Lane Detection Using Multiple Features

Abstract

Lane marker detection is a crucial challenge in developing self-driving cars. Despite significant research, large gaps remain between research and needs for fully autonomous driving. We highlight the limitations of present work and present a unified approach for robust and real-time lane marker detection. We present a multi-feature lane detection algorithm and give evidence why relying on one type of features can be harmful. We design a lane model using geometric constraints on lane shape and fit the lane model to the visual cues extracted. We improve the robustness of our algorithm by tracking lane markers temporally. We test our algorithm on KITTI dataset and show results that our algorithm can detect lane markers in presence of occlusions, sharp curves, and shadows.