Robust Visual-based Method and New Datasets for Ego-lane Index Estimation in Urban Environment

Abstract

Correct and robust ego-lane index estimation is crucial for autonomous in the absence of high-definition maps, especially in urban environments. Previous ego-lane index estimation approaches rely on feature extraction, which limited the robustness. To overcome these shortages, this study proposes a robust ego-lane index estimation framework upon only the original visual image. After optimization of processing route, the raw image was randomly cropped in height direction and then input into double supervised LaneLoc network to obtain the index estimations and confidences. A post process was also proposed to achieve the global ego-lane index from the estimated left and right indexes with total lane number. To evaluate our proposed method, we manually annotated the ego-lane index of public datasets which can work as an ego-lane index estimation baseline for the first time. The proposed algorithm achieved 96.48%/95.40% (precision/recall) on CULane dataset and 99.45%/99.49% (precision/recall) on TuSimple dataset, demonstrating the effectiveness and efficiency of lane localization in diverse driving environments. The code and datasets annotation results will be exposed publicly on https://github.com/haomo-ai/LaneLoc.