Recently, lane detection has made great progress in autonomous driving. RESA (REcurrent Feature-Shift Aggregator) is based on image segmentation. It presents a novel module to enrich lane feature after preliminary feature extraction with an ordinary CNN. For Tusimple dataset, there is not too complicated scene and lane has more prominent spatial features. On the basis of RESA, we introduce the method of position embedding to enhance the spatial features. The experimental results show that this method has achieved the best accuracy 96.93% on Tusimple dataset.
@article{arxiv.2203.12301,
title = {Lane detection with Position Embedding},
author = {Jun Xie and Jiacheng Han and Dezhen Qi and Feng Chen and Kaer Huang and Jianwei Shuai},
journal= {arXiv preprint arXiv:2203.12301},
year = {2022}
}