3D Lane Detection from Front or Surround-View using Joint-Modeling & Matching

arXiv:2401.08036v2 Announce Type: replace
Abstract: 3D lanes offer a more comprehensive understanding of the road surface geometry than 2D lanes, thereby providing crucial references for driving decisions and trajectory planning. While many efforts aim to improve prediction accuracy, we recognize that an efficient network can bring results closer to lane modeling. However, if the modeling data is imprecise, the results might not accurately capture the real-world scenario. Therefore, accurate lane modeling is essential to align prediction results closely with the …

abstract accuracy aim arxiv cs.cv decisions detection driving front geometry lane detection modeling network planning prediction replace results surface trajectory type understanding view while