Lane Line Detection based on Mask R-CNN
Bin Liu, Hongzhe Liu, Jiazheng Yuan
Available Online April 2019.
- https://doi.org/10.2991/icmeit-19.2019.111How to use a DOI?
- lane detection; deep learning; the diversity of samples; Mask R-CNN.
- Lane detection plays an important role in driverless system. However, the complexity of the actual road environment makes lane detection more challenging. In recent years, the rapid development of deep learning has pointed out the direction to solve this problem. Deep learning does not care about the change of environment, but only about the diversity of samples. As long as enough samples are trained, the target can be detected and identified. Based on this, a lane detection algorithm based on Mask R-CNN is proposed, which can not only detect lane quickly, but also reach to a total 97.9% of accuracy on our TSD-Max datasets.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
TY - CONF AU - Bin Liu AU - Hongzhe Liu AU - Jiazheng Yuan PY - 2019/04 DA - 2019/04 TI - Lane Line Detection based on Mask R-CNN BT - 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019) PB - Atlantis Press SN - 2352-538X UR - https://doi.org/10.2991/icmeit-19.2019.111 DO - https://doi.org/10.2991/icmeit-19.2019.111 ID - Liu2019/04 ER -