DLNet: Direction-Aware Feature Integration for Robust Lane Detection in Complex Environments

Description

Code for the paper "DLNet: Direction-Aware Feature Integration for Robust Lane Detection in Complex Environments". Zhaoxuan Lu, Lyuchao Liao, Ruimin Li, Fumin Zou, Sijing Cai and Guangjie Han. The paper is submitted to IEEE Transactions on Intelligent Transportation Systems.

DLNet

Results

Train

Run the following command to train a model on Curvelanes dataset:

python tools/train.py configs/dlnet/curvelanes/dlnet_curvelanes_dla34.py

Run the following command to train a model on CULane dataset:

python tools/train.py configs/dlnet/culane/dlnet_culane_dla34.py

References

• Hirotomusiker/CLRerNet
• Turoad/CLRNet
• CurveLanes Dataset
• CULane Dataset
• open-mmlab/mmdetection
• open-mmlab/mmcv

Acknowledgments

• We would like to express our sincere gratitude to the developers of CLRerNet for their invaluable contributions to the field.

• We thank the CULane , CurveLanes and TUSimple teams for providing their datasets, which were essential for our research on lane detection.