Supports lane line detection algorithm RESA 支持车道线检测算法 RESA

[OpenMMLab-Assistant-004]

Supports lane line detection algorithm RESA

支持车道线检测算法 RESA

Issue with requirements: [open-mmlab/mmsegmentation#3160](https://github.com/open-mmlab/mmsegmentation/issues/3160](https://github.com/open-mmlab/mmsegmentation/issues/3160))

1. need to align inference precision on the basis of CULane and Tusimple datasets
2. need to support model training, if the training accuracy cannot be aligned to the paper accuracy, this algorithm can be added to the projects
3. need to support the evaluation method required by the paper
   Reference Repo:[https://github.com/ZJULearning/resa](https://github.com/ZJULearning/resa](https://github.com/ZJULearning/resa))
   Reference paper: [https://arxiv.org/abs/2008.13719](https://arxiv.org/abs/2008.13719](https://arxiv.org/abs/2008.13719))

Translated with DeepL

提出需求的 issue: [open-mmlab/mmsegmentation#3160](https://github.com/open-mmlab/mmsegmentation/issues/3160](https://github.com/open-mmlab/mmsegmentation/issues/3160))

1. 需要在 CULane 和 Tusimple 数据集的基础上对齐推理精度
2. 需要支持模型训练，如训练精度不能对齐论文精度，可以将此算法加入到 projects 中
3. 需要支持论文要求的评估方法
   参考 Repo:[https://github.com/ZJULearning/resa](https://github.com/ZJULearning/resa](https://github.com/ZJULearning/resa))

参考论文：[https://arxiv.org/abs/2008.13719](https://arxiv.org/abs/2008.13719](https://arxiv.org/abs/2008.13719))

Task Information

Repository：MMSegmentation

Difficulty：Hard

Points：50

Estimated Time Consumption：28 days

Task Status

Claimant's Github ID：None

Claim Time：None

PR Link：None

Points to Note

To claim the task, please reply Claim the mission in the comment section. After claiming the task, please add our assistant bot called MeowMewo on WeChat at: openmmlabwx.

After completing the task, please submit a PR with the title starting with [MMSIG]. After submission, please reply with your PR link in the comments section of this Discussion. We will review your work as soon as possible.

在评论区回复 Claim the mission 领取任务，领取任务后请及时添加小助手喵喵微信: openmmlabwx

完成任务后提交相关链接（如是PR，标题请以[MMSIG]开头）回复到本Disucssion评论区，我们会第一时间审核您的贡献。