Journal
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
Volume -, Issue -, Pages 888-897Publisher
IEEE COMPUTER SOC
DOI: 10.1109/CVPR52688.2022.00097
Keywords
-
Funding
- National Key Research and Development Program of China [2018AAA0101400]
- National Nature Science Foundation of China [62036009, U1909203, 61936006, 62133013]
- Innovation Capability Support Program of Shaanxi [2021TD-05]
Ask authors/readers for more resources
In this work, a Cross Layer Refinement Network (CLRNet) is proposed to fully utilize both high-level and low-level features for lane detection. By using different feature levels, the contextual information and localization accuracy of lane detection can be improved.
Lane is critical in the vision navigation system of the intelligent vehicle. Naturally, lane is a traffic sign with high-level semantics, whereas it owns the specific local pattern which needs detailed low-level features to localize accurately. Using different feature levels is of great importance for accurate lane detection, but it is still under-explored. In this work, we present Cross Layer Refinement Network (CLRNet) aiming at fully utilizing both high-level and low-level features in lane detection. In particular; it first detects lanes with high-level semantic features then performs refinement based on low-level features. In this way, we can exploit more contextual information to detect lanes while leveraging local detailed lane features to improve localization accuracy. We present ROIGather to gather global context, which further enhances the feature representation of lanes. In addition to our novel network design, we introduce Line IoU loss which regresses the lane line as a whole unit to improve the localization accuracy. Experiments demonstrate that the proposed method greatly outperforms the state-of-the-art lane detection approaches.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available