Polar R-CNN: End-to-End Lane Detection with Fewer Anchors

TL;DR

Polar R-CNN, an end-to-end anchor-based method for lane detection that incorporates both local and global polar coordinate systems, facilitates flexible anchor proposals and significantly reduces the number of anchors required without compromising performance.

Abstract

Lane detection is a critical and challenging task in autonomous driving, particularly in real-world scenarios where traffic lanes can be slender, lengthy, and often obscured by other vehicles, complicating detection efforts. Existing anchor-based methods typically rely on prior lane anchors to extract features and subsequently refine the location and shape of lanes. While these methods achieve high performance, manually setting prior anchors is cumbersome, and ensuring sufficient coverage across diverse datasets often requires a large amount of dense anchors. Furthermore, the use of Non-Maximum Suppression (NMS) to eliminate redundant predictions complicates real-world deployment and may underperform in complex scenarios. In this paper, we propose Polar R-CNN, an end-to-end anchor-based method for lane detection. By incorporating both local and global polar coordinate systems, Polar R-CNN facilitates flexible anchor proposals and significantly reduces the number of anchors required without compromising performance.Additionally, we introduce a triplet head with heuristic structure that supports NMS-free paradigm, enhancing deployment efficiency and performance in scenarios with dense lanes.Our method achieves competitive results on five popular lane detection benchmarks--Tusimple, CULane,LLAMAS, CurveLanes, and DL-Rai--while maintaining a lightweight design and straightforward structure. Our source code is available at https://github.com/ShqWW/PolarRCNN.

Figures (17)

• Figure 1: Anchor (i.e., the yellow lines) settings of different methods and the ground truth lanes. (a) The initial anchor settings of CLRNet. (b) The learned anchor settings of CLRNet trained on CULane. (c) The flexible proposal anchors of our method. (d) The ground truth.
• Figure 2: Comparison of NMS thresholds in sparse and dense scenarios. (a) and (b) Ground truths in the dense and sparse scenarios, respectively. (c) Predictions with large NMS thresholds in a dense scenario, resulting in a lane prediction being mistakenly suppressed. (d) Predictions with small NMS thresholds in a sparse scenario, where redundant prediction results are not effectively removed.
• Figure 3: An illustration of the Polar R-CNN architecture. It has a similar pipeline with the Faster R-CNN for the task of object detection, and consists of a backbone, a Feature Pyramid Network with three levels of feature maps, respectively denote by $\boldsymbol{P}_1$, $\boldsymbol{P}_2$ and $\boldsymbol{P}_3$, followed by a Local Polar Module, and a Global Polar Module for lane detection. Based on the designed lane representation and lane anchor representation in polar coordinate system, the local polar module can propose sparse line anchors and the global polar module can produce the final accurate lane predictions. The global polar module includes a triplet head, which comprises the one-to-one (O2O) classification subhead, the one-to-many (O2M) classification subhead, and the one-to-many (O2M) regression subhead.
• Figure 4: Different descriptions for anchor parameters: (a) Ray: defined by its start point (e.g., the green point $\left( x_{1}^{s},y_{1}^{s} \right)$ or the yellow point $\left( x_{2}^{s},y_{2}^{s} \right)$) and direction $\theta^{s}$. (b) Polar: defined by its radius $r$ and angle $\theta$.
• Figure 5: The local polar coordinate system. The ground truth of the radius $\hat{r}_{i}^{l}$ of the $i$-th local pole is defines as the minimum distance from the pole to the lane curve instance. A positive pole has a radius $\hat{r}_{i}^{l}$ that is below a threshold $\lambda^{l}$, and vice versa. Additionally, the ground truth angle $\hat{\theta}_i$ is determined by the angle formed between the radius vector (connecting the pole to the closest point on the lanes) and the polar axis.