Rethinking Efficient Lane Detection via Curve Modeling

Feng, Zhengyang; Guo, Shaohua; Tan, Xin; Wang, Min; Ma, Lizhuang

doi:10.1109/cvpr52688.2022.01655

Cited by 117 publications

(61 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under the guidance of the vehicle's position information, the occluded lanes are completed. BézierLaneNet [5] proposes using bézier curves as lane representation and a feature flip fusion module to exploit the symmetry property of lanes. Its accuracy is higher than methods based on polynomial curve representation but still lags behind the state-of-the-art methods.…”

Section: Curve-based Methodsmentioning

confidence: 99%

“…To generate b-spline ground truth, similar to the method in BézierLaneNet [5], we fit the labeled points of the lanes in datasets to b-spline curves. N dis is the number of sample points on each curve.…”

Section: The Lane Representationmentioning

confidence: 99%

“…The previous distance calculation methods [5,27] between curves don't fully align with our optimization objective. For instance, PolyLaneNet [27] calculates the distance between sample points on the uniformly sampled row lines as the distance between curves.…”

Section: Distance Between Curvesmentioning

confidence: 99%

“…When angle θ between lane and sampled row lines is small, the magnifying factor will go to infinity. Recently, BézierLaneNet [5] proposes to calculate the distance of curves as the average of distances between sampling points with the same u, and the distance between bézier curves A and B is D AB . We show three bézier curves in Fig.…”

Section: Distance Between Curvesmentioning

confidence: 99%

See 3 more Smart Citations

BSNet: Lane Detection via Draw B-spline Curves Nearby

Haoxin¹,

Wang²,

Liu³

2023

Preprint

View full text Add to dashboard Cite

Curve-based methods are one of the classic lane detection methods. They learn the holistic representation of lane lines, which is intuitive and concise. However, their performance lags behind the recent state-of-the-art methods due to the limitation of their lane representation and optimization. In this paper, we revisit the curve-based lane detection methods from the perspectives of the lane representations' globality and locality. The globality of lane representation is the ability to complete invisible parts of lanes with visible parts. The locality of lane representation is the ability to modify lanes locally which can simplify parameter optimization. Specifically, we first propose to exploit the bspline curve to fit lane lines since it meets the locality and globality. Second, we design a simple yet efficient network BSNet to ensure the acquisition of global and local features. Third, we propose a new curve distance to make the lane detection optimization objective more reasonable and alleviate ill-conditioned problems. The proposed methods achieve state-of-the-art performance on the Tusimple, CU-Lane, and LLAMAS datasets, which dramatically improved the accuracy of curve-based methods in the lane detection task while running far beyond real-time (197FPS).

show abstract

Section: Curve-based Methodsmentioning

confidence: 99%

Section: The Lane Representationmentioning

confidence: 99%

Section: Distance Between Curvesmentioning

confidence: 99%

Section: Distance Between Curvesmentioning

confidence: 99%

See 2 more Smart Citations

BSNet: Lane Detection via Draw B-spline Curves Nearby

Haoxin¹,

Wang²,

Liu³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…By setting the row-anchor in the row direction and setting the grid cell in the colume direction to model the 2D lane lines on the image space, row-wise methods greatly improve the speed of inference. [9,31] argue that the lane line can be fitted by specific curve parameters on the 2D image space. So it is proposed that the 2D lane detection can be converted into the problem of curve parameters regressing by detecting starting point, ending point and curve parameters.…”

Section: Related Workmentioning

confidence: 99%

BEV Lane Det: Fast Lane Detection on BEV Ground

Wang¹,

Qin²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recently, 3D lane detection has been an actively developing area in autonomous driving which is the key to routing the vehicle. However, the previous work did not balance performance and effectiveness.This work proposes a deployment-oriented monocular 3D lane detector with only naive CNN and FC layers. This detector achieved state-of-the-art results on the Apollo 3D Lane Synthetic dataset and OpenLane real-world dataset with 96 FPS runtime speed. We conduct three techniques in our detector: (1) Virtual Camera eliminates the difference in poses of cameras mounted on different vehicles. (2) Spatial Transformation Pyramid as a light-weighed front-view to birdeye view transformer can utilize multiscale image-view featmaps. (3) YOLO-Style Representation makes a good balance between bird-eye view resolution and runtime speed, and it can reduce the inefficiency caused by the class imbalance due to the sparsity of the lane detection task during training. Experimental results show that our work outperforms state-of-the-art approaches by 10.6% F1-Score on OpenLane dataset and 4.0% F1-Score on Apollo 3D synthetic dataset and with speed of 96 FPS. The source code will release at https://github.com/hm-gigo-team/bev_lane_det.

show abstract