A Keypoint-based Global Association Network for Lane Detection

Wang, Jinsheng; Ma, Yinchao; Huang, Shaofei; Hui, Tianrui; Wang, Fei; Qian, Chen; Zhang, Tianzhu

doi:10.1109/cvpr52688.2022.00145

Cited by 71 publications

(36 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…UFLDv2 [21] proposes a hybrid anchor and uses ordinal classification to improve UFLD's performance. UFLDv2 maintains high speed and improves accuracy, but the accuracy is still lower than state-of-the-art methods (i.e., CLRNet [34], GANet [29]).…”

Section: Row-anchor-based Methodsmentioning

confidence: 99%

“…It first detects local keypoints, then uses offsets between adjacent keypoints to decode holistic lane curves. GANet [29] proposes using offsets between keypoints and lanes' start points to constrain the lane representation globality and proposes LFA to get features of holistic lanes. Keypoint-based methods get lane instances through post-processing, which is low-efficient.…”

Section: Keypoint-based Methodsmentioning

confidence: 99%

“…Curve-based methods' lane representations are holistic curves and have natural globality. The segmentationbased methods [1,17,18,30,33], keypoint-based methods [9,22,29], and row-anchor-based methods [13,20,21] lack lane representation globality. They usually use low-efficient structures to make up for the lack of lane representation globality and get holistic lanes, such as message-passing mechanisms and post-processing.…”

Section: Introductionmentioning

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

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: Row-anchor-based Methodsmentioning

confidence: 99%

Section: Keypoint-based Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

BSNet: Lane Detection via Draw B-spline Curves Nearby

Haoxin¹,

Wang²,

Liu³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Lane regression algorithms can be grouped into key points estimation [5], [6], anchor-based regression [7]- [11] and row-wise regression [12], [27]. PINet [5] combines key points estimation and instance segmentation, and GANet [6] represents lanes as a set of key points which are only related to the start point. PointLaneNet [7] and CurveLane-NAS [8] separate images into non-overlapping grids and regress lanes based on vertical anchors.…”

Section: Related Workmentioning

confidence: 99%

CurveFormer: 3D Lane Detection by Curve Propagation with Curve Queries and Attention

Bai¹,

Chen²,

Fu³

et al. 2022

Preprint

View full text Add to dashboard Cite

3D lane detection is an integral part of autonomous driving systems. Previous CNN and Transformerbased methods usually first generate a bird's-eye-view (BEV) feature map from the front view image, and then use a sub-network with BEV feature map as input to predict 3D lanes. Such approaches require an explicit view transformation between BEV and front view, which itself is still a challenging problem. In this paper, we propose CurveFormer, a single-stage Transformer-based method that directly calculates 3D lane parameters and can circumvent the difficult view transformation step. Specifically, we formulate 3D lane detection as a curve propagation problem by using curve queries. A 3D lane query is represented by a dynamic and ordered anchor point set. In this way, queries with curve representation in Transformer decoder iteratively refine the 3D lane detection results. Moreover, a curve cross-attention module is introduced to compute the similarities between curve queries and image features. Additionally, a context sampling module that can capture more relative image features of a curve query is provided to further boost the 3D lane detection performance. We evaluate our method for 3D lane detection on both synthetic and real-world datasets, and the experimental results show that our method achieves promising performance compared with the state-of-the-art approaches. The effectiveness of each component is validated via ablation studies as well.

show abstract

“…Autonomous driving [3,37,54,62] has drawn remarkable attention in recent years from both industry and academia for pursuing intelligent transportation. As one of the essential functions of autonomous driving system, freespace detection aims to perform binary classification on each pixel of the image to label it as drivable or non-drivable, so as to realize safety-ensured vehicle navigation.…”

Section: Introductionmentioning

confidence: 99%

Cross-Modality Domain Adaptation for Freespace Detection: A Simple yet Effective Baseline

Wang

Zhu

Huang

et al. 2022

Proceedings of the 30th ACM International Conference on Multimedia

View full text Add to dashboard Cite

As one of the fundamental functions of autonomous driving system, freespace detection aims at classifying each pixel of the image captured by the camera as drivable or non-drivable. Current works of freespace detection heavily rely on large amount of densely labeled training data for accuracy and robustness, which is time-consuming and laborious to collect and annotate. To the best of our knowledge, we are the first work to explore unsupervised domain adaptation for freespace detection to alleviate the data limitation problem with synthetic data. We develop a cross-modality domain adaptation framework which exploits both RGB images and surface normal maps generated from depth images. A Collaborative Cross Guidance (CCG) module is proposed to leverage the context information of one modality to guide the other modality in a cross manner, thus realizing inter-modality intra-domain complement. To better bridge the domain gap between source domain (synthetic data) and target domain (real-world data), we also propose a Selective Feature Alignment (SFA) module which only aligns the features of consistent foreground area between the two domains, thus realizing inter-domain intra-modality adaptation. Extensive experiments are conducted by adapting three different synthetic datasets to one real-world dataset for freespace detection respectively. Our method

show abstract

A Keypoint-based Global Association Network for Lane Detection

Cited by 71 publications

References 22 publications

BSNet: Lane Detection via Draw B-spline Curves Nearby

BSNet: Lane Detection via Draw B-spline Curves Nearby

CurveFormer: 3D Lane Detection by Curve Propagation with Curve Queries and Attention

Cross-Modality Domain Adaptation for Freespace Detection: A Simple yet Effective Baseline

Contact Info

Product

Resources

About