SOTAVerified

Lane Detection

Lane Detection is a computer vision task that involves identifying the boundaries of driving lanes in a video or image of a road scene. The goal is to accurately locate and track the lane markings in real-time, even in challenging conditions such as poor lighting, glare, or complex road layouts.

Lane detection is an important component of advanced driver assistance systems (ADAS) and autonomous vehicles, as it provides information about the road layout and the position of the vehicle within the lane, which is crucial for navigation and safety. The algorithms typically use a combination of computer vision techniques, such as edge detection, color filtering, and Hough transforms, to identify and track the lane markings in a road scene.

( Image credit: End-to-end Lane Detection )

Papers

Showing 150 of 251 papers

TitleStatusHype
Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation ModelsCode3
Panacea+: Panoramic and Controllable Video Generation for Autonomous DrivingCode3
PETRv2: A Unified Framework for 3D Perception from Multi-Camera ImagesCode3
TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving ScenesCode2
LATR: 3D Lane Detection from Monocular Images with TransformerCode2
A Keypoint-based Global Association Network for Lane DetectionCode2
Monocular Lane Detection Based on Deep Learning: A SurveyCode2
YOLOPv2: Better, Faster, Stronger for Panoptic Driving PerceptionCode2
End to End Learning for Self-Driving CarsCode2
CLRerNet: Improving Confidence of Lane Detection with LaneIoUCode2
Ultra Fast Structure-aware Deep Lane DetectionCode2
Rethinking Efficient Lane Detection via Curve ModelingCode2
Anchor3DLane++: 3D Lane Detection via Sample-Adaptive Sparse 3D Anchor RegressionCode2
TwinLiteNetPlus: A Stronger Model for Real-time Drivable Area and Lane SegmentationCode2
Sketch and Refine: Towards Fast and Accurate Lane DetectionCode2
Ultra Fast Deep Lane Detection with Hybrid Anchor Driven Ordinal ClassificationCode2
DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view RepresentationCode2
PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane BenchmarkCode2
Enhancing 3D Lane Detection and Topology Reasoning with 2D Lane PriorsCode2
CLRNet: Cross Layer Refinement Network for Lane DetectionCode2
ONCE-3DLanes: Building Monocular 3D Lane DetectionCode2
OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD MappingCode2
You Only Look at Once for Real-time and Generic Multi-TaskCode2
HybridNets: End-to-End Perception NetworkCode2
TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous DrivingCode2
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask LearningCode1
Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation MapsCode1
3D-LaneNet: End-to-End 3D Multiple Lane DetectionCode1
Polar R-CNN: End-to-End Lane Detection with Fewer AnchorsCode1
Key Points Estimation and Point Instance Segmentation Approach for Lane DetectionCode1
Keep your Eyes on the Lane: Real-time Attention-guided Lane DetectionCode1
Lane2Seq: Towards Unified Lane Detection via Sequence GenerationCode1
LaneAF: Robust Multi-Lane Detection with Affinity FieldsCode1
Inter-Region Affinity Distillation for Road Marking SegmentationCode1
Lane Detection in Low-light Conditions Using an Efficient Data Enhancement : Light Conditions Style TransferCode1
PolyLaneNet: Lane Estimation via Deep Polynomial RegressionCode1
FENet: Focusing Enhanced Network for Lane DetectionCode1
K-Lane: Lidar Lane Dataset and Benchmark for Urban Roads and HighwaysCode1
CLRmatchNet: Enhancing Curved Lane Detection with Deep Matching ProcessCode1
ADNet: Lane Shape Prediction via Anchor DecompositionCode1
CLRKDNet: Speeding up Lane Detection with Knowledge DistillationCode1
An intelligent modular real-time vision-based system for environment perceptionCode1
Generating Dynamic Kernels via Transformers for Lane DetectionCode1
End-to-End Lane detection with One-to-Several TransformerCode1
CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional ConvolutionCode1
Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse LanesCode1
LDNet: End-to-End Lane Marking Detection Approach Using a Dynamic Vision SensorCode1
CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World DomainsCode1
End-to-End Lane Marker Detection via Row-wise ClassificationCode1
Learning to Predict Navigational Patterns from Partial ObservationsCode1
Show:102550
← PrevPage 1 of 6Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DLNetF1 score81.23Unverified
2CLRerNet-DLA34F1 score81.12Unverified
3CLRerNet-Res101F1 score80.91Unverified
4CondLSTR(ResNet-101)F1 score80.77Unverified
5CLRerNet-Res34F1 score80.76Unverified
6CLRKDNet (DLA-34)F1 score80.68Unverified
7CLRNetV2 (DLA34)F1 score80.68Unverified
8CondLSTR(ResNet-34)F1 score80.55Unverified
9CLRNet(DLA-34)F1 score80.47Unverified
10CLRNetV2 (ResNet101)F1 score80.43Unverified
#ModelMetricClaimedVerifiedStatus
1SCNN_UNet_Attention_PL*Accuracy98.38Unverified
2GANet(ResNet-34)F1 score97.71Unverified
3GANet(ResNet-18)F1 score97.68Unverified
4CLRNet(ResNet-101)F1 score97.62Unverified
5GANet(ResNet-101)F1 score97.45Unverified
6CondLaneNet(ResNet-34)F1 score97.01Unverified
7CLRNetV2 (ResNet18)Accuracy96.99Unverified
8PE-RESAAccuracy96.93Unverified
9FOLOLane(ERFNet)Accuracy96.92Unverified
10CLRNet(ResNet-34)Accuracy96.9Unverified
#ModelMetricClaimedVerifiedStatus
1CondLSTR (ResNet-101)F1 score88.47Unverified
2CondLSTR (ResNet-34)F1 score88.23Unverified
3CondLSTR (ResNet-18)F1 score87.99Unverified
4CANet-LF1 score87.87Unverified
5CLRNetV2 (ResNet101)F1 score87.81Unverified
6CANet-MF1 score87.19Unverified
7CANet-SF1 score86.57Unverified
8CLRerNet-DLA34F1 score86.47Unverified
9CondLaneNet-L(ResNet-101)F1 score86.1Unverified
10CLRNet-DLA34F1 score86.1Unverified
#ModelMetricClaimedVerifiedStatus
1TwinLiteNetPlus-LargeIoU (%)34.2Unverified
2TwinLiteNetPlus-MediumIoU (%)32.3Unverified
3HybridNetsIoU (%)31.6Unverified
4TwinLiteNetIoU (%)31.08Unverified
5TriLiteNet-baseIoU (%)29.8Unverified
6TwinLiteNetPlus-SmallIoU (%)29.3Unverified
7A-YOLOM(s)IoU (%)28.8Unverified
8YOLOPv2IoU (%)27.25Unverified
9YOLOPIoU (%)26.2Unverified
10TwinLiteNetPlus-NanoIoU (%)23.3Unverified
#ModelMetricClaimedVerifiedStatus
1FENetV2mF171.85Unverified
2CLRNet (DLA-34)F10.96Unverified
3BézierLaneNet (ResNet-34)F10.96Unverified
4LaneAFF10.96Unverified
5CLRNet (ResNet-18)F10.96Unverified
6BézierLaneNet (ResNet-18)F10.96Unverified
7LaneATT (ResNet-34)F10.94Unverified
8LaneATT (ResNet-122)F10.94Unverified
9LaneATT (ResNet-18)F10.93Unverified
10PolyLaneNetF10.88Unverified
#ModelMetricClaimedVerifiedStatus
1DSLPIoU0.45Unverified
2LaneGraphNetIoU0.42Unverified
3STSUIoU0.39Unverified
#ModelMetricClaimedVerifiedStatus
1CondLSTR (ResNet-101)F1 score63.4Unverified
2CondLSTR (ResNet-34)F1 score62Unverified
3CondLSTR (ResNet-18)F1 score60.1Unverified
#ModelMetricClaimedVerifiedStatus
1VPGNetF10.88Unverified
2Overfeat CNN detector + DBSCANF10.87Unverified
#ModelMetricClaimedVerifiedStatus
1VPGNetF10.87Unverified
2Overfeat CNN detector + DBSCANF10.86Unverified
#ModelMetricClaimedVerifiedStatus
1LDNetAverage IOU62.79Unverified
#ModelMetricClaimedVerifiedStatus
1LLDN-GFCF182.12Unverified
#ModelMetricClaimedVerifiedStatus
1TopoLogicmAP33.2Unverified
#ModelMetricClaimedVerifiedStatus
1SCNN_UNet_Attention_PL*F10.92Unverified