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 51–75 of 251 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | DLNet | F1 score | 81.23 | — | Unverified |
| 2 | CLRerNet-DLA34 | F1 score | 81.12 | — | Unverified |
| 3 | CLRerNet-Res101 | F1 score | 80.91 | — | Unverified |
| 4 | CondLSTR(ResNet-101) | F1 score | 80.77 | — | Unverified |
| 5 | CLRerNet-Res34 | F1 score | 80.76 | — | Unverified |
| 6 | CLRKDNet (DLA-34) | F1 score | 80.68 | — | Unverified |
| 7 | CLRNetV2 (DLA34) | F1 score | 80.68 | — | Unverified |
| 8 | CondLSTR(ResNet-34) | F1 score | 80.55 | — | Unverified |
| 9 | CLRNet(DLA-34) | F1 score | 80.47 | — | Unverified |
| 10 | CLRNetV2 (ResNet101) | F1 score | 80.43 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SCNN_UNet_Attention_PL* | Accuracy | 98.38 | — | Unverified |
| 2 | GANet(ResNet-34) | F1 score | 97.71 | — | Unverified |
| 3 | GANet(ResNet-18) | F1 score | 97.68 | — | Unverified |
| 4 | CLRNet(ResNet-101) | F1 score | 97.62 | — | Unverified |
| 5 | GANet(ResNet-101) | F1 score | 97.45 | — | Unverified |
| 6 | CondLaneNet(ResNet-34) | F1 score | 97.01 | — | Unverified |
| 7 | CLRNetV2 (ResNet18) | Accuracy | 96.99 | — | Unverified |
| 8 | PE-RESA | Accuracy | 96.93 | — | Unverified |
| 9 | FOLOLane(ERFNet) | Accuracy | 96.92 | — | Unverified |
| 10 | CLRNet(ResNet-34) | Accuracy | 96.9 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | CondLSTR (ResNet-101) | F1 score | 88.47 | — | Unverified |
| 2 | CondLSTR (ResNet-34) | F1 score | 88.23 | — | Unverified |
| 3 | CondLSTR (ResNet-18) | F1 score | 87.99 | — | Unverified |
| 4 | CANet-L | F1 score | 87.87 | — | Unverified |
| 5 | CLRNetV2 (ResNet101) | F1 score | 87.81 | — | Unverified |
| 6 | CANet-M | F1 score | 87.19 | — | Unverified |
| 7 | CANet-S | F1 score | 86.57 | — | Unverified |
| 8 | CLRerNet-DLA34 | F1 score | 86.47 | — | Unverified |
| 9 | CondLaneNet-L(ResNet-101) | F1 score | 86.1 | — | Unverified |
| 10 | CLRNet-DLA34 | F1 score | 86.1 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | TwinLiteNetPlus-Large | IoU (%) | 34.2 | — | Unverified |
| 2 | TwinLiteNetPlus-Medium | IoU (%) | 32.3 | — | Unverified |
| 3 | HybridNets | IoU (%) | 31.6 | — | Unverified |
| 4 | TwinLiteNet | IoU (%) | 31.08 | — | Unverified |
| 5 | TriLiteNet-base | IoU (%) | 29.8 | — | Unverified |
| 6 | TwinLiteNetPlus-Small | IoU (%) | 29.3 | — | Unverified |
| 7 | A-YOLOM(s) | IoU (%) | 28.8 | — | Unverified |
| 8 | YOLOPv2 | IoU (%) | 27.25 | — | Unverified |
| 9 | YOLOP | IoU (%) | 26.2 | — | Unverified |
| 10 | TwinLiteNetPlus-Nano | IoU (%) | 23.3 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | FENetV2 | mF1 | 71.85 | — | Unverified |
| 2 | CLRNet (DLA-34) | F1 | 0.96 | — | Unverified |
| 3 | BézierLaneNet (ResNet-34) | F1 | 0.96 | — | Unverified |
| 4 | LaneAF | F1 | 0.96 | — | Unverified |
| 5 | CLRNet (ResNet-18) | F1 | 0.96 | — | Unverified |
| 6 | BézierLaneNet (ResNet-18) | F1 | 0.96 | — | Unverified |
| 7 | LaneATT (ResNet-34) | F1 | 0.94 | — | Unverified |
| 8 | LaneATT (ResNet-122) | F1 | 0.94 | — | Unverified |
| 9 | LaneATT (ResNet-18) | F1 | 0.93 | — | Unverified |
| 10 | PolyLaneNet | F1 | 0.88 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | DSLP | IoU | 0.45 | — | Unverified |
| 2 | LaneGraphNet | IoU | 0.42 | — | Unverified |
| 3 | STSU | IoU | 0.39 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | CondLSTR (ResNet-101) | F1 score | 63.4 | — | Unverified |
| 2 | CondLSTR (ResNet-34) | F1 score | 62 | — | Unverified |
| 3 | CondLSTR (ResNet-18) | F1 score | 60.1 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | VPGNet | F1 | 0.88 | — | Unverified |
| 2 | Overfeat CNN detector + DBSCAN | F1 | 0.87 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | VPGNet | F1 | 0.87 | — | Unverified |
| 2 | Overfeat CNN detector + DBSCAN | F1 | 0.86 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | LDNet | Average IOU | 62.79 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | LLDN-GFC | F1 | 82.12 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | TopoLogic | mAP | 33.2 | — | Unverified |
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | SCNN_UNet_Attention_PL* | F1 | 0.92 | — | Unverified |