LLAMAS

Labeled Lane Markers

Dataset Information
Modalities
Images
License
Unknown
Homepage

Overview

The unsupervised Labeled Lane MArkerS dataset (LLAMAS) is a dataset for lane detection and segmentation. It contains over 100,000 annotated images, with annotations of over 100 meters at a resolution of 1276 x 717 pixels. The Unsupervised Llamas dataset was annotated by creating high definition maps for automated driving including lane markers based on Lidar.

Paper: Unsupervised Labeled Lane Markers Using Maps

Source: Unsupervised Llamas Lane Marker Dataset

Image Source: Unsupervised Llamas Lane Marker Dataset

Variants: LLAMAS

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Lane Detection FENetV2 FENet: Focusing Enhanced Network for … 2023-12-28
Lane Detection CLRNet (DLA-34) CLRNet: Cross Layer Refinement Network … 2022-03-19
Lane Detection CLRNet (ResNet-18) CLRNet: Cross Layer Refinement Network … 2022-03-19
Lane Detection BézierLaneNet (ResNet-34) Rethinking Efficient Lane Detection via … 2022-03-04
Lane Detection BézierLaneNet (ResNet-18) Rethinking Efficient Lane Detection via … 2022-03-04
Lane Detection LaneAF LaneAF: Robust Multi-Lane Detection with … 2021-03-22
Lane Detection LaneATT (ResNet-122) Keep your Eyes on the … 2020-10-22
Lane Detection LaneATT (ResNet-34) Keep your Eyes on the … 2020-10-22
Lane Detection LaneATT (ResNet-18) Keep your Eyes on the … 2020-10-22
Lane Detection PolyLaneNet PolyLaneNet: Lane Estimation via Deep … 2020-04-23

Research Papers

Recent papers with results on this dataset: