lane-detection
pandar128-lane-line-detection
Pandar128 Lane Line Detection Dataset
Pandar128 is the largest public dataset for lane line detection using a
128-beam LiDAR. It contains synchronized camera frames and LiDAR scans
recorded in real-world driving conditions in Germany, together with full
sensor calibration (intrinsics, extrinsics, distortion) and synchronized
odometry — enabling projection, sensor fusion, temporal accumulation, and
map-level lane modeling.
This dataset accompanies the paper "Pandar128 dataset for… See the full description on the dataset page: https://huggingface.co/datasets/filipberanek/pandar128-lane-line-detection.lane-detectionLane-and-eye-detection-dataset
Fine-Tuning Directory Description
This directory stores domain-specific data captured for adaptation after base model training.
CEW_fine_tuning/: phone-domain eye images.
lane_fine_tuning/: Raspberry Pi lane-domain frames/videos and derived segmentation dataset.
Used mainly in stage 07 notebooks for each pipeline.
Datasets Directory Description
This directory contains the original source datasets used by the two pipelines:
CEW/ for eye-state classification.
tusimple/… See the full description on the dataset page: https://huggingface.co/datasets/AhmedNasr5804/Lane-and-eye-detection-dataset.wayno-lane-detectionlane-detection-sushi