Road Segmentation for ADAS/AD Applications
This work addresses road segmentation for autonomous vehicles, but it is incremental as it applies existing methods to new datasets without major innovations.
The study tackled road segmentation for autonomous driving by training modified VGG-16 and U-Net models on different datasets, achieving high accuracy with VGG-16 outperforming U-Net in cross-dataset tests.
Accurate road segmentation is essential for autonomous driving and ADAS, enabling effective navigation in complex environments. This study examines how model architecture and dataset choice affect segmentation by training a modified VGG-16 on the Comma10k dataset and a modified U-Net on the KITTI Road dataset. Both models achieved high accuracy, with cross-dataset testing showing VGG-16 outperforming U-Net despite U-Net being trained for more epochs. We analyze model performance using metrics such as F1-score, mean intersection over union, and precision, discussing how architecture and dataset impact results.