May 28, 2024 · To address the problem that road surface segmentation performance decreases in complex road scenes, we propose frequency-based semantic segmentation with a transformer …

The semantic segmentation GT for road surfaces contains 701 frames from RTK dataset. Classes are defined as follows: Paved, different pavements (eg.: Cobblestone); Cracks, used in …

Experiments on different datasets demonstrate that our designed fusion attention network outperforms the latest road segmentation models; our regularization algorithm shows strong …

Apr 13, 2024 · In summary, this research pushes the boundaries of current road detection technologies, introducing a comprehensive and adaptable approach to semantically segment …

This dataset is designed for implementing and testing road segmentation techniques in autonomous driving and computer vision. It includes high-quality road images and …

May 6, 2024 · In this paper, we introduce the road surface reconstruction dataset, providing multi-modal, high-resolution, and high-precision data collected by real-vehicle platform in diverse …

A method that utilizes a multistage feature fusion attention network (MFFANet) and regularization algorithm to extract road surfaces, centerlines, edges, and intersections and outperforms the …

This repository is the official implementation of Simultaneous Road Surface and Centerline Extraction From Large-Scale Remote Sensing Images Using CNN-Based Segmentation and …

At last, to reduce false positives relative to confusing pixels, we propose a pixel-aware contrastive-learning module to distinguish positive (roads) and negative (objects similar to …

Sep 25, 2024 · This study proposes a frequency-based semantic segmentation with a transformer (FSSFormer) based on the sensitivity of semantic segmentation to frequency information.