Skip to content
Conference Open access

NBASNet: a network-based approach with super token sampling for accurate road extraction in ambiguous and obscured environments

Sep 2026 · Journal of Physics, Conference Series · Vol 3308, pp. 012034 · 0 citations · 6 references
Physics

TL;DR

Experiments across two datasets show that NBASNet outperforms existing methods across all evaluation metrics, and visualizations further verify its effectiveness and reliability in addressing the aforementioned challenges.

Abstract

Road extraction remains a challenging task due to irregular shapes, varying widths, occlusions, and complex terrain. Existing models often fail to address key issues, such as extraction interruptions caused by trees, buildings, or shadows, and the difficulty of distinguishing road edges from surrounding features under dense occlusion and complex lighting conditions. To address these challenges, we propose NBASNet, a novel network architecture for improving road extraction in complex scenes. NBASNet integrates several key innovative modules: the SMC module captures texture features of occluded roads and contextual information; the STCM module captures global dependencies via super tokens; the CMSHA and DMLP modules enhance multi-scale feature extraction and local information; and the CGF module optimizes multi-scale feature representation. Experiments across two datasets show that NBASNet outperforms existing methods across all evaluation metrics, and visualizations further verify its effectiveness and reliability in addressing the aforementioned challenges.

Read PDF

Similar papers

Open access Oct 2026

RoadTopo-SAM:Topology-Aware Vectorized Road Network Extraction from High-Resolution Satellite Imagery of Open-Pit Mines

Open-pit mine road extraction is of significant value for intelligent navigation, yet it faces significant challenges due to unstructured terrain, spectral homogeneity, and physical occlusions. Traditional semantic segmentation methods frequently result in fragmented road masks. This paper proposes RoadTopo-SAM, a topo...

Bo Zou, Yi-Chun Jia, Rui-Fei Zhu et al. · 0 citations
Open access 2026

DBNINet: A Decoder-Guided Boundary Enhancement and Node Interaction Network for Road Extraction From Remote-Sensing Images

Roadextraction from remote-sensing images is a fundamental task in Earth observation applications. However, accurate extraction remains challenging due to complex backgrounds, weak boundaries, tree occlusion, and discontinuous road structures, particularly in forest and rural scenes. To address these issues, this artic...

Hong-Liang-Yang-Xiao-Mei-Du-Yun-Yan Fang, Zhi-Qiang Min, Yan-Rong Hu et al. · 0 citations
Open access 2026

DAGMNet: A Dual-Branch Network for Connectivity-Preserving Road Extraction

Accurate extraction of road networks from high-resolution remote sensing imagery is critical for autonomous driving, urban planning, and intelligent transportation systems. However, existing methods often struggle to preserve connectivity and topology due to the narrow and curvilinear nature of roads, complex backgroun...

Guo-Jun Chen, Jia-Le Chen, Yun-Yi Kong et al. · 0 citations
Open access Oct 2026

EDP-Net: An Edge-Enhanced Road Object Detection Algorithm with Dual-Path Feature Fusion

Road-object detection for autonomous driving faces challenges including dense occlusions, large-scale variations, and imaging degradation under nighttime and adverse weather conditions, making it difficult for efficient detectors to balance accuracy and robustness. To address this, we propose EDP-Net, an efficient and...

Gui-Chao Liu, Huai-Guang Wang, Ding-Hai Wu et al. · 0 citations
Open access Sep 2026

Road Extraction from High-Resolution Remote Sensing Images Based on MRCBL-Net and Multi-attention Mechanism

A Multi-scale Refined Convolutional Backbone Link Network (MRCBL-Net) is proposed, which adopts ConvNeXt as the backbone encoder to enhance feature extraction capability and embeds the proposed Multi-scale Dilated Convolution and Spatial-Channel Refinement (MULCSR)module into skip connections.

Jia-Jia Liu, Xuan Zhao, Wen-Xiang Dong et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.