DCA-Net: Dilated Context Attention Network for MLS Point Cloud Semantic Segmentation
Remote Sensing · 14.08.2026 · 18 (16) · 2740
DOI: 10.3390/rs18162740 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 14.08.2026. Verfasst von Bingchen Du und 4 weiteren Autor:innen. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Mobile LiDAR systems (MLS) enable rapid acquisition of large-scale 3D point cloud data. Semantic segmentation of the acquired point clouds is an important task in outdoor scene understanding and environmental perception for autonomous driving. However, existing methods tend to suffer from boundary confusion when segmenting MLS point clouds with long-tail categories. To address this problem, we propose the Dilated Context Attention Network (DCA-Net), which consists of a dilated local geometric encoding module, a channel attention pooling module, and a category-boundary sampling strategy. The dilated local geometric encoding module expands point-to-point connections within a fixed neighborhood to strengthen contextual modeling among neighboring points. The channel attention pooling module uses a channel attention mechanism to enhance informative channel responses in neighborhood features, thereby improving local feature representation. The category-boundary sampling strategy increases the sampling probabilities of minority-category points and boundary points, reducing feature information loss during down-sampling. Experimental results on the S3DIS, Toronto3D, and MLS road scene datasets show that DCA-Net achieves mIoU scores of 69.4%, 84.1%, and 96.6%, respectively. These results demonstrate that the proposed method alleviates boundary confusion in point cloud segmentation with long-tail categories, without causing a noticeable degradation in the segmentation performance of majority categories.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Du, B., Li, B., Zhang, Z., Cheng, P., & Cai, Z. (2026). DCA-Net: Dilated Context Attention Network for MLS Point Cloud Semantic Segmentation. Remote Sensing, 18(16), 2740. https://doi.org/10.3390/rs18162740
Vancouver
Du B, Li B, Zhang Z, Cheng P, Cai Z. DCA-Net: Dilated Context Attention Network for MLS Point Cloud Semantic Segmentation. Remote Sensing. 2026;18(16):2740. doi:10.3390/rs18162740
BibTeX
@article{Du2026,
author = {Du, Bingchen and Li, Bozhao and Zhang, Zhenkun and Cheng, Peng and Cai, Zhongliang},
title = {DCA-Net: Dilated Context Attention Network for MLS Point Cloud Semantic Segmentation},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {16},
pages = {2740},
doi = {10.3390/rs18162740}
}
EUVIMED