LDS-Net: A Lightweight Dual-Branch Network for Slender Tree Branch Segmentation in Complex Natural Scenes
Forests · 10.07.2026 · 17 (7) · 811
DOI: 10.3390/f17070811 ↗Kurz gefasst
Fachartikel in der Zeitschrift Forests, online erschienen am 10.07.2026. Verfasst von Xinyan Zhang und 4 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate semantic segmentation of slender curvilinear structures, such as tree branches, in complex natural scenes remains challenging. The main difficulties arise from frequent occlusions, ambiguous boundaries, and limited edge computing resources. To address these issues, we propose LDS-Net, a lightweight dual-branch network designed for thin and continuous branch structures. The Detail-Aware Branch uses the Dynamic Snake Convolution (DSConv) to model irregular local geometry, while the Context-Aware Branch uses a Spatial Efficient Separable Pyramid module (SESP) to capture multi-scale context. To improve segmentation under occlusion and boundary ambiguity, we further integrate a Global Topology Transformer module (GTT) and a boundary guidance mechanism (BG). These features are fused via a Pixel-Wise Attention Fusion module (PAF) and optimized using a multi-head compound loss. Experiments on USTD and N-ABSD show that LDS-Net outperforms six representative networks. It also requires only 14.19 G FLOPs, a 24% reduction compared with PIDNet-s. These results suggest that LDS-Net has potential for future deployment on resource-constrained agricultural and ecological monitoring platforms.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhang, X., Deng, T., Wu, Y., Wu, W., & Liu, Y. (2026). LDS-Net: A Lightweight Dual-Branch Network for Slender Tree Branch Segmentation in Complex Natural Scenes. Forests, 17(7), 811. https://doi.org/10.3390/f17070811
Vancouver
Zhang X, Deng T, Wu Y, Wu W, Liu Y. LDS-Net: A Lightweight Dual-Branch Network for Slender Tree Branch Segmentation in Complex Natural Scenes. Forests. 2026;17(7):811. doi:10.3390/f17070811
BibTeX
@article{Zhang2026,
author = {Zhang, Xinyan and Deng, Tianlong and Wu, Yin and Wu, Wenjie and Liu, Yanyi},
title = {LDS-Net: A Lightweight Dual-Branch Network for Slender Tree Branch Segmentation in Complex Natural Scenes},
journal = {Forests},
year = {2026},
volume = {17},
number = {7},
pages = {811},
doi = {10.3390/f17070811}
}
EUVIMED