Skip to content
DraconiticResearch
Search Sources API
197,761 studies31 sourcesUpdated 45 min ago
Peer-reviewedCC BY 4.0PLOS One

BTSR-Net: Boundary–topology guided structural refinement for high-resolution remote sensing image segmentation

  • Ziheng Wang1
  • Wu Wang2
  • Zhe Hu3
  • Yang Li
  • Kejia Ma
  1. 1School of Electronic and Information Engineering, Changchun University of Science and Technology, Changchun, Jilin, China
  2. 2North Navigation Control Technology Co., Ltd., No. 2 Kechuang Street, Beijing Economic-Technological Development Area, Beijing, China
  3. 3Unit of the People’s Liberation Army, Baicheng, Jilin, China
Open at sourcePDFDOICite

Abstract

Semantic segmentation of high-resolution remote sensing imagery in complex urban scenes often suffers from insufficient modeling of boundary neighborhoods, causing ambiguity near class interfaces and weakening the continuity of elongated structures. To address this issue, we propose a Boundary-Topology-Guided Structural Refinement Network (BTSR-Net). Built upon HRNet-OCR, BTSR-Net introduces a Geometric Boundary–Distance Branch (GBD) with joint boundary–distance supervision to capture spatial transitions around class boundaries, a Multi-scale Topology-Guided Structural Fusion (MTSF) module to enhance connectivity representation of elongated structures, and a dual-stream structural refinement mechanism to perform local residual correction within a boundary-distance-defined refinement narrow-band. Experiments on the ISPRS Potsdam and Vaihingen datasets demonstrate improvements in overall segmentation accuracy, boundary quality, and structural connectivity. On Potsdam, BTSR-Net achieves 84.70% mIoU, 43.17% mBIoU, and 81.63% clDice, exceeding the baseline by 2.91, 5.66, and 3.74 percentage points, respectively. On Vaihingen, it achieves 93.94% mIoU, 73.90% mBIoU, and 95.46% clDice, with corresponding improvements of 2.27, 9.39, and 2.12 percentage points. These results demonstrate the effectiveness of BTSR-Net for structure-sensitive semantic segmentation in high-resolution remote sensing imagery.

Related

  1. Real enumerative invariants relative to the toric boundary and their refinement
    Ilia Itenberg, Eugenii I. Shustin
    Algebraic geometryPeer-reviewedCC BYFull text6 citedGeometry & topologyOpenAlex
  2. Progressive Reliability-Guided Refinement with Cross-Modal Consistency and Iterative Correction for Weakly Supervised PET/CT Tumor Segmentation
    Zhaoshuo Diao, Huiyan Jiang
    MathematicsPeer-reviewedCC BY 4.0General mathematicsCrossref
  3. Reliability-Aware Refinement of High-Resolution Human Mobility Origin-Destination Tables under Sparsity and Suppression
    Yohei Shida, Ryosuke Susuta, Takuhiro Moriyama +1
    arXivPreprintarXiv licenceFull textStatisticsStatistical & nonlinear physicsarXiv
  4. Residual-Based Adaptive Refinement in Hybrid Variational-Collocation PINNs for Singular Elliptic PDEs with Mixed Dirichlet-Neumann Boundary Conditions
    Somnath Giri, Muslim Malik, Rishikesh Yadav
    arXivPreprintCC BY-NC-SA 4.0Full textNumerical analysis & scientific computingComputational physicsarXiv
  5. Boundary-Level-Constrained Refinement for Suppressing Trimming-Induced High-Frequency Outliers in Explicit Isogeometric Analysis
    Christoph Hollweck, Lukas Leidinger, Stefan Hartmann +2
    arXivPreprintarXiv licenceFull textNumerical analysis & scientific computingarXiv

Cite

BibTeXRIS
BibTeX
@article{wang2026btsrnet,
  title = {{BTSR-Net: Boundary–topology guided structural refinement for high-resolution remote sensing image segmentation}},
  author = {Ziheng Wang and Wu Wang and Zhe Hu and Yang Li and Kejia Ma},
  journal = {PLOS One},
  year = {2026},
  month = oct,
  doi = {10.1371/journal.pone.0360524},
  url = {https://doi.org/10.1371/journal.pone.0360524},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - BTSR-Net: Boundary–topology guided structural refinement for high-resolution remote sensing image segmentation
AU  - Ziheng Wang
AU  - Wu Wang
AU  - Zhe Hu
AU  - Yang Li
AU  - Kejia Ma
PY  - 2026
DA  - 2026/10/16
JO  - PLOS One
DO  - 10.1371/journal.pone.0360524
UR  - https://doi.org/10.1371/journal.pone.0360524
AB  - Semantic segmentation of high-resolution remote sensing imagery in complex urban scenes often suffers from insufficient modeling of boundary neighborhoods, causing ambiguity near class interfaces and weakening the continuity of elongated structures. To address this issue, we propose a Boundary-Topology-Guided Structural Refinement Network (BTSR-Net). Built upon HRNet-OCR, BTSR-Net introduces a Geometric Boundary–Distance Branch (GBD) with joint boundary–distance supervision to capture spatial transitions around class boundaries, a Multi-scale Topology-Guided Structural Fusion (MTSF) module to enhance connectivity representation of elongated structures, and a dual-stream structural refinement mechanism to perform local residual correction within a boundary-distance-defined refinement narrow-band. Experiments on the ISPRS Potsdam and Vaihingen datasets demonstrate improvements in overall segmentation accuracy, boundary quality, and structural connectivity. On Potsdam, BTSR-Net achieves 84.70% mIoU, 43.17% mBIoU, and 81.63% clDice, exceeding the baseline by 2.91, 5.66, and 3.74 percentage points, respectively. On Vaihingen, it achieves 93.94% mIoU, 73.90% mBIoU, and 95.46% clDice, with corresponding improvements of 2.27, 9.39, and 2.12 percentage points. These results demonstrate the effectiveness of BTSR-Net for structure-sensitive semantic segmentation in high-resolution remote sensing imagery.
SN  - 1932-6203
ER  -