EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Lightweight Spectral–Spatial Network for Efficient Semantic Segmentation of Ground-Based Hyperspectral Imagery

Fuqiang Yuan, Hongkun Zhang, Wenjun Li, Beiqi Wu, Yihao Liu

Remote Sensing · 23.10.2026 · 18 (21) · 3648

DOI: 10.3390/rs18213648 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 23.10.2026. Verfasst von Fuqiang Yuan und 4 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ground-based hyperspectral imaging extends remote sensing to road environments by providing material-sensitive spectra for distinguishing visually similar surfaces and objects. However, pixel-wise prediction from high-dimensional spectral cubes is computationally demanding. This study presents a lightweight spectral–spatial network for efficient semantic segmentation of ground-based hyperspectral imagery. A Spectral Token Stem compresses ordered bands into pooled, normalized, and statistical descriptors before high-resolution encoding. CoordSK blocks combine coordinate-aware directional aggregation with adaptive local-scale selection, while a lightweight guided decoder recovers dense predictions from multi-level features. Experiments on the public HyKo2 and HSI-Drive datasets yield Jaccard indices of 0.6670 and 0.8181, respectively, outperforming representative efficient segmentation baselines. The model contains 0.656 million trainable parameters and reaches FP32 batch-one throughputs of 151.49 and 168.21 FPS on an RTX 5090 for the respective benchmarks. In the additional pretrained-model comparison, the network uses less than 0.5% of HSI-Adapter’s total parameters. Ablation studies validate the contributions of spectral tokenization and coordinate-selective mixing, and an input-representation study demonstrates the benefit of retaining full hyperspectral observations over PCA and pseudo-RGB inputs. These results indicate a favorable accuracy–efficiency trade-off for ground-based hyperspectral remote sensing scene understanding.

Zitieren

APA

Yuan, F., Zhang, H., Li, W., Wu, B., & Liu, Y. (2026). A Lightweight Spectral–Spatial Network for Efficient Semantic Segmentation of Ground-Based Hyperspectral Imagery. Remote Sensing, 18(21), 3648. https://doi.org/10.3390/rs18213648

Vancouver

Yuan F, Zhang H, Li W, Wu B, Liu Y. A Lightweight Spectral–Spatial Network for Efficient Semantic Segmentation of Ground-Based Hyperspectral Imagery. Remote Sensing. 2026;18(21):3648. doi:10.3390/rs18213648

BibTeX
@article{Yuan2026,
  author = {Yuan, Fuqiang and Zhang, Hongkun and Li, Wenjun and Wu, Beiqi and Liu, Yihao},
  title = {A Lightweight Spectral–Spatial Network for Efficient Semantic Segmentation of Ground-Based Hyperspectral Imagery},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {21},
  pages = {3648},
  doi = {10.3390/rs18213648}
}
Kostenlos starten →