Kernel Tensor Sparse Coding Model for Precise Crop Classification of UAV Hyperspectral Image

Lixia Yang, Rui Zhang, Yajun Bao, Shuyuan Yang, Licheng Jiao

Abstract

In this letter, a kernel tensor sparse coding model (KTSCM) is proposed for precise crop classification of unmanned aerial vehicle (UAV) hyperspectral image (HSI). Benefiting from the kernel tensor representation mechanism in KTSCM, which can not only improve the linear separation but also preserve the spatial-spectral structures of land covers, the discriminability of UAV HSI is greatly improved. The L1-norm-based tensor sparsity makes the tensor operation in KTSCM be equivalently converted to matrix operation, which greatly reduces the computation cost. Furthermore, the analytical solution to KTSCM allows it to be well-optimized with very few iterations. The performance of KTSCM is assessed on two real UAV HSIs. The experimental results indicate that KTSCM can provide rapid and accurate crop classification results with limited labeled pixels and outperforms the related counterparts.
BibTeX
@article{yang2023kernel,
  author = {Lixia Yang and Rui Zhang and Yajun Bao and Shuyuan Yang and Licheng Jiao},
  title = {{Kernel Tensor Sparse Coding Model for Precise Crop Classification of UAV Hyperspectral Image}},
  journal = {IEEE Geosci. Remote. Sens. Lett.},
  year = {2023},
  doi = {10.1109/lgrs.2023.3326452},
}

Loading related content...

Figure