Dai Qiansen, Ma Chencong, Zhang Qizhong
School of Artificial Intelligence, Hangzhou Dianzi University, Hangzhou 310018, China.
School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou 310018, China.
Sensors (Basel). 2024 Jun 22;24(13):4072. doi: 10.3390/s24134072.
Hyperspectral images (HSIs) possess an inherent three-order structure, prompting increased interest in extracting 3D features. Tensor analysis and low-rank representations, notably truncated higher-order SVD (T-HOSVD), have gained prominence for this purpose. However, determining the optimal order and addressing sensitivity to changes in data distribution remain challenging. To tackle these issues, this paper introduces an unsupervised Superpixelwise Multiscale Adaptive T-HOSVD (SmaT-HOSVD) method. Leveraging superpixel segmentation, the algorithm identifies homogeneous regions, facilitating the extraction of local features to enhance spatial contextual information within the image. Subsequently, T-HOSVD is adaptively applied to the obtained superpixel blocks for feature extraction and fusion across different scales. SmaT-HOSVD harnesses superpixel blocks and low-rank representations to extract 3D features, effectively capturing both spectral and spatial information of HSIs. By integrating optimal-rank estimation and multiscale fusion strategies, it acquires more comprehensive low-rank information and mitigates sensitivity to data variations. Notably, when trained on subsets comprising 2%, 1%, and 1% of the Indian Pines, University of Pavia, and Salinas datasets, respectively, SmaT-HOSVD achieves impressive overall accuracies of 93.31%, 97.21%, and 99.25%, while maintaining excellent efficiency. Future research will explore SmaT-HOSVD's applicability in deep-sea HSI classification and pursue additional avenues for advancing the field.
高光谱图像（HSIs）具有固有的三阶结构，这引发了人们对提取三维特征的兴趣日益增加。张量分析和低秩表示，特别是截断高阶奇异值分解（T-HOSVD），为此目的而备受关注。然而，确定最佳阶数以及解决对数据分布变化的敏感性仍然具有挑战性。为了解决这些问题，本文介绍了一种无监督的超像素多尺度自适应T-HOSVD（SmaT-HOSVD）方法。该算法利用超像素分割来识别同质区域，便于提取局部特征以增强图像内的空间上下文信息。随后，将T-HOSVD自适应地应用于获得的超像素块，以进行跨不同尺度的特征提取和融合。SmaT-HOSVD利用超像素块和低秩表示来提取三维特征，有效地捕获了高光谱图像的光谱和空间信息。通过集成最优秩估计和多尺度融合策略，它获取了更全面的低秩信息，并减轻了对数据变化的敏感性。值得注意的是，当分别在印度松树数据集、帕维亚大学数据集和萨利纳斯数据集的2%、1%和1%的子集上进行训练时，SmaT-HOSVD分别实现了令人印象深刻的93.31%、97.21%和99.25%的总体准确率，同时保持了出色的效率。未来的研究将探索SmaT-HOSVD在深海高光谱图像分类中的适用性，并寻求推进该领域的其他途径。
