Department of Electronic Engineering, Xi'an Aeronautical University, Xi'an, Shaanxi, China.
PLoS One. 2022 Apr 29;17(4):e0267754. doi: 10.1371/journal.pone.0267754. eCollection 2022.
In the compressed processing of hyperspectral images, orthogonal matching pursuit algorithm (OMP) can be used to obtain sparse decomposition results. Aimed at the time-complex and difficulty in applying real-time processing, an evolutionary multi-objective optimization sparse decomposition algorithm for hyperspectral images is proposed. Instead of using OMP for the matching process to search optimal atoms, the proposed algorithm explores the idea of reference point non-dominated sorting genetic algorithm (NSGA) to optimize the matching process of OMP. Take two objective function to establish the multi-objective sparse decomposition optimization model, including the largest inner product of matching atoms and image residuals, and the smallest correlation between atoms. Utilize NSGA-III with advantage of high accuracy to solve the optimization model, and the implementation process of NSGA-III-OMP is presented. The experimental results and analysis carried on four hyperspectral datasets demonstrate that, compared with the state-of-the-art algorithms, the proposed NSGA-III-OMP algorithm has effectively improved the sparse decomposition performance and efficiency, and can effectively solve the sparse decomposition optimization problem of hyperspectral images.
在高光谱图像的压缩处理中，可以使用正交匹配追踪算法（OMP）来获得稀疏分解结果。针对时间复杂度高、实时处理应用困难的问题，提出了一种基于进化多目标优化的高光谱图像稀疏分解算法。该算法不是使用 OMP 进行匹配过程来搜索最优原子，而是探索参考点非支配排序遗传算法（NSGA）的思想来优化 OMP 的匹配过程。该算法采用两个目标函数来建立多目标稀疏分解优化模型，包括匹配原子和图像残差的最大内积以及原子之间的最小相关性。利用具有高精度优势的 NSGA-III 来求解优化模型，并给出了 NSGA-III-OMP 的实现过程。在四个高光谱数据集上的实验结果和分析表明，与现有的先进算法相比，所提出的 NSGA-III-OMP 算法有效地提高了稀疏分解性能和效率，能够有效地解决高光谱图像的稀疏分解优化问题。
