该文使用近10 a 4个时相的江苏全省Landsat遥感影像,在数据预处理的基础上提取归一化植被指数、比值植被指数、土壤调节植被指数、增强型植被指数、大气阻抗植被指数等5种植被指数,并进行主成分分析。运用最大似然法、随机森林法和光谱...该文使用近10 a 4个时相的江苏全省Landsat遥感影像,在数据预处理的基础上提取归一化植被指数、比值植被指数、土壤调节植被指数、增强型植被指数、大气阻抗植被指数等5种植被指数,并进行主成分分析。运用最大似然法、随机森林法和光谱角填图法进行分类,结合小班数据,对各方法的分类结果进行精度评价。评价结果表明,光谱角填图分类法在杨树信息提取时精度更高,对杨树的区分精度也达到42.67%。展开更多
The similarity measure is crucial to the performance of spectral clustering. The Gaussian kernel function based on the Euclidean distance is usual y adopted as the similarity measure. However, the Euclidean distance m...The similarity measure is crucial to the performance of spectral clustering. The Gaussian kernel function based on the Euclidean distance is usual y adopted as the similarity measure. However, the Euclidean distance measure cannot ful y reveal the complex distribution data, and the result of spectral clustering is very sensitive to the scaling parameter. To solve these problems, a new manifold distance measure and a novel simulated anneal-ing spectral clustering （SASC） algorithm based on the manifold distance measure are proposed. The simulated annealing based on genetic algorithm （SAGA）, characterized by its rapid convergence to the global optimum, is used to cluster the sample points in the spectral mapping space. The proposed algorithm can not only reflect local and global consistency better, but also reduce the sensitivity of spectral clustering to the kernel parameter, which improves the algorithm’s clustering performance. To efficiently apply the algorithm to image segmentation, the Nystrom method is used to reduce the computation complexity. Experimental results show that compared with traditional clustering algorithms and those popular spectral clustering algorithms, the proposed algorithm can achieve better clustering performances on several synthetic datasets, texture images and real images.展开更多
高光谱图像可以获取波段连续的图谱合一的立体数据,其具有丰富的图谱信息,能区分不同物质的类别,被广泛应用于各种遥感勘测领域。但在实际中高光谱图像的标注需要耗费大量的人力、财力和时间,可用的标注样本数量较少,难以通过训练来获...高光谱图像可以获取波段连续的图谱合一的立体数据,其具有丰富的图谱信息,能区分不同物质的类别,被广泛应用于各种遥感勘测领域。但在实际中高光谱图像的标注需要耗费大量的人力、财力和时间,可用的标注样本数量较少,难以通过训练来获得准确的分类结果,所以针对于只有少量标记样本的高光谱图像分类是一个挑战。近年来,自监督学习(Self-supervised Learning,SSL)已成为一种有效的方法,可以减少高光谱图像分类对昂贵的数据标注的依赖。SSL方法通过学习在同一图像的不同视图之间产生的潜在特征,在自然图像分类中取得了较高的分类精度。为了探索SSL方法在高光谱图像分类中的潜力,一种Bootstrap Your Own Latent(BYOL)框架下的自监督高光谱图像分类方法(BSSL)被提出。该方法通过引用自监督的图像特征学习框架BYOL,可以不需要负样本对,利用空间光谱相似的同类样本对进行网络训练及参数微调,提取到更具判别性特征。具体来说,该方法主要包括四个部分:BYOL的预训练、超像素聚类、基于“相似对”的BYOL的再训练和最终分类。为了验证该方法的有效性,在三个公开数据集上进行测试,并与五种先进的无监督、自监督分类方法SuperPCA、S3PCA、ContrastNet、SSCL和N2SSL进行对比,在Indian Pines和Salinas数据集上,BSSL方法的总体分类精度(OA)、平均分类精度(AA)、Kappa系数、召回率(recall)和f1分数(f1-score)都取得了更优值。其中在Indian Pines数据集上,OA分别比SuperPCA,S3PCA,ContrastNet,SSCL和N2SSL提高了1.32%,1.05%,5.68%,3.12%和1.27%。而在University of Pavia数据集上,BSSL方法表现没有那么出色,但在综合分类性能上也表现最优。这表明BSSL方法更适用于地物区域面积较大且分布较集中的场景,因为这对于超像素聚类来说更友好。展开更多
文摘该文使用近10 a 4个时相的江苏全省Landsat遥感影像,在数据预处理的基础上提取归一化植被指数、比值植被指数、土壤调节植被指数、增强型植被指数、大气阻抗植被指数等5种植被指数,并进行主成分分析。运用最大似然法、随机森林法和光谱角填图法进行分类,结合小班数据,对各方法的分类结果进行精度评价。评价结果表明,光谱角填图分类法在杨树信息提取时精度更高,对杨树的区分精度也达到42.67%。
基金supported by the National Natural Science Foundationof China(61272119)
文摘The similarity measure is crucial to the performance of spectral clustering. The Gaussian kernel function based on the Euclidean distance is usual y adopted as the similarity measure. However, the Euclidean distance measure cannot ful y reveal the complex distribution data, and the result of spectral clustering is very sensitive to the scaling parameter. To solve these problems, a new manifold distance measure and a novel simulated anneal-ing spectral clustering （SASC） algorithm based on the manifold distance measure are proposed. The simulated annealing based on genetic algorithm （SAGA）, characterized by its rapid convergence to the global optimum, is used to cluster the sample points in the spectral mapping space. The proposed algorithm can not only reflect local and global consistency better, but also reduce the sensitivity of spectral clustering to the kernel parameter, which improves the algorithm’s clustering performance. To efficiently apply the algorithm to image segmentation, the Nystrom method is used to reduce the computation complexity. Experimental results show that compared with traditional clustering algorithms and those popular spectral clustering algorithms, the proposed algorithm can achieve better clustering performances on several synthetic datasets, texture images and real images.
文摘高光谱图像可以获取波段连续的图谱合一的立体数据,其具有丰富的图谱信息,能区分不同物质的类别,被广泛应用于各种遥感勘测领域。但在实际中高光谱图像的标注需要耗费大量的人力、财力和时间,可用的标注样本数量较少,难以通过训练来获得准确的分类结果,所以针对于只有少量标记样本的高光谱图像分类是一个挑战。近年来,自监督学习(Self-supervised Learning,SSL)已成为一种有效的方法,可以减少高光谱图像分类对昂贵的数据标注的依赖。SSL方法通过学习在同一图像的不同视图之间产生的潜在特征,在自然图像分类中取得了较高的分类精度。为了探索SSL方法在高光谱图像分类中的潜力,一种Bootstrap Your Own Latent(BYOL)框架下的自监督高光谱图像分类方法(BSSL)被提出。该方法通过引用自监督的图像特征学习框架BYOL,可以不需要负样本对,利用空间光谱相似的同类样本对进行网络训练及参数微调,提取到更具判别性特征。具体来说,该方法主要包括四个部分:BYOL的预训练、超像素聚类、基于“相似对”的BYOL的再训练和最终分类。为了验证该方法的有效性,在三个公开数据集上进行测试,并与五种先进的无监督、自监督分类方法SuperPCA、S3PCA、ContrastNet、SSCL和N2SSL进行对比,在Indian Pines和Salinas数据集上,BSSL方法的总体分类精度(OA)、平均分类精度(AA)、Kappa系数、召回率(recall)和f1分数(f1-score)都取得了更优值。其中在Indian Pines数据集上,OA分别比SuperPCA,S3PCA,ContrastNet,SSCL和N2SSL提高了1.32%,1.05%,5.68%,3.12%和1.27%。而在University of Pavia数据集上,BSSL方法表现没有那么出色,但在综合分类性能上也表现最优。这表明BSSL方法更适用于地物区域面积较大且分布较集中的场景,因为这对于超像素聚类来说更友好。
