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
Seismic waveform clustering is a useful technique for lithologic identification and reservoir characterization.The current seismic waveform clustering algorithms are predominantly based on a fixed time window,which is...Seismic waveform clustering is a useful technique for lithologic identification and reservoir characterization.The current seismic waveform clustering algorithms are predominantly based on a fixed time window,which is applicable for layers of stable thickness.When a layer exhibits variable thickness in the seismic response,a fixed time window cannot provide comprehensive geologic information for the target interval.Therefore,we propose a novel approach for a waveform clustering workfl ow based on a variable time window to enable broader applications.The dynamic time warping(DTW)distance is fi rst introduced to effectively measure the similarities between seismic waveforms with various lengths.We develop a DTW distance-based clustering algorithm to extract centroids,and we then determine the class of all seismic traces according to the DTW distances from centroids.To greatly reduce the computational complexity in seismic data application,we propose a superpixel-based seismic data thinning approach.We further propose an integrated workfl ow that can be applied to practical seismic data by incorporating the DTW distance-based clustering and seismic data thinning algorithms.We evaluated the performance by applying the proposed workfl ow to synthetic seismograms and seismic survey data.Compared with the the traditional waveform clustering method,the synthetic seismogram results demonstrate the enhanced capability of the proposed workfl ow to detect boundaries of diff erent lithologies or lithologic associations with variable thickness.Results from a practical application show that the planar map of seismic waveform clustering obtained by the proposed workfl ow correlates well with the geological characteristics of wells in terms of reservoir thickness.展开更多
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。
基金supported by the National Science and Technology Major Project (No. 2017ZX05001-003)。
文摘Seismic waveform clustering is a useful technique for lithologic identification and reservoir characterization.The current seismic waveform clustering algorithms are predominantly based on a fixed time window,which is applicable for layers of stable thickness.When a layer exhibits variable thickness in the seismic response,a fixed time window cannot provide comprehensive geologic information for the target interval.Therefore,we propose a novel approach for a waveform clustering workfl ow based on a variable time window to enable broader applications.The dynamic time warping(DTW)distance is fi rst introduced to effectively measure the similarities between seismic waveforms with various lengths.We develop a DTW distance-based clustering algorithm to extract centroids,and we then determine the class of all seismic traces according to the DTW distances from centroids.To greatly reduce the computational complexity in seismic data application,we propose a superpixel-based seismic data thinning approach.We further propose an integrated workfl ow that can be applied to practical seismic data by incorporating the DTW distance-based clustering and seismic data thinning algorithms.We evaluated the performance by applying the proposed workfl ow to synthetic seismograms and seismic survey data.Compared with the the traditional waveform clustering method,the synthetic seismogram results demonstrate the enhanced capability of the proposed workfl ow to detect boundaries of diff erent lithologies or lithologic associations with variable thickness.Results from a practical application show that the planar map of seismic waveform clustering obtained by the proposed workfl ow correlates well with the geological characteristics of wells in terms of reservoir thickness.