滨海湿地信息提取方法比较研究

以江苏省典型滨海湿地为研究对象,利用2005年5月26日的Landsat7 ETM+图像数据,在湿地特征及其遥感图像表征分析的基础上,逐步提高湿地信息的提取精度,通过对多光谱遥感图像特征向量的分析,总结出一些湿地信息提取的规则和方法。在滨海湿地光谱特征分析的基础上,对研究区的图像进行了非监督分类,利用湿地的光谱相应特征、纹理特征、主成分变换、归一化差异水体指数等特征和相应的知识规则,得到用于优化分类的知识规则,采用分层分类的方法对非监督分类的结果进行了优化,从而使提取结果的精度较原来有了很大程度的提高。还利用给予数据挖掘的分层分类法进行分类比较,通过建立误差矩阵和对比各种分类方法的分类精度,总结出一套分类精度较高的针对该研究区的湿地信息提取方法。     

基于ALOS影像的盐城海滨湿地遥感信息分类方法研究

盐城海滨湿地类型丰富多样,湿地植物覆被类型之间的生态交错带十分明显,如何更为准确地获得海滨湿地覆盖信息,对湿地研究具有重要价值和意义。以ALOS影像为数据源,江苏盐城海滨湿地核心区为试验区,开展湿地信息遥感分类研究。在对研究区进行非监督分类,分析其限制分类精度原因基础上,针对研究区域的特点提出适合的分类精度改进方法。以非监督分类后的结果为模板,借助分区分层分类方法的思想,通过分析遥感影像光谱信息、纹理信息、主成分变换信息,得到知识规则,以基于知识规则修改的方法对芦苇、米草和盐蒿3种植被交错带进行修正。然后以基于GIS规则的方法对剩余区域进行修正。通过GPS数据进行精度检验,分类精度达到92.6829%,Kappa系数为0.9098。实验证明基于GIS规则和知识规则的分区分层分类法是提高海滨湿地遥感分类精度的有效方法。     

基于多尺度分割的遥感影像滨海湿地分类

基于多尺度的高分辨率遥感影像分类方法研究,可以为滨海湿地动态监测、规划保护提供更详尽的湿地分类信息和更快速的数据获取方法,对湿地保护具有重要意义。选取连云港青口河入海口处湿地为研究区,以高分辨率遥感影像WV\|Ⅱ和航空遥感影像为数据源,利用多尺度分割方法将影像分割成不同层次的实体对象;在不同层次,以实体对象为单元,结合光谱、形状、纹理等不同影像特征,进行滨海湿地分类研究,结果表明:利用该方法分类后,研究区各种湿地类型都达到较高精度。基于多尺度分割的影像分类方法能充分利用各种影像特征完成湿地分类,有效地减少了遥感影像中的“椒盐”现象,提高了分类精度;选择适宜的分割尺度和分割参数是基于多尺度分割的遥感影像分类方法提高精度的前提。     

基于决策树方法的淡水沼泽湿地信息提取——以三江平原东北部为例

湿地是生态系统的重要组成部分,及时、准确地获得湿地基础信息,对湿地的动态监测、保护与可持续利用及其它领域的研究具有重要意义。以三江平原东北部沼泽湿地为例,利用分类回归树(Classification and Regression Tree,CART)算法从训练样本数据集中挖掘分类规则,集成遥感影像的光谱特征、纹理特征和地学辅助数据建立研究区湿地信息提取的决策树模型。用实测的GPS样本点对分类结果进行精度验证,并与最大似然监督分类方法(Maximum Likelihood Classification,MLC)进行对比。结果表明,基于CART的决策树分类结果的总精度和Kappa系数分别为82.65%和0.7935,分类精度较MLC监督分类方法有明显提高,是内陆淡水沼泽湿地信息提取的有效手段。     

一种多级再分类技术耕地提取方法

鉴于土地利用中耕地类型的遥感光谱特征差异大,以及我国北方农牧交错带中撂荒地、耕地、裸地和草地混淆严重,耕地信息的获取难度大、精度低,提出了利用长时间序列遥感数据,通过多级再分类技术方法(multilevel reclassification,MLRC)提取可耕种区域。首先利用最大似然法对长时间序列的多期遥感数据进行监督分类,提取出耕地区域,之后在初级分类的基础上,通过统计不同区域在多期分类结果中被判定为耕地的次数进而确定可耕作区域的范围。通过对闪电河湿地实验区的研究表明,利用MLRC方法的精度达到了82.56%。     

基于遥感影像的军事阵地动态监测技术研究

针对部队快速机动作战的军事要求,提出基于高分辨率遥感影像的军用阵地动态监测方法。借助面向对象的多尺度分割技术将阵地影像分割为同质对象,以提取各个对象的特征;针对监督分类和非监督分类的弊端,提出通过一定的先验知识制定分类规则的方法对遥感影像进行地物识别,在此基础上定性和定量地输出变化检测结果。实验结果表明:利用基于对象影像分析方法具有较高的识别精度,能够有效监测军事阵地变化。     

结合自动分区与分层分析的多光谱遥感图像地物分类方法

结合分区与分层的思想,针对多光谱遥感图像,提出一种新的分类方法。在地物光谱分析基础上实现遥感影像的自动分区,然后运用多光谱图像主成份变换前后的地物光谱特征实现地物的分层提取。该分类方法在大庆部分地区地物分类中得到了应用,结果表明,该方法比常规的监督分类在分类精度上有了明显提高。     

多源信息复合的遥感影像水稻田信息提取方法研究

水稻是中国最主要的粮食作物之一。如何更精确更真实的获取水稻种植信息对于中国农业的可持续发展具有重要的意义。以江苏南京江宁区为试验区,融合遥感影像的光谱信息、纹理信息、空间分布特征等辅助性信息进行基于知识规则的水稻田信息提取,并将提取结果与传统的非监督分类和逻辑通道法的提取结果进行了比较。研究表明,基于知识规则的多源信息水稻田提取方法的精度最高。可见,融合多源信息的基于知识规则分类法是提高遥感水稻田提取精度的有效方法。     

基于光谱理论的遥感信息提取方法的研究

以东昌府区为例,根据区内各种地物不同的光谱特征,利用遥感光谱分析方法,基于ERDAS IMAGINE平台对东昌府区内各种地物分别用监督分类和非监督分类两种方法进行信息提取,对两种方法进行比较,选择效果比较好的一种对东昌府区遥感信息进行提取研究,并对提取结果进行分析。研究表明,基于光谱理论的遥感信息监督分类提取方法在对东昌府区进行信息提取时更为精确。     

基于分层分析的ASTER 影像土地利用/ 覆盖遥感监测研究

以龙海市为实验区, 利用ASTER 遥感数据, 在研究区典型地物光谱特征系统分析的基础上,进行基于分层分类思想的地物分类提取方法研究。首先将影像划分为独立的子区( 水体、植被覆盖区和非植被覆盖区域) 以避免分类过程中光谱的互相影响; 然后在每个独立的子区基础上根据各类地物的不同光谱特征和空间特征, 对各类地物进行逐层掩模、分层提取。结果表明该方法优于传统的监督和非监督分类效果。     

基于神经网络和数据融合的红树林群落分类研究

及时准确地掌握红树林群落现状信息可为保护和修复红树林生态系统提供重要的决策依据。对红树林群落进行遥感分类在实际应用中具有较大的意义。但红树林各群落间的光谱差异很微弱,有必要采用多源遥感数据融合的方法来提高分类的精度。本文以珠海淇澳岛红树林区为例,使用SAR图像与TM图像,探讨了监督分类、非监督分类以及神经网络分类3种分类方法和IHS融合、小波融合以及主成分融合3种融合方法对红树林群落进行分类的效果。结果表明,对SAR与TM主成分融合图像应用神经网络分类方法能够取得最好的分类效果。     

CBERS与TM遥感影像湿地覆被分类对比分析

为了对比CBERS与TM两种遥感影像在地表覆被信息提取中的具体性能,验证基于CBERS遥感影像进行湿地覆被分类的可行性,以典型内陆淡水湿地区为对象,基于CBERS与TM遥感影像,针对各波段进行信息量统计及光谱特性分析,获取了各波段覆被探测性能的初步认识;运用非监督、监督与面向对象三种代表性分类方法进行分类实验,通过精度误差矩阵对比分类结果,分析了两种遥感影像在湿地覆被分类中的准确程度差异;基于分类结果,通过景观格局指数计算,对比分析了两种影像在湿地覆被信息提取结果上的空间差异和特性。     

Wetland mapping by fusion of airborne laser scanning and multi-temporal multispectral satellite imagery

Wetlands play a major role in Europe’s biodiversity. Despite their importance, wetlands are suffering from constant degradation and loss, therefore, they require constant monitoring. This article presents an automatic method for the mapping and monitoring of wetlands based on the fused processing of laser scans and multispectral satellite imagery, with validations and evaluations performed over an area of Lake Balaton in Hungary. Markov Random Field models have already been shown to successfully integrate various image properties in several remote sensing applications. In this article, we propose the multi-layer fusion Markov Random Field model for classifying wetland areas, built into an automatic classification process that combines multi-temporal multispectral images with a wetland classification reference map derived from airborne laser scanning (ALS) data acquired in an earlier year. Using an ALS-based wetland classification map that relied on a limited amount of ground truthing proved to improve the discrimination of land-cover classes with similar spectral characteristics. Based on the produced classifications, we also present an unsupervised method to track temporal changes of wetland areas by comparing the class labellings of different time layers. During the evaluations, the classification model is validated against manually interpreted independent aerial orthoimages. The results show that the proposed fusion model performs better than solely image-based processing, producing a non-supervised/semi-supervised wetland classification accuracy of 81–93% observed over different years.     

基于多季相Sentinel-2影像的白洋淀湿地信息提取

白洋淀湿地是华北平原上重要的浅水湖泊湿地,对雄安新区绿色发展具有重要的生态价值。对白洋淀高度异质化的景观格局进行分类,能够为白洋淀湿地资源的遥感监测提供指导意义。针对湿地季节变化的特点,对白洋淀每个季节选取一期具有代表性的Sentinel-2影像,采用分类与回归树（CART）、支持向量机（SVM）、随机森林（RF）3种常用的机器学习分类器对15种季相组合实验方案进行分类,分析不同季相遥感影像及其组合对白洋淀湿地信息提取的优劣。结果表明：相较于使用单一季相影像分类,多季相影像的组合能够显著提高分类精度,春&夏季相组合能够得到最优的分类效果,相对单季影像总体分类精度提高了10.9%~25.5%,Kappa系数提高了0.09~0.29;SVM分类器的分类表现较为稳定,能够得到最高的平均分类精度,CART分类器在处理高维特征的能力不如随机森林和SVM;不同特征类型对湿地信息提取的贡献度从高到底依次是红边光谱特征、传统光谱特征、缨帽变换特征、主成分分析特征、纹理特征。实验成果能为湿地信息的遥感识别提供依据。     

Understanding urban wetland dynamics: cross-scale detection and analysis of remote sensing

This study aimed to detect and understand remotely sensed urban wetland dynamics as a sensitive indicator of the combined effects of human disturbances and climate impacts in the course of global change. To address this objective, the study developed technical approaches to detect and interpret wetland changes across spatial scales in complex urban landscapes. Using a series of Satellite Pour l’Observation de la Terre (SPOT) images covering 1992–2010, the study was conducted in the Kansas City metropolitan area of the USA, which has experienced significant urban sprawl in recent decades. As a fine-tuning of the traditional supervised image classification, a knowledge-based classification algorithm was developed to identify fine-scale, hidden wetlands that cannot be appropriately detected based on their spectral differentiability. The analyses of wetland change were implemented at the metropolitan, watershed, and sub-watershed scales as well as being based on the size of surface water bodies in order to reveal real pictures of urban wetland change trends in relation to major driving factors. The results of the study indicated that the knowledge-based classification approach improved the detection capability and accuracy of urban wetlands by fine-tuning the traditional classification results. The cross-scale analysis of detected land covers revealed that wetland dynamics varied in trend and magnitude from metropolitan, watersheds, to sub-watershed scales. The study found that increased precipitation swelled wetlands, which inflated the findings of remotely sensed wetland cover and related trend interpretation. During an 18 year study period, human development activities in the study area resulted in a large increase in impervious surfaces, which was mainly at the expense of farmland/grassland areas and some small wetlands in all urban watersheds. In contrast, increased precipitation in the region swelled large wetlands in particular. This mixed picture of urban wetland dynamics, associated with the analysis of underlying driving factors, provides a new baseline for relevant urban planning, management, and research in a global change perspective.     

Coastal wetland vegetation classification with a Landsat Thematic Mapper image

Coastal wetland vegetation classification with remotely sensed data has attracted increased attention but remains a challenge. This paper explored a hybrid approach on a Landsat Thematic Mapper (TM) image for classifying coastal wetland vegetation classes. Linear spectral mixture analysis was used to unmix the TM image into four fraction images, which were used for classifying major land covers with a thresholding technique. The spectral signatures of each land cover were extracted separately and then classified into clusters with the unsupervised classification method. Expert rules were finally used to modify the classified image. This research indicates that the hybrid approach employing sub-pixel information, an analyst's knowledge and characteristics of coastal wetland vegetation distribution shows promise in successfully distinguishing coastal vegetation classes, which are difficult to separate with a maximum likelihood classifier (MLC). The hybrid method provides significantly better classification results than MLC.     

Unsupervised spectral sub-feature learning for hyperspectral image classification

Spectral pixel classification is one of the principal techniques used in hyperspectral image (HSI) analysis. In this article, we propose an unsupervised feature learning method for classification of hyperspectral images. The proposed method learns a dictionary of sub-feature basis representations from the spectral domain, which allows effective use of the correlated spectral data. The learned dictionary is then used in encoding convolutional samples from the hyperspectral input pixels to an expanded but sparse feature space. Expanded hyperspectral feature representations enable linear separation between object classes present in an image. To evaluate the proposed method, we performed experiments on several commonly used HSI data sets acquired at different locations and by different sensors. Our experimental results show that the proposed method outperforms other pixel-wise classification methods that make use of unsupervised feature extraction approaches. Additionally, even though our approach does not use any prior knowledge, or labelled training data to learn features, it yields either advantageous, or comparable, results in terms of classification accuracy with respect to recent semi-supervised methods.     

Unsupervised spectral feature selection algorithms for high dimensional data

It is a significant and challenging task to detect the informative features to carry out explainable analysis for high dimensional data, especially for those with very small number of samples. Feature selection especially the unsupervised ones are the right way to deal with this challenge and realize the task. Therefore, two unsupervised spectral feature selection algorithms are proposed in this paper. They group features using advanced Self-Tuning spectral clustering algorithm based on local standard deviation, so as to detect the global optimal feature clusters as far as possible. Then two feature ranking techniques, including cosine-similarity-based feature ranking and entropy-based feature ranking, are proposed, so that the representative feature of each cluster can be detected to comprise the feature subset on which the explainable classification system will be built. The effectiveness of the proposed algorithms is tested on high dimensional benchmark omics datasets and compared to peer methods, and the statistical test are conducted to determine whether or not the proposed spectral feature selection algorithms are significantly different from those of the peer methods. The extensive experiments demonstrate the proposed unsupervised spectral feature selection algorithms outperform the peer ones in comparison, especially the one based on cosine similarity feature ranking technique. The statistical test results show that the entropy feature ranking based spectral feature selection algorithm performs best. The detected features demonstrate strong discriminative capabilities in downstream classifiers for omics data, such that the AI system built on them would be reliable and explainable. It is especially significant in building transparent and trustworthy medical diagnostic systems from an interpretable AI perspective.