GIS辅助下的基于知识的遥感影像分类方法研究：以土地覆盖／土地利用？…

提高计算机遥感影像的分类精度，是遥感应用中研究的主要问题之一。作者以规则的形式表示遥感影像解译知识，使用ＴＭ影像数据和ＤＥＭ、坡度、土地利用图等地理辅助数据，从遥感影像处理／地理数据／专家知识一体化的角度出发，使用基于知识的方法进行了研究，改善了分类精度。实例研究证明了方法的正确性。     

GIS辅助下的Bayes法遥感影像分类

介绍了Bayes分类器 ,提出了从GIS空间数据库中挖掘知识用以辅助进行遥感影像分类的方法。文中以规则的形式表示遥感影像的解译知识 ,并使用其它地理辅助数据 ,从遥感影像处理、地理辅助数据、专家知识一体化的角度出发 ,使用基于知识的方法进行了分类研究 ,改善了分类精度。实验表明这是一种较好的分类方法。     

GIS辅助下的Bayes法遥感影像分类

介绍了Bayes分类器,提出了从GIS空间数据库中挖掘知识用以辅助进行遥感影像分类的方法.文中以规则的形式表示遥感影像的解译知识,并使用其它地理辅助数据,从遥感影像处理、地理辅助数据、专家知识一体化的角度出发,使用基于知识的方法进行了分类研究,改善了分类精度.实验表明这是一种较好的分类方法.     

基于GIS和神经网络的森林植被分类

本文综述了国际遥感分类研究,使用Landsat7 ETM＋遥感数据和地理辅助数据,应用BP神经网络方法,将莽汉山林场作为研究区进行了遥感影像的分类研究。比较了BP神经网络分类与最大似然、简单和复杂非监督分类法之间的类型与数量精度。BP神经网络分类的总类型精度是70.5%,总数量精度为84.65%,KAPPA系数是0.6455。结果说明BP神经网络的分类质量优于其他方法,其总的类型精度与其他三种分类方法相比分别增加了10.5%、32%和33%,总的质量精度增加了5.3%。因此,辅以地理参考数据的BP神经网络分类可以作为一种有效的分类方法。     

基于分类规则挖掘的遥感影像分类研究

分析了目前遥感影像的统计分类、神经网络分类及基于符号知识的逻辑推理分类方法的优缺点.以GIS为平台,构建了多源空间数据库,将数据挖掘的思想和方法引入遥感影像分类中,提出了面向分类规则挖掘的遥感影像分类框架.针对遥感光谱数据及其他空间数据的特点,定义了连续属性样本分类概念和分割点评价指标,提出了一种新的连续属性样本分类规则挖掘算法.选择一个试验区,采用该算法分别对遥感光谱数据、遥感光谱和DEM数据相结合的数据进行分类规则挖掘、遥感影像分类和分类精度比较.结果表明：（1）该算法具有较高的分类精度;（2）加入DEM等与分类相关的其他空间数据可以提高遥感影像的分类精度.通过挖掘分类规则进行遥感影像分类,扩展了基于知识的逻辑推理分类方法中知识获取渠道,提高了分类规则获取的智能化程度.新的连续属性样本分类规则挖掘算法,扩展了归纳学习算法对连续属性样本分类的适应性.     

耦合知识图谱和深度学习的新一代遥感影像解译范式

在遥感大数据时代,遥感影像智能解译是挖掘遥感大数据价值并推动若干重大应用的关键技术,如何将知识推理和数据学习两类解译方法有机联合已成为遥感大数据智能处理的重要研究趋势。由此提出了面向遥感影像解译的遥感领域知识图谱构建与进化方法,建立了顾及遥感成像机理和地理学知识的遥感领域知识图谱。在遥感领域知识图谱支撑下,以零样本遥感影像场景分类、可解释遥感影像语义分割以及大幅面遥感影像场景图生成3个典型的遥感影像解译任务为例,研究了耦合知识图谱和深度学习的新一代遥感影像解译范式。在零样本遥感影像场景分类实验中,所提方法在不同的可见类/不可见类比例和不同的语义表示下,都明显优于其他方法;在可解释遥感影像语义分割实验中,知识推理与深度学习的联合方法取得了最好的分类结果;在大幅面遥感影像场景图生成实验中,知识图谱引导的方法精度明显高于基准的频率统计方法。遥感知识图谱推理与深度数据学习的融合可以有效提升遥感影像的解译性能。     

基于GIS的中国东北植被综合分类研究

ＮＯＡＡ／ＡＶＨＲＲ由于运行周期短、覆盖范围大、成本低、波段宽等特点,目前正越来越广泛地受到人们的普遍关注。在大尺度、中尺度植被遥感上,ＮＯＡＡ／ＡＶＨＲＲ具有陆地卫星无法比拟的优势,但在另一方面,ＮＯＡＡＡＶＨＲＲ也存在分辨率低、数据变形较大和几何畸变较严重等问题。这样,在应用ＮＯＡＡＡＶＨＲＲ数据进行大区域植被制图时,植被分类的精度仍待提高。本文从理论上探讨了将地理信息系统提供的地理数据与遥感数据复合的可行性;尝试在ＧＩＳ环境下,将气温、降水、高程３个影响区域植被覆盖的主要指标,按一定的地面网格系统和数学模式进行量化,生成数字地学影像,并使之与经过优化、压缩处理的ＮＯＡＡＡＶＨＲＲ数据进行复合,对复合后的综合影像进行监督分类。分类结果显示,与传统的应用最大似然分类方法对单一遥感图像分类相比,该综合分类方法分类精度提高了１８．３％,该研究方法改变了遥感影像的单一信息结构;丰富了图像的信息含量;完成了地理数据的数字传输、处理、存储及影像化显示。     

基于知识的遥感影像模糊分类方法

介绍了目前遥感影像分类的常用方法,提出了一种基于知识的信息提取的遥感影像模糊分类方法。采用GIS数据辅助进行遥感影像模糊法分类,从GIS数据库中提取一定数量的样本信息或挖掘知识形成规则,进行样本的训练学习或辅助进行分类判定。提高了分类的效率和精度,是对模糊分类方法一次有效改进。     

基于知识的遥感影像模糊分类方法

介绍了目前遥感影像分类的常用方法, 提出了一种基于知识的信息提取的遥感影像模糊分类方法.采用GIS数据辅助进行遥感影像模糊法分类,从GIS数据库中提取一定数量的样本信息或挖掘知识形成规则,进行样本的训练学习或辅助进行分类判定.提高了分类的效率和精度,是对模糊分类方法一次有效改进.     

面向对象和规则的高分辨率影像分类研究

随着航天遥感技术的发展,遥感数据的空间分辨率、光谱分辨率和时间分辨率极大提高,高效解译并处理海量的、具有空间几何信息和纹理信息的地物高分辨率遥感影像数据已成为遥感领域研究的重点与难点。对此,本文提出一种面向对象和规则的遥感影像数据的分类提取方法,即通过发现和挖掘高分辨率影像丰富的光谱和空间特征知识,建立影像对象多层次网络分割分类结构,实现对遥感影像准确快速的地物分类和精度评价。以藏南地区WorldView-2影像数据为试验研究对象,采用面向对象和规则的影像分类方法进行验证试验,即综合采用均值方差法、最大面积法、精度比较法进行分析,选择3种最佳分割尺度建立多层次影像对象网络层次结构进行影像分类试验。结果表明,采用面向对象规则分类方法对高分辨率影像进行分类,能使高分辨率影像分类结果近似于目视判读的结果,分类精度更高。面向对象规则分类法的综合精度和Kappa系数分别为97.38%、0.967 3;与面向对象SVM法相比,分别高出6.23%、0.078;与面向对象KNN法相比,分别高出7.96%、0.099 6。建筑物的提取精度、用户精度分别比面向对象SVM法高出18.39%、3.98%,比面向对象KNN法高出21.27%、14.97%。     

Toward accountable land use mapping: Using geocomputation to improve classification accuracy and reveal uncertainty

The classification of satellite imagery into land use/cover maps is a major challenge in the field of remote sensing. This research aimed at improving the classification accuracy while also revealing uncertain areas by employing a geocomputational approach. We computed numerous land use maps by considering both image texture and band ratio information in the classification procedure. For each land use class, those classifications with the highest class-accuracy were selected and combined into class-probability maps. By selecting the land use class with highest probability for each pixel, we created a hard classification. We stored the corresponding class probabilities in a separate map, indicating the spatial uncertainty in the hard classification. By combining the uncertainty map and the hard classification we created a probability-based land use map, containing spatial estimates of the uncertainty. The technique was tested for both ASTER and Landsat 5 satellite imagery of Gorizia, Italy, and resulted in a 34% and 31% increase, respectively, in the kappa coefficient of classification accuracy. We believe that geocomputational classification methods can be used generally to improve land use and land cover classification from imagery, and to help incorporate classification uncertainty into the resultant map themes.     

Fusion of HJ1B and ALOS PALSAR data for land cover classification using machine learning methods

Image classification from remote sensing is becoming increasingly urgent for monitoring environmental changes. Exploring effective algorithms to increase classification accuracy is critical. This paper explores the use of multispectral HJ1B and ALOS (Advanced Land Observing Satellite) PALSAR L-band (Phased Array type L-band Synthetic Aperture Radar) for land cover classification using learning-based algorithms. Pixel-based and object-based image analysis approaches for classifying HJ1B data and the HJ1B and ALOS/PALSAR fused-images were compared using two machine learning algorithms, support vector machine (SVM) and random forest (RF), to test which algorithm can achieve the best classification accuracy in arid and semiarid regions. The overall accuracies of the pixel-based (Fused data: 79.0%; HJ1B data: 81.46%) and object-based classifications (Fused data: 80.0%; HJ1B data: 76.9%) were relatively close when using the SVM classifier. The pixel-based classification achieved a high overall accuracy (85.5%) using the RF algorithm for classifying the fused data, whereas the RF classifier using the object-based image analysis produced a lower overall accuracy (70.2%). The study demonstrates that the pixel-based classification utilized fewer variables and performed relatively better than the object-based classification using HJ1B imagery and the fused data. Generally, the integration of the HJ1B and ALOS/PALSAR imagery can improve the overall accuracy of 5.7% using the pixel-based image analysis and RF classifier.     

高光谱影像的DAE分类

针对高光谱影像非线性分类问题,根据高光谱影像光谱分辨率高且光谱具有非线性的特点,结合深度学习理论,提出了一种采用降噪自动编码器(DAE)的高光谱影像分类方法。该方法结合降噪自动编码器与SOFTMAX分类器,构造深层网络分类模型;然后,利用加噪后的光谱数据,采用Dropout方法对分类模型进行预训练和微调;最后,利用训练得到的网络模型学习高光谱影像光谱的隐含特征,实现高光谱影像的分类。采用该方法对AVIRIS和PHI的高光谱影像分别进行分类对比实验,结果表明该方法能有效提高高光谱影像分类精度。     

基于高光谱影像的渤海海冰遥感监测研究

监督分类方法是海冰遥感监测中常用的有效方法,但不同的监督分类方法以及波段选择,在海冰识别中的精度有较大差异。为提高海冰监测的精度,本文使用高光谱传感器提供的可见光、近红外波段的连续成像光谱信息,对比了不同的波段组合在多种分类方法中海冰提取的精度,分析了不同波段组合、不同分类方法在海冰监测上的优缺点,最终得出海冰监测中最佳的波段组合以及最适宜的监督分类方法。     

遥感技术在黄土高原土地利用现状调查中的应用研究

本研究选取黄土高原典型丘陵沟壑区——陕西省米脂县为试验区,用TM磁带、TM假彩色合成影像、SPOT多光谱影像和彩色红外航空像片同时对试区进行土地利用现状分类与制图的比较研究。通过对土地利用现状分类系统、TM图像计算机增强处理与自动分类、TM最佳波段组合、三种影像的目视判读与制图、以及遥感信息源的综合评价等多方面的试验研究,为遥感技术在黄土高原1:5万土地利用现状调查制图中的应用提供了一套技术数据及可行的方法。     

Landsat7 ETM＋影像的融合和自动分类研究

利用SFIM、MLT、HPF和修改的Brovey(MB)等遥感影像融合算法对Landsat 7 ETM 影像进行融合和自动分类研究，并就融合影像的光谱保真度、高频空间信息融人度和分类精度对这些方法进行评价。结果表明SFIM变换几乎完全保持了原始影像的光谱特点，并具有最高的平均分类精度；MB变换具有最高的高频空间信息融人度；MLT变换也具有较高的分类精度；只有HPF变换的各项指标都不突出。所有4种融合影像的分类精度都较原始影像的分类精度有明显的提高。这表明，源于同一传感器系统的不同分辨率影像的融合可以避免异源传感器融合影像所常见的各种参数、时相和配准误差，所以能够明显地提高影像的自动分类精度。     

Spatial and semantic effects of LUCAS samples on fully automated land use/land cover classification in high-resolution Sentinel-2 data

In this study, we test the use of Land Use and Coverage Area frame Survey (LUCAS) in-situ reference data for classifying high-resolution Sentinel-2 imagery at a large scale. We compare several pre-processing schemes (PS) for LUCAS data and propose a new PS for a fully automated classification of satellite imagery on the national level. The image data utilizes a high-dimensional Sentinel-2-based image feature space. Key elements of LUCAS data pre-processing include two positioning approaches and three semantic selection approaches. The latter approaches differ in the applied quality measures for identifying valid reference points and by the number of LU/LC classes (7–12). In an iterative training process, the impact of the chosen PS on a Random Forest image classifier is evaluated. The results are compared to LUCAS reference points that are not pre-processed, which act as a benchmark, and the classification quality is evaluated by independent sets of validation points. The classification results show that the positional correction of LUCAS points has an especially positive effect on the overall classification accuracy. On average, this improves the accuracy by 3.7%. This improvement is lowest for the most rigid sample selection approach, PS₂, and highest for the benchmark data set, PS₀. The highest overall accuracy is 93.1% which is achieved by using the newly developed PS₃; all PS achieve overall accuracies of 80% and higher on average. While the difference in overall accuracy between the PS is likely to be influenced by the respective number of LU/LC classes, we conclude that, overall, LUCAS in-situ data is a suitable source for reference information for large scale high resolution LC mapping using Sentinel-2 imagery. Existing sample selection approaches developed for Landsat imagery can be transferred to Sentinel-2 imagery, achieving comparable semantic accuracies while increasing the spatial resolution. The resulting LC classification product that uses the newly developed PS is available for Germany via DOI: https://doi.org/10.15489/1ccmlap3mn39.     

Utility of image point cloud data towards generating enhanced multitemporal multisensor land cover maps

Multitemporal land cover classification over urban areas is challenging, especially when using heterogeneous data sources with variable quality attributes. A prominent challenge is that classes with similar spectral signatures (such as trees and grass) tend to be confused with one another. In this paper, we evaluate the efficacy of image point cloud (IPC) data combined with suitable Bayesian analysis based time-series rectification techniques to improve the classification accuracy in a multitemporal context. The proposed method uses hidden Markov models (HMMs) to rectify land covers that are initially classified by a random forest (RF) algorithm. This land cover classification method is tested using time series of remote sensing data from a heterogeneous and rapidly changing urban landscape (Kuopio city, Finland) observed from 2006 to 2014. The data consisted of aerial images (5 years), Landsat data (all 9 years) and airborne laser scanning data (1 year). The results of the study demonstrate that the addition of three-dimensional image point cloud data derived from aerial stereo images as predictor variables improved overall classification accuracy, around three percentage points. Additionally, HMM-based post processing reduces significantly the number of spurious year-to-year changes. Using a set of 240 validation points, we estimated that this step improved overall classification accuracy by around 3.0 percentage points, and up to 6 to 10 percentage points for some classes. The overall accuracy of the final product was 91% (kappa = 0.88). Our analysis shows that around 1.9% of the area around Kuopio city, representing a total area of approximately 0.61 km², experienced changes in land cover over the nine years considered.     

Mapping trees in high resolution imagery across large areas using locally variable thresholds guided by medium resolution tree maps

Large area tree maps, important for environmental monitoring and natural resource management, are often based on medium resolution satellite imagery. These data have difficulty in detecting trees in fragmented woodlands, and have significant omission errors in modified agricultural areas. High resolution imagery can better detect these trees, however, as most high resolution imagery is not normalised it is difficult to automate a tree classification method over large areas. The method developed here used an existing medium resolution map derived from either Landsat or SPOT5 satellite imagery to guide the classification of the high resolution imagery. It selected a spatially-variable threshold on the green band, calculated based on the spatially-variable percentage of trees in the existing map of tree cover. The green band proved more consistent at classifying trees across different images than several common band combinations. The method was tested on 0.5 m resolution imagery from airborne digital sensor (ADS) imagery across New South Wales (NSW), Australia using both Landsat and SPOT5 derived tree maps to guide the threshold selection. Accuracy was assessed across 6 large image mosaics revealing a more accurate result when the more accurate tree map from SPOT5 imagery was used. The resulting maps achieved an overall accuracy with 95% confidence intervals of 93% (90–95%), while the overall accuracy of the previous SPOT5 tree map was 87% (86–89%). The method reduced omission errors by mapping more scattered trees, although it did increase commission errors caused by dark pixels from water, building shadows, topographic shadows, and some soils and crops. The method allows trees to be automatically mapped at 5 m resolution from high resolution imagery, provided a medium resolution tree map already exists.