Object Detection in Remote Sensing Images Using Picture Fuzzy Clustering and MapReduce

In image processing, one of the most important steps is image segmentation. The objects in remote sensing images often have to be detected in order toperform next steps in image processing. Remote sensing images usually havelarge size and various spatial resolutions. Thus, detecting objects in remote sensing images is very complicated. In this paper, we develop a model to detectobjects in remote sensing images based on the combination of picture fuzzy clustering and MapReduce method (denoted as MPFC). Firstly, picture fuzzy clustering is applied to segment the input images. Then, MapReduce is used to reducethe runtime with the guarantee of quality. To convert data for MapReduce processing, two new procedures are introduced, including Map_PFC and Reduce_PFC.The formal representation and details of two these procedures are presented in thispaper. The experiments on satellite image and remote sensing image datasets aregiven to evaluate proposed model. Validity indices and time consuming are usedto compare proposed model to picture fuzzy clustering model. The values ofvalidity indices show that picture fuzzy clustering integrated to MapReduce getsbetter quality of segmentation than using picture fuzzy clustering only. Moreover,on two selected image datasets, the run time of MPFC model is much less thanthat of picture fuzzy clustering.

Sub-pixel change detection for urban land-cover analysis via multi-temporal remote sensing images

Conventional change detection approaches are mainly based on per-pixel processing,which ignore the sub-pixel spectral variation resulted from spectral mixture.Especially for medium-resolution remote sensing images used in urban landcover change monitoring,land use/cover components within a single pixel are usually complicated and heterogeneous due to the limitation of the spatial resolution.Thus,traditional hard detection methods based on pure pixel assumption may lead to a high level of omission and commission errors inevitably,degrading the overall accuracy of change detection.In order to address this issue and find a possible way to exploit the spectral variation in a sub-pixel level,a novel change detection scheme is designed based on the spectral mixture analysis and decision-level fusion.Nonlinear spectral mixture model is selected for spectral unmixing,and change detection is implemented in a sub-pixel level by investigating the inner-pixel subtle changes and combining multiple composition evidences.The proposed method is tested on multi-temporal Landsat Thematic Mapper and China–Brazil Earth Resources Satellite remote sensing images for the land-cover change detection over urban areas.The effectiveness of the proposed approach is confirmed in terms of several accuracy indices in contrast with two pixel-based change detection methods(i.e.change vector analysis and principal component analysis-based method).In particular,the proposed sub-pixel change detection approach not only provides the binary change information,but also obtains the characterization about change direction and intensity,which greatly extends the semantic meaning of the detected change targets.

Analysis of spatio-temporal pattern and driving force of land cover change using multi-temporal remote sensing images

Landuse and land cover change is regarded as a good indicator that represents the impact of human activities on earth’s environment.When the large collection of multi-temporal satellite images has become available,it is possible to study a long-term historical process of land cover change.This study aims to investigate the spatio-temporal pattern and driving force of land cover change in the Pearl River Delta region in southern China,where the rapid development has been witnessed since 1980s.The fast economic growth has been associated with an accelerated expansion of urban landuse,which has been recorded by historical remote sensing images.This paper reports the method and outcome of the research that attempts to model spatio-temporal pattern of land cover change using multi-temporal satellite images.The classified satellite images were compared to detect the change from various landuse types to built-up areas.The trajectories of land cover change have then been established based on the time-series of the classified land cover classes.The correlation between the expansion of built-up areas and selected economic data has also been analysed for better understanding on the driving force of the rapid urbanisation process.The result shows that,since early 1990s,the dominant trend of land cover change has been from farmland to urban landuse.The relationship between economic growth indicator(measured by GDP)and built-up area can well fit into a linear regression model with correlation coefficients greater than 0.9.It is quite clear that cities or towns have been sprawling in general,demonstrating two growth models that were closely related to the economic development stages.

Study of Forest Cover Change Dynamics between 2000 and 2015 in the Ikongo District of Madagascar Using Multi-Temporal Landsat Satellite Images

Satellite images are considered reliable data that preserve land cover information. In the field of remote sensing, these images allow relevant analyses of changes in space over time through the use of computer tools. In this study, we have applied the “discriminant” change detection algorithm. In this, we have verified its effectiveness in multi-temporal studies. Also, we have determined the change in forest dynamics in the Ikongo district of Madagascar between 2000 and 2015. During the treatments, we have used the Landsat TM satellite images for the years 2000, 2005 and 2010 as well as ETM+ for 2015. Thus, analyses carried out have allowed us to note that between 2000-2005, 1.4% of natural forest disappeared. And, between 2005-2010, forests degradation was 1.8%. Also, between 2010-2015, about 0.5% of the natural forest conserved in 2010 disappeared. Furthermore, we have found that the discriminant algorithm is considerably efficient in terms of monitoring the dynamics of forest cover change.

Towards an Intelligent Predictive Model for Analyzing Spatio-Temporal Satellite Image Based on Hidden Markov Chain

Nowadays remote sensing is an important technique for observing Earth surface applied to different areas such as, land use, urban planning, remote monitoring, real time deformation of the soil that can be associated with earthquakes or landslides, the variations in thickness of the glaciers, the measurement of volume changes in the case of volcanic eruptions, deforestation, etc. To follow the evolution of these phenomena and to predict their future states, many approaches have been proposed. However, these approaches do not respond completely to the specialists who process yet more commonly the data extracted from the images in their studies to predict the future. In this paper, we propose an innovative methodology based on hidden Markov models (HMM). Our approach exploits temporal series of satellite images in order to predict spatio-temporal phenomena. It uses HMM for representing and making prediction concerning any objects in a satellite image. The first step builds a set of feature vectors gathering the available information. The next step uses a Baum-Welch learning algorithm on these vectors for detecting state changes. Finally, the system interprets these changes to make predictions. The performance of our approach is evaluated by tests of space-time interpretation of events conducted over two study sites, using different time series of SPOT images and application to the change in vegetation with LANDSAT images.

基于残差密集块的激光遥感图像中目标检测方法

为了提高对目标检测的效果,提出基于残差密集块的激光遥感图像中目标检测方法。首先,设计基于残差密集块的卷积神经网络,在设计ReLU激活函数并完成网络训练后,基于含噪激光遥感图像的初步特征提取结果,利用单个卷积展开卷积映射处理,抽取出潜在干净图像。然后,通过聚类处理的方式,得到激光遥感图像中车辆目标的显著图,再利用大律法,通过建立的特征比例关系的方式检测出其中的目标信息。实验结果表明,应用该方法有效滤除激光遥感图像中的噪声,并精准检测出激光遥感图像中的车辆目标。相比于3种传统方法,该方法检测结果均值误差的最小值仅为0.0156,说明该方法有效实现了设计预期。

基于小波融合和PCA-核模糊聚类的遥感图像变化检测

本文提出了一种变化检测方法以提高算法的鲁棒性、检测精度以及抗噪性.首先对差值法构造的差异图和比值法构造的差异图进行小波融合.然后将融合图像分成互不重叠的小块,并用主成分分析得到图像块的正交基.通过将融合图像中每个像素的邻域小块映射到正交基上使得每个像素用一个特征向量来表示.最后用基于核的模糊C均值对特征向量进行聚类.实验结果显示与使用单一类型差异图的聚类方法相比,本方法由于采用了图像融合的策略而增强了鲁棒性,且由于采用了核模糊聚类,进一步提高了变化检测精度.此外由于使用了特征提取的技术,本方法具有一定的抗噪性能.

一种新的多波段遥感影像变化检测方法

随着遥感技术的发展,采用遥感影像对国土资源进行动态监测已经成为了热点。目前常用的差值法和分类后比较变化检测方法中存在着各种缺陷。提出一种基于模糊C均值聚类(FCM)算法的遥感影像变化检测方法,利用一个改进的模糊C均值聚类算法进行遥感影像分类处理,然后引入多波段综合变化掩膜的思想进行变化检测。实验结果表明这种方法是有效的,提高了检测精度,检测结果为国土资源调查提供了重要依据。

基于模糊C均值聚类和邻域分析的无监督多通道遥感图像变化检测

提出一种基于模糊C均值聚类(Fuzzy C-means,FCM)和邻域分析的多通道遥感图像变化检测方法。通常的多通道遥感图像变化检测方法将变化信息从多个波段压缩到一个波段,损失了遥感图像的波段信息。本文将多波段变化信息用FCM方法来实现多通道遥感图像的变化检测。但由于FCM有对孤立点敏感的特点,该方法容易受噪声的影响。本文在FCM的基础上,又提出了一种结合图像空间邻域信息的多通道遥感图像变化检测方法,改进了FCM对孤立点敏感的问题。实验结果表明,相对于其他变化检测方法及FCM方法,所提出的基于FCM和邻域分析的多通道遥感图像变化检测方法能较好地消除遥感图像中变化检测中噪声的影响,具有很好的变化检测性能。

基于快速EM算法和模糊融合的多波段遥感影像变化检测

提出了一种基于快速EM(expectation maximization)算法和模糊融合的多波段遥感影像无监督变化检测方法.该方法首先对各波段差异影像采用基于直方图分析的快速EM迭代算法获取变化分类阈值和变化信息,随后对各波段的变化信息进行模糊融合和判决,生成最终的变化检测图.利用真实的多波段遥感影像进行了实验,本文方法在运行时间和检测效果两个方面都具有优越性.

多时相遥感影像样本迁移模型与地表覆盖智能分类

利用时间序列遥感影像重建过去几十年的地表覆盖是实现时空多维地理场景感知与动态建模的基础,但存档历史遥感影像分类面临样本选择难、多时相影像协同解译水平低的问题。研究提出了一种基于已有土地覆盖产品与对应遥感影像中几何及属性特征约束的样本时空迁移方法,将迁移获得的训练样本嵌入多时相地表覆盖分类框架,获得多期地表覆盖分类结果,实现历史时期地表环境的智能感知与动态制图。太湖流域多时相分类的结果表明,无监督样本迁移方法可以充分利用先验几何约束和光谱属性,从参考地表覆盖产品中快速获得可靠的训练样本,多时相分类精度均高于89%,满足大区域多时相地表覆盖的分类需求,为地理环境演变建模提供了有效支持。

基于独立成分分析的多时相遥感图像变化检测

变化检测是通过分析多时相遥感图像间的差异实现地物变化信息的提取,而消除多时相遥感图像中的相关性是提取变化信息的一种有效途径。独立成分分析(ICA)作为近年出现的盲源分离技术,能够有效地消除多源信号间的二阶和高阶相关,经其变换的各分量之间相互独立。该文提出一种应用ICA变换实现多时相遥感图像变化检测的算法,首先对多时相多光谱遥感图像进行独立成分分析,得到彼此没有相关信息的独立成分,并且各独立成分图像中的变化信息得到增强:然后通过分析变换后的独立成分实现地物的变化检测。实验结果显示该算法比传统的方法具有更好的性能。

一种新的遥感图像海岸线检测方法

灰度遥感图像像素数一般比较大,特别是高分辨率的遥感图像,海岸线检测速度比较慢,限制了在工程中的实际应用。为了提高大型遥感图像的速度和精确性,提出了一种基于模糊聚类的快速海岸线检测方法。方法能够快速准确的提取和检测海岸线,对检测时间复杂度为常数,不随着遥感图像的增大而增大,并且检测过程中,无需人为干预,无需依靠阈值分割,而能够自动快速地从分割遥感图像中提取出海岸线。采用合成孔径雷达(SAR)遥感图像做了仿真实验,证明方法能够快速而有效的提取出海岸线。

从卫星遥感全色图像中自动提取城市目标

提出了一种从卫星遥感全色图像中自动提取城市目标的方法。在总结城市目标的卫星遥感全色图像特性的基础上 ,设计了一种层次提取的方法。首先在低分辨率图像中提取城市目标的候选区域 ;接着在候选区域内利用城市目标一些更复杂的特性在高分辨率图像中证实城市目标。为了获得城市目标的边界 ,提出了一种基于边缘点密度的算法 ,并将算法应用去提取SPOT图像中的城市目标 。

彩色遥感图像目标提取方法研究

目标提取是对遥感图像进行分析处理的一个重要内容。针对彩色遥感图像的特征,首先采用了传统的边缘检测方法,验证其存在的不足。进而运用模糊聚类分析的模糊C-均值算法,选择适当的正交彩色特征,实现了对图像中目标区域的有效分割与快速提取,为遥感图像识别与计算提供了可靠的基础。研究实例表明了算法的有效性。

基于模糊度与简化PCNN的遥感图像变化检测

遥感图像变化检测必须充分考虑不同时间、不同环境背景等具体情况对于图像的影响,尽可能消除这些"伪变化"影响,以获得比较客观的感兴趣区域变化检测结果。针对遥感图像这一特点提出了一种基于脉冲耦合神经网络的变化检测法。该方法利用脉冲耦合神经网络实现多时相遥感图像的多层次分类,将分类结果进行差值比对,即可检测出感兴趣的变化区域。并提出根据最小模糊度准则,自动确定PCNN循环迭代次数和最佳阈值。实测数据的实验结果表明该方法的变化检测效果优于基于最大熵变化检测算法。

结合高分辨遥感影像和GIS数据的土地利用变化监测

研究了一种结合高分辨率遥感影像和GIS数据的土地利用自动变化监测方法。分别采用马氏距离、支持向量机、神经网络3种分类方法对研究区域进行模糊分类,然后通过多分类器模糊决策融合分类方法对3种分类结果进行融合,提高总体分类精度。在获得高精度分类结果的基础上,结合历史时期GIS专题数据和分类结果,计算对应的图斑多边形内各类别成份,并与其历史属性对比分析,自动实现土地利用变化监测。实验数据选取QuickBird高分辨率遥感影像和1∶1万土地利用GIS数据,实验结果表明模糊决策融合分类能够明显改善分类效果,获得比单一分类器更为精准的结果。利用决策分类结果并结合GIS数据进行变化区域判定实验,结果表明,对区域中存在较大变化能够准确自动判定为变化区域,而区域中存在较少部分变化则存在部分误判现象。

差异特征融合的无监督SAR图像变化检测

针对Siamese网络忽略不同层级差异特征之间的关联导致检测精度有限的问题,提出了基于差异特征融合的无监督SAR(synthetic aperture radar)图像变化检测算法。首先,利用对数比值算子和均值比值算子构建两幅信息互补的差异图,通过引入能量矩阵对差异图进行像素级融合以提高其信噪比;其次,设计了一种基于差异特征融合的Siamese网络(difference feature fusion for Siamese,DFF-Siamese),该网络能够通过差异特征提取模块在决策层综合衡量不同层级特征之间的差异程度,从而有效增强网络的特征表达能力;最后,利用模糊聚类算法对融合结果进行分类构建“伪标签”,用于训练DFF-Siamese网络以实现高精度SAR图像变化检测。在3组真实遥感数据集上的实验结果表明,本文提出的算法与其他对比算法相比具有更高的检测精度和更低的错误率。

多时相遥感影像变化检测综述

近几十年来,多时相影像处理和变化检测是遥感领域一个较为活跃的研究方向。虽然在环境变化监测和检测方面成功的应用有很多,但是从多时相影像及时提取地球环境和人类活动的动态信息仍面临很多挑战。近年来,随着新型遥感平台和传感器的发展,在克服技术障碍方面取得了很大进步。历史影像档案提供范围的扩大也使得长期变化检测和建模成为可能。这些发展推动了更先进的影像处理方法的开发和处理时间维度影像数据新方法的研究工作。本文回顾了多时相数据处理和变化检测的发展现状。作者首先对地球表面环境变化的性质进行了分析,从四个方面总结了遥感变化检测技术的发展,包括变化检测影像预处理、变化检测方法和途径分类、遥感变化检测方法和多时相影像处理的准确度评估。文章试图在先验知识的基础上从多源数据、集成处理和智能方法角度提出综合解决方案。为促进遥感影像变化检测技术的深入研究,本文还指出了变化检测所面临的挑战和可能的对策。

基于KICA的多时相遥感图像变化检测

针对PCA变化检测方法的精度较低和ICA方法的线性局限性问题,提出了基于核独立成分分析(KICA)的多时相遥感图像变化检测方法。首先,将每一时相的图像转化为列向量,并把这些列向量组成矩阵;然后,通过核函数将矩阵映射到高维特征空间中,再在该空间中利用ICA方法分离出相互独立的图像分量;接着通过FCM算法分割表征变化信息的图像分量,并采用区域生长算法获得完整的变化信息;最后,分别利用本文方法与差值法、PCA方法和ICA方法对多时相遥感图像进行变化检测,并对检测结果进行定性分析和定量比较。结果表明,该方法能更好地分离出多时相遥感图像的变化信息,具有更高检测精度。