Landscape Pattern Evaluation Based on Maximum Likelihood Classification——A Case Study of Irrigated Area of Hongsibao Town in China

By using maximum likelihood classification, several landscape indexes have been adopted to evaluate landscape structure of the irrigated area of Hongsibao Town, and landscape pattern and dynamic change of Hongsibao in 1989, 1999, 2003 and 2008 had been analyzed based on landscape patch, landscape type and transfer matrix. The results show that landscape pattern had changed obviously, patch number, fragmentation and dominance had increased, evenness had decreased, and landscape shape had become regular in the irrigated area of Hongsibao Town from 1989 to 2008. The primary landscape type in 1989 was grassland and in 2008 was sand, directly influenced by human activities.

A NEW LIKELIHOOD-BASED MODULATION CLASSIFICATION ALGORITHM USING MCMC

In this paper,a new likelihood-based method for classifying phase-amplitude-modulated signals in Additive White Gaussian Noise (AWGN) is proposed.The method introduces a new Markov Chain Monte Carlo (MCMC) algorithm,called the Adaptive Metropolis (AM) algorithm,to directly generate the samples of the target posterior distribution and implement the multidimensional integrals of likelihood function.Modulation classification is achieved along with joint estimation of unknown parameters by running an ergodic Markov Chain.Simulation results show that the proposed method has the advantages of high accuracy and robustness to phase and frequency offset.

Parallelizing maximum likelihood classification (MLC) for supervised image classification by pipelined thread approach through high-level synthesis (HLS) on FPGA cluster

High spectral,spatial,vertical and temporal resolution data are increasingly available and result in the serious challenge to pro-cess big remote-sensing images effectively and efficiently.This article introduced how to conduct supervised image classification by implementing maximum likelihood classification(MLC)over big image data on a field programmable gate array(FPGA)cloud.By comparing our prior work of implementing MLC on conventional cluster of multicore computers and graphics processing unit,it can be concluded that FPGAs can achieve the best performance in comparison to conventional CPU cluster and K40 GPU,and are more energy efficient.The proposed pipelined thread approach can be extended to other image-processing solutions to handle big data in the future.

综合后向散射特征与极化特征的L波段SAR数据岩石分类

以菲律宾民都洛岛为研究区域,选取ALOS PALSAR双极化数据(极化方式为HH和HV极化)作为数据源,通过提取后向散射系数(Sigma0 HH和Sigma0 HV)和极化分解参数(熵、角和反熵),使用最大似然分类方法实现研究区的岩石单元分类和填图。在加入了极化分解参数之后,总体精度由仅使用后向散射系数的36.706%提高到65.000%。海岸带沼泽和珊瑚礁的F1分数超过了0.80,辉长岩和Mansalay组的F1分数超过了0.75。引入极化特征后,岩石单元的边界被更好地提取,Mansalay组和Mindoro变质岩与其他岩石的可分性增强。3个极化分解参数弥补了多种岩石单元的后向散射系数难以区分的不足,显著提高了岩石单元的可分性。研究表明,L波段SAR数据的极化分解参数和后向散射系数相结合能提高植被覆盖区岩石单元的分类精度。

典型遥感影像分类方法适用性分析

分类技术是从遥感影像数据中提取信息必不可少的步骤,选择合适的分类器对提高分类精度至关重要,针对特定的研究如何选择适合的分类算法是一个亟需研究的问题。以北京市中心诚区中某一区域为研究区,应用“高分一号”(GF-1)数据和Landsat 8数据,分别采用最常用且分类精度相对较高的监督分类中的最小距离法、最大似然法、支持向量机法,将研究区分为林地、草地、水体、裸土、建筑物5种类型,并对分类结果进行空间分布、面积、精度三个方面的比对分析。结果表明,分类算法的选择主要取决于研究区的地物特点,其中最小距离法应用于植被覆盖面积较大的区域时精度较高,最大似然法适合于分类建筑物较多的区域,支持向量机法对各类地物的分类具有较高的普适性。

基于机器学习的典型岩溶区岩性分类技术-以广西平果地区为例

快速准确识别碳酸盐岩对于岩溶区的基础设施建设和重大工程实施十分重要,通过遥感岩性分类实现碳酸盐岩的快速提取目前仍然是最高效的途径之一。文章基于Landsat和AW3D 30DSM遥感数据,以广西平果地区典型岩溶区为研究对象,采用碳酸盐岩的可见光到短波红外的多光谱信息、熵和角二阶矩等纹理信息及曲率和坡度等地形特征,对平果地区岩溶分布区的碳酸盐岩、碎屑岩、第四系及水体进行岩性分类,在选取606个总体样本并验证303个分类样本的基础上,采用最大似然分类方法对区域岩性进行快速分类。结果表明:碳酸盐岩的生产者精度和用户精度分别达到94.54%和97.64%,基本能够实现碳酸盐岩的快速提取和准确识别的需求,在典型岩溶区的岩性分类方法中具有准确率高、实现路径简单、所需数据源易获取的特点,将为典型岩溶区的岩性快速分类提供一种新的思路。

关中平原耕地RS影像精准提取方法研究

【目的】高效获取大面积耕地影像分布数据,助力关中平原地区耕地保护动态监测和管理。【方法】以陕西省西安市临潼区为研究区,基于SNAP平台和ENVI处理软件,使用监督分类中的最大似然分类法对哨兵二号高分辨率遥感影像耕地RS(Remote Sensing)遥感数据进行识别提取,获取耕地空间分布及面积等地理信息。【结果】提取耕地总面积为411.57 km2,主要分布于临潼区北部相桥、交口、栋阳等街道及中东部何寨、零口街道等平缓地区,与官方统计面积相近,误差仅为0.92%,提取总体分类精度为96.07%,Kappa系数为0.94,符合精度要求。【结论】通过最大似然分类法提取耕地结果与实际数据较为贴合,证明最大似然分类法在实际耕地地类识别检测应用中有着较高的匹配度,可以较为精准地实现土地利用类型识别。

Weed detection in canola fields using maximum likelihood classification and deep convolutional neural network

Herbicide use is rising globally to enhance food production,causing harm to environment and the ecosystem.Precision agriculture suggests variable-rate herbicide application based on weed densities to mitigate adverse effects of herbicides.Accurate weed density estimation using advanced computer vision techniques like deep learning requires large labelled agriculture data.Labelling large agriculture data at pixel level is a time-consuming and tedious job.In this paper,a methodology is developed to accelerate manual labelling of pixels using a two-step procedure.In the first step,the background and foreground are segmented using maximum likelihood classification,and in the second step,the weed pixels are manually labelled.Such labelled data is used to train semantic segmentation models,which classify crop and background pixels as one class,and all other vegetation as the second class.This paper evaluates the proposed methodology on high-resolution colour images of canola fields and makes performance comparison of deep learning meta-architectures like SegNet and UNET and encoder blocks like VGG16 and ResNet-50.ResNet-50 based SegNet model has shown the best results with mean intersection over union value of 0.8288 and frequency weighted intersection over union value of 0.9869.

An effective approach for low-complexity maximum likelihood based automatic modulation classification of STBC-MIMO systems

A low-complexity likelihood methodology is proposed for automatic modulation classification of orthogonal space-time block code(STBC)based multiple-input multiple-output(MIMO)systems.We exploit the zero-forcing equalization technique to modify the typical average likelihood ratio test(ALRT)function.The proposed ALRT function has a low computational complexity compared to existing ALRT functions for MIMO systems classification.The proposed approach is analyzed for blind channel scenarios when the receiver has imperfect channel state information(CSI).Performance analysis is carried out for scenarios with different numbers of antennas.Alamouti-STBC systems with 2×2 and 2×1 and space-time transmit diversity with a 4×4 transmit and receive antenna configuration are considered to verify the proposed approach.Some popular modulation schemes are used as the modulation test pool.Monte-Carlo simulations are performed to evaluate the proposed methodology,using the probability of correct classification as the criterion.Simulation results show that the proposed approach has high classification accuracy at low signal-to-noise ratios and exhibits robust behavior against high CSI estimation error variance.

Parallelizing maximum likelihood classification on computer cluster and graphics processing unit for supervised image classification

Supervised image classification has been widely utilized in a variety of remote sensing applications.When large volume of satellite imagery data and aerial photos are increasingly available,high-performance image processing solutions are required to handle large scale of data.This paper introduces how maximum likelihood classification approach is parallelized for implementation on a computer cluster and a graphics processing unit to achieve high performance when processing big imagery data.The solution is scalable and satisfies the need of change detection,object identification,and exploratory analysis on large-scale high-resolution imagery data in remote sensing applications.

Assessment of Supervised Classifiers for Land Cover Categorization Based on Integration of ALOS PALSAR and Landsat Data

Many supervised classification algorithms have been proposed, however, they are rarely evaluated for specific application. This research examines the performance of machine learning classifiers support vector machine (SVM), neural network (NN), Random Forest (RF) against maximum classifier (MLC) (traditional supervised classifier) in forest resources and land cover categorization, based on combination of Advanced Land Observing Satellite (ALOS) Phased Array type L-band Synthetic Aperture Radar (PALSAR) and Landsat Thematic Mapper (TM) data, in Northern Tanzania. Various data categories based on Landsat TM surface reflectance, ALOS PALSAR backscattering and their derivatives were generated for various classification scenarios. Then a separate and joint processing of Landsat and ALOS PALSAR data were executed using SVM, NN, RF and ML classifiers. The overall classification accuracy (OA), kappa coefficient (KC) and F1 score index values were computed. The result proves the robustness of SVM and RF in classification of forest resource and land cover using mere Landsat data and integration of Landsat and PALSAR (average OA = 92% and F1 = 0.7 to 1). A two sample t-statistics was utilized to evaluate the performance of the classifiers using different data categories. SVM and RF indicate there is no significance difference at 5% significance level. SVM and RF show a significant difference when compared to NN and ML. Generally, the study suggests that parametric classifiers indicate better performance compared to parametric classifier.

Application of Parametric and Non Parametric Classifiers for Assessing Land Use/Land Cover Categories in Cocoa Landscape of Juaboso and Bia West Districts of Ghana

Satellite image classification has been used for long time in the field of remote sensing since classification results are used in environmental research, agriculture, climate change and natural resource management. The cocoa landscape of Ghana is complex and diverse in nature, composing of mixture of closed forest, open forest, settlements, croplands and cocoa farms which make mapping the landscape difficult. The purpose of this research is to assess and compare the classification performances of three machine learning classifiers: Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN) and a statistical classification algorithm: Maximum Likelihood (ML) to know which classifier is best suited for mapping the cocoa landscape of Ghana using Juaboso and Bia West districts of Ghana as study area. A representative sampling approach was adopted to collect 1246 sample points for the various Land Use/Land Cover (LULC) types. These sample points were divided at random into 869 which form 70% for classification and 377 which constitute 30% of the total sample points for validation. The Stacked sentinel-2 image, classification data and validation data storing the identities of the LULC classes were imported in R to run supervised classification for each classifier. The classification results show that the highest overall accuracy and kappa statistics were produced by the support vector machine (86.47%, 0.7902);next is the artificial neural network (85.15%, 0.7700), followed by the random forest (84.08%, 0.7559) and finally the maximum likelihood (78.51%, 0.6668). The final LULC map produced under this study can be used to monitor cocoa driven deforestation especially in the gazetted forest and game reserves. This map will also be very useful in the national forest monitoring framework for the REDD + cocoa landscape project.

基于北京二号与地理国情数据的林地提取

由于地理国情林地数据不包含实地面积小于400 m~2的树木或四旁单排林,若仅利用地理国情的林地数据统计区域森林覆盖率,将对四旁树面积较大地区的林地统计结果产生较大误差。为提取区域内准确的林地覆盖与空间分布状况,本文借助地理国情地表覆盖数据,提出了一种基于北京二号高分辨率遥感影像的林地提取方法。首先,根据遥感影像光谱特征,将研究区按植被、道路、铁路、建筑用地进行地类划分,并基于遥感影像进行各地类的样本提取,通过可分离检验的样本利用最大似然分类提取研究区内植被覆盖范围;然后,借助地理国情地表覆盖数据,使用叠置分析剔除误分、错分地类,得到区域林地的空间分布。试验结果表明:(1)研究区内林地覆盖率为20.3%,尚未满足北京新一轮林地规划需求;(2)地理国情地表覆盖数据内林地面积占提取林地总面积的54.03%,说明在部分地区使用本文方法对地理国情林地数据进行补充是有必要的。通过将试验结果与遥感影像进行目视比对并结合外业调查结果发现,提取的林地空间分布情况与实际分布基本相符。本文为地理国情的应用提供了一种新方法,研究结果可辅助区域的绿色发展规划,有助于构建科学的生态空间格局。

多样种植区冬小麦RS影像精确提取方法研究

以河北省邯郸市永年区为示例,基于ENVI平台,采用最大似然分类法对Sentinel-2冬小麦RS(Remote Sensing)影像数据进行精确解析,并通过混淆矩阵评价其分类精度。研究结果表明,使用最大似然分类法可快速提取冬小麦影像数据,精准获取粮食种植面积及其分布情况,有助于提升农业区土地利用的监测评估效果,并提升精细化灌溉水资源管理水平。

米波极化敏感阵列的实值MUSIC测高方法

为获得更高的相干信号角度估计精度,并提高算法可实现性,在极化敏感阵列的基础上,文中提出了一种米波极化敏感阵列的实值多重信号分类测高方法。该方法首先采用矩阵重构的方法消除多径相干信号的影响;其次,利用酉变换对接收数据进行实值处理使其变为实数数据,并利用奇异值技术降低接收数据维度及噪声对接收数据的影响;然后,通过对特征值分解获得的噪声子空间矩阵进行空间谱估计获得目标仰角;最后,利用几何关系获得目标高度。由于该方法完全用实值运算来表述,因而可以显著降低计算复杂度。仿真结果表明:该方法测高精度更高,更利于工程实现。

石家庄主城区土地类型不同遥感解译对比实验分析

为了探究不同分类方法的分类效果,以石家庄市主城区土地类型为研究区,基于监督分类和面向对象分类对研究区的土地类型进行划分并对比精度。采用最大似然、支持向量机、神经网络3种分类器对比不同分类器的分类效果,并与面向对象分类进行对比。结果表明:与面向对象分类相比,监督分类精度较高,其中监督分类采用的3种分类器中支持向量机效果最佳。

Urbanization and Other Land Use Land Cover Change Assessment in the Greater Kumasi Area of Ghana

Urbanization posits the expression of urban expanse expansion due to population growth, rise in built-up areas, high population density and its correspondingly urban way of life. Unrestrained impetus of development and land use land cover change (LULCC) portent several issues such as unlawful urban sprawl, loss of agricultural land, forest loss and other associated complications. This study analyzed the dynamics of urbanization and other LULCC in Ghana’s Greater Kumasi area via Landsat images (TM 1986, OLI 2013 and OLI 2023) using ERDAS Imagine, Idrisi and ArcGIS software. Implementing supervised classification technique, the Maximum Likelihood Classifier (MLC) procedure was employed to categories the study area into five LULC classes. Accuracy assessment undertaken on the resultant LULC maps was deemed very satisfactory. The results from 1986-2023 pointed to an upsurge in a built-up extent as of 8% to 41%, a decrease in Closed Forest from 9% to 4%, another decrease in Open Forests from 64% to 33%, a slight increase from 16% to 20% in farmlands and a stable level of water share. Further analysis indicated that the study area had undergone LULCC within the periods 1986-2013 and 2013-2023 at 60% and 37% respectively. The findings showed uncontrolled urban sprawling along major roads and forest loss as deforestation outside protected areas and degradation in protected forest. The monitoring of urbanization and other LULCC is important for local, and national governments and other bodies charged with the implementation of programs and policies that manage and utilize natural resources. Development adapts to mitigate the effect on the environment.

基于SAR影像的干旱区冲/洪积扇地貌面定量分期研究——以河西走廊西部沙漠区的疏勒河洪积扇为例

河流作用形成的洪积扇和河流阶地可以提供过去构造活动、气候变化和地貌演变过程的有效记录;而准确划分洪积扇地貌面的期次是开展环境变化及构造活动定量研究的基础。已有研究往往利用L波段数据SAR后向散射系数值作为地貌粗糙度替代参数,进行地貌面定量分期,但并未考虑不同时间数据源对分期结果的影响。以疏勒河洪积扇为研究对象,通过分析多时相L波段SAR数据后验统计指标以及大气评估条件,确定最佳数据源,并运用最大似然分类法对后向散射强度值进行分类,以实现地貌面的定量分期。结果表明:使用分期后验统计指标作为选取最佳时像影像数据的标准,可以获得更好的分期结果;L波段HH单极化数据可得到较好的分期结果,与C波段数据相比,对于不同年龄地貌面的划分更具优势,且数据更易获取,具备自动化分期潜力;SAR影像质量以及分期结果与成像时大气条件密切相关,而与季节相关性不大,因此建议优先选择成像时地表含水量较低的影像,例如,高蒸发强度的夏季。文章提出的这套对遥感数据质量分析并进行地貌面分期的方法可用于完成干旱地区大尺度冲/洪积扇的快速定量分期,为构造和气候的研究提供有价值的信息。

遥感图像最大似然分类方法的EM改进算法

基于参数化密度分布模型的最大似然方法 (MLC)是遥感影像分类最常用手段之一 ,与其他非参数方法 (如神经网络 )相比较 ,它具有清晰的参数解释能力、易于与先验知识融合和算法简单而易于实施等优点。但是由于遥感信息的统计分布具有高度的复杂性和随机性 ,当特征空间中类别的分布比较离散而导致不能服从预先假设的分布 ,或者样本的选取不具有代表性 ,往往得到的分类结果会偏离实际情况。首先介绍了用基于有限混合密度理论的期望最大(EM)算法来作为最大似然函数 (MLC)参数估计的方法———EM MLC。该模型首先假设总体混合密度分布可被分解为有限个参数化的高斯密度分布 ,然后把具有先验知识的样本与随机选取的未知样本混合在一起 ,通过EM迭代计算来估计出各密度分布的最大似然函数的参数集 ,从而一定程度上避免了参数估计可能出现的偏离。最后 ,本文提出了基于EM MLC遥感影像分类的具体实施流程和应用示范 ,并与一般最大似然方法 (MLC)得到的分类结果进行了定性和定量的综合比较 ,认为EM

比值居民地指数在城镇信息提取中的应用

TM图像中由于裸地与城镇光谱特征相似,利用传统的分类方法难以区分二者,城镇提取精度很难令人满意.针对这一问题,本文提出了一种新的方法即比值居民地指数(RR I)法用于城镇信息提取,同时与最大似然监督分类法作对比,研究结果表明,RR I法(精度达87.50%)优于最大似然分类法(精度为78.13%),是一种提取城镇居民地信息的理想方法,尤其适合裸地较多的干旱半干旱地区.