Comparison of decision tree methods for finding active objects

The automated classification of objects from large catalogs or survey projects is an important task in many astronomical surveys. Faced with various classification algorithms, astronomers should select the method according to their requirements. Here we describe several kinds of decision trees for finding active objects by multi-wavelength data, such as REPTree, Random Tree, Decision Stump, Random Forest, J48, NBTree, AdTree. All decision tree approaches investigated are in the WEKA package. The classification performance of the methods is presented. In the process of classification by decision tree methods, the classification rules are easily obtained, moreover these rules are clear and easy to understand for astronomers. As a result, astronomers are inclined to prefer and apply them, thus know which attributes are important to discriminate celestial objects. The experimental results show that when various decision trees are applied in discriminating active objects (quasars, BL Lac objects and active galaxies) from non-active objects (stars and galaxies), ADTree is the best only in terms of accuracy, Decision Stump is the best only considering speed, J48 is the optimal choice considering both accuracy and speed.     

Glacier mapping based on rough set theory in the Manas River watershed

Precise glacier information is important for assessing climate change in remote mountain areas. To obtain more accurate glacier mapping, rough set theory, which can deal with vague and uncertainty information, was introduced to obtain optimal knowledge rules for glacier mapping. Optical images, thermal infrared band data, texture information and morphometric parameters were combined to build a decision table used in our proposed rough set theory method. After discretizing the real value attributes, decision rules were calculated through the decision rule generation algorithm for glacier mapping. A decision classifier based on the generated rules classified the multispectral image into glacier and non-glacier areas. The result of maximum likelihood classification (MLC) was used to compare with the result of the classification based on the rough set theory. Confusion matrix and visual interpretation were used to evaluate the overall accuracy of the results of the two methods. The accuracies of the rough set method and maximum likelihood classification were compared, yielding overall accuracies of 94.15% and 93.88%, respectively. It showed the area difference based on rough set was smaller by comparing the glacier areas of the rough set method and MLC with visual interpreter, respectively. The high accuracy for glacier mapping and the small area difference for glacier based on rough set theory demonstrated that this method was effective and promising for glacier mapping.     

遥感卫星多光谱图像模拟真彩色算法研究

地球资源遥感卫星ZY-1 02C和CBERS-04搭载的全色多光谱相机缺少蓝光波段，需要通过波段模拟方法首先生成蓝波段，进而合成模拟真彩色图像。根据多光谱数据特点，提出一种基于波段线性关系模型的模拟真彩色方法。首先用具有蓝色波段的多光谱数据作为参考图像进行回归分析，计算得到相关系数，将结果作为参数应用于待模拟图像生成蓝波段。然后按照地物类别进行单景图像局部区域颜色畸变矫正。最后按特定顺序合成模拟真彩色图像。试验表明，该算法简单快速，减少了偏色现象，能够获得较好的模拟效果。     

Comprehensive data reduction package for the Immersion GRating INfrared Spectrograph: IGRINS

We present a Python-based data reduction pipeline package (PLP) for the Immersion GRating INfrared Spectrograph (IGRINS), an instrument that covers the complete H- and K-bands in one exposure with a spectral resolving power of 40,000. The reduction steps carried out by the PLP include flat-fielding, background removal, order extraction, distortion correction, wavelength calibration, and telluric correction using spectra of A type standard stars. As the spectrograph has no moving parts, the PLP automatically reduces the data using predefined functions for the processes of order extraction, distortion correction, and wavelength calibration. Before the telluric correction of the target spectra, the intrinsic hydrogen absorption features of the standard A star are removed with a Gaussian fitting algorithm. The final result is the flux of the target as a function of wavelength. Users can customize the predefined functions for the extraction of the spectrum from the echellogram and adjust the parameters for the fitting functions for the spectra of celestial objects, using “fine-tuning” options, as necessary. Presently, the PLP produces the best results for point-source targets.     

Hierarchical object oriented classification using very high resolution imagery and LIDAR data over urban areas

Urban land cover information extraction is a hot topic within urban studies. Heterogeneous spectra of high resolution imagery—caused by the inner complexity of urban areas—make it difficult. In this paper a hierarchical object oriented classification method over an urban area is presented. Combining QuickBird imagery and light detection and ranging (LIDAR) data, nine kinds of land cover objects were extracted. The Spectral Shape Index (SSI) method is used to distinguish water and shadow from black body mask, with 100% classification accuracy for water and 95.56% for shadow. Vegetation was extracted by using a Normalized Difference Vegetation Index (NDVI) image at first, and then a more accurate classification result of shrub and grassland is obtained by integrating the height information from LIDAR data. The classification accuracy of shrub was improved from 85.25% to 92.09% and from 82.86% to 97.06% for grassland. More granularity of this classification can be obtained by using this method. High buildings and low buildings can, for example, be distinguished from the original building class. Road class can also be further classified into roads and crossroads. The comparison of the classification accuracy between this method and the traditional pixel-based method indicates that the total accuracy is improved from 69.12% to 89.40%.     

基于光谱特征的自适应子空间波段选择方法

针对现有波段选择方法无法依据感兴趣地物划分数据子空间及子空间划分容易受背景地物影响等问题,提出一种基于光谱特征的自适应子空间波段选择方法.利用感兴趣地物的光谱曲线,建立光谱自适应因子(SAF,Spectral Adaptive Factor);通过聚类划分子空间,在每个子空间内,利用J-M距离筛选类别可分性最大波段作为子空间最优波段,从而得到整个数据空间的最佳波段组合.利用AOTF (Acousto-Optic Tunable Filter)成像光谱仪数据与波段指数(BI,Band Index)和基于类间可分性最佳波段选择两种方法比较,SAF方法选择的最佳波段组合,包含信息量丰富,地物之间差异较大,且地物平均J-M距离大于另外两种方法.用最大似然法(maximum likelihood)对最佳波段组合进行分类,总体分类精度为96.8%,Kappa系数为0.894.结果验证了SAF方法的有效性和实用性.     

Non-linear methods in remotely sensed multispectral data classification

The aim of this research is to develop an effective approach being able to deal with the stochastic nature of remote sensing data. In order to achieve this objective it is necessary to structure the methodological knowledge in the area of data mining and reveal the most suitable methods for the prediction and decision support based on large amounts of multispectral data. The idea is to establish a framework by decomposing the task into functionality objectives and to allow the end-user to experiment with a set of classification methods and select the best methods for specific applications. As a first step, we compare our results from Bayesian classification based on non-parametric probability density estimates of the data to the results obtained from other classification methods. Tree scenarios are considered, making use of a small benchmark dataset, a larger dataset from Corine land cover project for Bulgaria and analyzing different features and feature selection methods. We show that the theoretically optimal Bayesian classification can also achieve optimal classification in practice and provides a realistic interpretation of the world where land cover classes intergrade gradually.     

Feature selection for high-dimensional data in astronomy

With an exponentially increasing amount of astronomical data, the complexity and dimension of astronomical data are likewise growing rapidly. Extracting information from such data becomes a critical and challenging problem. For example, some algorithms can only be employed in the low-dimensional spaces, so feature selection and feature extraction become important topics. Here we describe the difference between feature selection and feature extraction methods, and introduce the taxonomy of feature selection methods as well as the characteristics of each method. We present a case study comparing the performance and computational cost of different feature selection methods. For the filter method, ReliefF and fisher filter are adopted; for the wrapper method, improved CHAID, linear discriminant analysis (LDA), Naive Bayes (NB) and C4.5 are taken as learners. Applied on the sample, the result indicates that from the viewpoints of computational cost the filter method is superior to the wrapper method. Moreover, different learning algorithms combined with appropriate feature selection methods may arrive at better performance.     

基于FRFT域特征差异的压制干扰检测与分类算法

针对干信比未知情况下有源压制干扰分类识别结果可信度较低的问题, 提出了一种基于FRFT域特征差异的压制干扰检测与分类算法。首先, 通过FRFT域峰值阶次的序贯判决算法, 进行压制干扰的存在性检测, 以保证压制干扰分类识别在较高的干信比条件下进行; 然后, 在此基础上, 分别提取回波信号在FRFT域的极值阶次标准差和峰值阶次标准差作为分类识别特征量, 同时, 为避免硬判决造成的分类错误, 采用模糊判决的方法得到基于不同特征参数的分类识别结果; 最后, 按一定准则将2种分类识别结果进行融合, 以进一步提高分类识别正确率。仿真结果表明, 与现有压制干扰分类识别算法相比, 该算法较好地解决了分类识别结果可信度较低的问题, 同时具有较高的分类识别正确率。      

Multi-Criteria Decision Analysis integrated with GIS and remote sensing for astronomical observatory site selection in Antalya province,Turkey

Astronomical observatory site selection is a complex problem that involves evaluation of multiple factors from different sources. The aim of this study is to select the best possible candidates for astronomical observations sites using Multi-Criteria Decision Analysis integrated with Geographical Information Systems and remote sensing technologies. The study was implemented in the Antalya province of Turkey, which is convenient for astronomical site observatory facilities with its appropriate climate properties and weather conditions. Eleven factors (cloud cover, precipitable water, earthquake zones, geology, landslide inventory, active fault lines, Digital Elevation Model, city lights, mining activities, settlement areas, roads) were determined, splitting into three categories; meteorological, geographical and anthropogenic criteria. These factors were evaluated using Analytical Hierarchy Process method and the weights of criteria layers were determined. As a result, the most suitable areas were located extensively in western and eastern part of Antalya. This study offers a robust, accurate, cost and time effective procedure for preliminary site selection for astronomical observatory. However, for a final decision of the best location of astronomical observatory, site testing measurements and atmospheric seeing observations will be further required in these preliminary areas.     

Examining LiDAR – WorldView-3 data synergy to generate a detailed stand map in a mixed forest in the north-west of Turkey

Although stand delineation approach based on aerial photographs and field survey produces high accuracy maps, it is labour-intensive and time consuming. Furthermore, conventional forest stand maps may have some uncertainties that can hardly be verified due to the experiments and skills of photo-interpreters. Therefore, researchers have been seeking more objective and cost-effective methods for forest mapping. LiDAR (Light Detection and Ranging) data have a high potential to automatically delineate forest stands. Unlike optical sensors, LiDAR height data provides information about both the horizontal and vertical structural characteristics of forest stands. However, it deprives of spectral data that may be successfully used in separating tree species. In this study, we investigate the potential of LiDAR – WorldView-3 data synergy for the automatic generation of a detailed forest stand map which can be used for a tactical forest management plan. Firstly, image segmentation was applied to LiDAR data alone and LiDAR/WorldView-3 data set in order to obtain the most suitable image objects representing forest stands. Visual inspection of the segmentation results showed that image objects based on the LiDAR/WorldView-3 data set were more compatible with the reference forest stand boundaries. After the segmentation process, the LiDAR and LiDAR/WorldView-3 data sets were independently classified using object-based classification method. We tested two levels of classification. The first was a detailed classification with 14 classes considering reference stand types. The second was the rough classification with 9 classes where some stand types were combined. The mean, standard deviation and texture features of LiDAR metrics and spectral information were used in the classification. The accuracy assessment results of LiDAR data showed that the Overall Accuracy (OA) was calculated as 0.31 and 0.43, and the Kappa Index (KIA) was calculated as 0.26 and 0.32 for the detailed and rough classifications, respectively. For the LiDAR/WorldView-3 data set, the OA values were calculated as 0.50 and 0.61, and the KIA were calculated as 0.46 and 0.55 for the detailed and rough classifications, respectively. These results showed that the forest stand map derived from the LiDAR/WorldView-3 data synergy is more compatible with the reference forest stand map. In conclusion, it can be said that the forest stand maps produced in this study may provide strategic forest planning needs, but it is not sufficient for tactical forest management plans.     

An optimal selection of probability distribution functions for unsupervised land cover classification of PALSAR-2 data

Different types of classification techniques are available in the literature for the classification of Synthetic Aperture Radar (SAR) data into various land cover classes. Various SAR images are available for land cover classification such as ALOS PALSAR (PALSAR-1, PALSAR-2), RADARSAT and ENVISAT. In this paper, we have attempted to explore probability distribution function (pdf) based land cover classification using PALSAR-2 data. Over 20 different statistical distribution functions are analyzed for different classes based on statistical parameters. Probability distribution functions are selected based on Chi-squared goodness of fit test for each individual class. A decision tree based classifier is developed for classification based on the selected pdf functions and its statistical parameters. The proposed classification approach has an accuracy of 83.93%.     

基于深度学习的航空发动机故障融合诊断

通过对航空发动机故障诊断,能够正确判断各部件工作状态,快速确定维修方案,保证飞行安全。在结合深度信念网络和决策融合算法的基础上,提出了基于深度学习的航空发动机故障融合诊断模型。该模型通过分析发动机的大量性能参数,先利用深度学习模型提取出性能参数中的隐藏特征,得出故障分类置信度;其后对多次故障分类结果进行决策融合,从而得出更准确的诊断结果。将普惠JT9D发动机故障系数用于数据仿真,通过算例验证本文算法的有效性;算例计算结果表明:多次实验结果经数据融合提高了可信度,该模型具有较高的故障分类诊断准确性和抗干扰能力。      

基于ViBE与面向对象分类的视频卫星运动车辆检测

为了提高视频卫星对运动车辆的检测质量，在经典视觉背景提取器(ViBE)算法的基础上，结合遥感的面向对象分类技术，从提升正确检测运动目标数量和抑制虚假运动目标检测数量两个方面着手，提出了一种新的运动车辆检测方法（VOMVD）。首先通过优化ViBE模型参数，尽可能多地获取真实运动目标，但这在一定程度引入了许多的虚假目标。研究继而依据影像上地面小尺度运动目标和道路的依存关系，采用面向对象的分类方法，基于光谱、纹理、空间属性，构建了均值、标准差、卷积核内平均灰度值、卷积核内平均信息熵、面积、长度、紧密度、延伸度等8个特征，用于提取道路信息，以此掩膜ViBE提取的虚假运动目标和伪运动目标。结果表明，基于本研究提出的视频卫星运动目标检测方法较之三帧差分法、ViBE检测方法等，其精度有明显提升。在本研究中，三帧差分法、ViBE和VOMVD对运动目标的检测精度P分别为70.91%，61.49%和85.71%，召回率R分别为84.78%，98.91%和97.83%，F值分别为77.23%，75.83%和91.37%，有效提升了方法对运动目标的检测效果。     

超低轨道地球卫星脉冲星/星光折射/光谱组合导航

针对超低轨道地球卫星导航自主需求,提出了一种脉冲星/星光折射/光谱测速组合天文导航方法。首先根据地球超低轨道卫星运行轨道动力学方程建立导航系统状态模型;分别根据脉冲到达时间差和星光折射角与天体光谱频率建立导航系统量测模型;使用Unscented卡尔曼滤波方法,降低随机误差对导航精度的影响,使用基于UKF的信息融合方法,有效融合了三种天文导航方法结果数据。经计算机仿真分析,该组合导航方法位置导航误差均值为85.62m,速度误差均值0.190m/s,能够满足超低轨道地球卫星在轨运行导航需求。     

面向制造的飞机复合材料构件数字化定义

为满足数字化研制环境中制造环节的数据需求和对构件可制造性的要求,总结了面向制造的飞机复合材料构件数字化定义的完整构成.通过定义方向坐标系来建立方向基准,并根据构件高斯曲率的不同,给出了3种方向坐标系的定义方法和映射规则.给出了三维模型中几何数据的内容、几何数据和复合材料特征对象的关联关系以及材料铺放数据中复合材料特征对象的层次关系.总结了数字化定义中工艺信息的详细内容和定义方法,并采用基于视图的方式组织管理数字化定义数据集.      

An improved land cover classification using polarization signatures for PALSAR 2 data

Land cover classification in mixed land cover scenarios is challenging with PolSAR data. Polarimetric decomposition techniques are most popular methods for PolSAR data classification in recent times. These techniques focus on identification of dominant scattering phenomena and hence result in sub-optimal classification in mixed land cover scenarios. Alternatively, polarization signatures (PSs) are good illustrations of SAR target responses as they depict a detailed physical information from target backscatter. Researchers have successfully utilized SAR PSs for land cover (LC) classification. Some reports suggested utilizing correlation between observed PSs and standard target PSs as features for LC classification. This paper presents a study on improved utilization of PSs for optimal LC classification in mixed class scenarios. First, PS based SAR features are derived using fully polarimetric SAR data. The features represent a degree of similarity between observed and standard PSs. The derived features are termed as polarization signatures correlation features or PSCFs. The novel PSCFs are analyzed, evaluated and compared with decomposition based features for the purpose of LC classification. Classification performance indicators highlight potential of PSCFs for mixed LC classification problems. Therefore, further an adaptive and optimal LC class boundary estimation approach for LC classification is proposed and developed. Observed PSs and reference LC class PS statistics are used to build empirical models between classification performance indicators and LC class boundaries. The empirical models are optimized using the evolutionary genetic algorithm to maximize classification performance. A decision tree is constructed based on the optimal class boundaries to prepare LC classification. The proposed classification approach is compared with some recent popular classifiers and comparison suggests that the proposed approach provides satisfactory results for mixed LC classification scenarios.     

核空间聚类在图像纹理分类中的简化算法

模糊c均值聚类已广泛应用于模糊模式识别领域,但对于线性不可分数据并不适用.在核方法中通过将输入数据经过非线性映射投影到高维特征空间来解决非线性分类的问题.将传统的模糊c均值聚类算法应用于核空间中,对线性不可分的样本进行了核空间聚类的分类实验,得到了正确的分类结果.由于图像分类中分类样本(对应图像像素)数目庞大,造成了核空间聚类算法中特征距离的计算量过大.因此,在核空间聚类的基础上,提出了对图像先进行过分割,再对过分割的图像块进行核空间聚类的方法,大大降低了高维空间特征距离计算的运算成本,并取得了良好的分类效果.      

实时棒材图像识别与跟踪方法研究

多目标识别跟踪的关键问题是特征提取和目标匹配.为了提取生产线上堆积棒材的特征,提出粘连目标分割和多目标识别的方法.采用中值滤波和形态学滤波去除噪声,自适应阈值化和分水岭变换分割粘连目标;然后采用区域统计、参数识别、噪声区域去除以及聚类分析等手段进行目标特征识别,提取出棒材的质心点坐标作为特征;对棒材图像序列提出采用模板匹配、相近位移匹配和Kalman滤波的方法建立跟踪链,通过插入、删除、更新链节点进行目标跟踪;对于图像处理中可能出现的漏检目标和虚增目标,进行了计数结果校正.在现场采集了100帧连续图像后,采用此方法跟踪计数的精度为96.2%.