3D tree modeling from incomplete point clouds via optimization and L1-MST

Reconstruction of 3D trees from incomplete point clouds is a challenging issue due to their large variety and natural geometric complexity. In this paper, we develop a novel method to effectively model trees from a single laser scan. First, coarse tree skeletons are extracted by utilizing the L₁-median skeleton to compute the dominant direction of each point and the local point density of the point cloud. Then we propose a data completion scheme that guides the compensation for missing data. It is an iterative optimization process based on the dominant direction of each point and local point density. Finally, we present a L₁-minimum spanning tree (MST) algorithm to refine tree skeletons from the optimized point cloud, which integrates the advantages of both L₁-median skeleton and MST algorithms. The proposed method has been validated on various point clouds captured from single laser scans. The experiment results demonstrate the effectiveness and robustness of our method for coping with complex shapes of branching structures and occlusions.     

基于决策树的天津地区冰雹天气雷达因子分析

利用决策树对天津地区2005—2014年4—9月间的25次有灾情资料的冰雹天气进行多普勒天气雷达因子识别,采用冰雹概率(POH)、强冰雹概率(POSH)、垂直液态含水量(VIL)、最大反射率因子(DBZM)、风暴质心高度(HT)、风暴顶高(TOP)等主要雷达识别指标,归纳出天津地区冰雹云雷达回波判识指标:(1)当DBZM≤54.5dBz,或者当DBZM54.5dBz但POSH≤35,单体不会降雹;(2)当DBZM54.5dBz且POSH35,则该单体将会降雹。与判别分析方法比较,基于决策树分析的识别降雹单体的成功率达90.2%,临界成功指数达78.3%,识别结果明显优于判别分析方法。     

Multiple source and attenuation relationships for evaluation of deterministic seismic hazard: logic tree approach considering local site effects

The most important seismic hazard parameters required to demarcate seismic zones are the peak horizontal acceleration (PHA) and spectral acceleration (SA). The two approaches for evaluation of seismic hazard are the probabilistic seismic hazard analysis and the deterministic seismic hazard analysis (DSHA). The present study evaluates the seismic hazard of the South Indian Peninsular region based on the DSHA methodology. In order to consider the epistemic uncertainties in a better manner, a logic tree approach was adopted in the evaluation of seismic hazard. Two types of seismic sources and three different attenuation relations were used in the analysis. The spatial variation of PHA (mean and 84th percentile values) and SA values for 1 Hz and 10 Hz at bedrock level (84th percentile values) for the entire study area were evaluated and the results are presented here. The surface level peak ground acceleration (PGA) values will be different from that of the bedrock level values due to the local site conditions. The PGA values at ground surface level were evaluated for four different National Earthquake Hazard Reduction Program site classes by considering the non-linear site response of different soil types. The response spectra for important cities in South India were also prepared using the deterministic approach and the results are presented in this paper.     

The use of single-date MODIS imagery for estimating large-scale urban impervious surface fraction with spectral mixture analysis and machine learning techniques

Urban impervious surface information is essential for urban and environmental applications at the regional/national scales. As a popular image processing technique, spectral mixture analysis (SMA) has rarely been applied to coarse-resolution imagery due to the difficulty of deriving endmember spectra using traditional endmember selection methods, particularly within heterogeneous urban environments. To address this problem, we derived endmember signatures through a least squares solution (LSS) technique with known abundances of sample pixels, and integrated these endmember signatures into SMA for mapping large-scale impervious surface fraction. In addition, with the same sample set, we carried out objective comparative analyses among SMA (i.e. fully constrained and unconstrained SMA) and machine learning (i.e. Cubist regression tree and Random Forests) techniques. Analysis of results suggests three major conclusions. First, with the extrapolated endmember spectra from stratified random training samples, the SMA approaches performed relatively well, as indicated by small MAE values. Second, Random Forests yields more reliable results than Cubist regression tree, and its accuracy is improved with increased sample sizes. Finally, comparative analyses suggest a tentative guide for selecting an optimal approach for large-scale fractional imperviousness estimation: unconstrained SMA might be a favorable option with a small number of samples, while Random Forests might be preferred if a large number of samples are available.     

一种基于曲率法的曲线特征点选取方法

本文提出使用弯曲树来组织曲线的弯曲形态,根据弯曲特征以一定范围计算曲线弯曲程度所得到的值度量点的宏观弯曲量,作为特征点的选取标准;并根据微观弯曲量微调领域内特征点的位置,来确定特征点。实验对比发现,本算法可以在一定程度上克服传统曲率算法的不足,选取的特征点能够控制曲线的宏观形态,并且位置准确。     

基于Contourlet变换的高空间分辨率遥感影像检索研究

本文在高空间分辨率遥感影像纹理特征提取研究中引入Contourlet变换,将不同尺度、不同方向子带系数矩阵的均值、方差和能量作为纹理特征,并为分类能力强的特征量赋予较大的权值,体现相应子带分类能力的差异性。以QuickBird影像为样本数据、采用五叉树分解策略的纹理检索实证研究表明,基于Contourlet变换提取高空间分辨率遥感影像纹理特征信息的效果优于Gabor小波变换。     

The spatial prediction of tree species diversity in savanna woodlands of Southern Africa

In this study, we tested the utility of remotely sensed data in predicting tree species diversity in savanna woodlands. Specifically, we developed linear regression functions based on a combination of the coefficient of variation of near infrared (NIR) radiance and the soil-adjusted vegetation index (SAVI), both derived from advanced space-borne thermal emission and reflection radiometer satellite imagery. Using the regression functions in a Geographic Information System (GIS), we predicted the spatial variations in tree species diversity. Our results showed that tree species diversity can be predicted using a combination of the coefficient of variation of NIR radiance and SAVI. We conclude that remotely sensed data can be used to spatially predict tree species diversity in savanna woodlands.     

Support vector machines for tree species identification using LiDAR-derived structure and intensity variables

Tree species identification and forest type classification are critical for sustainable forest management and native forest conservation. Recent success in forest classification and tree species identification using LiDAR (light detection and ranging)-derived variables has been reported in many studies. However, there is still considerable scope for further improvement in classification accuracy. It has driven research into more efficient classifiers such as support vector machines (SVMs) to take maximum advantage of the information extracted from LiDAR data for potential increases in the accuracy of tree species classification. This study demonstrated the success of the SVMs for the identification of the Myrtle Beech (the dominant species of the Australian cool temperate rainforest in the study area) and adjacent tree species – notably, the Silver Wattle at individual tree level using LiDAR-derived structure and intensity variables. An overall accuracy of 92.8% was achieved from the SVM approach, showing significant advantages of the SVMs over the traditional classification methods such as linear discriminant analysis in terms of classification accuracy.     

Residences information extraction from Landsat imagery using the multi-parameter decision tree method

Abstract

The rapid and accurate grasp of changes in residences is crucial for urban planning and urbanisation. However, the traditional methods for extracting residences exists several problems, which lead to inaccurate extraction results. In this study, the Landsat image is used to establish a new method for extracting the residences quickly and accurately. The specific steps are as follows: (1) We calculate surface albedo to exclude the interference of waters and shadows; (2) Using single-band threshold method, we eliminate the interference of shadows; (3) Normalized Difference Vegetation Index is calculated to exclude the effects of vegetation; (4) Roads are removed by calculating the shape index. Verification shows that the accuracy of this extraction method is 92.81%, which is more accurate than the traditional methods and solves the problems existed in the traditional methods. This novel method is a new reference for other land cover research on the technical aspect.     

A novel ensemble approach of bivariate statistical-based logistic model tree classifier for landslide susceptibility assessment

Abstract

This study addresses landslide susceptibility mapping (LSM) using a novel ensemble approach of using a bivariate statistical method (weights of evidence [WoE] and evidential belief function [EBF])-based logistic model tree (LMT) classifier. The performance and prediction capability of the ensemble models were assessed using the area under the ROC curve (AUROC), standard error, 95% confidence intervals and significance level P. Model performance analyses indicated that the AUROC values of the WoE–LMT ensemble model using the training and validation data-sets were 86.02 and 85.9%, respectively, whereas those of the EBF–LMT ensemble model were 88.2 and 87.8%, respectively. On the other hand, the AUC curves for the four landslide susceptibility maps indicated that the AUC values of the ensemble models of WoE–LMT (85.11 and 83.98%) and EBF–LMT (86.21 and 85.23%) could improve the performance and prediction accuracy of single WoE (84.23 and 82.46%) and EBF (85.39 and 81.33%) models for the training and validation data-sets.