激光雷达点云树木建模研究进展与展望

三维树木几何模型是数字城市与数字林业工程的重要组成部分.针对点云树木建模,深入分析了基于广义(泛在)激光雷达点云的树木模型重建方法,提出了聚类思想建模、图论方法建模、先验假设建模、拉普拉斯算子建模与轻量化表达建模5类建模体系,归纳总结了不同建模体系在树冠枝干的细节表达、建模算法性能、树木模型的多层次细节表达、建模体系综...     

结合MST划分和RHMRF-FCM算法的高分辨率遥感图像分割

针对基于像素的HMRF-FCM算法抗噪性差以及对地物复杂边界分割精度低的问题,提出一种结合形状信息的静态MST区域划分和RHMRF-FCM算法的高分辨率遥感图像分割方法。该方法定义一种静态MST同质区域划分准则,借助MST能较好表达边界和形状信息、能较好抑制几何噪声的特点,解决地物复杂边界的表达和降低分割结果中几何噪声问题。首先,利用MST静态划分将图像域划分成若干个均质区域,假设每个均质区域内光谱测度服从独立同一的多元高斯分布。然后,在此基础上构建了区域隐马尔可夫随机场模型,以及建立基于信息熵和KL信息正则化项的模糊聚类目标函数。最后,采用偏微分方法对分割模型参数进行求解,从而得到全局最优分割结果。为验证本文方法,对WorldView-3高分遥感图像进行分割试验。定性、定量分析了尺度参数、光谱相似性参数和区域紧致度参数对最优分割结果的影响,并对比分析本文算法和eCognition软件中的多分辨率分割算法、分水岭算法。     

Closed-loop randomized kinodynamic path planning for an autonomous underwater vehicle

A randomized kinodynamic path planning algorithm based on the incremental sampling-based method is proposed here as the state-of-the-art in this field applicable in an autonomous underwater vehicle. Designing a feasible path for this vehicle from an initial position and velocity to a target position and velocity in three-dimensional spaces by considering the kinematic constraints such as obstacles avoidance and dynamic constraints such as hard bounds and non-holonomic characteristic of AUV are the main motivation of this research. For this purpose, a closed-loop rapidly-exploring random tree (CL-RRT) algorithm is presented. This CL-RRT consists of three tightly coupled components: a RRT algorithm, three fuzzy proportional-derivative controllers for heading and diving control and a six degree-of-freedom nonlinear AUV model. The branches of CL-RRT are expanded in the configuration space by considering the kinodynamic constraints of AUV. The feasibility of each branch and random offspring vertex in the CL-RRT is checked against the mentioned constraints of AUV. Next, if the planned branch is feasible by the AUV, then the control signals and related vertex are recorded through the path planner to design the final path. This proposed algorithm is implemented on a single board computer (SBC) through the xPC Target and then four test-cases are designed in 3D space. The results of the processor-in-the-loop tests are compared by the conventional RRT and indicate that the proposed CL-RRT not only in a rapid manner plans an initial path, but also the planned path is feasible by the AUV.     

高分六号遥感卫星新增波段下的树种分类精度分析

高分六号卫星具有覆盖广、多种分辨率、波段多的优势,能为遥感解译提供更丰富的信息。为探究高分六号卫星新增波段在森林树种识别上的应用,本文以覆盖根河市阿龙山林业局的一期高分六号宽幅影像为数据源,基于特征优化空间算法（Feature Space Optimization,FSO）和最大似然分类法,分别利用高分六号的前4个波段和所有波段（8波段）的光谱、纹理等特征进行了森林树种分类,并逐一添加新增波段特征确定了各波段的贡献率排名。结果表明：在加入了优选出的均匀性纹理、均值纹理和角二阶矩纹理3种纹理特征后,前4波段和8波段的分类精度比只基于光谱特征时的精度分别高出13.23%和24.63%;利用8波段信息比只利用前4波段在基于光谱特征上的精度高11.88%,在基于光谱+纹理特征上则高23.24%;基于8波段光谱+纹理特征的树种分类精度最高,达到68.74%,新增4波段的贡献率排名为B6>B5>B8>B7,说明新增红边波段对于本次树种分类试验的贡献率最高,能为北方树种识别提供有效帮助。     

改进的最小曲率迭代法在重力剖面数据插值中的应用

基于将约束点也作为待解算结点的思想,对传统最小曲率迭代法进行改进。改进后的方法在待解算结点周围存在约束点时,避免了根据约束点与待解算结点之间的不同关系需要进行分类推导的复杂过程,同时也避免了因使用泰勒展开式进行分解造成的精度损失,提高了解算精度。     

锁块式水下采油树井口连接器性能分析

水下采油树井口连接器是连接采油树和井口的关键设备,对深海水下勘探开发及采油树的安装连接具有不可或缺的重要意义。以一种锁块式水下连接器为例,介绍其结构组成和工作原理,通过有限元建立连接器的三维模型,分析连接器在下放安装工况、连接锁紧工况、正常生产工况和钻完井工况下的连接性能,得出井口与采油树本体接触面作用力、VX钢圈接触应力和锁块受力情况随外部载荷的相互关系。结果表明,VX钢圈在整个过程中都能够保持良好密封,井口与采油树本体接触面未发生分离,弯矩对连接器连接性能影响很大,在额定弯矩作用时连接器部分锁块已发生弹塑性失效。     

一种海洋混合层深度的智能识别方法研究

文章提出了一种识别混合层深度的人工智能方法。该方法在温度(密度)与压强(或深度)间建立线性模型, 并且将其系数和方差做成一组表征廓线特征的统计量。初始时为模型设定一个主观的先验分布, 在一个自海表向下移动的窗口内通过贝叶斯链式法则和最小描述长度原理学习新数据, 得到系数均值的最大后验概率估计。用F-检验识别系数发生突变的位置, 以此确定混合层的存在性及其深度。通过2017年2月太平洋海域的地转海洋学实时观测阵(Array for Real-time Geostrophic Oceanography, ARGO)数据进行测试, 并且以质量因子(Quality Index, QI)值作为判断识别混合层深度结果准确性的依据, 发现该方法相比于梯度法、阈值法、混合法、相对变化法、最大角度法和最优线性插值法在识别结果上具备更大的QI值。表明该方法能够准确识别混合层深度。     

检定场的机载激光雷达精度评价方法

为了对机载激光雷达测量精度进行科学地评价,保障数据成果质量,满足新型仪器装备计量检测的需要,该文基于空对地检定场圆形标志点,利用平均值法和最小外包圆法对机载激光雷达的平面精度和高程精度进行评价研究。结果表明:针对低空机载激光雷达可以获取高密度的地面点云,可以利用轮廓突出且特殊形状的控制点进行三维精度评价;利用平均值法和最小外包圆法均可以对机载激光雷达进行快速、有效地三维精度评价。     

Geospatial data mining for digital raster mapping

We performed an in-depth literature survey to identify the most popular data mining approaches that have been applied for raster mapping of ecological parameters through the use of Geographic Information Systems (GIS) and remotely sensed data. Popular data mining approaches included decision trees or “data mining” trees which consist of regression and classification trees, random forests, neural networks, and support vector machines. The advantages of each data mining approach as well as approaches to avoid overfitting are subsequently discussed. We also provide suggestions and examples for the mapping of problematic variables or classes, future or historical projections, and avoidance of model bias. Finally, we address the separate issues of parallel processing, error mapping, and incorporation of “no data” values into modeling processes. Given the improved availability of digital spatial products and remote sensing products, data mining approaches combined with parallel processing potentials should greatly improve the quality and extent of ecological datasets.     

Building a model-based personalised recommendation approach for tourist attractions from geotagged social media data

When travelling, people are accustomed to taking and uploading photos on social media websites, which has led to the accumulation of huge numbers of geotagged photos. Combined with multisource information (e.g. weather, transportation, or textual information), these geotagged photos could help us in constructing user preference profiles at a high level of detail. Therefore, using these geotagged photos, we built a personalised recommendation system to provide attraction recommendations that match a user's preferences. Specifically, we retrieved a geotagged photo collection from the public API for Flickr (Flickr.com) and fetched a large amount of other contextual information to rebuild a user's travel history. We then created a model-based recommendation method with a two-stage architecture that consists of candidate generation (the matching process) and candidate ranking. In the matching process, we used a support vector machine model that was modified for multiclass classification to generate the candidate list. In addition, we used a gradient boosting regression tree to score each candidate and rerank the list. Finally, we evaluated our recommendation results with respect to accuracy and ranking ability. Compared with widely used memory-based methods, our proposed method performs significantly better in the cold-start situation and when mining ‘long-tail’ data.