融合点云和多视图的车载激光点云路侧多目标识别

城市环境中的行道树、车辆、杆状交通设施是重要的交通地物,也是智能交通,导航与位置服务,自动驾驶和高精地图等行业应用的核心要素.为了准确识别这些路侧目标,本文提出一种融合点云和多视角图像的深度学习模型PGVNet(point-group-vi ew network),充分利用目标点云数据中空间几何信息及其多视角图像中高级全局特征提升路侧行道树、车辆和杆状设施的分类精度.为了减少视图间的冗余信息并增强显著视图特征,PGVNet模型利用预训练的VGG网络提取多视图特征,对其进行分组赋权获取最优视图特征;采用嵌入注意力机制的融合策略,利用最优视图特征动态调整PGVNet模型对点云不同局部关系的注意力度,学习不同路侧目标的多层次、多尺度显著特征,实现行道树、车辆和杆状交通设施的精确分类.试验采用5份不同车载激光扫描系统获取的不同城市场景数据验证本文方法的有效性,其中行道树、车辆及杆状交通设施分类结果中的准确率、召回率、精度和F1指数分别达(99.19％、94.27％、93.58％、96.63％);(94.20％、97.56％、92.02％、95.68％);(91.48％、98.61％、90.39％、94.87％).结果表明,本文方法融合多视图全局信息和点云局部结构特征可以有效区分城市场景中的行道树、车辆和杆状交通设施,可为高精度地图中要素构建与矢量化提供数据支撑.     

Grenville age of basement rocks in Cape May NJ well: new evidence for Laurentian crust in u.s. Atlantic Coastal Plain basement Chesapeake terrane

The Chesapeake terrane of the U.S. mid-Atlantic Coastal Plain basement is bounded on the northwest by the Salisbury positive gravity and magnetic anomaly and extends to the southeast as far as the Atlantic coast. It underlies the Coastal Plain of Virginia, Maryland, Delaware and southern New Jersey. Rubidium/ Strontium dating of the Chesapeake terrane basement yields an age of 1.025±0.036 Ga. This age is typical of Grenville province rocks of the Middle to Late Proterozoic Laurentian continent. The basement lithologies are similar to some exposed Grenville-age rocks of the Appalachians. The TiO₂ and Zr/P₂O₅ composition of the metagabbro from the Chesapeake terrane basement is overlapped by those of the Proterozoic mafic dikes in the New Jersey Highlands. These new findings support the interpretation that Laurentian basement extends southeast as far as the continental shelf in the U.S. mid-Atlantic region. The subcrop of Laurentian crust under the mid-Atlantic Coastal Plain implies unroofing by erosion of the younger Carolina (Avalon) supracrustal terrane. Dextral-transpression fault duplexes may have caused excessive uplift in the Salisbury Embayment area during the Alleghanian orogeny. This extra uplift in the Salisbury area may have caused the subsequent greater subsidence of the Coastal Plain basement in the embayment. © 1999 Elsevier Science Ltd. All rights reserved.     

城市元胞自动机扩展邻域效应的测量与校准研究

城市元胞模型由于在定量分析与预测城市动态的潜力而受到众多研究者的持续关注.邻域规则是主导城市元胞模型模拟过程的关键组件.研究表明,不同土地利用组合间存在显著的邻域效应,且邻域效应具有惯性、排斥和吸引等影响.然而,传统城市元胞模型主要考虑的是特定分辨率下较小窗口的邻域范围.本文尝试刻画更大窗口的邻域效应及其对元胞模型的影响.基于测量的扩展邻域因子,应用粒子群优化算法校准大窗口邻域规则,并创建了考虑扩展邻域效应的城市元胞模型.为验证模型有效性,将其应用于模拟厦门市1995-2010年期间的城市扩张动态.与3×3摩尔邻域的逻辑回归模型相比较,1995-2010年期间的建设用地模拟精度从80.7％提高到83.9％,总体精度从87.8％提高到89.6％,Kappa系数从70.0％提高到74.5％,表明考虑扩展邻域效应的城市模型取得了更好的模拟效果.     

Assessing seawater quality with a variable fuzzy recognition model

With the rapid development of the marine economy industry, human exploitation of marine resources is increasing, which is contributing to the growing trend of eutrophication and frequent occurrence of red tide. Accordingly, investigations of seawater quality have attracted a great deal of attention. This study was conducted to construct a seawater environmental quality assessment model based on the variable fuzzy recognition model. The uncertainty and ambiguity of the seawater quality assessment were then considered, combining the monitoring values of evaluation indicators with the standard values of seawater quality. Laizhou Bay was subsequently selected for a case study. In this study, the correct variable model for different parameters was obtained according to the linear and nonlinear features of evaluation objects. Application of the variable fuzzy recognition model for Laizhou Bay, water quality evaluation and comparison with performance obtained using other approaches revealed that the generated model is more reliable than traditional methods, can more reasonably determine the water quality of various samples, and is more suitable for evaluation of a multi-index, multi-level, nonlinear marine environment system; accordingly, the generated model will be an effective tool for seawater quality evaluation.     

Evacuation behaviour of households and drivers during a tornado

With increasing concerns over the possibility of tornadoes in highly populated areas in Canada, emergency managers are looking into ways to mitigate the impacts of tornadoes. Given that tornadoes can cause enormous destruction, early warnings and proper evacuation actions are critically important in helping save lives. In this paper, a survey was conducted to analyse the evacuation behaviour of households and drivers during a hypothetical tornado warning situation in the city of Calgary, Alberta. Nearly 500 Calgarians took part in the online survey and provided information on how they would respond to tornado warnings after receiving them. This paper presents the results of the survey. Using probit models, the factors influencing these evacuation decisions are identified and discussed in detail. The results of the household evacuation model show the importance of improving awareness about the safest locations during a tornado. It further highlights the need for targeting the population under the age of 30, who are more likely to take unsafe evacuation actions. The model for evacuation of drivers shows that several factors, such as knowing the difference between a watch and a warning, awareness of safe cover, receipt of warnings through natural environmental cues and the level of education, trigger evacuation actions in avoiding a tornado threat.     

Transformation Process and Mechanism of Lithium Borates

正Amounts of lithium-containing salt lake brine resources are widely distributed in the four provinces named Qinghai,Tibet,Inner Mongolia and Xinjiang province,especially the salt lakes in Qinghai-Tibet Plateau are abundant of     

中国植物地理学研究进展与展望

中国植物地理学从20世纪20年代初创到当前繁荣经历了100年的发展,近30年来测序技术和生物信息技术的进步,促进了分类、进化和生态等学科交叉融合,中国植物地理学在诸多方面取得了突破性进展,主要包括：① 植物类群和区系在中国整体上按纬度、经度和海拔呈现出规律性;物种丰富度、系统发生多样性和特有性热点集中分布在南部山地,少数分布在北方山地和干旱地区。② 关于大尺度植物多样性格局及形成机制,多数热带起源科的物种多样性格局受冬季低温的限制,而多数温带起源科的物种多样性格局由末次冰期以来的气候变化主导;中国山地植物和群落具有显著的垂直地带性和空间分布异质性,热量因子是中国高山植物区系地理分异的首要气候因子。③ 中国大多数现生被子植物属（约66%）是在中新世及其以后分化;500 mm年等降水线是中国植物区系年龄和植被分区最重要的分界线;中国植物区系、区系中的特征或关键类群的起源和多样化与青藏高原抬升和亚洲季风加强密切相关。未来,时间和空间的结合仍是植物地理学研究的主旋律,类群、群落和区系分化时间的估算及物种分布数据的分辨率是研究者关注的焦点,植物大数据的持续积累和完善将为学科发展提供强大动力和广阔前景。     

地理国情普查中卫星影像景范围线的分析应用

地理国情普查项目中,多源卫星遥感影像应用广泛,制作图幅DOM、要素解译时都需要确定卫星遥感影像各景的有效使用范围。在生产实践的基础上,提出合理应用景范围线,有效提高图幅DOM、要素解译和元数据生产效率的方法。     

基于DBN的车载激光点云路侧多目标提取

提出一种基于深度信念网络（DBN）的车载激光点云路侧多目标提取方法。首先通过预处理对原始数据进行分段,并将地面和建筑物点云与路侧目标进行分离;然后利用连通分支聚类分析算法进行路侧点云聚类,并采用基于体素的归一化分割方法分割重叠点云,从而生成独立目标点云;在此基础上,生成基于多方向目标对象的二值图像并展开成二值向量作为独立目标点云的描述特征;最后构建并训练DBN,利用训练好的DBN提取行道树、车辆及杆状目标等3类路侧目标。试验采用两份不同城市道路场景的点云数据,行道树、车辆及杆状目标提取结果的准确率分别达97.31%、97.79%、92.78%,召回率分别达98.30%、98.75%和96.77%,精度分别达95.70%、93.81%和90.00%,F1值分别达97.80%、96.81%和94.73%。试验结果验证了本文的有效性。     

基于北斗(BDS)的野外安全生产平台设计与实现

野外安全生产平台是应用北斗短报文通信,实现地质勘查项目野外数据采集安全管理、数据管理和质量管理功能。据地质勘查野外作业特点,提出构建智能移动终端、生产管理助手和实时监控综合应用平台的设计方案,提高野外作业工作效率,增强野外作业安全保障。