影像分割的城市不透水面信息提取

针对线性光谱混合分解在端元选取中的不足,该文提出了结合影像分割的线性光谱混合分解不透水面估算模型。选取植被、高反射率、低反射率、土壤4种端元,利用线性光谱混合分解和结合影像分割的线性光谱混合分解两种模型,以2010年的TM5遥感影像为数据源对哈尔滨市主城区的不透水面进行估算,并对两种模型进行了对比分析。研究结果表明:线性光谱混合分解和结合影像分割的线性光谱混合分解的平均绝对误差分别为19.84%和14.76%,说明结合影像分割的线性光谱混合分解模型比线性光谱混合分解方法的估算精度高。     

波段选择协同表达高光谱异常探测算法

高光谱遥感影像具有光谱分辨率极高的特点,承载了大量可区分不同类型地物的诊断性光谱信息以及区分亚类相似地物之间细微差别的光谱信息,在目标探测领域具有独特的优势。与此同时,高光谱遥感影像也带来了数据维数高、邻近波段之间存在大量冗余信息的问题,高维度的数据结构往往使得高光谱影像异常目标类和背景类之间的可分性降低。为了缓解上述问题,本文提出了一种基于波段选择的协同表达高光谱异常探测算法。首先,使用最优聚类框架对高光谱波段进行选择,获得一组波段子集来表示原有的全部波段,使得高光谱影像异常目标类与背景类之间的可分性增强。然后使用协同表达对影像上的像元进行重建,由于异常目标类和背景类之间的可分性增强,对异常目标像元进行协同表达时将会得到更大的残差,异常目标像元的输出值增大,可以更好地实现异常目标和背景类的分离。本文使用了3组高光谱影像数据进行异常目标探测实验,实验结果表明,该方法与其他现有高光谱异常目标探测算法对比,曲线下面积AUC(Area Under Curve)值更高,可以更好地实现异常目标与背景分离,能够更有效地对高光谱影像进行异常目标探测。     

车载激光点云的道路标线提取及语义关联

自动驾驶技术已成为未来智能交通的发展方向之一,高精度地图为L3级及以上自动驾驶实现高精度定位和路径规划提供先验信息,是自动驾驶车辆传感器在遮挡或观测距离受限情况下的重要补充。道路标线的位置和语义信息,比如实线和虚线的绝对位置是高精度地图的基本组成部分。本文从车载激光点云中提取扫描线,根据道路边缘位置几何形态的突变从扫描线中提取道路路面,在此基础上首先利用反距离加权插值的方法把路面点云图像以一定的分辨率转换为栅格图像,其次利用基于积分图的自适应阈值分割方法把栅格图像转化为二值图像,然后利用欧氏聚类的方法从二值图像中提取标线点云,并利用特征属性筛选的方法对提取的标线点云进行语义识别,最后建立交通标线和交通规则之间的语义关联。     

An evaluation of Guided Regularized Random Forest for classification and regression tasks in remote sensing

New Earth observation missions and technologies are delivering large amounts of data. Processing this data requires developing and evaluating novel dimensionality reduction approaches to identify the most informative features for classification and regression tasks. Here we present an exhaustive evaluation of Guided Regularized Random Forest (GRRF), a feature selection method based on Random Forest. GRRF does not require fixing a priori the number of features to be selected or setting a threshold of the feature importance. Moreover, the use of regularization ensures that features selected by GRRF are non-redundant and representative. Our experiments based on various kinds of remote sensing images, show that GRRF selected features provides similar results to those obtained when using all the available features. However, the comparison between GRRF and standard random forest features shows substantial differences: in classification, the mean overall accuracy increases by almost 6% and, in regression, the decrease in RMSE almost reaches 2%. These results demonstrate the potential of GRRF for remote sensing image classification and regression. Especially in the context of increasingly large geodatabases that challenge the application of traditional methods.     

机载多光谱LiDAR的随机森林地物分类

机载多光谱LiDAR技术利用激光进行探测和测距,不仅可以快速获取地面物体的三维坐标,还可以获得多个波段的地物光谱信息,可广泛用于地形测绘、土地覆盖分类、环境建模、森林资源调查等。本文提出了多光谱LiDAR的随机森林地物分类方法。该方法通过对LiDAR强度数据和高程数据提取分类特征,完成多光谱LiDAR的随机森林地物分类;并分析随机森林的特征贡献度特性,采用后向特征选择方法实现分类特征选择。通过对加拿大Optech Titan多光谱LiDAR数据的试验表明：随机森林方法可以获得较好的地物分类精度,而且可以适当地去除部分冗余和相关的特征,从而有效提高分类精度。     

基于GIS的高校物流代理点选址研究

随着电子商务在社会生活中的广泛兴起,校园物流代理点也随之产生;物流代理点在很大程度上方便了师生快递领取,但由于高校物流代理点选址普遍存在随意性和不合理性,导致师生快递领取时浪费过多时间和精力。针对此问题,本研究结合GIS空间分析技术,通过对广西师范大学雁山校区学生宿舍、教学楼、食堂和道路分布数据的分析,利用缓冲区分析和叠置分析优选出物流代理点最佳分布区域,并对校园中现有的物流代理点分布合理性做出评价,进而给出合理的校园物流代理点选址区域建议,旨在为学校物流代理点科学选址及改善和提升校园人文品质提供合理建议,同时为物流企业规划选址及GIS空间分析应用提供参考。     

隧（巷）道测量瞄准误差与觇标选取

根据隧（巷）道双欠观测值的统计资料，分析觇标对瞄准误差的影响，提出觇标的选取方法的观测中注意的问题。     

Influence of environmental and prey variables on low tide shorebird habitat use within the Robbins Passage wetlands,Northwest Tasmania

Shorebirds feed primarily on tidal flats, and their distribution over these flats is influenced by their prey and abiotic factors. These factors act by influencing the distribution and abundance of the prey, or the shorebirds ability to exploit it. The aims of this study were to investigate the low tide foraging distribution of shorebirds at four sites within the Robbins Passage wetlands, and the environmental and invertebrate factors that may influence their distribution. The greatest densities and number of shorebirds were found at Shipwreck Point and East Inlet. The shorebirds within-site distribution was also non-random, with the shorebirds present in greatest densities at the water's edge and low intertidal stratum, although this varied among species. Generally, on a small spatial scale, invertebrate diversity was positively correlated, and seagrass leaf mass was negatively correlated, with shorebird feeding density. On a large spatial scale, invertebrate biomass and seagrass root mass were positively correlated with shorebird feeding density. Invertebrate biomass and seagrass root mass explained 71% of the variance in total shorebird feeding density on the tidal flats. The variation in shorebird feeding density and diversity was therefore partly explained by invertebrate diversity and biomass, as well as the environmental factors seagrass roots and leaf mass and tidal flat area, although the strength of these relationships was influenced by the two different spatial scales of the study. The strength of the relationships between shorebird feeding density and the invertebrate and environmental variables was stronger on a large spatial scale. The presence of seagrass may have influenced shorebird-feeding density by affecting the invertebrate abundance and composition or the shorebirds ability to detect and capture their prey. The area of the tidal flat had opposing effects on the shorebird species. These results can be used to assist in the development of management plans for the Robbins Passage wetlands and the conservation of important shorebird areas.     

两个龙须菜新品系经济性状及琼胶特性的初步研究

2008年2～5月在广东省南澳县深澳海区对选育的龙须菜新品系07-1,07-2和对照组福建宁德栽培的981品系进行海上栽培比较试验,测定了3个品系的藻体日平均生长速率,试验了敌害生物(藻钩虾和团水虱)对3个品系的影响,比较了琼胶特性.结果显示,在水温11～20 ℃,盐度32.4～32.8的条件下,品系07-1,07-2的藻体日平均生长速率分别为3.8%/d和4.1%/d,宁德栽培品系的藻体日平均生长速率为3.2%/d.品系07-1,07-2的生长适应水温下限为16 ℃,比宁德栽培品系降低了2 ℃.与宁德栽培的981品系相比较,选育的龙须菜品系07-1,07-2对藻钩虾和团水虱有较强的耐受能力.品系07-1,07-2的琼胶含量比福建宁德栽培的981品系分别提高10.0%和14.4%,凝胶强度也分别提高了5.46%和14.5%,表明2个新品系具有潜在的推广应用价值.