影像与激光雷达数据的城市地物信息提取

针对城市地物信息提取中地物边界难以确定、分类精度不高的问题,该文提出一套综合利用影像及激光雷达点云高程信息的面向对象分类方法。在分割中,各类地物的最佳分割尺度由监督法分割精度评价确定,最终分割结果利用粒度理论下的分割尺度综合方法进行合成,能兼顾不同地物最优分割尺度,获得准确地物边界;在分类中,采用ReliefF特征选择算法度量从影像及点云数据提取的对象特征重要度,选择最佳特征组合,并采用多分类器组合方法进行分类,以消除Hughes现象,提高分类精度。选择德国斯图加特市两块实验区进行分类实验,结果表明:该方法有利于提高大范围城市地物精细信息提取的精度和效率,具有较高的应用价值。     

融合机载雷达和航空正射影像的道路提取

针对单一遥感数据源提取道路信息中存在的问题,该文提出一种融合多源数据的方法:采用面向对象思想,融合机载激光雷达和航空正射影像,运用对象平均强度指数进行道路精确提取。首先利用点云强度信息进行道路粗提取,再结合影像光谱信息对粗提取点云进行优化,得到"一次点云";然后通过分形网络演化算法对影像进行多尺度分割形成对象,将"一次点云"导入分割对象,利用对象平均强度辅之以对象面积完成道路精确提取。实验结果表明,该方法提取流程简单快速、无须精确配准、道路提取精度较高。     

改进支持向量机的高分遥感影像道路提取

针对支持向量机受分类数的限制在高分辨率遥感影像中无法直接获取高精度道路网信息的问题,该文提出一种新的混合的基于支持向量机的方法:首先,利用模糊C均值聚类方法将输入的遥感影像分为3类,以减少支持向量机的错分现象;其次,运用支持向量机将不同类别的像素分为道路类和非道路类;最后,应用马尔科夫随机场对分类结果进行噪声去除,并采用形态学进行后处理,进而得到精确道路网信息。实验结果表明:该算法不仅能够从高分辨率遥感影像中提取出道路网,而且精度优于直接使用支持向量机算法以及对比算法。     

倾斜摄影测量的城市真三维模型构建方法

针对如何基于近年来新推出的倾斜摄影测量技术快速构建城市真三维模型的问题,在研究分析国内基于该技术构建三维模型方法的基础上,提出了利用Street Factory系统,结合少量人工干预快速构建城市真三维模型的方法。采用倾斜影像联合空中三角测量技术,实现了多角度倾斜影像的一体化区域网平差;通过多视影像密集匹配和自动纹理关联,实现了高精度真实三维模型的构建。基于RCD-30倾斜相机获取的西安大雁塔景区倾斜影像,开展城市真三维模型构建试验。结果表明,所提方法构建的城市真三维模型满足相关规范的要求,适合大规模区域城市三维模型快速构建,对测绘生产单位规模化生产具有一定的参考价值。     

Use of cartographic images by expert and novice field geologists in planning fieldwork routes

Topographic maps and aerial photographs are particularly useful when geoscientists are faced with fieldwork tasks such as selecting paths for observation, establishing sampling schemes, or defining field regions. These types of images are crucial in bedrock geologic mapping, a cognitively complex field-based problem-solving task. Geologic mapping requires the geologist to correctly identify rock types and three-dimensional bedrock structures from often partial or poor-quality outcrop data while navigating through unfamiliar terrain. This paper compares the walked routes of novice to expert geologists working in the field (n = 66) with the results of a route planning and navigation survey of a similar population of geologists (n = 77). Results show clearly that those geologists with previous mapping experience make quick and decisive determinations about field areas from available imagery and maps, regardless of whether they are or not physically present in the field area. Recognition of geologic features enabled experts to form and verbalize a specific plan for travel through a landscape based on those features. Novices were less likely to develop specific travel route plans and were less likely to identify critical landscape cues from aerial photographs.     

干旱半干旱高寒山区蚀变矿物遥感信息提取效果与找矿预测

新疆阿尔金地区位于阿尔金成矿带,属于干旱半干旱高寒山区景观区,该区成矿条件优越,但自然地理条件较差,基岩裸露利于蚀变矿物准确提取,采用CASI/SASI航空高光谱遥感进行蚀变矿物遥感信息提取及找矿预测,可以克服自然条件影响,降低成本。本文以CASI/SASI航空高光谱遥感数据为数据源,以干旱半干旱高寒山区景观区为研究背景,评价研究该区CASI/SASI航空高光谱蚀变矿物遥感信息提取效果,通过野外地质调查,发现了镍、铁、钴、钒、钛、铜等元素多金属矿化线索,并最终圈定了YC01和YC02等两处找矿预测区。说明CASI/SASI航空高光谱遥感在干旱半干旱高寒山区蚀变矿物遥感信息提取效果显著。     

Interaction of cnoidal waves with an array of vertical concentric porous cylinders

An array of large concentric porous cylinder arrays is mounted in shallow water exposed to cnoidal waves. The interactions between waves and cylinders are studied theoretically using an eigenfunction expansion approach. Semi-analytical solutions of hydrodynamic loads and wave run-up on each cylinder are obtained using first approximation to cnoidal waves. The square array configuration of four-legged identical concentric porous cylinder is investigated in present study. Numerical results reveal the variation of dimensionless wave force and wave run-up on individual cylinder with angle of incidence, porosity parameter, spacing between outer and inner cylinders, spacing between concentric porous cylinders and wave parameter. Different mechanism of wave force is found under different range of scattering parameter.     

基于SPOT6遥感影像的滩涂湿地入侵种互花米草植株高度的反演研究

本文以SPOT6 高空间分辨率遥感影像为数据源,通过植被覆盖度和地上生物量两个参数进行滩涂湿地入侵种互花米草植株高度的估算研究。结果表明,三沙湾滩涂湿地互花米草植株高度平均值为2.04 m,以1~2 m和2~3 m植株为主要分布高度,分布面积分别为6.83 km2和10.31 km2,占研究区互花米草总面积的33.83%和51.06%,小于1 m和大于3 m的互花米草仅占9.26%和5.84%。估算值与真实值之间的均方根误差为0.204,绝对误差为0.04~0.37 m。该方法是对高空间分辨率光学影像应用研究的重要尝试,其反演方法具有较好的可行性,可较为准确的获取滩涂湿地植株高度信息。     

基于岩石图像深度学习的岩性自动识别与分类方法

岩石岩性的识别与分类对于地质分析极为重要,采用机器学习的方法建立识别模型进行自动分类是一条新的途径。基于Inception-v3深度卷积神经网络模型,建立了岩石图像集分析的深度学习迁移模型,运用迁移学习方法实现了岩石岩性的自动识别与分类。采用此方法对所采集的173张花岗岩图像、152张千枚岩图像和246张角砾岩图像进行了学习和识别分类研究,通过训练学习建立岩石图像深度学习迁移模型,并分别采用训练集和测试集中的岩石图像对模型进行了检验分析。对于训练集中的岩石图像,每组岩石分别用3张图像测试,三种岩石的岩性分类均正确,且分类概率值均达到90%以上,显示了模型良好的鲁棒性;对于测试集中的岩石图像,每组岩石分别采用9张图像进行识别分析,三种岩石的岩性分类均正确,并且千枚岩组图像分类概率均高于90%,但是花岗岩组2张图像和角砾岩组的1张图像分类概率值不足70%,概率值较其他岩石图像低,推测其原因是训练集中相同模式的岩石图像较少,导致模型的泛化能力减小。为了提高识别精确度,对准确率较低的岩石图像进行截取,分别取其中的3张图像加入训练集进行再训练,增加与测试图像具有相同模式的训练样本;在新的模型中,对3张图像进行二次检验,测试概率值均达到85%以上,说明在数据足够的状况下模型具有良好的学习能力。与传统的机器学习方法相比,所提出的岩石图像深度学习方法具有以下优点:第一,模型通过搜索图像像素点提取物体特征,不需要手动提取待分类物体特征;第二,对于图像像素大小,成像距离及光照要求低;第三,采用适当的训练集可获得较好的识别分类效果,并具有良好鲁棒性和泛化能力。     

Geometric-constrained multi-view image matching method based on semi-global optimization

Targeting at a reliable image matching of multiple remote sensing images for the generation of digital surface models, this paper presents a geometric-constrained multi-view image matching method, based on an energy minimization framework. By employing a geometrical constraint, the cost value of the energy function was calculated from multiple images, and the cost value was aggregated in an image space using a semi-global optimization approach. A homography transform parameter calculation method is proposed for fast calculation of projection pixel on each image when calculating cost values. It is based on the known interior orientation parameters, exterior orientation parameters, and a given elevation value. For an efficient and reliable processing of multiple remote sensing images, the proposed matching method was performed via a coarse-to-fine strategy through image pyramid. Three sets of airborne remote sensing images were used to evaluate the performance of the proposed method. Results reveal that the multi-view image matching can improve matching reliability. Moreover, the experimental results show that the proposed method performs better than traditional methods.