基于语义相似度的海量遥感图像可视化研究

针对海量遥感图像如何有效的传达分类结果以实现有效的可视化问题,本文按照分类的语义标注结果的相似度并运用现有的信息可视化技术来实现图像的可视化。首先采用了贝叶斯网络学习的方法进行图像的自动分类标注,然后利用基于图像布局的多维标度算法(Multi-dimensional Scale)以及无需降维的Value and Relation(VaR)技术实现可视化。实验表明本文的方法能够填补图像低层视觉特征和高层语义之间鸿沟,对大量的图像在一个视图内进行有效的浏览,而不造成图像的混乱,并能实现高层次的图像分析。实验的可视化结果是十分有效的。     

Comparing spatially varying coefficient models: a case study examining violent crime rates and their relationships to alcohol outlets and illegal drug arrests

In this paper, we compare and contrast a Bayesian spatially varying coefficient process (SVCP) model with a geographically weighted regression (GWR) model for the estimation of the potentially spatially varying regression effects of alcohol outlets and illegal drug activity on violent crime in Houston, Texas. In addition, we focus on the inherent coefficient shrinkage properties of the Bayesian SVCP model as a way to address increased coefficient variance that follows from collinearity in GWR models. We outline the advantages of the Bayesian model in terms of reducing inflated coefficient variance, enhanced model flexibility, and more formal measuring of model uncertainty for prediction. We find spatially varying effects for alcohol outlets and drug violations, but the amount of variation depends on the type of model used. For the Bayesian model, this variation is controllable through the amount of prior influence placed on the variance of the coefficients. For example, the spatial pattern of coefficients is similar for the GWR and Bayesian models when a relatively large prior variance is used in the Bayesian model.      

基于Membrane MRF模型的SAR图像贝叶斯去斑

SAR图像可以看作是真实反映地物后向散射特性的无噪图像与相干斑噪声的乘积,通过贝叶斯估计从图像观测值估计出图像真值即可去除相干斑.而贝叶斯去斑的关键在于建立能与SAR图像特性相匹配的先验信息模型.用MembraneMRF模型对先验信息建模,克服了以往所用GMRF模型对参数估计十分敏感的问题,并通过对该模型邻域结构的自适应调整来分类处理处于匀质区域和含结构特征区域的像元,在有效抑制相干斑的同时较好地保持图像的结构特征.仿真和实际SAR图像数据的实验结果,验证了所提方法的有效性.     

Vision-based tracking with projective mapping for parameter identification of remotely operated vehicles

Parameter identification of a remotely operated vehicle (ROV) is often based on the dynamic responses collected by its onboard sensors. However, for commercial ROVs, the required data for identification may not be available due to the absence of suitable sensors or limitations in accessing onboard sensor data. Therefore, this study proposes a vision-based tracking system to measure the dynamic response of an ROV. The tracking system is independent of the ROV, and is able to localize an ROV to a high degree of precision by means of projective mapping. The validity of the proposed tracking system is demonstrated through identification of a commercial ROV. A simplified nonlinear ROV dynamic model with six degrees of freedom (DOF) is used for identification. Uncoupled motions, including surge, sway, and yaw, are obtained from the ROV dynamic model, and the corresponding experiments are carried out for each DOF. Hydrodynamic parameters are then estimated with numerical optimizations by comparing the measured ROV responses with the output of the mathematical model. The experimental results show that the vision-based tracking system can accurately measure the transient and steady-state responses of an ROV. Additionally, the simulations of the ROV dynamic model, with the optimal parameter estimates, give results in agreement with the measured data.     

Parameter estimation for basin-scale ecosystem-linked population models of large pelagic predators: Application to skipjack tuna

A Spatial Ecosystem and Population Dynamic Model (SEAPODYM) is used in a data assimilation study aiming to estimate model parameters that describe dynamics of Pacific skipjack tuna population on ocean-based scale. The model based on advection–diffusion–reaction equations explicitly predicts spatial dynamics of large pelagic predators, while taking into account data on several mid-trophic level components, oceanic primary productivity and physical environment. In order to improve its quantitative ability, the model was parameterized through assimilation with commercial fisheries data, and optimization was carried out using maximum likelihood estimation approach. To address the optimization task we implemented an adjoint technique to obtain an exact, analytical evaluation of the likelihood gradient. We conducted a series of computer experiments in order to (i) determine model sensitivity with respect to variable parameters and, hence, investigate their observability; (ii) estimate observable parameters and their errors; and (iii) justify the reliability of the computed solution. Parameters describing recruitment, movement, habitat preferences, natural and fishing mortality of skipjack population were analysed and estimated. Results of the study suggest that SEAPODYM with achieved parameterization scheme can help to investigate the impact of fishing under various management scenarios, and also conduct forecasts of a given species stock and spatial dynamics in a context of environmental and climate changes.     

a′Trous小波变换与PCA变换相结合的遥感影像融合分析

随着高分辨率遥感卫星的产生,传统的融合技术难以达到较好的融合效果,如主成分分析(PrincipalComponents Analysis)变换融合受到融合区域的限制,而传统的小波融合(Wavelet Transformation)算法由于高频直接替换,导致了一定程度的光谱失真,由此本文在分析主成分分析变换和a′Trous小波变换(WT)的基础上,以QuickBird全色和多光谱数据为实验数据,提出了一种将两者相结合的遥感影像融合方法,通过与其他融合方法的定量和视觉比较,结果表明该方法能得到更好的融合效果。     

琼胶降解菌F-6筛选、培养条件及对条斑紫菜(Porphyra yezoensis)细胞解离作用的研究

利用琼胶作为唯一的碳源从青岛太平角海域的海水和红藻样品中筛选分离得到一株高产琼胶酶的海洋菌F-6,对其最适的产酶条件,利用琼胶酶分离条斑紫菜的原生质体和原生质体的培养进行研究。结果表明,通过单次单因子和正交实验确定琼胶降解菌株F-6最适产酶培养基配方为(W/V):琼胶0.7%;酵母粉0.3%;蛋白胨0.5%;NaCl2.0%;K2HPO40.1%;CaCl20.02%;MgSO4·7H2O0.05%;FeSO4·7H2O0.002%;起始pH=7.5,最适的发酵产酶条件为:26℃培养36h。经条件优化后,粗酶液的酶活高达631.6U/ml。发酵液经过6000g离心30min得到粗酶液,粗酶液经过8k分离膜超滤,加入1mol/L渗透剂,0.22μm滤膜过滤除菌后降解条斑紫菜组织块,成功地分离得到大量的紫菜原生质体,其产率为3×106个原生质体/g新鲜紫菜组织。原生质体经初步培养发育成愈伤组织,其成活率为60%。     

基于贝叶斯网络的海洋生态环境状况评价——以山东省为例

在海洋开发利用活动日益增多,海洋环境保护压力日益增大的背景下,进行海洋生态环境状况科学评价方法的研究可以为开展海洋生态环境监测评估与海洋生态环境保护政策制定提供科学依据,促进改善海洋生态环境状况。本文首先基于贝叶斯网络基本理论,构建了海洋生态环境状况贝叶斯网络评价模型;再以山东省为例,充分融合专家经验知识与客观数据,从定性与定量两个角度评价了2013—2019年山东省近海生态环境状况,分析了各评价指标间关系及其对近海生态环境状况的影响程度。评价结果表明2013—2019年山东省近海生态环境状况保持一般状态,海洋环境质量与海洋生态灾害类指标对评价结果影响最大,山东省海洋环境保护工作初见成效。研究结果表明该评价模型能有效评价海洋生态环境状况,分析结果对于环境保护政策制定具有一定的借鉴意义。     

结合遗传算法的LVQ神经网络在声学底质分类中的应用

学习向量量化（Learning Vector Quantization,LVQ）神经网络在声学底质分类中具有广泛应用. 常用的LVQ神经网络存在神经元未被充分利用以及算法对初值敏感的问题,影响底质分类精度. 本文提出采用遗传算法（Genetic Algorithms,GA）优化神经网络的初始值,将GA与LVQ神经网络结合起来,迅速得到最佳的神经网络初始权值向量,实现对海底基岩、砾石、砂、细砂以及泥等底质类型的快速、准确识别. 将其应用于青岛胶州湾海区底质分类识别研究中,通过与标准的LVQ神经网络的分类结果进行比较表明,该方法在分类速度以及精度上都有了较大提高.     

一种基于GPU和内存映射文件的高分辨率遥感图像快速处理方法

高分辨率遥感图像处理经常面临程序执行时间过长和内存空间不足的问题,虽然并行计算技术可以提高遥感图像的处理速度,但是无法降低算法占用的巨大内存空间。为了解决这一问题,本文提出了一种利用CUDA和内存映射文件的高分辨率遥感图像快速处理方法,并以K-Means算法为例进行了实现。其中,CUDA技术可以有效利用GPU强大的并行计算能力,而内存映射文件技术降低了磁盘I/O速度较慢对算法性能的影响。实验结果表明,本文方法比传统K-Means聚类算法计算速度提高了30倍左右,内存使用量降低了90%以上。