基于KNN运动模式识别的改进PDR室内定位

为提高行人航迹推算(PDR)的定位精度,首先利用K最近邻法(KNN)对智能手机采集的6种行人运动模式数据进行识别,再与基于支持向量机(SVM)和高斯朴素贝叶斯(GNB)的运动模式识别方法进行对比,最后在实际环境下进行运动模式辅助的PDR实验。结果表明,KNN方法不仅比SVM和GNB方法易于实现,而且具有更高的识别正确率。在识别行人运动模式的前提下,PDR的室内定位效果比传统PDR方法定位效果更好。     

基于中心点检测和重识别的多行人跟踪算法

在基于视频的多目标运动跟踪中,目标检测和重识别具有很强的相关性。目前常将目标检测和重识别网络分别进行训练和使用,因此实时跟踪速度不能达到要求。针对多目标跟踪(multiple object tracking,MOT)中行人身份切换和跟踪丢失问题,将行人重识别模块进行遮挡优化并嵌入行人检测网络,由此提出了一种基于中心点检测和重识别的多行人跟踪算法。首先建立了行人运动模型,通过中心点检测得到行人最优状态估计;然后根据深层特征融合的行人重识别模型,利用马氏距离和余弦距离增强行人身份辨别能力;最后利用匈牙利算法进行在线数据关联,同时利用卡尔曼滤波剔除不准确的结果,对未关联的丢失目标做运动预测。利用所提算法和其他跟踪算法分别在MOT15、MOT16、MOT17数据集上进行多行人跟踪对比实验,结果表明,所提算法的多目标跟踪精度(multiple object tracking accuracy,MOTA)分别为63.5、72.4、70.9,正确识别的检测和计算的检测数的比值(identity F1-measure,IDF1)最优,且保证了实时跟踪速率,验证了所提跟踪算法的有效性。     

结合CNN-BiLSTM-SA运动模式识别的自适应步频检测方法

随着位置服务(LBS)的普及，基于智能手机的行人步频检测方法对行人航迹推算(PDR)有重要影响.针对传统步频检测方法在行人多种运动模式下计步误差大的问题，提出一种结合CNN-BiLSTM-SA运动模式识别的自适应步频检测方法.首先根据行人行走特点划分运动模式，使用卷积神经网络(CNN)提取行人不同运动模式的局部特征，利用自注意力机制(SA)对提取的运动特征进行权重分配；再结合双向长短期记忆网络(BiLSTM)挖掘行人运动特征的前后时序关系进行分类识别；然后根据分类结果提出自适应最小峰距和自适应动态阈值两个特征约束的峰值检测算法对步频进行检测，并在步行中动态调整阈值大小.实验结果表明：本文提出方法在8种组合运动模式下步频检测平均误差率为1.31%，与传统峰值检测相比误差率降低5.97%，同时也优于固定阈值法.     

视觉惯导紧耦合的行人室内自主定位方法

针对行人在大型复杂建筑环境中的高精度和高可靠性室内定位需求,传统的基于视觉点特征方法易受环境纹理缺失、相机快速运动导致图像模糊而定位失效问题,提出了一种基于视觉点线特征与IMU紧耦合的行人室内 自主定位方法.在视觉惯导融合导航系统框架下,前端部分,在点特征基础上引入结构化建筑环境中丰富的线特征,并采取基于梯度密度过滤机制的改进线特征提取策略,剔除局部线特征密集区域;利用点线特征与IMU紧耦合优化机制提高行人位姿估计及定位的准确性和稳定性.通过利用EuRoC数据集和在实际楼道场景下的实验,特别是在弱纹理、光照变化等条件下实验,验证了所提方法进行行人室内定位的准确性和可行性.     

面向遥感目标识别耦合GA与SVM的特征优选方法

提出了GA-SVM耦合用于高分遥感目标识别的特征优选方法,将GA中的特征降维和适应度函数构建与SVM中的特征空间映射、样本训练以及分类结果在内容上耦合,利用SVM的识别结果指导GA的进化方向。同时,为减小未成熟收敛风险,对传统GA做了改进。实验表明,该方法在高分遥感影像目标识别中效果较好。     

应用时空核密度估计的室内疏散过程分析方法

针对室内场景下疏散规划方案设计简单、施行复杂以及管控困难的问题,应用一种时空核密度分析方法对疏散中的行人时空分布特征进行分析探讨.基于疏散仿真行人的位置数据进行核密度分析,对分析结果进行可视化输出后能够针对性的提出相关应急疏散布防布控建议与对策.最终实验结果表明,利用时空核密度分析方法能够有效分析全疏散流程行人聚集特征,对估计结果的三维可视化能够快速准确定位疏散瓶颈位置、识别拥堵区域,基于分析结果能够给出相应的应急疏散布防布控指导建议.     

结合ReliefF、GA和SVM的面向对象建筑物目标识别特征选择方法

提出结合ReliefF算法、遗传算法(Genetic algorithm,GA)和支持向量机(Support Vector Machine,SVM)的高分辨率遥感影像建筑物目标识别特征选择算法。首先使用ReliefF算法进行初步的特征筛选,然后将SVM参数和特征子集编码到GA染色体中,以SVM识别精度构建适应度函数,同时优化特征子集和SVM参数。实验结果表明,将文中算法应用于建筑物目标识别,能以较小的特征子集和较短的优化时间达到较高的识别精度。     

MRELBP特征、Franklin矩和SVM相结合的遥感图像建筑物识别方法

为了进一步提高遥感图像建筑物区域的识别精度,提出了一种基于中值稳健扩展局部二值模式(median robust extended local binary pattern,MRELBP)、Franklin矩和布谷鸟优化支持向量机(support vector machine,SVM)的分类方法。首先,通过MRELBP特征算子计算图像块的纹理特征向量,并根据Franklin矩得到形状特征向量,组合图像块的纹理特征向量和形状特征向量得到综合特征向量;然后,利用训练样本对SVM进行训练,同时由布谷鸟搜索算法对SVM的核函数参数和惩罚因子进行优化;最后,通过训练好的SVM得到建筑物区域识别结果。通过30组试验的结果表明,与基于三原色(red green blue,RGB)和SVM的分类方法、基于LBP和SVM的分类方法、基于Zernike矩和SVM的分类方法相比,本文提出的方法所识别的遥感图像建筑物区域准确度更高。     

手机加速度计的行人行进状态识别

针对行人在行进过程中会出现后退而导致对行人航位轨迹的错误判断问题,该文以手机内加速度传感器信号为数据依据,以识别行人正常前进中的后退状态为研究目标,研究三轴信号的均值、方差、轴间协方差等时域特征,采用经验模态分解、最大相关最小冗余、最小二乘支持向量机等方法,识别行人实时的前进或后退。研究结果表明:两人将手机置于不同位置,分别采集前进中出现不同后退步数的实验数据,以一组为建模数据,识别其他情况的运动状态,其识别平均成功率达96.00%,具有较大的理论参考价值。     

利用行人轨迹挖掘城市区域功能属性

城市土地利用功能区是城市规划中的一个重要概念,遥感技术手段在城市土地利用类型识别和动态监测中取得了很大进展。然而,由于城市实际功能的复杂,往往很难从遥感影像中获得城市各个区域的社会、经济或文化等功能属性。互联网技术的发展和移动定位设备的普及,极大地便利了行人移动轨迹数据的获取。本文从行人移动规律和模式与城市功能分区之间高度相关的角度出发,通过机器学习的方法,从大量行人轨迹数据中挖掘隐含的城市功能属性与强度。该方法首先利用矢量栅格化和数学形态学方法,将城市不同等级的路网分割为互不相同的空间单元;其次,根据行人轨迹数据的时空分布特点,定义9个变量并构建高斯混合模型(Gaussian mixture model,GMM),对上述空间单元进行非监督分类,得到7种城市用地类型;随后,结合选定的60个样本区以及人为标识的6种功能区(教育用地、绿地休闲区、一般商业区、政府设施、中心商业区、住宅区),依据样本功能区GPS轨迹时间分布特征,最终对7种城市用地类型进行功能配对;最后,利用核密度估计方法进行功能区强度的可视化。该框架结合机器学习的优势,结果具有较高的准确度。     

Extraction and motion estimation of vehicles in single-pass airborne LiDAR data towards urban traffic analysis

Airborne LiDAR data are characterized by involving not only rich spatial but also temporal information. It is possible to extract vehicles with motion artifacts from single-pass airborne LiDAR data, based on which the motion state and velocity of vehicles can be identified and derived. In this paper, a complete strategy for urban traffic analysis using airborne LiDAR data is presented. An adaptive 3D segmentation method is presented to facilitate the task of vehicle extraction. The method features an ability to detect local arbitrary modes at multi scales, thereby making it particularly appropriate for partitioning complex point cloud data. Vehicle objects are then extracted by a binary classification using object-based features. Furthermore, the motion analysis for extracted vehicles is performed to distinguish between moving and stationary ones. Finally, the velocity is estimated for moving vehicles. The applicability and efficiency of the presented strategy is demonstrated and evaluated on three ALS datasets acquired for the propose of city mapping, where up to 87% of vehicles have been extracted and up to 83% of moving traffic can be recovered together with reasonable velocity estimates. It can be concluded that airborne LiDAR data can provide value-added products for traffic monitoring applications, including vehicle counts, location and velocity, along with traditional products such as building models, DEMs and vegetation models.     

绝对空间定位到相对空间感知的行人导航研究趋势

相对空间比绝对空间更易于被人理解。行人导航本质是以相对于人的导航环境视觉与空间等相对语义来动态引导行人的过程,即相对导航。目前,GIS导航理论以绝对定位与空间建模为基础,没有充分理解人对相对语义的认知差异,缺乏基于相对语义的导航理论模型。首先,总结了以绝对空间定位与表达为基础的行人导航研究,提出了相对空间感知的行人导航研究新方向。然后,剖析了相对导航研究的理论研究需求,如:行人相对导航数据采集与建模、行人导航环境相对语义的提取、行人导航行为的自动感知分析、行人导航的多感官交互机制、行人导航路径选择与确认机制等。最后,展望了未来行人导航研究与重要创新的3个阶段。     

利用SVM的全极化、双极化与单极化SAR图像分类性能的比较

支持向量机(SVM)以其在小训练样本时良好的分类性能,目前已广泛应用于多个领域.本文在极化SAR图像特征提取基础上,将SVM应用于极化SAR图像分类,定性和定量地比较了全极化、双极化和单极化SAR图像的分类性能,分析了不同的极化组合对分类结果的影响,并根据地物极化散射特性分析了分类精度差异的成因.实测极化SAR数据的实验结果表明,全极化数据能获得最好的分类性能,双极化次之,单极化最低,且在某些情况下,双极化与全极化分类性能接近.     

支撑向量机及其遥感影像空间特征提取和分类的应用研究

提出了基于支撑向量机（SVM）的遥感影像空间特征提取的新方法，并以SPOT全色波段影像上城市特征信息的提取为应用实例，并与人工神经网络（ANN）等特征提取方法进行综合比较，认为SVM方法不但能够获得比较高的分类精度，而且在学习速度、自适应能力、特征空间高维不限制、可表达性等方面具有优势。     

Evaluation of classifiers for processing Hyperion (EO-1) data of tropical vegetation

There is an urgent necessity to monitor changes in the natural surface features of earth. Compared to broadband multispectral data, hyperspectral data provides a better option with high spectral resolution. Classification of vegetation with the use of hyperspectral remote sensing generates a classical problem of high dimensional inputs. Complexity gets compounded as we move from airborne hyperspectral to Spaceborne technology. It is unclear how different classification algorithms will perform on a complex scene of tropical forests collected by spaceborne hyperspectral sensor. The present study was carried out to evaluate the performance of three different classifiers (Artificial Neural Network, Spectral Angle Mapper, Support Vector Machine) over highly diverse tropical forest vegetation utilizing hyperspectral (EO-1) data. Appropriate band selection was done by Stepwise Discriminant Analysis. The Stepwise Discriminant Analysis resulted in identifying 22 best bands to discriminate the eight identified tropical vegetation classes. Maximum numbers of bands came from SWIR region. ANN classifier gave highest OAA values of 81% with the help of 22 selected bands from SDA. The image classified with the help SVM showed OAA of 71%, whereas the SAM showed the lowest OAA of 66%. All the three classifiers were also tested to check their efficiency in classifying spectra coming from 165 processed bands. SVM showed highest OAA of 80%. Classified subset images coming from ANN (from 22 bands) and SVM (from 165 bands) are quite similar in showing the distribution of eight vegetation classes. Both the images appeared close to the actual distribution of vegetation seen in the study area. OAA levels obtained in this study by ANN and SVM classifiers identify the suitability of these classifiers for tropical vegetation discrimination.     

Modeling and forecast of the polar motion excitation functions for short-term polar motion prediction

Short-term forecast of the polar motion is considered by introducing a prediction model for the excitation function that drives the polar motion dynamics. The excitation function model consists of a slowly varying trend, periodic modes with annual and several sub-annual frequencies (down to the 13.6-day fortnightly tidal period), and a transient decay function with a time constant of 1.5 days. Each periodic mode is stochastically specified using a second-order auto-regression process, allowing its frequency, phase, and amplitude to vary in time within a statistical tolerance. The model is used to time-extrapolate the excitation function series, which is then used to generate a polar motion forecast dynamically. The skills of this forecast method are evaluated by comparison to the C-04 polar motion series. Over the lead-time horizon of four months, the proposed method has performed equally well to some of the state-of-art polar motion prediction methods, none of which specifically features forecasting of the excitation function. The annual mode in the ₂ component is energetically the most dominant periodicity. The modes with longer periods, annual and semi-annual in particular, are found to contribute more significantly to forecast accuracy than those with shorter periods.     

Evaluating SAR polarization modes at L-band for forest classification purposes in Eastern Amazon,Brazil

Single, interferometric dual, and quad-polarization mode data were evaluated for the characterization and classification of seven land use classes in an area with shifting cultivation practices located in the Eastern Amazon (Brazil). The Advanced Land-Observing Satellite (ALOS) Phased Array L-band Synthetic Aperture Radar (PALSAR) data were acquired during a six month interval. A clear-sky Landsat-5/TM image acquired at the same period was used as additional ground reference and as ancillary input data in the classification scheme. We evaluated backscattering intensity, polarimetric features, interferometric coherence and texture parameters for classification purposes using support vector machines (SVM) and feature selection. Results showed that the forest classes were characterized by low temporal backscattering intensity variability, low coherence and high entropy. Quad polarization mode performed better than dual and single polarizations but overall accuracies remain low and were affected by precipitation events on the date and prior SAR date acquisition. Misclassifications were reduced by integrating Landsat data and an overall accuracy of 85% was attained. The integration of Landsat to both quad and dual polarization modes showed similarity at the 5% significance level. SVM was not affected by SAR dimensionality and feature selection technique reveals that co-polarized channels as well as SAR derived parameters such as Alpha-Entropy decomposition were important ranked features after Landsat’ near-infrared and green bands. We show that in absence of Landsat data, polarimetric features extracted from quad-polarization L-band increase classification accuracies when compared to single and dual polarization alone. We argue that the joint analysis of SAR and their derived parameters with optical data performs even better and thus encourage the further development of joint techniques under the Reducing Emissions from Deforestation and Degradation (REDD) mechanism.     

Impact of feature selection on the accuracy and spatial uncertainty of per-field crop classification using Support Vector Machines

Crop mapping is one major component of agricultural resource monitoring using remote sensing. Yield or water demand modeling requires that both, the total surface that is cultivated and the accurate distribution of crops, respectively is known. Map quality is crucial and influences the model outputs. Although the use of multi-spectral time series data in crop mapping has been acknowledged, the potentially high dimensionality of the input data remains an issue. In this study Support Vector Machines (SVM) are used for crop classification in irrigated landscapes at the object-level. Input to the classifications is 71 multi-seasonal spectral and geostatistical features computed from RapidEye time series. The random forest (RF) feature importance score was used to select a subset of features that achieved optimal accuracies. The relationship between the hard result accuracy and the soft output from the SVM is investigated by employing two measures of uncertainty, the maximum a posteriori probability and the alpha quadratic entropy. Specifically the effect of feature selection on map uncertainty is investigated by looking at the soft outputs of the SVM, in addition to classical accuracy metrics. Overall the SVMs applied to the reduced feature subspaces that were composed of the most informative multi-seasonal features led to a clear increase in classification accuracy up to 4.3%, and to a significant decline in thematic uncertainty. SVM was shown to be affected by feature space size and could benefit from RF-based feature selection. Uncertainty measures from SVM are an informative source of information on the spatial distribution of error in the crop maps.     

基于Sentinel-1的典型地物时间失相干分析

为了探究影响Sentinel-1时间失相干的因素,实验选取美国南加州柯汶纳市及其周边区域进行研究,使用50景Senti-nel-1数据,分析了不同地物的时间失相干现象,并研究了风雨等天气因素及不同极化方式对相干性的影响.主要得出以下结论:Sentinel-1数据典型地物的失相干特征区别较大,可以较好地指导地物识别、辅助...     

High resolution multisensor fusion of SAR,optical and LiDAR data based on crisp vs. fuzzy and feature vs. decision ensemble systems

Synthetic Aperture Radar (SAR) data are of high interest for different applications in remote sensing specially land cover classification. SAR imaging is independent of solar illumination and weather conditions. It can even penetrate some of the Earth’s surface materials to return information about subsurface features. However, the response of radar is more a function of geometry and structure than a surface reflection occurs in optical images. In addition, the backscatter of objects in the microwave range depends on the frequency of the band used, and the grey values in SAR images are different from the usual assumption of the spectral reflectance of the Earth’s surface. Consequently, SAR imaging is often used as a complementary technique to traditional optical remote sensing. This study presents different ensemble systems for multisensor fusion of SAR, multispectral and LiDAR data. First, in decision ensemble system, after extraction and selection of proper features from each data, crisp SVM (Support Vector Machine) and Fuzzy KNN (K Nearest Neighbor) are utilized on each feature space. Finally Bayesian Theory is applied to fuse SVMs when Decision Template (DT) and Dempster Shafer (DS) are applied as fuzzy decision fusion methods on KNNs. Second, in feature ensemble system, features from all data are applied on a cube. Then classifications were performed by SVM and FKNN as crisp and fuzzy decision making system respectively. A co-registered TerrraSAR-X, WorldView-2 and LiDAR data set form San Francisco of USA was available to examine the effectiveness of the proposed method. The results show that combinations of SAR data with different sensor improves classification results for most of the classes.