首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 31 毫秒
1.
Point cloud classification plays a critical role in many applications of airborne light detection and ranging (LiDAR) data. In this paper, we present a deep feature-based method for accurately classifying multiple ground objects from airborne LiDAR point clouds. With several selected attributes of LiDAR point clouds, our method first creates a group of multi-scale contextual images for each point in the data using interpolation. Taking the contextual images as inputs, a multi-scale convolutional neural network (MCNN) is then designed and trained to learn the deep features of LiDAR points across various scales. A softmax regression classifier (SRC) is finally employed to generate classification results of the data with a combination of the deep features learned from various scales. Compared with most of traditional classification methods, which often require users to manually define a group of complex discriminant rules or extract a set of classification features, the proposed method has the ability to automatically learn the deep features and generate more accurate classification results. The performance of our method is evaluated qualitatively and quantitatively using the International Society for Photogrammetry and Remote Sensing benchmark dataset, and the experimental results indicate that our method can effectively distinguish eight types of ground objects, including low vegetation, impervious surface, car, fence/hedge, roof, facade, shrub and tree, and achieves a higher accuracy than other existing methods.  相似文献   

2.
孟祥锐  张树清  臧淑英 《地理科学》2018,38(11):1914-1923
以洪河国家级自然保护区为研究对象,应用卷积神经网络（CNN）方法进行高分辨率湿地遥感影像的分类研究,并与基于光谱支持向量机（SP-SVM）的方法和基于纹理及光谱的支持向量机（TSP-SVM）的方法进行了对比。结果显示,对于所选取的2个研究区域,CNN分类方法的全局精度高于SP-SVM方法5.61%和5%,高于TSP-SVM方法4.18%和4.15%。尤其对于部分湿地植被的分类精度明显高于SP-SVM和TSP-SVM方法。研究表明,卷积神经网络为湿地识别的精细划分提供了有利的手段。  相似文献   

3.
利用卷积神经网络从遥感影像中提取水体时,水体对象边缘像素的特征与内部像素的特征之间往往存在较大差异,导致提取结果中边界模糊、内部像素与边缘像素的提取精度差异较大,影响了整体精度的提高。针对如何从高分辨率遥感影像中进行水体高精度、自动化提取的问题,文章首先以高分辨率遥感图像为基础,利用边缘提取算法生成边缘图像,然后以高分辨率遥感图像和边缘图像作为输入,建立了语义特征和边缘特征融合的高分辨率遥感图像水体提取模型（Semantic Feature and Edge Feature Fusion Network, SEF-Net）,用于从高分辨率遥感图像中提取水体对象。实验结果表明,SEF-Net模型在3个数据集中的召回率（91.97%、92.07%、93.97%）,精确率（91.12%、98.37%、97.88%）,准确率（89.56%、95.07%、94.06%）和F1分数（91.54%、95.12%、95.88%）均优于对比模型,说明SEF-Net模型从高分辨率遥感图像中提取水体时,具有更高的精度和泛化能力。  相似文献   

4.
基于深度学习方法在城市激光点云语义分割任务中的应用效果缺乏客观的对比与评价,该文选取当前4种代表性点云语义分割深度网络(PointNet、PointNet++、PointCNN、SPG)以及一种基于特征描述子的层次化点云语义分割方法,采用3组开放点云数据集(Semantic 3D、Oakland及TerraMobilita/iQmulus3Durban)对不同方法的语义分割质量进行对比分析,结果发现:1)层次化点云语义分割方法的语义分割质量优于另外4种深度学习方法;2)考虑局部信息的深度网络(PointNet++、PointCNN、SPG)的表现优于仅考虑点云全局特征的方法(Point-Net);3)在基于深度学习的方法中,基于超点图的SPG网络在测试数据中的效果优于其他几种网络。研究结果对于实际应用选择点云语义分割方法以及点云语义分割深度网络的设计优化具有借鉴意义。  相似文献   

5.
  相似文献   

6.
Abstract

Multiresolution data structures provide a means of retrieving geographical features from a database at levels of detail which are adaptable to different scales of representation. A database design is presented which integrates multi-scale storage of point, linear and polygonal features, based on the line generalization tree, with a multi-scale surface model based on the Delaunay pyramid. The constituent vertices of topologically-structured geographical features are thus distributed between the triangulated levels of a Delaunay pyramid in which triangle edges are constrained to follow those features at differing degrees of generalization. Efficient locational access is achieved by imposing a spatial index on each level of the pyramid.  相似文献   

7.
Spatial data can be represented at different scales, and this leads to the issue of multi-scale spatial representation. Multi-scale spatial representation has been widely applied to online mapping products (e.g., Google Maps and Yahoo Maps). However, in most current products, multi-scale representation can only be achieved through a series of maps at fixed scales, resulting in a discontinuity (i.e., with jumps) in the transformation between scales and a mismatch between the available scales and users' desired scales. Therefore, it is very desirable to achieve smoothly continuous multi-scale spatial representations. This article describes an integrated approach to build a hierarchical structure of a road network for continuous multi-scale representation purposes, especially continuous selective omission of roads in a network. In this hierarchical structure, the linear and areal hierarchies are constructed, respectively, using two existing approaches for the linear and areal patterns in a road network. Continuous multi-scale representation of a road network can be achieved by searching in these hierarchies. This approach is validated by applying it to two study areas, and the results are evaluated by both quantitative analysis with two measures (i.e., similarity and average connectivity) and visual inspection. Experimental results show that this integrated approach performs better than existing approaches, especially in terms of preservation of connectivity and patterns of a road network. With this approach, efficient and continuous multi-scale selective omission of road networks becomes feasible.  相似文献   

8.
ABSTRACT

Vector-based cellular automata (VCA) models have been applied in land use change simulations at fine scales. However, the neighborhood effects of the driving factors are rarely considered in the exploration of the transition suitability of cells, leading to lower simulation accuracy. This study proposes a convolutional neural network (CNN)-VCA model that adopts the CNN to extract the high-level features of the driving factors within a neighborhood of an irregularly shaped cell and discover the relationships between multiple land use changes and driving factors at the neighborhood level. The proposed model was applied to simulate urban land use changes in Shenzhen, China. Compared with several VCA models using other machine learning methods, the proposed CNN-VCA model obtained the highest simulation accuracy (figure-of-merit = 0.361). The results indicated that the CNN-VCA model can effectively uncover the neighborhood effects of multiple driving factors on the developmental potential of land parcels and obtain more details on the morphological characteristics of land parcels. Moreover, the land use patterns of 2020 and 2025 under an ecological control strategy were simulated to provide decision support for urban planning.  相似文献   

9.
基于三维激光点云的复杂道路场景杆状交通设施语义分类   总被引：1，自引：0，他引：1  
汤涌  项铮  蒋腾平 《热带地理》2020,40(5):893-902
文章提出一种完整的全自动化处理框架,基于三维激光点云数据对高速公路和城市道路场景的杆状目标进行了检测和分类,主要包括3个步骤：数据预处理、杆状目标检测和分类。其中,在数据预处理阶段,采用基于布料模拟滤波算法自动分离地面点和非地面点,然后基于欧氏距离聚类方法对非地面点进行快速聚类,以及采用迭代图割算法进一步分割目标对象;在目标检测阶段,集成先验信息、形状信息和位置导向搭建滤波器,对杆状目标进行检测;在对象分类过程中基于多属性特征,利用随机森林分类器对目标的特征进行计算和分类。并使用3个道路场景数据集进行测试,结果显示,3个数据集的整体MCC系数为95.6%,分类准确率为96.1%。这说明文章所构建方法具有较高性能。另外,该方法还可以鲁棒地检测杆状目标的重叠区域,较为适应复杂程度不同的道路场景。  相似文献   

10.
高分辨率遥感影像提供了丰富的外观信息和空间结构信息,广泛应用于土地利用分类当中,源于文章领域的视觉词袋（Bag-of-Visual-Words,BoVW）模型现已成功应用于图像分类领域。传统的BoVW模型忽略了特征之间的空间布局信息和像素一致性信息,提出多重分割关联子特征,融合图像的外观信息、空间布局信息和像素一致性信息,实验表明该方法能够获取优于许多经典的遥感图像特征的性能。  相似文献   

11.
ABSTRACT

With large amounts of digital map archives becoming available, automatically extracting information from scanned historical maps is needed for many domains that require long-term historical geographic data. Convolutional Neural Networks (CNN) are powerful techniques that can be used for extracting locations of geographic features from scanned maps if sufficient representative training data are available. Existing spatial data can provide the approximate locations of corresponding geographic features in historical maps and thus be useful to annotate training data automatically. However, the feature representations, publication date, production scales, and spatial reference systems of contemporary vector data are typically very different from those of historical maps. Hence, such auxiliary data cannot be directly used for annotation of the precise locations of the features of interest in the scanned historical maps. This research introduces an automatic vector-to-raster alignment algorithm based on reinforcement learning to annotate precise locations of geographic features on scanned maps. This paper models the alignment problem using the reinforcement learning framework, which enables informed, efficient searches for matching features without pre-processing steps, such as extracting specific feature signatures (e.g. road intersections). The experimental results show that our algorithm can be applied to various features (roads, water lines, and railroads) and achieve high accuracy.  相似文献   

12.
ABSTRACT

The abstract classification system Nature in Norway (NiN) has detailed ecological definitions of a high number of ecosystem units, but its applicability in practical vegetation mapping is unknown because it was not designed with a specific mapping method in mind. To investigate this further, two methods for mapping – 3D aerial photographic interpretation of colour infrared photos and field survey – were used to map comparable neighbouring sites of 1 km2 in Hvaler Municipality, south-eastern Norway. The classification accuracy of each method was evaluated using a consensus classification of 160 randomly distributed plots within the study sites. The results showed an overall classification accuracy of 62.5% for 3D aerial photographic interpretation and 82.5% for field survey. However, the accuracy varied for the ecosystem units mapped. The classification accuracy of ecosystem units in acidic, dry and open terrain was similar for both methods, whereas classification accuracy of calcareous units was highest using field survey. The mapping progress using 3D aerial photographic interpretation was more than two times faster than that of field survey. Based on the results, the authors recommend a method combining 3D aerial photographic interpretation and field survey to achieve effectively accurate mapping in practical applications of the NiN system.  相似文献   

13.
Urban land use information plays an important role in urban management, government policy-making, and population activity monitoring. However, the accurate classification of urban functional zones is challenging due to the complexity of urban systems. Many studies have focused on urban land use classification by considering features that are extracted from either high spatial resolution (HSR) remote sensing images or social media data, but few studies consider both features due to the lack of available models. In our study, we propose a novel scene classification framework to identify dominant urban land use type at the level of traffic analysis zone by integrating probabilistic topic models and support vector machine. A land use word dictionary inside the framework was built by fusing natural–physical features from HSR images and socioeconomic semantic features from multisource social media data. In addition to comparing with manual interpretation data, we designed several experiments to test the land use classification accuracy of our proposed model with different combinations of previously acquired semantic features. The classification results (overall accuracy = 0.865, Kappa = 0.828) demonstrate the effectiveness of our strategy that blends features extracted from multisource geospatial data as semantic features to train the classification model. This method can be applied to help urban planners analyze fine urban structures and monitor urban land use changes, and additional data from multiple sources will be blended into this proposed framework in the future.  相似文献   

14.
ABSTRACT

Quantifying aspects of urban design on a massive scale is crucial to help develop a deeper understanding of urban designs elements that contribute to the success of a public space. In this study, we further develop the Street-Frontage-Net (SFN), a convolutional neural network (CNN) that can successfully evaluate the quality of street frontage as either being active (frontage containing windows and doors) or blank (frontage containing walls, fences and garages). Small-scale studies have indicated that the more active the frontage, the livelier and safer a street feels. However, collecting the city-level data necessary to evaluate street frontage quality is costly. The SFN model uses a deep CNN to classify the frontage of a street. This study expands on the previous research via five experiments. We find robust results in classifying frontage quality for an out-of-sample test set that achieves an accuracy of up to 92.0%. We also find active frontages in a neighbourhood has a significant link with increased house prices. Lastly, we find that active frontage is associated with more scenicness compared to blank frontage. While further research is needed, the results indicate the great potential for using deep learning methods in geographic information extraction and urban design.  相似文献   

15.
This paper introduces the concept of the smooth topological Generalized Area Partitioning (tGAP) structure represented by a space-scale partition, which we term the space-scale cube. We take the view of ‘map generalization as extrusion of data into an additional dimension’. For 2D objects the resulting vario-scale representation is a 3D structure, while for 3D objects the result is a 4D structure.

This paper provides insights in: (1) creating valid data for the cube and proof that this is always possible for the implemented 2D tGAP generalization operators (line simplification, merge and split/collapse), (2) obtaining a valid 2D polygonal map representation at arbitrary scale from the cube, (3) using the vario-scale structure to provide smooth zoom and progressive transfer between server and client, (4) exploring which other possibilities the cube brings for obtaining maps having non-homogenous scales over their domain (which we term mixed-scale maps), and (5) using the same principles also for higher dimensional data; illustrated with 3D input data represented in a 4D hypercube.

The proposed new structure has very significant advantages over existing multi-scale/multi-representation solutions (in addition to being truly vario-scale): (1) due to tight integration of space and scale, there is guaranteed consistency between scales, (2) it is relatively easy to implement smooth zoom, and (3) compact, object-oriented encoding is provided for a complete scale range.  相似文献   


16.
DEM 点位地形信息量化模型研究   总被引：2，自引：0，他引：2  
董有福  汤国安 《地理研究》2012,31(10):1825-1836
针对DEM 点位, 首先应用微分几何法对其所负载的语法信息量进行测度, 其次根据地形特征点类型及地形结构特征确定其语义信息量, 然后基于信息学理论构建了DEM 点位地形信息综合量化模型。在此基础上, 以黄土丘陵沟壑区作为实验样区, 对DEM 点位地形信息量提取方法及其在地形简化中的初步实例应用进行了探讨和验证。实验结果显示, 所提出的DEM 点位地形信息量化方案可行;基于DEM 地形信息量指数的多尺度DEM 构建方案, 具有机理明确、易于实现的特点, 并通过优先保留地形骨架特征点, 可以有效减少地形失真, 从而满足不同层次的多尺度数字地形建模和表达要求。对DEM 点位地形信息进行有效量化, 为认识DEM 地形信息特征提供了一个新的切入点, 同时为多尺度数字地形建模提供理论依据与方法支持。  相似文献   

17.
陈洪  韩峰  赵庆展  刘伟  张天毅 《干旱区地理》2017,40(6):1256-1263
棉花叶面积指数（LAI）是描述其长势的重要指标,准确获取冠层结构参数是叶面积指数反演的必要条件。以ScoutB-100油动单旋翼无人机为飞行平台,搭载RIEGL VUX-1激光雷达,精确获取棉花高密度点云数据,得到研究区棉田数字表面模型（DSM）和数字高程模型（DEM）,通过差值运算获得其冠层高度模型（CHM）,进而提取有效的冠层结构参数。利用相关性分析法选取相关系数大于0.2的激光穿透力指数（LPI）、回波点云密度（D）、孔隙率（fgap）、归一化高程值（VnDSM）构建棉花LAI反演模型,并与实测叶面积指数进行精度验证与评价。实验结果表明：模型估算的LAI与实测LAI之间的决定系数为0.824,均方根误差为0.072,验证了模型的可靠性。  相似文献   

18.
ABSTRACT

The spatio-temporal residual network (ST-ResNet) leverages the power of deep learning (DL) for predicting the volume of citywide spatio-temporal flows. However, this model, neglects the dynamic dependency of the input flows in the temporal dimension, which affects what spatio-temporal features may be captured in the result. This study introduces a long short-term memory (LSTM) neural network into the ST-ResNet to form a hybrid integrated-DL model to predict the volumes of citywide spatio-temporal flows (called HIDLST). The new model can dynamically learn the temporal dependency among flows via the feedback connection in the LSTM to improve accurate captures of spatio-temporal features in the flows. We test the HIDLST model by predicting the volumes of citywide taxi flows in Beijing, China. We tune the hyperparameters of the HIDLST model to optimize the prediction accuracy. A comparative study shows that the proposed model consistently outperforms ST-ResNet and several other typical DL-based models on prediction accuracy. Furthermore, we discuss the distribution of prediction errors and the contributions of the different spatio-temporal patterns.  相似文献   

19.
基于QuickBird卫星数据的土地利用分类规则集研究   总被引：1，自引：0，他引：1  
以天津滨海新区为实验区,研究面向对象技术的高分辨率遥感影像土地利用分类规则集。针对耕地、草地、水域、建设用地、交通运输用地、空闲地的特征差异,综合多尺度的分割特征,尝试不同的分割尺度,最终选定两个最优分割层次,即大尺度层次(分割尺度为400)和小尺度层次(分割尺度为240)。采用有效的特征参数,包括自定义的特征增强参数(NDVI参数、色度放大函数)以及最大差异特征参数、面积参数、不对称性参数、标准差参数,确定各特征的隶属度函数,最终建立分类规则集;应用该分类规则集,通过图层间信息的传递与合并,对实验区的QuickBird(QB)遥感影像进行土地利用分类,精度达86.98%,有效避免了椒盐现象。实验证明了面向对象的遥感影像分类方法可充分利用高分辨率影像丰富的信息,有效地提高分类精度。  相似文献   

20.
Artificial Intelligence (AI) models such as Artificial Neural Networks (ANNs), Decision Trees and Dempster–Shafer's Theory of Evidence have long claimed to be more error‐tolerant than conventional statistical models, but the way error is propagated through these models is unclear. Two sources of error have been identified in this study: sampling error and attribute error. The results show that these errors propagate differently through the three AI models. The Decision Tree was the most affected by error, the Artificial Neural Network was less affected by error, and the Theory of Evidence model was not affected by the errors at all. The study indicates that AI models have very different modes of handling errors. In this case, the machine‐learning models, including ANNs and Decision Trees, are more sensitive to input errors. Dempster–Shafer's Theory of Evidence has demonstrated better potential in dealing with input errors when multisource data sets are involved. The study suggests a strategy of combining AI models to improve classification accuracy. Several combination approaches have been applied, based on a ‘majority voting system’, a simple average, Dempster–Shafer's Theory of Evidence, and fuzzy‐set theory. These approaches all increased classification accuracy to some extent. Two of them also demonstrated good performance in handling input errors. Second‐stage combination approaches which use statistical evaluation of the initial combinations are able to further improve classification results. One of these second‐stage combination approaches increased the overall classification accuracy on forest types to 54% from the original 46.5% of the Decision Tree model, and its visual appearance is also much closer to the ground data. By combining models, it becomes possible to calculate quantitative confidence measurements for the classification results, which can then serve as a better error representation. Final classification products include not only the predicted hard classes for individual cells, but also estimates of the probability and the confidence measurements of the prediction.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号