共查询到20条相似文献,搜索用时 15 毫秒
1.
海底底质分类对于海洋资源开发与利用、海洋科学研究等多方面具有重要意义。目前,多波束探测是实现大范围海底底质分类的有效手段之一,通常基于多波束反向散射强度提取角度响应(AR)特征及反向散射图像特征进行底质分类。由于特征来源较单一,分类器结构简单,往往分类精度不高。为此,本文提出了一种基于深层卷积神经网络(CNN)的多波束海底底质分类方法。除反向散射强度特征外,还利用地形特征,将特征向量转换为波形图,再输入卷积神经网络进行训练和分类。试验对比不同特征组合以及BP网络、支持向量机(SVM)、K近邻(KNN)、随机森林(RF)4种常规分类器,本文模型算法总体分类精度达到94.86%,Kappa系数为0.93,精度具有明显优势,效率也比较高。表明该方法有效利用两种数据类型所蕴含的海底底质信息,充分发挥卷积神经网络权值共享、高效率等特点,实现高分辨率海底底质分类,可对海底底质分类研究提供参考。 相似文献
2.
3.
4.
联合卷积神经网络与集成学习的遥感影像场景分类 总被引:1,自引:0,他引:1
针对人工设计的中、低层特征难以实现复杂场景影像的高精度分类以及卷积神经网络依赖大量训练数据等问题,结合迁移学习与集成学习,提出了一种联合卷积神经网络与集成学习的遥感影像场景分类算法。首先基于迁移学习的思想,利用在自然影像数据集上训练好的多个深层卷积神经网络模型作为特征提取器,提取图像多个高度抽象的语义特征;然后构建由Logistic回归和支持向量机组成的Stacking集成模型,对同一图像的多个特征分别训练Logistic模型,将预测概率结果融合构建概率特征;最后利用支持向量机对概率特征训练和预测,得到场景影像的分类结果。利用UCMerced_LandUse和NWPU-RESISC 45两种不同规模的遥感影像数据集进行试验,即使在只有10%的数据作为训练样本情况下,本文方法能够分别达到90.74%和87.21%的分类精度。 相似文献
5.
Classification of very high resolution imagery (VHRI) is challenging due to the difficulty in mining complex spatial and spectral patterns from rich image details. Various object-based Convolutional Neural Networks (OCNN) for VHRI classification have been proposed to overcome the drawbacks of the redundant pixel-wise CNNs, owing to their low computational cost and fine contour-preserving. However, classification performance of OCNN is still limited by geometric distortions, insufficient feature representation, and lack of contextual guidance. In this paper, an innovative multi-level context-guided classification method with the OCNN (MLCG-OCNN) is proposed. A feature-fusing OCNN, including the object contour-preserving mask strategy with the supplement of object deformation coefficient, is developed for accurate object discrimination by learning simultaneously high-level features from independent spectral patterns, geometric characteristics, and object-level contextual information. Then pixel-level contextual guidance is used to further improve the per-object classification results. The MLCG-OCNN method is intentionally tested on two validated small image datasets with limited training samples, to assess the performance in applications of land cover classification where a trade-off between time-consumption of sample training and overall accuracy needs to be found, as it is very common in the practice. Compared with traditional benchmark methods including the patch-based per-pixel CNN (PBPP), the patch-based per-object CNN (PBPO), the pixel-wise CNN with object segmentation refinement (PO), semantic segmentation U-Net (U-NET), and DeepLabV3+(DLV3+), MLCG-OCNN method achieves remarkable classification performance (> 80 %). Compared with the state-of-the-art architecture DeepLabV3+, the MLCG-OCNN method demonstrates high computational efficiency for VHRI classification (4–5 times faster). 相似文献
6.
栅格DEM微地形分类是数字地形精细化应用的基础,基于规则化知识的栅格DEM微地形分类方法存在自动化程度低、分类残缺等问题。本文利用BP神经网络的优势构建了栅格DEM微地形分类的人工智能方法与实现途径。以山体部位分类为微地形分类典型样例进行试验验证与分析,试验结果表明,栅格DEM微地形分类的BP神经网络法较已有的地形因子叠加分析方法存在明显优势,不仅在流程上可避免烦琐的数据叠加分析过程,而且分类结果的完整性和错分率都得到有效改善;在山体部位分出的6种微地形中,冲积地对该方法适应性最强,准确率为100%,背坡的适应性最弱准确率为89.23%。 相似文献
7.
8.
针对BP神经网络在遥感影像分类中存在易陷入局部极值和单一影像特征缺乏有效地物判别信息的问题,该文提出了一种遗传算法(GA)结合指数粒子群算法(ExpPSO)优化BP神经网络的多特征融合遥感影像分类方法(GA-ExpPSO-BP).该方法将设计的基于指数函数的ExpPSO与GA结合构建GA-ExpPSO算法,利用GA-ExpPSO算法对BP神经网络的权阈值进行初始寻优从而构建GA-ExpPSO-BP模型.以高分二号、资源三号遥感影像为实验数据,通过制作多特征融合数据集训练及实验验证.结果 表明:该方法的类别精度、总体精度和Kappa系数均最高,且训练耗时和误差最小,能有效改善影像的分类效果,提高分类效率和精度. 相似文献
9.
实时地图匹配技术在智能交通、自动驾驶等领域起着关键作用.现有实时地图匹配算法在高架、立交道路等复杂场景受到平行道路的干扰,匹配正确率较低.针对这一问题,本文提出了一种利用与车辆轨迹同步采集的图像对行驶场景进行分类,从而辅助城市复杂道路环境下地图匹配的方法.该方法在车辆靠近高架区域时利用图像对车辆行驶场景进行分类,结合车辆行驶方向、轨迹点与路段的距离、匹配路段邻接性等指标,对当前轨迹点进行实时匹配.以上海市三段高频采集的轨迹数据为例进行试验,使用匹配率、召回率、精确率等指标对结果进行精度评价.结果表明,本文方法的平均匹配率、召回率和精确率达到96.86%、97.17%、93.46%,优于传统实时匹配方法;对原始轨迹进行降采样后,匹配率、召回率、精确率等指标保持稳定.比较高架道路、立交等复杂场景的匹配效果,以及对比单点匹配耗时、延时和内存占用情况,本文方法均能保持较好的匹配结果. 相似文献
10.
针对基于人工提取特征的传统分类方法无法有效表达高空间分辨率遥感影像高层语义信息,且需要大量高质量训练数据,而带标签样本数据匮乏的问题。迁移学习运用已有知识对不同但相关领域问题进行求解,可有效解决目标领域中仅有少量标签样本数据的学习问题。该文提出利用迁移学习,基于卷积神经网络的深度学习模型进行高分影像场景分类。首先,基于ImageNet预训练的卷积神经网络Inception-v3模型提取高分影像数据的特征向量;然后,将特征向量作为输入数据训练一个新的单层全连接神经网络,经少量带标签影像场景数据训练后得到最终分类结果。该方法在UC Merced、AID和Wuhan 7类场景影像数据集上分别取得99%、93.3%和96.6%的准确率,相比已有方法,有效提高高分影像场景分类精度,同时说明知识迁移在高分影像场景分类领域的可行性。 相似文献
11.
12.
针对互联网媒体数据中地名信息表达不规范、实体边界不清晰、地名简化表达问题,该文提出了一种混合神经网络的中文地名识别方法.通过ALBERT层学习字级别特征表达与BiLSTM层提取文本上下文语义特征,由CRF层获得全局最优标记序列,更有效地识别并提取中文地名.数据测试表明:相较于BiLSTM的地名识别模型,本文模型精确率提高12.89%,F1值提高10.83%;相较于BiLSTM-CRF的地名识别模型,本文模型精确率提高3.56%,F1值提高2.1%;相较于ALBERT-CRF的地名识别模型,本文模型精确率提高1.22%,F1值提高0.72%. 相似文献
13.
云模型是用自然语言值表示的某个定性概念与其定量表示之间的不确定性转换模型,RBF神经网络已经广泛应用于遥感影像分类。考虑到传统的RBF神经网络分类技术不能有效表达影像分类过程中存在的不确定性、难以自适应地确定隐含层神经元,本文提出了一个基于高维云模型和改进RBF神经网络的不确定性分类技术。利用高维正态云创建隐含层神经元,使RBF神经网络能充分表达影像分类过程中存在的不确定性。通过峰值法云变换和高维云算法自适应地确定最优隐含层神经元。通过基于概率的权值确定和频率阈值调整,进一步优化RBF神经网络的结构。实验表明,本文提出的方法有较高的分类精度,分类结果基本上与人眼目视解译一致。 相似文献
14.
15.
基于卷积神经网络的高光谱图像分类是当前的研究热点,先后发展了空洞卷积、可形变卷积等先进模型。然而,现有可形变卷积只在空间维偏移,忽略了高光谱图像光谱之间的差异信息。为此,本文将可形变卷积从空间维扩展到光谱维,设计了光谱可形变卷积,提出了光谱可形变卷积网络SDCNN (Spectral Deformable Convolutional Neural Network)。首先,利用全连接层学习光谱可形变卷积的偏移量,采用线性差值对图像光谱维进行特征校准;其次,采用多层1×1卷积进行光谱维特征聚合;最后,使用三维卷积层提取光谱—空间联合特征。不同于空间可形变卷积,光谱可形变卷积只在光谱维上进行偏移,可以为不同类别选择更合适的特征波段,提升模型的判别性。在国际通用测试数据Indian Pines、University of Pavia以及University of Houston上进行了实验,结果表明:本文提出的SDCNN方法优于其他深度学习方法,在相同样本条件下取得了更高的分类精度,总体精度达到了98.86%(Indian Pines,10%/类)、99.81%(University of P... 相似文献
16.
Chengyi Liu Renjian Zhai Haizhong Qian Xianyong Gong Andong Wang Fang Wu 《Transactions in GIS》2023,27(3):752-776
Various geological factors shape drainage patterns. Identifying drainage patterns is a classic problem in topographical knowledge mining and map generalization. Existing rule-based methods rely heavily on the parameter settings of cartographers for drainage-pattern recognition. These methods effectively identify drainage patterns in specific areas but require manual parameter tuning to identify drainage patterns in other areas. Owing to the complexity of topological and geometric characteristics, drainage pattern recognition involves nonlinear problems, and it is difficult to build mapping relationships between characteristics and patterns using rule-based methods. Therefore, we proposed a data-driven method based on a graph convolutional neural network to avoid heavy reliance on human experience and automatically mine implicit relationships between characteristics and drainage patterns. First, six typical drainage patterns (dendritic, rectangular, parallel, trellis, reticulate, and fanned) were listed based on map specifications, and the unique characteristics of each drainage pattern were illustrated. Subsequently, the drainage graphs were constructed. The characteristics of the whole, local, and individual units in the drainage networks were quantified based on drainage vector data. Finally, an identification model was developed using graph convolution, self-attention pooling, and multiple fully connected layers for drainage pattern recognition. After training and testing, the accuracy of our model (0.801 ± 0.014) was better than that of the rule-based method (0.572 ± 0.000) and the traditional machine learning methods (less than 0.733 ± 0.016). The results demonstrate that the ability of our model to identify drainage patterns surpasses that of other methods. 相似文献
17.
基于K-L变换的自组织竞争神经网络在海底底质分类中的应用 总被引:1,自引:0,他引:1
针对海底质地的特点,利用灰度纹理共生矩阵作为特征参数,K-L变换对海底底质图像进行降维,采用自组织竞争神经网络对图像进行自动分类,对各分类方法精度进行对比。以海底侧扫声纳图像为例,通过实测数据验算,取得理想的效果。 相似文献
18.
Improving neural network performance on the classification of complex geographic datasets 总被引:4,自引:0,他引:4
Neural Networks are now established computational tools used for search minimisation and data classification. They offer
some highly desirable features for landuse classification problems since they are able to take in a variety of data types,
recorded on different statistical scales, and combine them. As such, neural networks should offer advantages of increased
accuracy. However, a barrier to their general acceptance and use by all but `experts' is the difficulty of configuring the
network initially.
This paper describes the architectural problems of applying neural networks to landcover classification exercises in geography
and details some of the latest developments from an ongoing research project aimed at overcoming these problems. A comprehensive
strategy for the configuration of neural networks is presented, whereby the network is automatically constructed by a process
involving initial analysis of the training data. By careful study of the functioning of each part of the network it is possible
to select the architecture and initial weights on the node connections so the constructed network is `right first time'. Further
adaptations are described to control network behaviour, to optimise functioning from the perspective of landcover classification.
The entire configuration process is encapsulated by a single application which may be treated by the user as a `black box',
allowing the network to the applied in much the same way as a maximum likelihood classifier, with no further effort being
required of the user. 相似文献
19.
M. R. Mosavi 《GPS Solutions》2006,10(2):97-107
Position information obtained from standard global positioning system (GPS) receivers has time variant errors. For effective use of GPS information in a navigation system, it is essential to model these errors. A new approach is presented for improving positioning accuracy using neural network (NN), fuzzy neural network (FNN), and Kalman filter (KF). These methods predict the position components’ errors that are used as differential GPS (DGPS) corrections in real-time positioning. Method validity is verified with experimental data from an actual data collection, before and after selective availability (SA) error. The result is a highly effective estimation technique for accurate positioning, so that positioning accuracy is drastically improved to less than 0.40 m, independent of SA error. The experimental test results with real data emphasize that the total performance of NN is better than FNN and KF considering the trade-off between accuracy and speed for DGPS corrections prediction. 相似文献