共查询到19条相似文献，搜索用时 837 毫秒
1.
2.
西北旱区遥感影像分类的支持向量机法 总被引：1，自引：0，他引：1
针对较大范围、不同时相、不同气候和地貌类型的遥感影像的土地利用现状分类问题,提出了一种结合标准植被指数和纹理特征的支持向量机法。此方法改进了陕西延安、甘肃嘉峪关和青海果洛的遥感影像分类,有效地解决了最大似然法和BP神经网络法的缺陷造成的分类精度不高的问题。分类结果表明:与最大似然法和BP神经网络法相比,结合标准植被指数和纹理特征的支持向量机法的分类总精度最高(97.75%),Kappa系数为0.9691。该方法可为西北旱区遥感影像解译和土地资源可持续发展战略提供方法支撑。 相似文献
3.
BP神经网络具有收敛速度快和自学习、自适应功能强的特点,能最大限度地利用样本集的先验知识,自动提取合理的模型。本文采用Landsat TM遥感图像作为数据源,以山西省定襄县为研究区,通过主成分分析方法来压缩输入数据,并结合NDVI和纹理特征来建立BP神经网络的土地利用分类模型,将分类结果与基于光谱单元信息的神经网络分类和基于纹理特征的神经网络分类结果进行定性和定量比较分析。结果表明:该方法总精度达到了80.50%,分别比基于光谱单元信息的神经网络分类和基于纹理特征的神经网络分类提高了18.89%和6.23%,能够有效地解决地物光谱混淆、分类精度不高等问题。 相似文献
4.
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
5.
基于PCA-BPNN的多光谱遥感影像分类 总被引：7，自引：0，他引：7
基于BP算法的神经网络方法目前已广泛运用于遥感影像分类,提出一种主成分分析(PCA)与BP神经网络相结合的遥感影像分类方法——PCA-BPNN,实验证明该方法是可行并且有效的,在减少计算量和加快收敛的同时,提高了分类的精度。 相似文献
6.
基于BP神经网络高光谱图像分类研究 总被引：1，自引：0，他引：1
遥感影像常常存在"异物同谱"现象,影响了遥感影像的分类精度。为了提高分类精度,本文提出了基于BP神经网络的分类算法。采用环境一号卫星HJ-1A星上搭载的超光谱成像仪(HSI)获取的高光谱数据,利用BP神经网络对黄岛区进行遥感图像分类,根据得到的分类结果对原图像进行"异物同谱"现象纠正后重新选取训练样本,然后利用BP神经网络再分类,从而有效解决了"异物同谱"现象。实验结果表明,经处理后的高光谱影像的分类精度得到显著提高,分类总体精度为92.386 5%,比异物同谱纠正前提高了7.83%,Kappa系数也从0.768 2提升到了0.885 8。 相似文献
7.
8.
基于K-L变换的BP神经网络遥感图像分类 总被引：5，自引：1，他引：4
为了提高多光谱遥感图像的分类正确,提出了一种基于主成分分析(K-L变换)的分类方法。该方法先应用K-L变换对多波段遥感图像进行降维,提取最主要的三个成分合成假彩色图,然后利用BP神经网络对假彩色图进行监督分类。由于主成分之间是不相关的,增强了图象信息,降低了神经网络的计算量,提高了分类精度。实验结果证明,该算法分类精度优于传统分类方法,总正确率为88.5%,Kappa系数为0.862,因而具有实用价值。 相似文献
9.
为了能有效地从高分辨率遥感影像中提取地物信息,本文通过影像的光谱和纹理特征,利用BP神经网络算法进行影像分类研究。首先提取分类所需的光谱和纹理特征源,然后根据影像和地物特征,建立BP神经网络,用于样本训练和分类处理,实现地物分类。为验证该方法的可靠性,以2006年11月获取的成都平原某区域的Quickbird影像为实验数据,进行高分辨率遥感影像的地物分类实验。实验结果表明,结合影像光谱和纹理特征的BP神经网络分类算法,不仅可以有效保证BP神经网络分类训练的稳定性和收敛速度,还能达到较高的分类精度。 相似文献
10.
11.
ABSTRACTRice mapping with remote sensing imagery provides an alternative means for estimating crop-yield and performing land management due to the large geographical coverage and low cost of remotely sensed data. Rice mapping in Southern China, however, is very difficult as rice paddies are patchy and fragmented, reflecting the undulating and varied topography. In addition, abandoned lands widely exist in Southern China due to rapid urbanization. Abandoned lands are easily confused with paddy fields, thereby degrading the classification accuracy of rice paddies in such complex landscape regions. To address this problem, the present study proposes an innovative method for rice mapping through combining a convolutional neural network (CNN) model and a decision tree (DT) method with phenological metrics. First, a pre-trained LeNet-5 Model using the UC Merced Dataset was developed to classify the cropland class from other land cover types, i.e. built-up, rivers, forests. Then, paddy rice field was separated from abandoned land in the cropland class using a DT model with phenological metrics derived from the time-series data of the normalized difference vegetation index (NDVI). The accuracy of the proposed classification methods was compared with three other classification techniques, namely, back propagation neural network (BPNN), original CNN, pre-trained CNN applied to HJ-1 A/B charge-coupled device (CCD) images of Zhuzhou City, Hunan Province, China. Results suggest that the proposed method achieved an overall accuracy of 93.56%, much higher than those of other methods. This indicates that the proposed method can efficiently accommodate the challenges of rice mapping in regions with complex landscapes. 相似文献
12.
Neural network based on rough sets and its application to remote sensing image classification 总被引：2，自引：0，他引：2
WUZhaocong LIDeren 《地球空间信息科学学报》2002,5(2):17-21
This paper presents a new kind of back propagation neural network(BPNN) based on rough sets,called rough back propagation neural network (RBPNN).The architecture and training method of RBPNN are presented and the survey and analysis of RBPNN for the classification of remote sensing multi-spectral image is discussed.The successful application of RBPNN to a land cover classification illustrates the simple computation and high accuracy of the new neural network and the flexibility and practicality of this new approach. 相似文献
13.
This paper presents a new kind of back propagation neural network (BPNN) based on rough sets, called rough back propagation neural network (RBPNN). The architecture and training method of RBPNN are presented and the survey and analysis of RBPNN for the classification of remote sensing multi-spectral image is discussed. The successful application of RBPNN to a land cover classification illustrates the simple computation and high accuracy of the new neural network and the flexibility and practicality of this new approach. 相似文献
14.
本文以雷州半岛为研究区,利用Sentinel-2A影像数据和真实植被样本数据,综合探讨了机器学习中随机森林与支持向量机的分类效果,并与传统的最大似然法进行比较。提取Sentinel-2A影像9个波段、7个植被指数、72个纹理特征,通过递归特征消除法挑选了10个特征组合,并将其应用于3种分类方法中,对其分类效果进行比较。结果表明:①有效使用多种特征变量是提高植被类型识别精度的关键,就不同特征对植被类型识别的重要性而言,光谱特征与纹理特征相当且大于植被指数,三者重要性相差不大;②随机森林分类效果最佳,不但能对特征进行有效选择,而且能保证植被类型提取精度,提高运行效率;③基于随机森林特征选择的递归特征消除法得到的特征组合不能对其他分类器性能进行优化,对随机森林模型本身的优化效果也有限。 相似文献
15.
16.
Dawei Li Fengbao Yang Xiaoxia Wang 《Journal of the Indian Society of Remote Sensing》2017,45(2):229-237
High resolution remote sensing image contains abundant information, but remote sensing classification only based on spectral information is affected in the complex spectrum area. Crop area and other land-cover objects contain different texture features. This paper extracts texture information based on gray-level co-occurrence matrix and Gabor filters group, sets up spectrum-texture joint feature set. To enhance classification efficiency, Ensemble learning strategy is introduced to improve classical support vector machine and back propagation neural network classifiers in training process. To prove the effectiveness of proposed methods, several experiment images are utilized to execute experiments. Results indicate that proposed methods improve classification accuracy compared with classical algorithms significantly, and promote running efficiency compared with the situation of large sample, support corn area statistical process and yield estimation. 相似文献
17.
针对现有三维点云数据分割分类方法存在分类目标内部不一致的问题,提出一种超体素随机森林与长短期记忆神经网络（long short-term memory,LSTM）联合优化的室内点云高精度分类方法。该方法根据超体素结构具备内部特征一致性的特点,对原始点云进行超体素划分,并以超体素为基本单元进行多元特征计算,搭建室内点云超体素随机森林分类模型,实现点云数据的粗分类。在此基础上,引入LSTM对粗分类的超体素邻域连接关系进行神经网络模型训练与预测,实现超体素粗分类结果的优化。基于开放数据集对所提分类方法进行有效性和精度验证,结果显示,该方法在公开数据集中对13类要素的分类精度可达到83.2%;与经典的深度学习框架相比,该方法在小样本训练时可以达到更优的分类精度。 相似文献
18.
针对传统手工提取特征方法需要专业领域知识，提取高质量特征困难的问题，将深度迁移学习技术引入到高分影像树种分类中，提出一种结合面向对象和深度特征的高分影像树种分类方法。为了获取树种的精确边界，该方法首先利用多尺度分割技术分割整幅遥感影像，并选择训练样本作为深度卷积神经网络的输入。为了避免样本数量少导致过拟合问题，采用迁移学习方法，使用ImageNet上训练的VGG16模型参数初始化深度卷积神经网络，并利用全局平局池化压缩参数，在网络最后添加1024个节点的全连接层和7个节点的Softmax分类器，利用反向传播和Adam优化算法训练网络。最后分类整幅遥感影像，生成树种专题地图。以安徽省滁州市的皇甫山国家森林公园为研究区，QuickBird高分影像作为数据源，采用本文方法进行树种分类。试验结果表明，本文方法树种分类总体精度和Kappa系数分别为78.98%和0.685 0，在保证树种精度的同时实现了端到端的树种分类。 相似文献
19.
Shenghui Fang Yuan Le Qi Liang Xiaojun Liu 《Journal of the Indian Society of Remote Sensing》2014,42(4):733-743
The aim of this study is to estimate leaf area index (LAI) in different type of plants using vegetation indices (VIs) and neural network algorithms retrieved from MODIS data. Four VI were calculated, and neural networks were built up based on MODIS surface reflectance products. Among the tested VIs, normalized difference vegetation index (NDVI) and chlorophyll index (CI) appeared to be the best candidate indices in estimating LAI across sites with different vegetation types. The models having the highest accuracy were CI for grassland and deciduous broad leaf forest with determination coefficients (R-square above 0.70, and NDVI for crop R-square?=?0.78). Neural network showed better results than VI methods except in grassland sites. The added VI information showed no significant improvement of model accuracy for the neural networks in most sites. 相似文献