共查询到20条相似文献，搜索用时 46 毫秒
1.
科学准确地监测红树林是保护海陆过渡性生态系统的基础和前提,但红树林分布于潮间带,难以进行大规模人工监测。遥感技术能够对红树林进行长时间、大面积监测,但已有研究尚存不足。一方面,红树林分布于热带、亚热带区域,受到天气条件限制难以获得长时间覆盖的有效光学遥感数据;另一方面,红树林极易与其他陆生植被混淆,仅利用多波段数据的光谱信息难以精确识别。本文以恒河三角洲孙德尔本斯地区为例,基于谷歌地球引擎GEE（Google Earth Engine）获取2016年全年的Landsat 8 OLI和Sentinel-2 MSI数据,利用物候信息进行红树林提取研究。首先,基于最小二乘回归构建两个传感器在相同指数之间的关系,重建时间序列数据,之后根据可分性判据选取增强型植被指数EVI（Enhanced Vegetation Index）和陆地表面水分指数LSWI（Land Surface Water Index）。其次,对两个指数的时间序列数据进行Savitzky-Golay滤波处理,并分别提取生长期始期等13种物候信息。最后,将两个指数的物候信息进行特征级联,采用随机森林RF（Random Forest）方法进行分类,提取研究区红树林范围。实验结果表明：Landsat 8 OLI和Sentinel-2 MSI数据融合可有效提升时间序列质量,与基于单一传感器数据的分类结果相比,总体精度提高1.58%;物候信息可以显著增强红树林与其他植被的可分性,与直接使用时间序列数据的分类结果相比,总体精度提高1.92%;同时考虑EVI和LSWI指数可极大地提升分类效果,与采用单一指数相比,总体精度分别提高14.11%和9.69%。因此,本文通过数据融合、物候信息提取和指数特征级联可以更好地提取红树林,总体精度达到91.02%,Kappa系数为0.892。研究验证了物候信息在红树林遥感监测中的应用潜力,提出的方法对科学准确地监测全球或区域红树林具有一定参考价值。 相似文献
2.
目前普遍采用的分类器通常都是针对单一或小量任务而设计的,在小数据量的处理中能取得比较满意的结果。但对于海量遥感数据的处理,其在处理时效和分类精度方面还有待研究。本文以遥感图像场景分类任务为例,着重对遥感数据分类问题中几种典型分类方法的适用性进行比较研究,包括K近邻(KNN)、随机森林(RF),支持向量机(SVM)和稀疏表达分类器(SRC)等。分别从参数敏感性,训练样本数据量,待分类样本数据量和样本特征维数对分类器性能的影响等几个方面进行比较分析。实验结果表明:(1)KNN,RF和L0-SRC方法相比RBF-SVM,Linear-SVM和L1-SRC,受参数影响的程度更弱;(2)待分类样本固定的情况下,随着训练样本数目的增加,SRC类型分类方法的分类性能最佳,SVM类型方法次之,然后是RF和KNN,在总体分类时间上呈现出L0-SRCL1-SRCRFRBF-SVM/Linear-SVMKNN/L0-SRC-Batch的趋势;(3)训练样本固定的情况下,所有分类方法的分类精度几乎都不受待分类样本数目变化的影响,RBF-SVM方法性能最佳,其次是L1-SRC,然后是Linear-SVM,最后是RF和L0-SRC/L0-SRC-Batch,在总体分类时间上,L1-SRC和L0-SRC相比其他分类方法最为耗时;(4)样本特征维数的变化不仅影响分类器的运行效率,同时也影响其分类精度,其中SRC和KNN分类器器无需较高的特征维数即可获得较好的分类结果,SVM对高维特征具有较强的包容性和学习能力,RF分类器对特征维数增加则表现得并不敏感,特征维数的增加并不能对其分类精度的提升带来更多的贡献。总的来说,在大数据量的遥感数据分类任务中,现有分类方法具有良好的适用性,但是对于分类器的选择应当基于各自的特点和优势,结合实际应用的特点进行权衡和选择,选择参数敏感性较小,分类总体时间消耗低但分类精度相对较高的分类方法。 相似文献
3.
Automatic land cover update was an effective means to obtain objective and timely land cover maps without human disturbance. This study investigated the efficacy of multi-temporal remote sensing data and advanced non-parametric classifier on improving the classification accuracy of the automatic land cover update approach integrating iterative training sample selection and Markov Random Fields model when the historical remote sensing data were unavailable. The results indicated that two-temporal remote sensing data acquired in one crop growth season could significantly improve the classification accuracy of the automatic land cover update approach by approximately 3–4%. However, the support vector machine (SVM) classifier was not suitable to be integrated in the automatic land cover update approach, because the huge initially selected training samples made the training of the SVM classifier unrealizable. 相似文献
4.
Landsat TM数据不同辐射校正方法对土地覆盖遥感分类的影响 总被引：2，自引：0，他引：2
本文主要是探索Landsat TM数据不同辐射校正方法对土地覆盖遥感分类的影响。介绍了使用的3种不同辐射校正方法(ATCOR3、FLAASH以及查找表)和两种分类算法。在分类实验部分,根据样本的地理坐标在3景校正影像中分别采集训练样本并训练各自的分类器,并交叉用于其他辐射校正影像的土地覆盖遥感分类。实验结果表明:(1)用于分类器训练的样本采集自待分类影像时的分类精度明显高于采集自其他影像的分类精度;(2)3种辐射校正影像的分类结果存在差异,其中使用ATCOR3和FLAASH方法校正后影像的分类结果有更相近的精度;(3)辐射校正对分类类别的影响不同,其中对森林类型影响最大,对裸地等其他类别影响相对较小。 相似文献
5.
Forest cover plays a key role in climate change by influencing the carbon stocks, the hydrological cycle and the energy balance. Forest cover information can be determined from fine-resolution data, such as Landsat Enhanced Thematic Mapper Plus (ETM+). However, forest cover classification with fine-resolution data usually uses only one temporal data because successive data acquirement is difficult. It may achieve mis-classification result without involving vegetation growth information, because different vegetation types may have the similar spectral features in the fine-resolution data. To overcome these issues, a forest cover classification method using Landsat ETM+ data appending with time series Moderate-resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) data was proposed. The objective was to investigate the potential of temporal features extracted from coarse-resolution time series vegetation index data on improving the forest cover classification accuracy using fine-resolution remote sensing data. This method firstly fused Landsat ETM+ NDVI and MODIS NDVI data to obtain time series fine-resolution NDVI data, and then the temporal features were extracted from the fused NDVI data. Finally, temporal features combined with Landsat ETM+ spectral data was used to improve forest cover classification accuracy using supervised classifier. The study in North China region confirmed that time series NDVI features had significant effects on improving forest cover classification accuracy of fine resolution remote sensing data. The NDVI features extracted from time series fused NDVI data could improve the overall classification accuracy approximately 5% from 88.99% to 93.88% compared to only using single Landsat ETM+ data. 相似文献
6.
7.
面向对象的覆膜农田信息遥感表征方法 总被引：1，自引：0，他引：1
为解决复杂土地利用背景下覆膜农田信息遥感提取方法缺乏的问题,该文以河套灌区为研究区,以Sentinel-2A卫星数据为基础,结合面向对象影像分析和随机森林算法,开展了复杂土地利用背景下灌水与无灌水覆膜农田信息遥感同步提取研究。首先进行遥感影像尺度分割研究,优选出最佳分割尺度。在此基础上,提取光谱特征、纹理特征、几何特征,获取优化特征子集,并采用随机森林机器学习算法表征覆膜农田信息。研究表明,结合利用Sentinel-2A数据与OBIA方法能够有效表征覆膜农田信息,总体精度达93.03%,Kappa系数为0.91;其中,灌水覆膜农田用户精度为91.35%,制图精度为88.57%;无灌水覆膜农田用户精度为97.10%,制图精度为98.63%。研究证明了Sentinel-2A卫星数据和OBIA方法和机器学习算法在覆膜农田信息遥感表征中的应用潜力,能够为地物信息遥感表征研究中提供参考依据。 相似文献
8.
The invasion by Striga in most cereal crop fields in Africa has posed a significant threat to food security and has caused substantial socioeconomic losses. Hyperspectral remote sensing is an effective means to discriminate plant species, providing possibilities to track such weed invasions and improve precision agriculture. However, essential baseline information using remotely sensed data is missing, specifically for the Striga weed in Africa. In this study, we investigated the spectral uniqueness of Striga compared to other co-occurring maize crops and weeds. We used the in-situ FieldSpec® Handheld 2™ analytical spectral device (ASD), hyperspectral data and their respective narrow-band indices in the visible and near infrared (VNIR) region of the electromagnetic spectrum (EMS) and four machine learning discriminant algorithms (i.e. random forest: RF, linear discriminant analysis: LDA, gradient boosting: GB and support vector machines: SVM) to discriminate among different levels of Striga (Striga hermonthica) infestations in maize fields in western Kenya. We also tested the utility of Sentinel-2 waveband configurations to map and discriminate Striga infestation in heterogenous cereal crop fields. The in-situ hyperspectral reflectance data were resampled to the spectral waveband configurations of Sentinel-2 using published spectral response functions. We sampled and detected seven Striga infestation classes based on three flowering Striga classes (low, moderate and high) against two background endmembers (soil and a mixture of maize and other co-occurring weeds). A guided regularized random forest (GRRF) algorithm was used to select the most relevant hyperspectral wavebands and vegetation indices (VIs) as well as for the resampled Sentinel-2 multispectral wavebands for Striga infestation discrimination. The performance of the four discriminant algorithms was compared using classification accuracy assessment metrics. We were able to positively discriminate Striga from the two background endmembers i.e. soil and co-occurring vegetation (maize and co-occurring weeds) based on the few GRRF selected hyperspectral vegetation indices and the GRRF selected resampled Sentinel-2 multispectral bands. RF outperformed all the other discriminant methods and produced the highest overall accuracy of 91% and 85%, using the hyperspectral and resampled Sentinel-2 multispectral wavebands, respectively, across the four different discriminant models tested in this study. The class with the highest detection accuracy across all the four discriminant algorithms, was the “exclusively maize and other co-occurring weeds” (>70%). The GRRF reduced the dimensionality of the hyperspectral data and selected only 9 most relevant wavebands out of 750 wavebands, 6 VIs out of 15 and 6 out of 10 resampled Sentinel-2 multispectral wavebands for discriminating among the Striga and co-occurring classes. Resampled Sentinel-2 multispectral wavebands 3 (green) and 4 (red) were the most crucial for Striga detection. The use of the most relevant hyperspectral features (i.e. wavebands and VIs) significantly (p ≤ 0.05) increased the overall classification accuracy and Kappa scores (±5% and ±0.2, respectively) in all the machine learning discriminant models. Our results show the potential of hyperspectral, resampled Sentinel-2 multispectral datasets and machine learning discriminant algorithms as a tool to accurately discern Striga in heterogenous maize agro-ecological systems. 相似文献
9.
提出了一种基于深度学习技术的遥感分类方法，它能有效解决中分辨率影像在分类过程中出现的像元混分问题。研究选用2016年5月12日武汉市Landsat 7 ETM+遥感影像，基于GoogleNet模型中的Inception V3网络结构，借助迁移学习方法，构建出遥感分类模型，实现了对武汉市主城区4类典型地物（不透水层、植被、水体和其他用地）的自动分类提取，并将分类结果与传统最大似然分类（ML）结果进行了对比分析。研究表明：基于深度学习方法的遥感影像总体分类精度高达88.33%，Kappa系数为0.834 2，明显优于传统ML方法总体分类精度83%和Kappa系数0.755 0，而且有效抑制了地物在分类过程中出现的像元混分现象。 相似文献
10.
水稻冠层氮素含量光谱反演的随机森林算法及区域应用 总被引：5，自引：0，他引：5
利用地面实测数据构建高精度的水稻冠层氮素含量光谱反演点模型并将其进行尺度转换,实现了水稻冠层氮素含量准实时、大区域监测。以氮素光谱敏感指数作为输入变量,冠层氮素含量数据为输出变量,利用随机森林算法构建水稻冠层氮素含量高光谱反演模型,并用苏州市水稻农田验证区数据,检验模型的普适性和有效性;利用准同步的Hyperion数据,采用对输入、输出变量进行线性变换的简单尺度转换方法实现了点模型的区域应用。结果表明:基于随机森林算法的水稻冠层氮素含量高光谱反演模型可解释、所需样本少、不会过拟合、精度高(模型在实验区的预测精度为R2=0.82,验证区检验精度为R2=0.73)且具有普适性;点模型基于高光谱遥感卫星影像和尺度转换进行区域应用,精度较高(R2=0.81)。 相似文献
11.
《International Journal of Digital Earth》2013,6(2):106-132
Improvements in the acquisition of three-dimensional (3D) information from the Airborne Laser Scanner (ALS) increase its applications for studying Earth's surface. The use of ALS data in natural resource inventories is still in an experimental stage in central Europe. Here, a survey was completed in Germany, where plot-level features from LANDSAT Thematic Mapper and ALS data were applied. An automated process was developed for forest stratification using orthoimages. A genetic algorithm was applied for variable screening. Variable subsets of different sizes were employed for simultaneous predictions of structural forest attributes using the ‘Random Forest’ (RF) method. Performance was assessed by leave-one-out cross-validations on bootstrap resample data. Results indicate that the stratification of forest notably improved the results of predictions. The improvements were more obvious for the strata-related attributes. Accuracy was enhanced as the number of selected variables increased. However, parsimonious models are still essentially required for practical applications. The RF errors were slightly greater than those from least squares regression, as the non-parametric methods do not share the same mix of error components as regression. Through the combination of remote sensing and modelling, we conclude that our results are helpful for bridging the gap between regional earth observation and on-the-ground forest structure. 相似文献
12.
针对高分辨遥感影像同谱异物、同物异谱导致单一特征分类结果精度较差的问题,本文提出了多特征流形鉴别嵌入的高分辨率遥感影像分类方法。该方法首先提取高分辨率影像数据的光谱特征与LBP纹理特征;然后通过样本数据的联合光谱、纹理特征的空间距离及对应的类别信息,构建影像对象的类间图与类内图,用于学习高分辨率影像上的鉴别流形结构,保证在嵌入空间上尽可能不同地物特征分离、相同地物特征紧聚,确保相同地物光谱、纹理特征的相似性,完成光谱、纹理鉴别特征的有效提取,以充分挖掘影像特征,有效提高影像的分类精度。在GF-2遥感数据集上进行试验,结果表明本文算法可实现多特征的有效融合,分类精度均优于传统方法,可达93.41%。 相似文献
13.
针对基于像元的非监督分类方法对高空间遥感影像分类时易形成“椒盐”噪声和产生大量错分、漏分的问题,提出了一种结合L0平滑和超像素的非监督分类方法．首先采用L0算法对高空间遥感影像进行平滑操作,减少大量图像噪声及冗余信息;然后采用简单的线性迭代聚类（SLIC）超像素方法处理平滑后图像,进一步抑制椒盐现象的同时降低处理复杂度,得到初始聚类图;最后采用K-means非监督分类方法得到最终分类结果图．为验证本文提出的方法,选取3景高空间遥感影像作为实验数据．试验结果表明,采用提出的方法能准确对地物分类,且总体精度分别达到了72.46％、77.55％和78.44％,Kappa系数分别达到0.788、0.779和0.779．提出方法能有效解决分类中存在的“椒盐”现象,可提高分类精度,对高空间遥感影像分类具有一定的参考价值． 相似文献
14.
自监督学习可以不依赖样本标签对遥感影像进行特征提取,但是特征分类仍然依赖有监督方法。为了克服有监督特征分类过程的不足,实现遥感影像特征的无监督自动分类,本文提出一种融合半监督学习的无监督语义聚类方法。首先,使用自监督学习提取遥感影像特征,抽象出图像包含的高层语义信息;然后,基于特征相似度寻找每个样本最相似的近邻,使用在线聚类将相似样本聚为一类,训练一个线性分类器;最后,根据聚类结果为高置信度样本生成伪标签,构造标注样本集,使用半监督方法对模型微调。在4个公开遥感影像场景分类数据集EuroSAT、GID、AID和NWPU-RESISC45上进行验证,分类精度分别达到了94.84%、63.55%、76.42%和86.24%。本文方法结合了在线聚类和半监督学习的优点,缓解了已有方法存在的误差积累和样本利用不充分的问题,在完全不使用标注样本的情况下,充分利用自监督特征训练分类模型,对遥感影像进行场景分类,达到接近有监督学习的分类效果,具有良好的应用价值。 相似文献
15.
Landslides susceptibility maps were constructed in the Pyeong-Chang area, Korea, using the Random Forest and Boosted Tree models. Landslide locations were randomly selected in a 50/50 ratio for training and validation of the models. Seventeen landslide-related factors were extracted and constructed in a spatial database. The relationships between the observed landslide locations and these factors were identified by using the two models. The models were used to generate a landslide susceptibility map and the importance of the factors was calculated. Finally, the landslide susceptibility maps were validated. Finally, landslide susceptibility maps were generated. For the Random Forest model, the validation accuracy in regression and classification algorithms showed 79.34 and 79.18%, respectively, and for the Boosted Tree model, these were 84.87 and 85.98%, respectively. The two models showed satisfactory accuracies, and the Boosted Tree model showed better results than the Random Forest model. 相似文献
16.
高分辨率遥感影像上细节信息繁杂、干扰物普遍存在,对其进行自动化道路识别与提取的相关研究仍处在探索阶段。在道路提取过程中引入矢量数据辅助,可解决初始信息获取的困难,得到可靠性较强的训练样本。为此,提出一种矢量数据辅助下的道路提取方法,能够筛选出矢量数据中包含的有效信息,引导实现对高分辨率遥感影像的道路自动提取。利用Mean-shift滤波对图像进行预处理后,首先从矢量数据获取候选种子点,并通过提炼同质区域的形状特征剔除错误候选点;然后,自动获取负样本点以进行朴素贝叶斯分类,并采用邻域质心投票算法从分类影像提取道路中心线;最后,结合像素跟踪与方向判断矢量化道路中心线,并提出一种基于矢量几何分析的断线连接与毛刺剔除方法,对提取结果进行信息修复与规整、优化。实验结果显示,该算法的提取质量达到80%以上,且具备较强的稳健性,能够适应具有不同道路辐射和分布特征的高分辨率遥感影像。 相似文献
17.
基于深度卷积神经网络的高分辨率遥感影像场景分类 总被引：2，自引：0，他引：2
场景分类对于高分辨率遥感影像的理解和信息提取具有重要意义。传统方法利用低、中级或语义特征来对影像的场景进行判别，但是针对高分影像涵盖的细节多、类别复杂等特点，中低层特征无法对影像语义进行准确描述。本文提出了一种基于深度卷积神经网络DCNN场景分类模型。首先利用卷积层对影像的纹理、颜色等低阶特征进行提取，然后利用池化层对重要特征进行筛选，最后将提取到的特征进行组合，形成高阶语义特征，利用高阶语义特征对高分影像进行场景分类。为了解决模型的过拟合问题，使用了数据增广、正则化及Dropout提高模型的泛化能力。本文方法在UC Merced-21取得了91.33%的准确率，相比于传统方法，有效地提高了分类精度，同时证明了深度卷积神经网络在遥感影像分类领域优越性。 相似文献
18.
针对传统遥感影像解译效率较低、人力物力需求量大等问题,该文以谷歌地球引擎为依托平台,利用Landsat5TM影像,采用分类回归树算法对2010年北京市土地覆被/土地利用类型开展了解译研究,并从类型构成、类型混淆和空间一致性3个方面将解译所得LUC-2010产品与Globeland30-2010产品进行空间一致性分析。研究表明,谷歌地球引擎(GEE)平台通过编程运算,数据处理速度极快,大幅提高工作效率。解译产品与训练样本交叉验证的学习精度为94.2%。两套产品总体对比发现,林地、水体和耕地的空间一致性比率分别为84.28%、74.75%和73.56%;林地、水体和人工地表的地类纯净度分别为87.23%、77.04%和72.97%;总体分布空间一致性为74.0%。两套产品局部对比发现,LUC-2010产品分类结果更准确和精细,精度更高。 相似文献
19.
The aim of this study was to detect and map MSV using RapidEye multispectral sensor in Ofcolaco farm. To achieve this objective, the acquired RapidEye sensor was classified using the robust Random Forest algorithm. Furthermore, the variable importance technique was used to determine the influence of each spectral band and indices on the mapping accuracy. For better performance of image data, the value of the commonly used vegetation indices in improving the classification accuracy was tested. The results revealed that the use of RapidEye spectral bands in detection and mapping of MSV yielded good classification results with an overall accuracy of 82.75%. The inclusion of vegetation indices computed from RapidEye sensor improved the classification accuracies by 3.4%. The most important RapidEye spectral bands in classifying MSV were near infrared, blue and red-edge. On the other hand, the most important vegetation indices were the Soil adjusted vegetation index, Enhanced vegetation index, Red index and Normalized Vegetation Index. The current study recommends future studies to assess the importance of multi-temporal remote sensing applications in detecting and monitoring the spread of MSV. 相似文献
20.
特征空间的构建和优化对遥感图像识别能力的提高具有重要作用。针对面向对象方法对波段光谱信息利用不足,以及像元识别法无法充分利用图像空间几何等信息的问题,本文建立了新颖的联合像素级和对象级特征的航摄遥感图像城市变化检测方法。首先,充分利用像素级和对象级特征的优势,建立考虑光谱、指数、纹理、几何、表面高度及神经网络深度特征的特征空间;然后,引入LightGBM(light gradient boosting machine)算法对大量特征进行选择研究;最后,采用随机森林识别器对宜兴市2012年和2015年两期遥感图像进行识别,利用变化矩阵进行城市的变化检测。结果表明:联合像元、深度、对象特征和LightGBM特征选择算法的识别效果最好,平均的总体识别精度达到了88.50%,Kappa系数达到0.86,比基于像元、深度或对象特征的识别方法分别提高了10.50%、15.00%和4.00%;城市变化检测精度达到了87.50%。因此,本文方法是利用甚高分辨率航摄遥感图像进行城市变化的检测的有效方法。 相似文献