共查询到20条相似文献，搜索用时 31 毫秒
1.
S. Rajesh S. Arivazhagan K. Pratheep Moses R. Abisekaraj 《Journal of the Indian Society of Remote Sensing》2012,40(2):313-324
Texture in high resolution satellite images requires substantial improvement in the conventional segmentation algorithms.
The use of wavelet packet transforms for texture analysis and image classification of high spatial resolution LISS IV imagery
provide more details about the urban areas. This paper analyses the performance of a combination of Wavelet Packet Statistical
Features (WPSFs) and Wavelet Packet Co-occurrence Features (WPCFs) for the classification of LISS IV images. The classification
accuracy per pixel is improved in this paper by varying the window size. Four indices—user’s accuracy, producer’s accuracy,
overall accuracy and kappa co-efficient are used to assess the accuracy of the classified data. Experimental results show
that a multi-band and multi-level wavelet packet approach can be used to drastically increase the classification accuracy. 相似文献
2.
E. P. Nobi E. Dilipan K. Sivakumar T. Thangaradjou 《Journal of the Indian Society of Remote Sensing》2012,40(3):467-481
Seagrasses ecosystems are fragile yet highly productive ecosystems of the world showing declining trend throughout the world due to natural and anthropogenic pressures. Effective conservation and management plan is thus required to protect these resources, to aid with conservation need mapping and monitoring of seagrasses using high resolution remote sensing data is very much required. Hence, the present study was made to record the seagrass aerial cover in the Lakshadweep islands using IRS P6 LISS IV satellite data. The suitability of LISS IV sensor for seagrass mapping was tested for the first time with an overall accuracy of 73.16%. The study found an area of 2590.2?ha of seagrasses in Lakshadweep islands with 1310.8?ha and 1279.4?ha dense and sparse seagrass cover respectively. The study recommends the use of LISS IV data for mapping the shallow water seagrasses, as mapping efficiency increases nearly 4 times more than the LISS III data, as the former (LISS IV) picks up the small patches of seagrasses and delineates the coral and reef vegetation patches from seagrass class. 相似文献
3.
Peijun Du Yu Chen Junshi Xia Kun Tan 《Journal of the Indian Society of Remote Sensing》2013,41(2):213-222
In this paper, we propose a novel scheme to improve the accuracy of remote sensing image classification by integrating data fusion, multiple feature combination and ensemble learning. Intensity-Hue-Saturation (IHS), Gram-Schmidt (GS), Brovey and wavelet fusion methods are first performed to obtain the optimal fusion images of high resolution and multispectral images. Support Vector Machine (SVM) classifier is then adopted to classify the fused image with different feature sets, and ensemble learning algorithm based on dynamic classifier selection (DCS) is finally used to integrate multiple classification maps. The proposed classification scheme is implemented with three remote sensing data sets, obtaining the highest overall accuracy and kappa coefficient in all cases (92.63% and 0.8917 for BJ-1 data set, 81.89% and 0.7513 for Landsat TM and SPOT4 data set, 92.21% and 0.8838 for ALOS data set respectively). The experimental results show that the integration of data fusion, feature combination and ensemble learning improves the classification performance obviously and has great potential in practical uses. 相似文献
4.
基于分类规则挖掘的遥感影像分类研究 总被引：6，自引：0，他引：6
分析了目前遥感影像的统计分类、神经网络分类及基于符号知识的逻辑推理分类方法的优缺点.以GIS为平台,构建了多源空间数据库,将数据挖掘的思想和方法引入遥感影像分类中,提出了面向分类规则挖掘的遥感影像分类框架.针对遥感光谱数据及其他空间数据的特点,定义了连续属性样本分类概念和分割点评价指标,提出了一种新的连续属性样本分类规则挖掘算法.选择一个试验区,采用该算法分别对遥感光谱数据、遥感光谱和DEM数据相结合的数据进行分类规则挖掘、遥感影像分类和分类精度比较.结果表明：（1）该算法具有较高的分类精度;（2）加入DEM等与分类相关的其他空间数据可以提高遥感影像的分类精度.通过挖掘分类规则进行遥感影像分类,扩展了基于知识的逻辑推理分类方法中知识获取渠道,提高了分类规则获取的智能化程度.新的连续属性样本分类规则挖掘算法,扩展了归纳学习算法对连续属性样本分类的适应性. 相似文献
5.
基于再生核Hilbert空间小波核函数支持向量机的高光谱遥感影像分类 总被引：1，自引：0，他引：1
针对支持向量机用于高光谱遥感影像分类存在的分类精度不高、参数选择困难等问题,提出一种再生核Hilbert空间的小波核.其可以逼近任意非线性函数,能够有效改进参数估计的效果,进而实现基于再生核Hilbert空间的小波核函数支持向量机(小波支持向量机).并选取北京昌平地区的国产高光谱数据operational modula... 相似文献
6.
基于小波与遗传算法的特征提取与特征选择 总被引：5，自引：0，他引：5
高维遥感数据的分类与识别与传统的多光谱遥感分类技术具有明显的区别。本文提出了一种基于遗传算法和小波／小波包分析相结合的特征提取方法用于高维遥感数据降维与分类。该方法综合了遗传算法的全局优化和小波／小波包分析的多尺度、多分辨率的特点。首先,通过离散的小波变换(DWT)或小波包变换(WP)将高光谱信号变换到特征域进行光谱分解。由于DWT变换是一种线性变换,不同尺度的DWT系数可作为线性光谱特征。然后,对这些线性光谱特征利用遗传算法结合训练样本计算类内／类间距离搜索最优分类子集,其具体染色体编码取可能的特征号,适应度函数基于样本平均Jeffries-Matusita距离计算。所用的分类器采用最大似然分类器。试验结果表明该方法与常规特征提取算法如主成分变换(PCA)、判别分析特征提取(DAFE)、决策边界特征提取(DBFE)相比,能提高分类精度约1.1％-6.5％。 相似文献
7.
Automatic change detection of land cover features using high-resolution satellite images, is a challenging problem in the field of intelligent remote sensing data interpretation, and is becoming more and more effective for its applications viz. urban planning and monitoring, disaster assessment etc. In the present study, a change in detection approach based on the image morphology that analyses change in the local image grids is proposed. In this approach, edges from both the images are extracted and grid wise comparison is made by probabilistic thresholding and power spectral density analysis for identifying change area. One of the advantages of the proposed methodology is that the temporal images used in the change analysis need not be radiometrically corrected as analysis is based on edge extractions. The grid-based analysis further reduces the error, which might have been introduced by image mis-registration. The proposed methodology is validated by finding the temporal changes in the linear land cover features in parts of Kolkata city, India using three different image data-sets from LISS IV, Cartosat-1 and Google earth having varied spatial resolutions of 5.8 m, 2.5 m and about 1 m, respectively. The overall accuracy in identifying changes is found to be 64.82, 73.86 and 80.93% for LISS IV, Cartosat-1 and Google earth data-set, respectively. 相似文献
8.
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
9.
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
10.
J. Krishnamurthy 《国际地球制图》2013,28(3):39-52
In order to evaluate the potentials of IRS‐1A Linear Imaging Self‐scanning Sensor (LISS‐I) data for geological and geomorphological applications and also to compare the IRS‐1A LISS‐I data with Landsat Thematic Mapper (TM) data, a study has been attempted for parts of Uttar Pradesh and Madhya Pradesh in Northern India. The first four spectral bands of Landsat TM sensor data which are similar and close to IRS‐1A LISS‐I senor have been utilised for the comparative evaluation. Various techniques employed for both the data set to derive the required geology and geomorphology related information include (i) band combination (ii) spectral response analysis (iii) principal component analysis (iv) supervised classification techniques and (v) visual observation of various outputs generated by the above methods. The Optimum Index Factor (OIF) method adopted for selecting suitable band combinations showed similar OIF rankings for IRS‐1A LISS‐I data and Landsat TM data. It has been visually observed that the band combination 1, 3 & 4 offers relatively better feature display. The spectral responses derived for various major geologic rock units such as Deccan Trap, Vindhyan Formation, Bundelkhand Granite and for a few landcovers such as surface water bodies and black soil show striking similarity in pattern for both LISS‐I and TM. The Principal Component (PC) analysis of both data sets suggested that the total scene brightness tends to dominate in the first PC. The percentage information contributed by PCs 1&2 as also by PCs 1,2 & 3 in both the LISS‐I and TM are comparable. It was observed from the classified image generated by performing supervised classification with a maximum likelihood algorithm that major geomorphic landforms were clearly distinguishable. Thus the qualitative and quantitative evaluation of both IRS‐1A LISS‐I and Landsat TM data showed that significant similarities exist between them. The study also revealed that IRS‐1A LISS‐I data can be effectively used for deriving geology and geomorphology related details. 相似文献
11.
Belkacem Marir Mahdi Kalla Fouzi Douak Abdelhamid Daamouche 《Journal of the Indian Society of Remote Sensing》2018,46(4):515-529
In this work, we present a new strategy of active learning, based on a modular version of support vector machine (MSVM) applied to urban remote sensing images in Algeria. In general, the training set is highly imbalanced, which gives more complex models; this difficulty is solved by dividing the problem at hand into a set of sub-problems, where each sub-model could be simpler to solve. The support vector machine is introduced to solve the problem of classification based on image remote sensing data related to atmospheric conditions and illumination reflectance. The aim of the proposed method is to improve the accuracy in order to understand the correlated elements of urban structures (the site, the built, the parcels, the network, the space), to generate the final classification result. In particular, we propose a new method based on the modular support vector machine (MSVM) adopted to active learning method, using three different clustering methods (i) k-means, (ii) fuzzy c-means (FCM), and (iii) Gustafson–Kessel (GKclust). Experimental results obtained on two QuickBird multispectral images of Sétif and Batna cities in the eastern of Algeria confirm the capabilities of the proposed methods based on the ensemble of model trained with different task decomposition compared to a traditional model using active learning. This method improves each class presents a main register in urban structure tissues. 相似文献
12.
基于小波理论的遥感图像高保真压缩方法研究 总被引：16，自引：2，他引：14
根据遥感图像局部相关性较弱、纹理复杂丰富的特点,提出了基于小波分析理论的自适应标量、矢量混合量化压缩方法。该方法根据遥感图像小波变换后高频子图的局部块纹理强弱将这些块划分为４类,对平坦块进行高倍压缩,对纹理块进行高保真压缩,使各块的恢复误差大致平衡。其主要特点是避免了矢量编码过程中的码书训练和码书搜索,因而时间性能好,并且对单幅图像的压缩比和峰值信噪比（ＰＳＮＲ）优于ＪＰＥＧ方法。此方法与ＫＬ变换去波段相关技术相结合,应用于多波段遥感图像压缩领域,收到了良好的效果。 相似文献
13.
This study investigates the potential of multi-temporal signature analysis of satellite imagery to map rice area in South
24 Paraganas district of West Bengal. Two optical data (IRS ID LISS III) and three RADARSAT SAR data of different dates were
acquired during 2001. Multi-temporal SAR backscatter signatures of different landcovers were incorporated into knowledge based
decision rules and kharif landcover map was generated. Based on the spectral variation in signature, the optical data acquired
during rabi (January) and summer (March) season were classified using supervised maximum likelihood classifier. A co-incidence
matrix was generated using logical approach for a combined “rabi-summer” and “kharif-rabi-summer” landcover mapping. The major
landcovers obtained in South 24 Paraganas using remote sensing data are rice, water, aquaculture ponds, homestead, mangrove,
and urban area. The classification accuracy of rice area was 98.2% using SAR data. However, while generating combined “kharif-rabi-summer”
landcovers, the classification accuracy of rice area was improved from 81.6% (optical data) to 96.6% (combined SAR-Optical).
The primary aim of the study is to achieve better accuracy in classifying rice area using the synergy between the two kinds
of remotely sensed data. 相似文献
14.
Chihda Wu Chichuan Cheng Hannchung Lo Yeongkeung Chen 《International Journal of Applied Earth Observation and Geoinformation》2010
This study focuses on using remote sensing techniques to estimate the evapotranspiration cover coefficient (CV) which is an important parameter for stream flow. The objective is to derive more accurate stream flow from the estimated CV. The study area is located in the Dan-Shuei watershed in northern Taiwan. The processes include the land-use classification using hybrid classification and four Landsat-5 TM images; the CV estimations based on remote sensing and traditional approaches; comparison of stream flow simulation according to the above two CV values. The result indicated that the study area was classified into seven land-use types with 88.3% classification accuracy. The simulated stream flow using remote sensing approach could represent more accurate hydrological characteristics than a traditional approach. Obviously integrating remote sensing technique and the SEBAL model is a useful approach to estimate the CV. The CV parameter estimated by remote sensing technique did improve the accuracy of the stream flow simulation. Therefore, the results can be extended to further studies such as forest water management. 相似文献
15.
16.
遥感成像过程中,地面、大气等诸多要素的不确定性和波段之间的相关性等原因影响了分类精度,导致变化检测的不准确性。为了提高分类精度往往需要引入先验知识。贝叶斯网络是一种新的数据表达和推理模型,对数据没有严格的正态分布前提要求,通过动态地调整先验概率密度,能有效提高分类精度。以北京通州地区1996-05-29和2001-05-19两个时相的陆地卫星Landsat TM遥感影像为例,介绍了基于贝叶斯网络的分类算法,并在此基础上实现了两个时相遥感影像的变化检测。实验结果表明:基于贝叶斯网络分类算法的后分类比较变化检测方法是遥感影像变化检测的一种新的有效方法。 相似文献
17.
高分辨率遥感影像地物复杂,分类难度大,而深度学习方法可以提取地物更多更深层次的特征信息,适用于高分辨率遥感影像的地物分类。本文研究对高分辨率影像中不透水地面、建筑、低矮植被、树、车辆等地物的高精度分类。结合遥感多地物分类的特点,以DeepLab v3+网络模型为基础,提出E-DeepLab网络模型。主要改进为：（1）改进编码器和解码器的结合方式,使用简洁有效的加成连接方式。（2）缩小单次上采样倍数,增加上采样层,提高编码器与解码器连接的紧密性。（3）使用改进的自适应权重损失函数,自动调节地物损失权重。同时根据数据特点,提出结合DSM、NDVI数据等多通道训练方式。使用两个地区数据进行实验,结果表明,两地区精度均明显优于原始DeepLab v3+模型和其他相关模型,Potsdam地区总体提取精度达到93.2%,建筑物提取精度达到97.8%,Vaihingen地区总体提取精度达到90.7%,建筑物提取精度达到96.3%。目视对比分类图和标准标记图,两者具有高度的一致性。本文所提出的E-DeepLab网络在高分辨率遥感影像地物高精度提取和分类中有较好的应用价值。 相似文献
18.
针对南方复杂地区水稻遥感信息提取研究中机器自动学习分类研究较少、分类精度不高的问题,以福建省三明市建宁县溪口镇为研究区,基于GF-1号卫星影像,采用面向对象的随机森林遥感分类算法对研究区内水稻田信息进行提取。首先通过优化面向对象分割参数和随机森林分类模型参数,提取并调用了影像中的多种特征;再对光谱特征、植被指数特征、纹理特征、几何特征进行特征空间优选;最后通过设置4种特征优选试验进行对比,得到最优分类模型。实验结果显示,基于特征空间优选的面向对象随机森林分类算法的水稻提取精度高达90%,分类总体精度可达87%,Kappa系数为0.85;与其他试验结果相比,漏分和误分现象较少,实现了南方地区水稻信息高精度自动识别。该方法计算特征少、实现简便,对于国产高分卫星影像在南方复杂地区作物自动提取中的应用具有参考性。 相似文献
19.
20.
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