检索结果-内蒙古大学图书馆

object classification of Aerial Images With Bag-of-Visual Words

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2010年第2期7卷 366-370页

作者： Xu, Sheng Fang, Tao Li, Deren Wang, Shiwei Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai 200240 Peoples R China Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China

This letter presents a Bag-of-Visual Words (BOV) representation for object-based classification in land-use/cover mapping of high spatial resolution aerial photograph. The method is introduced to handle the special characteristics of aerial images, i.e., variability of spectral and spatial content. Specifically, patch detection and description are used to divide and represent various subregions of objects comprising multiple homogeneous components. Moreover, the BOV representation is constructed with the statistics of the occurrence of visual words, which are learned from the training data set. A combination of spectral and texture features is verified to be a satisfactory choice through the evaluations of various patch descriptors. Furthermore, a threshold-based method is employed to reduce the impact of outliers on classification in test data. Experiments based on aerial-image data set show that the proposed BOV representation yields better classification performance than the low-level features, such as the spectral and texture features.

关键词： Bag-of-Visual Words (BOV) composite object low-level features object-based classification

来源：评论

学校读者我要写书评

暂无评论

Pixel, object and hybrid classification comparisons

引用

JOURNAL OF SPATIAL SCIENCE 2010年第1期55卷 43-54页

作者： Bernardini, A. Frontoni, E. Malinverni, E. S. Mancini, A. Tassetti, A. N. Zingaretti, P. Polytech Univ Marche Fac Engn DARDUS Ancona Italy Polytech Univ Marche Fac Engn DIIGA Ancona Italy

The choice of the best classification approach for thematic map generation relies on many factors, such as image resolution and minimum mapping unit The generalized GIS-ready pi ducts derived from the results of pixel-based approaches and the availability of higher-resolution imagery have directed research towards object-based classification approaches In this paper we present the superior performance of a hybrid methodology that combines the results of automatic segmentation with the land cover in derived from a pixel classification by means of the Winner Takes All (WTA) algorithm Land use and land cover results obtained though this hybrid classification approach are compared with those of a One Against All (OAA) object-oriented classification approach

关键词： pixel-based classification object-based classification thematic map Winner Takes All (WTA) algorithm One Against All (OAA) algorithm stability map land use/land cover (LULC)

来源：评论

学校读者我要写书评

暂无评论

Divergent crop mapping accuracies across different field types in smallholder farming regions

引用

International Journal of Applied Earth Observation and Geoinformation 2025年 139卷

作者： Huang, Xin Vrieling, Anton Dou, Yue Li, Xueying Nelson, Andrew Faculty of Geo-Information Science and Earth Observation (ITC) University of Twente Enschede 7500 AE Netherlands Department of Physical Geography and Ecosystem Science Lund University Sölvegatan 12 Lund SE-223 62 Sweden

Accurately mapping crop types in smallholder farming regions is crucial for monitoring crop dynamics and estimating production but remains challenging, especially over large extents. Remote sensing based crop mapping studies in smallholder farming regions often focus on major crops and the challenge of mapping small fields. However, minor but possibly emerging crops are often overlooked, nor is the impact of environmental factors, such as water stress, on mapping accuracy considered. This study addresses these gaps by categorizing crop fields into different types and assessing mapping accuracy for both major and minor crops within each field type. We first categorized crop fields into four field types (big/small fields with/without water stress) based on field size and the shortwave infrared water stress index (SIWSI) derived from Sentinel-2 (S2). Crop mapping accuracies for different field types and crops (maize as a major crop and soybean as a minor crop) were compared at pixel-based (PB) and object-based (OB) levels using random forest classification applied to S2 and two additional publicly accessible multispectral datasets (PlanetScope with four bands (PS4) and eight bands (PS8)). The season-averaged SIWSI (SIWSI_mean) provided a useful categorization of field types, as it is sensitive to mapping accuracy and is independent from field size. based on S2 data, big fields without water stress can be most accurately mapped (F1-score = 0.89 for maize and 0.85 for soybean), followed by small fields without water stress (0.85 and 0.68) and big fields with water stress (0.82 and 0.59), while small fields with water stress are the most challenging type (0.77 and 0.37). Despite that the use of PS8 data with higher spatial resolution and OB classification improved mapping accuracy for small soybean fields with water stress, limitations to map such fields remain (F1-score < 0.50). This study provides a new perspective on crop type mapping in smallholder farming r

关键词： Balanced random forest Crop classification object-based classification PlanetScope Smallholder farming

来源：评论

学校读者我要写书评

暂无评论

The use of logistic model tree (LMT) for pixel- and object-based classifications using high-resolution WorldView-2 imagery

引用

GEOCARTO INTERNATIONAL 2017年第1期32卷 71-86页

作者： Colkesen, Ismail Kavzoglu, Taskin Gebze Tech Univ Dept Geodet & Photogrammetr Engn Gebze Turkey

Logistic model tree (LMT), a new method integrating standard decision tree (DT) induction and linear logistic regression algorithm in a single tree, have been recently proposed as an alternative to DT-based learning algorithms. In this study, the LMT was applied in the context of pixel-and object-based classifications using high-resolution WorldView-2 imagery, and its performance was compared with C4.5, random forest and Adaboost. Results of the study showed that the LMT generally produced more accurate classification results than the other methods for both pixel-and object-based classifications. The improvement in classification accuracy reached to 3% in pixel-based and 5% in object-based classifications. It was also estimated that the LMT algorithm produced the most accurate results considering the allocation and overall disagreement errors. based on the Wilcoxon's Signed-Ranks tests, the performance differences between the LMT and the other methods were statistically significant for both pixel-and object-based image classifications.

关键词： Logistic model tree random forest boosting decision tree object-based classification

来源：评论

学校读者我要写书评

暂无评论

A FULLY ADAPTIVE object EXTRACTION TECHNIQUE USED FOR SPECTRAL-SPATIAL classification OF REMOTELY SENSED DATA

A FULLY ADAPTIVE OBJECT EXTRACTION TECHNIQUE USED FOR SPECTR...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Zehtabian, Amin Ghassemian, Hassan Tarbiat Modares Univ Fac Elect & Comp Engn Tehran Iran

ISBN: (纸本)9781479979295

The effectiveness of object-based image classification approaches has been frequently addressed and discussed in literature, especially for remote sensing applications. Unlike the traditional pixel-wise methods, object-based classifiers benefit from a segmentation step before the classification process in order to generate objects. In this paper, we propose to use the Pixon concept for segmentation of the data. Meanwhile, in order to form objects which are spectrally homogenous, spatial smoothing is applied as a preprocessing step through using regularized nonlinear partial differential equations (RegAPDE). The parameters of RegAPDE as well as important thresholds used in the Pixon extraction technique are adaptively tuned using three different adaptation algorithms. We also propose to localize the smoothing process via separately applying the RegAPDE algorithm to individual partitions extracted from each layer of the hyperspectral datasets. To this end, a simple partitioning step based on Watershed transformation is used before the smoothing procedure.

关键词： object-based classification regularized partial differential equations adaptive parameters watershed

来源：评论

学校读者我要写书评

暂无评论

Land Cover Changes and Drivers in the Water Source Area of the Middle Route of the South-to-North Water Diversion Project in China from 2000 to 2015

引用

Chinese Geographical Science 2020年第1期30卷 115-126页

作者： GAO Wenwen ZENG Yuan ZHAO Dan WU Bingfang REN Zhiyuan State Key Laboratory of Remote Sensing Science Institute of Remote Sensing and Digital EarthChinese Academy of SciencesBeijing 100101China Research Center for Policy and Technology of the Office of the South-to-North Water Diversion Project Ministry of Water ResourcesBeijing 100038China

The Middle Route of the South-to-North Water Diversion Project(MR-SNWDP)in China,with construction beginning in 2003,diverts water from Danjiangkou Reservoir to North China for residential,agriculture and industrial *** water source area of the MR-SNWDP is the region that is most sensitive to and most affected by the construction of this water diversion *** this study,we used Landsat Thematic Mapper(TM)and HJ-1 A/B images from 2000 to 2015 by an object-based approach with a hierarchical classification method for mapping land cover in the water source *** changes in land cover were illuminated by transfer matrixes,single dynamic degree,slope zones and fractional vegetation cover(FVC).The results indicated that the area of cropland decreased by 31%and was replaced mainly by shrub over the past 15 years,whereas forest and settlements showed continuous increases of 29.2% and 77.7%,*** changes in cropland were obvious in all slope zones and decreased most remarkably(–43.8%)in the slope zone above 25°.Compared to the FVC of forest and shrub,significant improvement was exhibited in the FVC of grassland,with a growth rate of 16.6%.We concluded that local policies,including economic development,water conservation and immigration resulting from the construction of the MR-SNWDP,were the main drivers of land cover changes;notably,they stimulated the substantial and rapid expansion of settlements,doubled the wetlands and drove the transformation from cropland to settlements in immigration areas.

关键词： remote sensing land cover change object-based classification Middle Route of the South-to-North Water Diversion Project(MR-SNWDP) China

来源：评论

学校读者我要写书评

暂无评论

Species Discrimination of Plantations in Subtropical China Using 4-Band VHR Imagery and an Operational Image Analysis Framework

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2018年第8期11卷 2800-2813页

作者： Chen, Ling Mei, Guangyi Yan, Kai Hao, Wenqian Yu, Xiaolong Beijing Forestry Univ State Forestry Adm Key Lab Forest Resources & Environm Management Beijing 100083 Peoples R China Beijing Normal Univ State Key Lab Remote Sensing Sci Inst Remote Sensing Sci & Engn Fac Geog Sci Beijing 100875 Peoples R China Jiangle State Owned Forest Farm Sanming 353300 Peoples R China

Species information of forest plantations is of central interest to forest managers, especially under the current pressing demand for more structurally and functionally healthy and diverse plantations in China. In this study, five evergreen forest types were discriminated using a 4-band very high spatial resolution (VHR) satellite image with an operational image analysis framework which particularly involves a two-step feature selection (TSFS) method and image textural orientations. Two hundred and twenty-five object-based spectral and textural features were retrieved as candidates for the TSFS method to select the most influential feature subsets. Five schemes using random forest classification with optimal user-defined parameters were tested and compared. Both qualitative and quantitative assessment results indicated that the best scheme is the integration of spectral and textural features with individual orientations. The feature selection rate as low as 4% for the optimal scheme reflected the high effectiveness of the TSFS. The geometric intersections showed that many archive even-aged pure coniferous plantations were in fact mixed with nonconiferous species with different proportions (8.05-16.02%) and spatial aggregation patterns over very rugged terrain. Special management strategies are needed to perform the transition of pure coniferous plantations into more structurally balanced coniferous-broadleaved mixed woodland in subtropical China.

关键词： Feature selection object-based classification QuickBird random forest (RF) subtropical plantation textural orientations

来源：评论

学校读者我要写书评

暂无评论

Spectral normalization of SPOT 4 data to adjust for changing leaf phenology within seasonal forests in Cambodia

引用

REMOTE SENSING OF ENVIRONMENT 2014年第0期143卷 122-130页

作者： Langner, Andreas Hirata, Yasumasa Saito, Hideki Sokh, Heng Leng, Chivin Pak, Chealy Rasi, Rastislav Forestry & Forest Prod Res Inst Bur Climate Change Tsukuba Ibaraki 3058687 Japan Forestry Adm Khann Daun Penh Phnom Penh Cambodia European Commiss Joint Res Ctr Inst Environm & Sustainabil I-21027 Ispra VA Italy Forestry Res Inst Zvolen Natl Forest Ctr Zvolen 96092 Slovakia

As cloud cover exacerbates the application of optical satellite data for forest monitoring in tropical wet and dry regions during the rainy season, data acquisition is mainly restricted to the dry season. When analyzing wide areas, large numbers of single scenes obtained at different times of the dry season are often handled. Such imagery is characterized by changes of spectral reflectance due to vegetation phenology, varying atmospheric effects and solar geometries. In order to allow batch processing with automatic classification techniques, inter-scene comparability is required and data have to be radiometrically normalized. Cambodia is characterized by a mixture of evergreen, semi-evergreen and deciduous forest types, the latter two experiencing at least partial leaf shedding over the course of the dry season. Using spatial medium resolution SPOT 4 data and a manually delineated base map a season adjustment model was developed. The model is adapting the land cover specific spectral signatures of a slave scene (acquired in the middle of the dry season with its seasonal forests defoliated) to an adjacent master scene (from the beginning of the dry season, showing the same forest types with leafs). The relative position of every pixel reflectance was determined in relation to the mean reflectance and its standard deviation for each land cover type and sensor band of the unadjusted slave scene. For seasonality adjustment these pixel reflectance values were transformed (rescaled) to the corresponding position in spectral space defined by the band mean reflectance and standard deviation derived from the corresponding land cover class of the master scene. While the variability of spectral profiles of the pixels in the slave scene is rescaled, the mean reflectance value of the land cover class in the slave scene is conformed to the mean reflectance of the corresponding land cover class in the master scene. The Transformed Divergence (TD) separability index was used to in

关键词： Cambodia Transformed divergence Seasonality Artifacts Forest monitoring Deciduous forest SPOT 4 Normalization Seam line object-based classification

来源：评论

学校读者我要写书评

暂无评论

Over 150 Years of Change: object-Oriented Analysis of Historical Land Cover in the Main River Catchment, Bavaria/Germany

引用

REMOTE SENSING 2020年第24期12卷 4048-4048页

作者： Ulloa-Torrealba, Yrneh Stahlmann, Reinhold Wegmann, Martin Koellner, Thomas Univ Bayreuth BayCEER Professorship Ecol Serv PES D-95440 Bayreuth Germany Munich Univ Appl Sci Fac Geoinformat D-80333 Munich Germany Univ Bayreuth BayCEER Dept Biogeog D-95440 Bayreuth Germany Univ Wurzburg Inst Geog Dept Remote Sensing D-97074 Wurzburg Germany

The monitoring of land cover and land use change is critical for assessing the provision of ecosystem services. One of the sources for long-term land cover change quantification is through the classification of historical and/or current maps. Little research has been done on historical maps using object-based Image Analysis (OBIA). This study applied an object-based classification using eCognition tool for analyzing the land cover based on historical maps in the Main river catchment, Upper Franconia, Germany. This allowed land use change analysis between the 1850s and 2015, a time span which covers the phase of industrialization of landscapes in central Europe. The results show a strong increase in urban area by 2600%, a severe loss of cropland (-24%), a moderate reduction in meadows (-4%), and a small gain in forests (+4%). The method proved useful for the application on historical maps due to the ability of the software to create semantic objects. The confusion matrix shows an overall accuracy of 82% for the automatic classification compared to manual reclassification considering all 17 sample tiles. The minimum overall accuracy was 65% for historical maps of poor quality and the maximum was 91% for very high-quality ones. Although accuracy is between high and moderate, coarse land cover patterns in the past and trends in land cover change can be analyzed. We conclude that such long-term analysis of land cover is a prerequisite for quantifying long-term changes in ecosystem services.

关键词： historical land cover change object-based classification eCognition

来源：评论

学校读者我要写书评

暂无评论

Intact rock bridge breakage and rock mass fragmentation upon failure: quantification using remote sensing techniques

引用

PHOTOGRAMMETRIC RECORD 2017年第160期32卷 513-536页

作者： Spreafico, Margherita C. Franci, Francesca Bitelli, Gabriele Borgatti, Lisa Ghirotti, Monica Univ Milano Bicocca Milan Italy Univ Bologna Bologna Italy Univ Ferrara Ferrara Italy

In this work, two processes related to the onset and the evolution of large-scale rockfalls have been analysed by means of remote sensing techniques. First, the number of rock bridges as a proportion of pre-existing fractures has been estimated in a newly formed landslide scarp by analysing the spectral information of the rock mass in terrestrial laser scanner (TLS) and unmanned aerial vehicle (UAV) photogrammetric point clouds. Second, the fragmentation of the rock mass after failure has been assessed by comparing the percentage of newly formed fractures in the scarp and in the deposit. For this purpose, an orthophoto of the landslide deposit was classified using an object-based method. The presented workflow gained new data on the intact rock breakage during and after failure, and consequently deepened knowledge about rock failure and fragmentation mechanisms. Resume Dans cette etude, deux processus lies au declenchement et a l'evolution de grands eboulements ont ete analyses au moyen de techniques de modelisation 3D. Dans un premier temps, le nombre de ponts rocheux est estime en proportion des fractures preexistantes dans un escarpement de glissement de terrain nouvellement forme en analysant l'information spectrale de la masse rocheuse dans des nuages de points generes par balayage laser terrestre et par drone photogrammetrique. La fragmentation de la masse rocheuse apres rupture est ensuite evaluee en comparant le pourcentage de fractures nouvellement formees dans l'escarpement et dans le depot. cette fin, une orthophotographie de l'eboulis est traitee par une classification orientee objet. La methode presentee a permis d'obtenir de nouvelles donnees sur la rupture de la roche intacte pendant et apres la fracturation, et par consequent d'approfondir les connaissances sur les mecanismes de fracture et de fragmentation des roches. Zusammenfassung Die vorgestellte Arbeit behandelt zwei Prozesse in Bezug auf die Entstehung und die Entwicklung gro ss flachiger Fels

关键词： fragmentation object-based classification rock bridges spectral information terrestrial laser scanner UAV

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：