检索结果-内蒙古大学图书馆

IEEE International Geoscience and Remote Sensing Symposium

作者： Emmanuel Maggiori Yuliya Tarabalka Guillaume Charpiat Inria Sophia Antipolis Mediterranee TITANE team Inria Saclay TAO team

ISBN: (纸本)9781479979301

We propose a new binary partition tree (BPT)-based framework for multi-class segmentation of remote sensing images. In the literature, BPTs are typically computed in a bottom-up manner based on spectral similarities, then analyzed to extract image objects. When image objects exhibit a considerable internal spectral variability, it often happens that such objects are composed of several disjoint regions in the BPT, yielding errors in object extraction. We pose the multi-class segmentation problem as an energy minimization task and solve it by using BPTs. Our main contribution consists in introducing a new dissimilarity function for the tree construction, which combines both spectral discrepancies and supervised class-specific information to take into account the within-class spectral variability. The experimental validation proved that the proposed method constitutes a competitive alternative for object-based image classification.

关键词： Binary partition tree Segmentation object-based classification Energy minimization segmentation Segmentation ENERGY MINIMISATION object orientation images Trees remote sensing extraction of object partitions BEST PRACTICAL TECHNOLOGY multi-class Binary trees trees remote sensing images Image classification

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Potential of GF-1 Pan-multispectral Camera Imagery for Identifying the Quasi-circular Vegetation Patches in the Yellow River Delta,China

Evaluating the Potential of GF-1 Pan-multispectral Camera Im...

引用

2019第十一届数字图像处理国际会议

作者： Qingsheng Liu State Key of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of Sciences

Gaofen-1（GF-1） is the first high resolution optical imaging satellite of China primary civilian Earth observation project under the China High-resolution Earth Observation *** the GF-1 trio launched on March 31,2018,the combined 3+1 GF-1 constellation will offer one-day revisit coverage,which provides more available high resolution remote sensing images for monitoring decametric-scale vegetation patches and long-term pattern *** this study,a panchromatic image,the original multispectral image,and the pan-sharpened multispectral image from GF-1 Panmultispectral Camera was compared to evaluate their potential for identifying the quasi-circular vegetation patches（QVPs） in the Yellow River Delta,*** results showed that high spatial resolution was more important for identifying the QVPs than more additional spectral bands of GF-1,and the pan-sharpened multispectral image had the highest identification accuracy of the QVPs（F-measure is 64.6%）.In the future,multi-temporal pan-sharpened GF-1 images should be used to obtain higher accuracy,which is basis for studying vegetation patch pattern dynamics.

关键词： GF-1 pan-multispectral camera imagery object-based classification support vector machine quasi-circular vegetation patch Yellow River Delta

来源：评论

学校读者我要写书评

暂无评论

Fine-grained wetland classification for national wetland reserves using multi-source remote sensing data and Pixel Information Expert Engine (PIE-Engine)

引用

GISCIENCE & REMOTE SENSING 2023年第1期60卷

作者： Liu, Han Liao, Tongkui Wang, Yu Qian, Xiaoming Liu, Xiaochen Li, Chengming Li, Shiwei Guan, Zhanlei Zhu, Lijue Zhou, Xiaoyuan Liu, Chong Hu, Tengyun Luo, Ming Minist Nat Resources Technol Innovat Ctr Land Engn Land Consolidat & Rehabil Ctr Key Lab Land Consolidat & Rehabil Beijing Peoples R China Minist Nat Resources Key Lab Digital Mapping & Land Informat Applicat Wuhan Peoples R China Piesat Informat Technol Co Ltd Beijing Peoples R China Minist Emergency Management Natl Disaster Reduct Ctr China Beijing Peoples R China Beijing Municipal Inst City Planning & Design Beijing Peoples R China

Timely and accurate wetland information is necessary for wetland resource management. Recent advances in machine learning and remote sensing have facilitated cost-effective monitoring of wetlands. However, reliable methods for fine-grained and rapid wetland mapping are still lacking. To address the issue, a wetland sample set with 20 categories for China was collected based on a sampling strategy that combines automatic sample generation and visual interpretation. Simultaneously, a novel multi-stage method for fine-grained wetland classification was proposed, which integrates pixel-based and object-based strategies using ensemble learning algorithms and multi-source remote sensing data. First, a pixel-based ensemble learning algorithm was implemented to classify five rough wetland categories and six non-wetland categories. Second, an object-based ensemble learning approach was designed to separate the water cover in the pixel-based classification results into eight detailed categories. Third, the merged pixel-based and object-based classification results were refined with knowledge-based post-processing procedures to identify 14 fine-grained wetland categories. Results using the Pixel Information Expert Engine (PIE-Engine) cloud platform proved the effectiveness of the proposed wetland classification method. The overall accuracy, kappa, and weighted F1 reached 87.39%, 82.80%, and 86.02%, respectively. The adopted ensemble learning algorithm yielded better performance than classifiers such as CatBoost, random forest, and XGBoost. The incorporation of spectral, texture, shape, topographic, and geographic features from multi-source data contributed to differentiating wetland categories. According to the relative contribution, spectral indexes (NDVI and NDWI), texture features (sum average and contrast), and topographic features (slope and elevation) were identified as important leading predictors for the first-stage pixel-based classification. Shape features (shape ind

关键词： Wetland mapping remote sensing ensemble learning pixel-based classification object-based classification PIE-Engine

来源：评论

学校读者我要写书评

暂无评论

ENSEMBLE CLASSIFIERS FOR BUILDING DAMAGE DETECTION

ENSEMBLE CLASSIFIERS FOR BUILDING DAMAGE DETECTION

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： David Dubois Richard Lepage Ecole de technologie superieure

ISBN: (纸本)9781479979301

Each year, numerous disasters cause high amount of human and material losses. With the presence of both technological and social means like very high spatial resolution (VHR) satellite images and the International Charter "Space and Major Disasters" respectively, decision makers can obtain the needed information to make fast life-saving decisions. The automation of parts of the image analysis process is thus of great interest. This is why we propose to apply an ensemble classification method to provide better building damage evaluation using optical images acquired before and after the event. We base this work on our previous framework for fast building detection and damage evaluation by supervised classification. The results show the positive impact of ensemble classifiers in damage mapping.

关键词： Damage evaluation Disaster response Ensemble classifier object-based classification Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Utility of landsat Image in the Study of Land Cover and Land Surface Temperature Change

Utility of landsat Image in the Study of Land Cover and Land...

引用

2011 3rd International Conference on Environmental Science and Information Application Technology(ESIAT 2011)

作者： Zhi-qiang Lv Qi-gang Zhou Tourism and Land Department Chongqing Technology and Business University Chongqing Engineering Technology Research Center for Information Mangement in Developent Chongqing Technology and Business University

Scientists have aimed at exploring land use and land cover(LULC) and their environmental influence in order to improve our understanding of the causes and consequences of these phenomena. This study addresses and use and land cover change(LUCC) in the upper reaches of Pearl River Delta, China, from 1990 to 2008. based on remotely sensed images of Landsat, LUCC and land surface temperature were assessed. Results showed that land surface temperature was highly influenced by the LUCC from 1990 to 2008. An examination of the relationship between the LULC and LST maps was finally conducted to comprehension their interactions. Results indicated that Landsat image was effective for quantifying the heat environment and providing reliable measurements of land use change. LST was found to be positively correlated with impervious surface but negatively correlated with vegetated land. Each temperature zone was associated with a dominant LULC category.

关键词： Land use land surface temperature object-based classification TM/ETM+ Fast developing region

来源：评论

学校读者我要写书评

暂无评论

DECISION TREE REPOSITORY AND RULE SET based MINGJIANG RIVER ESTUARINE WETLANDS CLASSIFACTION

DECISION TREE REPOSITORY AND RULE SET BASED MINGJIANG RIVER ...

引用

The ISPRS Technical Commission III Midterm Symposium on "Developments, Technologies and Applications in Remote Sensing"

作者： Wenyan Zhang Xintong Li Wei Xiao College of Geography Fujian Normal University

The increasing urbanization and industrialization have led to wetland losses in estuarine area of Mingjiang River over past three decades. There has been increasing attention given to produce wetland inventories using remote sensing and GIS technology. Due to inconsistency training site and training sample, traditionally pixel-based image classification methods can't achieve a comparable result within different organizations. Meanwhile, object-oriented image classification technique shows grate potential to solve this problem and Landsat moderate resolution remote sensing images are widely used to fulfill this ***, the standardized atmospheric correct, spectrally high fidelity texture feature enhancement was conducted before implementing the object-oriented wetland classification method in e Cognition. Secondly, we performed the multi-scale segmentation procedure, taking the scale, hue, shape, compactness and smoothness of the image into account to get the appropriate parameters,using the top and down region merge algorithm from single pixel level, the optimal texture segmentation scale for different types of features is ***, the segmented object is used as the classification unit to calculate the spectral information such as Mean value, Maximum value, Minimum value, Brightness value and the Normalized value. The Area, length, Tightness and the Shape rule of the image object Spatial features and texture features such as Mean, Variance and Entropy of image objects are used as classification features of training samples. based on the reference images and the sampling points of on-the-spot investigation,typical training samples are selected uniformly and randomly for each type of ground objects. The spectral, texture and spatial characteristics of each type of feature in each feature layer corresponding to the range of values are used to create the decision tree repository. Finally, with the help of high resolution reference images, the rando

关键词： Landsat Satellite Image Texture Feature Enhancement object-based classification Wetland Mapping Repository Rule Set

来源：评论

学校读者我要写书评

暂无评论

THE IDENTIFICATION OF LAND UTILIZATION IN COASTAL RECLAMATION AREAS IN TIANJIN USING HIGH RESOLUTION REMOTE SENSING IMAGES

THE IDENTIFICATION OF LAND UTILIZATION IN COASTAL RECLAMATIO...

引用

The ISPRS Technical Commission III Midterm Symposium on "Developments, Technologies and Applications in Remote Sensing"

作者： Yunshan Meng Yingzhi Cao Hongjun Tian Zhicong Han National Marine Data and Information Service

In recent decades, land reclamation activities have been developed rapidly in Chinese coastal regions, especially in Bohai Bay. The land reclamation areas can effectively alleviate the contradiction between land resources shortage and human needs, but some idle lands that left unused after the government making approval the usage of sea areas are also supposed to pay attention to. Due to the particular features of land coverage identification in large regions, traditional monitoring approaches are unable to perfectly meet the needs of effectively and quickly land use classification. In this paper, Gaofen-1 remotely sensed satellite imagery data together with sea area usage ownership data were used to identify the land use classifications and find out the idle land resources. It can be seen from the result that most of the land use types and idle land resources can be identified precisely.

关键词： Reclamation High resolution images object-based classification Decision tree method

来源：评论

学校读者我要写书评

暂无评论

SENTINEL-1 AND SENTINEL-2 DATA FUSION FOR WETLANDS MAPPING: BALIKDAMI, TURKEY

SENTINEL-1 AND SENTINEL-2 DATA FUSION FOR WETLANDS MAPPING: ...

引用

The ISPRS Technical Commission III Midterm Symposium on "Developments, Technologies and Applications in Remote Sensing"

作者： Gordana Kaplan Ugur Avdan Anadolu University Remote Sensing and GIS programme Anadolu University Earth and Space Sciences Institute

Wetlands provide a number of environmental and socio-economic benefits such as their ability to store floodwaters and improve water quality, providing habitats for wildlife and supporting biodiversity, as well as aesthetic values. Remote sensing technology has proven to be a useful and frequent application in monitoring and mapping wetlands. Combining optical and microwave satellite data can help with mapping and monitoring the biophysical characteristics of wetlands and wetlands` vegetation. Also, fusing radar and optical remote sensing data can increase the wetland classification accuracy. In this paper, data from the fine spatial resolution optical satellite, Sentinel-2 and the Synthetic Aperture Radar Satellite, Sentinel-1, were fused for mapping wetlands. Both Sentinel-1 and Sentinel-2 images were pre-processed. After the pre-processing, vegetation indices were calculated using the Sentinel-2 bands and the results were included in the fusion data set. For the classification of the fused data, three different classification approaches were used and compared. The results showed significant improvement in the wetland classification using both multispectral and microwave data. Also, the presence of the red edge bands and the vegetation indices used in the data set showed significant improvement in the discrimination between wetlands and other vegetated areas. The statistical results of the fusion of the optical and radar data showed high wetland mapping accuracy, showing an overall classification accuracy of approximately 90% in the object-based classification method. For future research, we recommend multi-temporal image use, terrain data collection, as well as a comparison of the used method with the traditional image fusion techniques.

关键词： Image Fusion Sentinel-1 Sentinel-2 Wetlands object-based classification

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC MULTI-SCALE SEGMENTATION OF HIGH SPATIAL RESOLUTION SATELLITE IMAGES USING WATERSHEDS

AUTOMATIC MULTI-SCALE SEGMENTATION OF HIGH SPATIAL RESOLUTIO...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Kerem Sahin Ilkay Ulusoy METUVISION Lab. Dept. of Electrical and Electronics Eng. METU

ISBN: (纸本)9781479911127

An automatic segmentation algorithm that is based on watersheds and region merging type multi-scale segmentation (MSS) is proposed, which can be used as the initial step of an object-based classifier. First, the image is segmented using watershed segmentation. Then, primitive segments are merged to create meaningful objects by the proposed hybrid region merging algorithm. During these steps, an unsupervised segmentation accuracy metric is considered so that best performing parameters of the proposed algorithm are determined automatically. By this way, the proposed segmentation algorithm has become fully automatic. Experiments are done on images taken from Google Earth software. Algorithm performance is computed using the ground truths of these images. Also, results for some other Google Earth images are presented for qualitative performance assessment.

关键词： Watershed segmentation Multi-scale segmentation Automatic segmentation High spatial resolution satellite images object-based classification

来源：评论

学校读者我要写书评

暂无评论

The Urban Landscapes Interpretation of Beijing Olympic Center based on High Resolution Remote Sensing Image

The Urban Landscapes Interpretation of Beijing Olympic Cente...

引用

2015 International Conference on Advanced Educational Technology and Information Engineering(AETIE 2015)

作者： Y.Li Z.Wang L.Yuan Y.Y.Shi Z.H.Li W.Wang Institute of Geographic Sciences and Natural Resources Chinese Academy of Sciences University of Chinese Academy of Sciences China University of Geosciences

Rapid development of high resolution remote sensing technology makes the researches in area of urban geography be more convenient. This paper took Beijing Olympic Center as a case to analyze the application of object-based classification method in interpretation of key ground objects in typical functional area of metropolis. By using World View-2 images with resolution of 0.5 m(panchromatic image) and 2 m(multi-spectral image), this paper interpreted the pivotal study objects based on e Cognition Developer 8.7 software. The interpretation result achieved a high overall accuracy(0.927).

关键词： urban high resolution remote sensing object-based classification

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：