检索结果-南通市图书馆

基于遥感obia和U-Net的土壤侵蚀监测方法研究

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

林业调查规划 2022年第3期47卷 27-31页

作者：赵明海黎飞明王栋牛丽娟陕西铁路工程职业技术学院陕西渭南714000

为改善传统土壤监测过程效率低、成本高及扩展性差等缺点,在分析obia技术和深度学习图像分割算法基础上,设计了一种端对端的多分辨率遥感土壤监测算法。该算法使用obia作为训练标签,通过U-Net提供像素级别属于特定土壤侵蚀类别的概率信... 详细信息

为改善传统土壤监测过程效率低、成本高及扩展性差等缺点,在分析obia技术和深度学习图像分割算法基础上,设计了一种端对端的多分辨率遥感土壤监测算法。该算法使用obia作为训练标签,通过U-Net提供像素级别属于特定土壤侵蚀类别的概率信息,并结合阈值产生最终分割结果图。仿真结果表明,该方法准确率和召回率结果明显优于传统obia方法。

关键词：遥感影像土壤监测土壤侵蚀图像分割 U-Net obia

维普期刊数据库博看期刊

在线全文

学校读者我要写书评

暂无评论

基于obia的高分辨率遥感作物识别

科技视界 2016年第24期 286-286页

作者：胡蝶薛以晶高梦菲中国地质大学<北京>信息工程学院中国北京100083

自2014年起我国相继发射了高分系列卫星,中国遥感卫星进入亚米级的"高分时代"。随着遥感影像分辨率的提高,地物识别不能只采用像元的光谱信息作为分类的依据,需要综合考虑地物的形状、纹理、结构等空间信息的共同作用,obia(面向对象的... 详细信息

自2014年起我国相继发射了高分系列卫星,中国遥感卫星进入亚米级的"高分时代"。随着遥感影像分辨率的提高,地物识别不能只采用像元的光谱信息作为分类的依据,需要综合考虑地物的形状、纹理、结构等空间信息的共同作用,obia(面向对象的影像分析)使之得到了比较完美的实现。本项目通过卫星传感影像记录的地球表面信息,以e Cognition软件为分析工具,基于obia细致化地从高空间分辨率遥感影像上提取地物(农作物)信息,并进行类型识别,综合考虑地物的形象、纹理、结构等方面来弥补传统基于像元的分类方法的不足之处,以提高目标地物分类的精确程度。

关键词： obia eCognition 作物识别高分辨率

Early landslide mapping with slope units division and multi-scale objectbased image analysis——A case study in the Xianshui River basin of Sichuan,China

在线全文

学校读者我要写书评

暂无评论

Journal of Mountain Science 2022年第6期19卷 1618-1632页

作者： GAO Hui HE Li HE Zheng-wei BAI Wen-qian State Key Laboratory of Geohazard Prevention and Geoenvironment Protection Chengdu University of TechnologyChengdu 610059China College of Earth Sciences Chengdu University of TechnologyChengdu 610059China Chengdu Center China Geological SurveyChengdu 610081China College of Tourism and Urban-Rural Planning Chengdu University of TechnologyChengdu 610059China

Previous studies on optical remote sensing mapping of landslides mainly focused on new landslides that have occurred, but little attention was paid to the early landslide due to its high concealment. In SAR technology, a prevalent method to detect early landslides, only can be used to identify the potential hazards of slow deformation. Therefore, it is necessary to explore new method of early landslides mapping by integrating all types of direct and indirect early features, such as cracks on slopes, small collapses inside and topographic features. In this study, an object-oriented image analysis method based on slope unit division and multi-scale segmentation was proposed to obtain accurate location and boundary extraction of early landslides. In the middle-and small-scale segmentation, the object, texture, spectrum, geometric features,topographic features, and other features were obtained to determine the local feature location of early landslides. The slope unit boundary was combined with the feature of a large-scale segmentation object to determine the scope of landslides. This method was tested in the Xianshui River basin in the Daofu County, Sichuan Province, China. The results demonstrate that:(1) Such features as landslide cracks and the small collapse at the bottom of slope can effectively determine the landslide position.(2) The slope unit division and the correct setting of shape factors in multiple segmentation can effectively determine the landslide boundary.(3) The accuracy of landslide location extraction was 83.33%, and the accuracy of boundary extraction for early landslides that were completely identified was evaluated as 82.67%. It is indicated that this method can improve the accuracy of boundary extraction and meet the requirements of the early landslides mapping.

关键词： Early characteristics of landslides Multiscale segmentation obia Slope units

Land cover changes and fragmentation in mountain neotropical ecosystems of Oaxaca, Mexico under community forest management

在线全文

学校读者我要写书评

暂无评论

Journal of Forestry Research 2019年第1期30卷 143-155页

作者： Rafael M~a Navarro Cerrillo Dennis J.Esteves Vieira Susana Ochoa-Gaona Bernardus H.J.de Jong M~a del Mar Delgado Serrano Depto. Ingeniería Forestal Laboratorio de SelviculturaDendrocronología y Cambio Climático.Dendrodat Lab-ERSAF Universidad de Córdoba Depto. de Engenharia Florestal Faculdade de Engenharia Florestal Laboratório de Sensoriamento Remoto e Geotecnologia Universidade Federal de Mato Grosso Departamento de Ciencias de la Sustentabilidad El Colegio de la Frontera Sur-Unidad Campeche Depto. Economía Sociología y Política Agrarias Grupo de Evaluación y Restauración de Sistemas Agrícolas y Forestales-ERSAF Universidad de Córdoba

Changes in land cover have a direct impact on forest ecosystem goods and services. In this study, changes in land cover in Sierra de Juarez–Oaxaca ecosystems were estimated using a consistent processing of Landsat images and obia methodology. Additionally, landscape analyses using FRAGSTAT were conducted. In 2014, Sierra de Juarez–Oaxaca was covered by approximately 84% of forests, mainly pine-oak and cloud forests. After extensive deforestation until 2001, this trend was reversed and the forest cover surface area in 2014 was slightly higher than in 1979. The comparison of the landscape structure of the forested and agricultural lands suggests an increase in habitat heterogeneity. However, interspersion and juxtaposition indices, showing the patch shape by patch area and perimeter, were similar throughout the study period(1979–2014). Social and economic drivers can explain this situation: namely, community organization, forest enterprises, payment for ecosystem services programs, and changes of agricultural activity. Communities in the Sierra of Oaxaca have reforested degraded lands, created community forest enterprises, and preserved the forest under conservation schemes like those proposed by the Mexican payment for ecosystem services programs. However, their sustainable management faces internal challenges and has become highly dependent on political and institutional decisions beyond their control.

关键词： Tropical and temperate forests Social forestry Land uses segmentation obia FRAGSTAT

Investigating the Use of a Modified NSGA-II Solution for Land-Use Planning in Mediterranean Islands

在线全文

学校读者我要写书评

暂无评论

Journal of Geographic Information System 2016年第3期8卷 369-386页

作者： Miltiades Lazoglou Polychronis Kolokoussis Efi Dimopoulou Department of Civil Engineering Aristotle University of Thessaloniki Thessaloniki Greece School of Rural and Surveying Engineering National Technical University of Athens Athens Greece

This paper explores the potential application of a modified version of the Non-dominated Sorting Genetic Algorithm (NSGA)-II for land-use planning in Mediterranean islands that constitute a geographical entity with similar characteristics. Study area is the island of Naxos, which is a typical Mediterranean island. In order to monitor the land-use changes of the island for the period 1987-2010, object-based classification of three Landsat images has been carried out. The 1987 land-use classification defined the initial population for the Genetic Algorithm (GA) and the aim was to provide the optimal development scenario for Naxos island taking into consideration legislation, geological characteristics and environmental parameters. The GA was used in order to introduce land use changes while maximizing transformation suitability, compactness, economic return, and minimizing soil erosion. The output of the GA was compared to the actual development of the island. The outcomes confirmed the proposed algorithm’s convergence process, while the GA solutions eventually formed a Pareto Front and performed adequately across all objectives. The GA algorithm has proposed reduction of Irrigated farming land by 16%, increase of Dry farming land by 131%, and the maximum allowed by the defined constraints increase of Urban land (100%), mostly on the eastern and central part of Naxos. These changes significantly differ from the actual development of the island. Economic return after optimization increased by 18%, while soil erosion decreased from 1948 t/y to 1843 t/y.

关键词： Land-Use Planning Multiobjective Optimization Genetic Algorithm NSGA-II Landsat obia

Effects of Increasing Impervious Surface on Water Quality in Ile-Ife Urban Watershed, Southwestern Nigeria

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Geoscience and Environment Protection 2022年第12期10卷 126-160页

作者： Olusola-Ige Olufayo Adetoro Victor Osarenren Samuel Oladimeji Popoola Space Applications and Environmental Science Laboratory Institute of Ecology and Environmental Studie OAU Nigeria Obafemi Awolowo University Ile-Ife Nigeria Information Network Regional Advanced Space Technology Application Laboratory National Space Research and Development Agency (NASRDA) Ile-Ife Nigeria

The urban environment has continued to experience changes from increasing impervious surfaces, which alters the proper functioning of the ecological zones and impairs water quality in the watershed. Impervious cover is predominantly used as an indicator to assist in understanding and forecasting the impact of human actions and other related activities on aquatic resources. In this study, the rate of change in land uses using the impervious surface as an indicator, and the percentage of imperviousness on the effect on water quality in the urban watershed were assessed. Ile-Ife was delineated as an urban watershed, and the percentage of imperviousness from 2008 to 2016 and the effect of imperviousness on water bodies were assessed. The study utilized ASTERDEM, Worldview (0.46 m), IKONOS (1.4 m), Landsat (30 m) for 2008 and 2016, GPS and Drone (10 cm). Water sampling was carried out in selected locations as generated by the impervious surface analyst tool, (ISAT). The percentage (%) of impervious surfaces accounted for 59.4% (4567.1/7691.5ha) in 2008 and 70.3% (5408.2/7691.5ha) in 2016, from the total number of lands investigated. The turbidity values from low to high regions were 32.3, 55.9 and 82.4 NUT. Changes in LULC of the watershed led to increased surface temperature, impermeable surfaces, and decreased vegetation, which exposes the area to flooding and reduced water quality. This study emphasized the importance of GIS and its integration into urban changes and water quality assessment.

关键词： Urban Watershed Impervious Surface Water Quality ISAT obia Turbidity

An Optical High and Medium Spatial Resolution Approach for Erosion-Prone Areas Assessment in Mustang, Nepal

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Geosciences 2014年第4期5卷 383-393页

作者： Kabir Uddin Madhav Dhakal Govinda Joshi International Centre for Integrated Mountain Development Kathmandu Nepal

Every year during the rainy season, water-induced soil erosion poses serious spatial-environmental problems, causing heavy damage to agricultural lands, sedimentation in reservoirs, and water quality problems in nearby surface water bodies, from the plains to the mountain areas in Nepal. The goal of this study is to identify potential areas for soil erosion in sub and macro watershed in Mustang, Nepal using remote sensing (RS) and geographic information systems (GIS) techniques. The study examines the possibility of advanced mapping of soil erosion-prone areas using a high spatial resolution image of QuickBird satellite and medium spatial resolution of Landsat satellite. The satellite image was classified using object-based image analysis (obia) techniques, taking into account spectral, spatial, and context information as well as hierarchical properties. The resulting land cover classification was thereafter combined with additional data in ArcGIS, where the input layers were reclassified and all classes of the input layers were ranked according to their proneness to soil erosion. Soil erosion-prone areas were delineated in five classes ranging from “very high” to “very low”. Using high spatial resolution image the study revealed that 22% area categorized as “high erosion-prone” areas and 5% as “very high” or “extremely erosion-prone”. Using medium resolution image the study exposed that 27% area categorized as “high erosion-prone” areas and 6% as “very high” or “extremely erosion-prone”. Comparison between two analysed erosion results almost all the erosion zone area was very close excluding medium erosion-prone category. The study proved GIS modeling techniques can successfully identify soil erosion-prone areas. The soil erosion-prone map produced out of the exercise can be used in decision making, particularly in selecting conservation measures to reduce soil loss.

关键词： Remote Sensing GIS obia Soil Erosion Watershed

基于卷积神经网络的面向对象遥感影像分类方法研究

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于卷积神经网络的面向对象遥感影像分类方法研究

作者：陈扬洋中国地质大学(北京)

学位级别：硕士

近年来,随着遥感技术的迅猛发展,人们可以十分便捷、高效地获取高空间分辨率遥感影像(简称高分影像)。高空间分辨率使影像中的地物细节更加清晰与丰富,但是同时也为地物分类带来了新的挑战。使用传统的分类方法对高分影像进行分类只能... 详细信息

近年来,随着遥感技术的迅猛发展,人们可以十分便捷、高效地获取高空间分辨率遥感影像(简称高分影像)。高空间分辨率使影像中的地物细节更加清晰与丰富,但是同时也为地物分类带来了新的挑战。使用传统的分类方法对高分影像进行分类只能提取影像中的低层次特征,难以得到满意的分类结果。如何深入挖掘蕴藏在高分影像中的高层次特征是高分影像分类精度提升的关键。目前有学者提出基于卷积神经网络技术的逐像素分类方法,可以提取并利用影像中的高层次特征,取得更高的分类精度。但是由于采用像素作为分析基元,在实际应用中仍存在一定的缺陷与不足,如在分类结果中存在大量椒盐现象等。因此研究将面向对象影像分析思想和卷积神经网络分类技术相结合的理论与方法,充分利用高分遥感影像的深度特征进行地物识别和分类,对于高分辨率遥感影像的高精度信息提取具有重要意义与实用价值。本文结合高分影像自身的特点,剖析了高分影像分类的难点,对目前卷积神经网络技术在高分影像分类中应用的优劣进行了分析与综述。在卷积神经网络技术与面向对象分析的理论基础上,建立了一种基于卷积神经网络的面向对象高分影像分类思想与框架。以分割对象作为分析基元,利用卷积神经网络提取的高层次特征对其进行分类,提出了基于单尺度卷积神经网络的超像素分类方法。此外,本文针对高分影像尺度效应明显的特点,对卷积神经网络的结构进行改进,提出了基于多尺度卷积神经网络的超像素分类方法。本文以两幅高分影像作为实验数据进行对比试验,印证了所提新方法的优越性和可靠性。通过实验结果可知,基于卷积神经网络的面向对象分类方法有三个主要优点:(1)以分割对象作为分析基元,克服了基于卷积神经网络逐像素分类方法的缺陷。可以有效避免由于混合像元造成的椒盐现象,极大减少了分类的计算量,并取得更高的分类精度。(2)使用卷积神经网络可以充分提取并利用高分影像中的高层次特征,大幅提升高分影像的分类精度。(3)使用多尺度卷积神经网络可以充分提取影像中多尺度的高层次信息,减少了尺度效应对分类结果的影响,解决高分影像多尺度特征难以提取与利用的难题,进一步提升高分影像的分类精度。本文建立了卷积神经网络技术与面向对象分析之间的桥梁,从新的角度将卷积神经网络技术与遥感影像分类相结合,对未来的研究有重要的理论意义和应用价值。

关键词：深度学习卷积神经网络高空间分辨率遥感影像 obia 超像素

基于梯度尺度空间的遥感影像多尺度分割方法及应用研究

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

安徽农业科学 2013年第30期41卷 12190-12195页

作者：张万强赵俊三李洪波谢相建昆明理工大学国土资源工程学院云南昆明650093 昆明理工大学建筑工程学院云南昆明650093

针对当前高空间分辨率遥感影像数据的迅速普及和面向对象影像分析技术的发展成熟等特点,引入基于梯度尺度空间的多尺度分割技术,对遥感影像自适应平滑滤波处理、梯度尺度空间的构建、多尺度分割等系列处理技术作了一些理论探讨和应用研... 详细信息

针对当前高空间分辨率遥感影像数据的迅速普及和面向对象影像分析技术的发展成熟等特点,引入基于梯度尺度空间的多尺度分割技术,对遥感影像自适应平滑滤波处理、梯度尺度空间的构建、多尺度分割等系列处理技术作了一些理论探讨和应用研究工作,并结合面向对象影像分析方法,用具体的影像实例验证了该方法在面向对象影像分类中的适用性和有效性。

关键词：分水岭变换梯度尺度空间多尺度分割 obia