检索结果-内蒙古大学图书馆

Comparative Assessment of Supervised Classifiers for Land Use-Land Cover classification in a Tropical Region Using Time-Series PALSAR Mosaic Data

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2014年第4期7卷 1186-1199页

作者： Shiraishi, Tomohiro Motohka, Takeshi Thapa, Rajesh Bahadur Watanabe, Manabu Shimada, Masanobu Japan Aerosp Explorat Agcy Earth Observat Res Ctr Tsukuba Ibaraki 3058505 Japan

Numerous classification algorithms have been proposed to create accurate classification maps using optical remote sensing data. However, few comparative studies evaluate the performance of classification algorithms with focus on tropical forests due to cloud effects. Advances in synthetic aperture radar (SAR) techniques and spatial resolution, mapping, and comparison of classification algorithms are possible. This research investigated the accuracy and processing speeds of five supervised classifiers, including Naive Bayes, AdaBoost, multi-layer perceptron, random forest (RF), and support vector machine, for land use-land cover (LULC) classification in a tropical region using time-series Advanced Land Observing Satellite-phased array type L-band SAR (ALOS-PALSAR) 25-m mosaic data. The study area is located in central Sumatra, Indonesia, where abundant forest-related carbon stocks exist. This investigation was intended to aid the implementation of a classification algorithm for the automatic creation of LULC classification maps. We perform object-based and pixel-based analyses to investigate the ability of the classifiers and their accuracies, respectively. RF had the best classification accuracy and processing speed in which the accuracies for 10 classes and 2 classes were 64.07% and 90.22% for pixel-based and 82.94% and 86.23% for object-based evaluations, respectively. These results indicate that RF is a useful classifier for the analysis of PALSAR mosaic data and that the automatic creation of highly accurate classification maps is possible by using time-series data. The outcome of this research will be valuable resources for biodiversity and global-warming mitigation efforts in the region.

关键词： Land use-land cover (LULC) classification object-based classification Sumatra supervised classification time-series PALSAR mosaic data

来源：评论

学校读者我要写书评

暂无评论

Interpretation of Forest Resources at the Individual Tree Level at Purple Mountain, Nanjing City, China, Using WorldView-2 Imagery by Combining GPS, RS and GIS Technologies

引用

REMOTE SENSING 2014年第1期6卷 87-110页

作者： Deng, Songqiu Katoh, Masato Guan, Qingwei Yin, Na Li, Mingyang Shinshu Univ Fac Agr Forest Measurement & Planning Lab Nagano 3994598 Japan Nanjing Forestry Univ Forest Resources & Environm Fac Nanjing 210037 Jiangsu Peoples R China Shinshu Univ Fac Agr Forest Environm & Ecol Lab Nagano 3994598 Japan

This study attempted to measure forest resources at the individual tree level using high-resolution images by combining GPS, RS, and Geographic Information System (GIS) technologies. The images were acquired by the WorldView-2 satellite with a resolution of 0.5 m in the panchromatic band and 2.0 m in the multispectral bands. Field data of 90 plots were used to verify the interpreted accuracy. The tops of trees in three groups, namely 10 cm, 15 cm, and 20 cm DBH (diameter at breast height), were extracted by the individual tree crown (ITC) approach using filters with moving windows of 3 x 3 pixels, 5 x 5 pixels and 7 x 7 pixels, respectively. In the study area, there were 1,203,970 trees of DBH over 10 cm, and the interpreted accuracy was 73.68 +/- 15.14% averaged over the 90 plots. The numbers of the trees that were 15 cm and 20 cm DBH were 727,887 and 548,919, with an average accuracy of 68.74 +/- 17.21% and 71.92 +/- 18.03%, respectively. The pixel-based classification showed that the classified accuracies of the 16 classes obtained using the eight multispectral bands were higher than those obtained using only the four standard bands. The increments ranged from 0.1% for the water class to 17.0% for Metasequoia glyptostroboides, with an average value of 4.8% for the 16 classes. In addition, to overcome the mixed pixels problem, a crown-based supervised classification, which can improve the classified accuracy of both dominant species and smaller classes, was used for generating a thematic map of tree species. The improvements of the crown- to pixel-based classification ranged from -1.6% for the open forest class to 34.3% for Metasequoia glyptostroboides, with an average value of 20.3% for the 10 classes. All tree tops were then annotated with the species attributes from the map, and a tree count of different species indicated that the forest of Purple Mountain is mainly dominated by Quercus acutissima, Liquidambar formosana and Pinus massoniana. The findings from t

关键词： 3S technology forest resource measurement individual tree crown approach object-based classification Purple Mountain

来源：评论

学校读者我要写书评

暂无评论

Multiagent object-based Classifier for High Spatial Resolution Imagery

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2014年第2期52卷 841-857页

作者： Zhong, Yanfei Zhao, Bei Zhang, Liangpei Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China

object-based classification, including object-based segmentation and classification, has been applied for the classification of high spatial resolution imagery due to the increase in the spatial resolution and the limited spectral resolution. Because of the independent design of the object-based segmentation and classification in many of the traditional object-based classification methods, additional work is required to select the appropriate segmentation algorithms to match the classification algorithms. The object-based segmentation algorithms, e. g., the fractal net evolution approach (FNEA), have been successfully utilized to provide the homogeneous regions, and are the basis of object-based classification. However, the traditional FNEA algorithm is greatly influenced by the global control strategy of the region-growing procedure. In addition, the existing object classification methods take little account of the object context information, which is important for high spatial-resolution image interpretation. To improve the accuracy of the object-based classification, in this paper, a multiagent object-based classification framework (MAOCF) for high-resolution remote sensing imagery is proposed. The proposed approach avoids the issue of segmentation algorithm selection by unifying the processing of object-based segmentation and classification through the use of a 4-tuple agent model. In the uniform framework, a multiagent object-based segmentation (MAOS) algorithm is proposed to optimally control the procedure of object merging. In addition, a MAOC is proposed to utilize the contextual information from the surrounding objects by taking advantage of the benefits of a multiagent system, e. g., strong interaction, high flexibility, and parallel global control capability. Due to the characteristics of a multiagent system, MAOCF has the potential for a parallel computing ability. Three experiments with different types of images were performed to evaluate the performanc

关键词： Global control high spatial resolution image multiagent systems object-based classification segmentation

来源：评论

学校读者我要写书评

暂无评论

Influence of river channel morphology and bank characteristics on water surface boundary delineation using high-resolution passive remote sensing and template matching

引用

EARTH SURFACE PROCESSES AND LANDFORMS 2014年第7期39卷 977-986页

作者： Gueneralp, Inci Filippi, Anthony M. Hales, Billy Texas A&M Univ Dept Geog College Stn TX 77843 USA

Accurate mapping of water surface boundaries in rivers is an important step for monitoring water stages, estimating discharge, flood extent, and geomorphic response to changing hydrologic conditions, and assessing riverine habitat. Nonetheless, it is a challenging task in spatially and spectrally heterogeneous river environments, commonly characterized by high spatiotemporal variations in morphology, bed material, and bank cover. In this study, we investigate the influence of channel morphology and bank characteristics on the delineation of water surface boundaries in rivers using high spatial resolution passive remote sensing and a template-matching (object-based) algorithm, and compare its efficacy with that of Support Vector Machine (SVM) (pixel-based) algorithm. We perform a detailed quantitative evaluation of boundary-delineation accuracy using spatially explicit error maps in tandem with the spatial maps of geomorphic and bank classes. Results show that template matching is more successful than SVM in delineating water surface boundaries in river sections with spatially challenging geomorphic landforms (e.g. sediment bar structures, partially submerged sediment deposits) and shallow water conditions. However, overall delineation accuracy by SVM is higher than that of template matching (without iterative hierarchical learning). Vegetation and water indices, especially when combined with texture information, improve the accuracy of template matching, for example, in river sections with overhanging trees and shadows - the two most problematic conditions in water surface boundary delineation. By identifying the influence of channel morphology and bank characteristics on water surface boundary mapping, this study helps determine river sections with higher uncertainty in delineation. In turn, the most suitable methods and data sets can be selectively utilized to improve geomorphic/hydraulic characterization. The methodology developed here can also be applied to simi

关键词： water boundary channel morphology remote sensing object-based classification spatially explicit accuracy assessment

来源：评论

学校读者我要写书评

暂无评论

Mapping fuels at the wildland-urban interface using colour ortho-images and LiDAR data

引用

GEOCARTO INTERNATIONAL 2014年第5期29卷 570-588页

作者： Rosa, Melissa F. Stow, Douglas A. Conservat Int Arlington VA 22202 USA San Diego State Univ Dept Geog San Diego CA 92182 USA

Fuel type mapping of the wildland-urban interface (WUI) in support of firespread simulation modelling should include both natural and urban features. The objective of this study was to evaluate the utility of (1) Light Detection and Ranging (LiDAR) structural data, (2) ortho-image data, and (3) a combination of both as input to an object-based classification approach for mapping fuels within two WUI areas in San Diego, California. A separability analysis was utilised to determine the surface topographical and spectral layers most influential for discriminating WUI fuels. An accuracy assessment revealed that the combination of LiDAR and ortho-image data inputs substantially increased classification accuracy by 20-30% and achieved overall accuracies > 80%. Results from the study provide knowledge on how reliable fuel types within the WUI can be mapped using high-resolution LiDAR and ortho-image data while presenting new insights into fuel type mapping.

关键词： remote sensing LiDAR multi-senor fusion object-based classification wildland-urban interface

来源：评论

学校读者我要写书评

暂无评论

Near real-time characterisation of urban environments: a holistic approach for monitoring dengue fever risk areas

引用

International Journal of Digital Earth 2014年第11期7卷 916-934页

作者： Muhammad Shahzad Sarfraz Nitin Kumar Tripathi Asanobu Kitamoto Department of Computer Science COMSATS Institute of Information Technology(CIIT)AbbottabadPakistan Remote Sensing and GIS Asian Institute of Technology(AIT)BangkokThailand Digital Content and Media Sciences Research Division National Institute of Informatics(NII)TokyoJapan

Despite frequent use of digital devices in everyday life,cost-effective measurement of public health issues in urban areas is still *** study was,therefore,planned to extract land-use types using object-based and spatial metric approaches to explore the dengue incidence in relation to the surrounding environment in near real-time using Google and Advanced Land Observation Satellite *** characterised image showed useful classification of an urban areawith 77%accuracy and 0.68 *** analysis on public health data indicated that most of the dengue cases were found in densely populated areas surrounded by dense *** living in independent houses having sparsely vegetated surroundings were found to be less *** incidence was more prevalent in people of 5-24 years of age(67%);while in terms of occupation,mostly students,the unemployed,labourers and farmers(88%)were *** general,males were affected slightly more(10%)than *** analyses indicated that most of the dengue cases were around institutions(40%),religious places(18%)and markets(15%).Thus,usage of Digital Earth scalable tools for monitoring health issues would open new ways for maintaining a healthy and sustainable society in the years ahead.

关键词： dengue fever land-use land-cover monitoring dengue risk urban environment object-based classification

来源：评论

学校读者我要写书评

暂无评论

Quantification of recent changes to the forest- tundra ecotone through numerical analysis of aerial photographs

引用

ECOSCIENCE 2014年第3-4期21卷 419-433页

作者： Provencher-Nolet, Laurence Bernier, Monique Levesque, Esther Ctr Eau Terre Environm Inst Natl Rech Sci Quebec City PQ G1K 9A9 Canada Univ Quebec Trois Rivieres Dept Sci Environm Trois Rivieres PQ G9A 5H7 Canada

Arctic ecosystems at the forest-tundra ecotone are particularly sensitive to climate-driven vegetation changes. Many recent studies have observed shifts in vegetation cover, particularly an increase in shrub growth. Here, vegetation changes were assessed at the local scale near Umiujaq, northern Quebec (Canada, 56.55 degrees, 76.55 degrees W) using colour aerial photographs (1994 and 2010). By applying semi-automated image classification methods and change-detection analysis, we were able to detect and map the dominant vegetation cover changes. Comparison of classification results shows a 12% increase in shrub cover, loss of nearly 8% of lichen cover, stability of the spruce zones, and disappearance of nearly a quarter of thermokarst ponds. The 2 resulting maps were superimposed to spatialize the change. Change-detection analysis revealed that a shift toward shrub-dominated landscape was the most important change in the 1994 vegetation classes. This shift affected 18% of the studied area in the valley. The resulting "from-to" land-cover change map illustrates the general ongoing shrubification in the region.

关键词： arctic shrub tundra change-detection analysis object-based classification shrubification Umiujaq

来源：评论

学校读者我要写书评

暂无评论

Remote detection of invasive plants: a review of spectral, textural and phenological approaches

引用

BIOLOGICAL INVASIONS 2014年第7期16卷 1411-1425页

作者： Bradley, Bethany A. Univ Massachusetts Dept Environm Conservat Amherst MA 01003 USA

Remote sensing image analysis is increasingly being used as a tool for mapping invasive plant species. Resulting distribution maps can be used to target management of early infestations and to model future invasion risk. Remote identification of invasive plants based on differences in spectral signatures is the most common approach, typically using hyperspectral data. But several studies have found that textural and phenological differences are also effective approaches for identifying invasive plants. I review examples of remote detection of invasive plants based on spectral, textural and phenological analysis and highlight circumstances where the different approaches are likely to be most effective. I also review sources and availability of remotely sensed data that could be used for mapping and suggest field data collection approaches that would support the analysis of remotely sensed data. Remote mapping of biological invasions remains a relatively specialized research topic, but the distinct cover, morphology and/or seasonality of many invaded versus native ecosystems suggests that more species could be detected remotely. Remote sensing can sometimes support early detection and rapid response directly, however, accurately detecting small, nascent populations is a challenge. However, even maps of heavily infested areas can provide a valuable tool for risk assessment by increasing knowledge about temporal and spatial patterns and predictors of invasion.

关键词： Aerial photograph Hyperspectral Invasive plant object-based classification Phenology Satellite remote sensing

来源：评论

学校读者我要写书评

暂无评论

object based Building Extraction by Quick Bird Image for Population Estimation

Object Based Building Extraction by Quick Bird Image for Pop...

引用

IEEE Joint International Geoscience and Remote Sensing Symposium (IGARSS) / 35th Canadian Symposium on Remote Sensing

作者： Li, Wei Wang, Shiqian Li, Jonathan Univ Waterloo Dept Geog & Environm Management Waterloo ON N2L 3G1 Canada

ISBN: (纸本)9781479957750

This paper used QuickBird high resolution image to estimate the population of the city of Waterloo, ON, Canada. Two approaches of object based classification were compared to extract buildings from the original image. One is rule based classification and the other is example based classification. We chose two districts which are Lakeshore and Columbia as our testing areas. Rule based result is better than example based. The overall accuracy of rule based classification in Lakeshore District and Columbia District are 92.5% and 85.5%. With census data, the average area per person is about 38.8 m(2) and the estimated population of the city of Waterloo is about 109589.

关键词： Keywords high resolution object-based classification population estimation QuickBird

来源：评论

学校读者我要写书评

暂无评论

Development of transferable rule-sets for urban areas using QuickBird satellite imagery

Development of transferable rule-sets for urban areas using ...

引用

IEEE INTERNATIONAL CONFERENCE ON AEROSPACE ELECTRONICS AND REMOTE SENSING (ICARES)

作者： Tathiri, Anahita Shafri, Helmi Zulhaidi Mohd Hamedianfar, Alireza Univ Putra Malaysia Fac Engn Dept Civil Engn Serdang 43400 Selangor Malaysia Univ Putra Malaysia Fac Engn GISRC Serdang 43400 Selangor Malaysia

ISBN: (纸本)9781479961887

Although rule-based object-based classification can often perform better than the supervised approaches, its attribute selection is very time consuming and hardly transferable between different urban areas. The purpose of this study is to identify transferable rule-sets for different areas from QuickBird satellite imagery for urban areas consisting heterogeneous man-made and natural features. object-based classification was used in this research, and a mathematical method was proposed for rule transferability for different urban areas.

关键词： object-based classification transferability rule-based classification urban areas

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：