检索结果-内蒙古大学图书馆

Unsupervised image segmentation evaluation and refinement using a multi-scale approach

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2011年第4期66卷 473-483页

作者： Johnson, Brian Xie, Zhixiao Florida Atlantic Univ Dept Geosci Boca Raton FL 33431 USA

In this study, a multi-scale approach is used to improve the segmentation of a high spatial resolution (30 cm) color infrared image of a residential area. First, a series of 25 image segmentations are performed in Definiens Professional 5 using different scale parameters. The optimal image segmentation is identified using an unsupervised evaluation method of segmentation quality that takes into account global intra-segment and inter-segment heterogeneity measures (weighted variance and Moran's I, respectively). Once the optimal segmentation is determined, under-segmented and over-segmented regions in this segmentation are identified using local heterogeneity measures (variance and Local Moran's I). The under- and over-segmented regions are refined by (1) further segmenting under-segmented regions at finer scales, and (2) merging over-segmented regions with spectrally similar neighbors. This process leads to the creation of several segmentations consisting of segments generated at three different segmentation scales. Comparison of single- and multi-scale segmentations shows that identifying and refining underand over-segmented regions using local statistics can improve global segmentation results. Published by Elsevier B.V. on behalf of International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS).

关键词： object-based image analysis Multi-scale segmentation image segmentation evaluation Under-segmentation Over-segmentation

来源：评论

学校读者我要写书评

暂无评论

Comparing object-based and pixel-based classifications for mapping savannas

引用

INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION 2011年第6期13卷 884-893页

作者： Whiteside, Timothy G. Boggs, Guy S. Maier, Stefan W. Bachelor Inst Indigenous Tertiary Educ Fac Hlth Business & Sci Batchelor NT 0845 Australia Charles Darwin Univ Sch Environm & Life Sci Darwin NT 0909 Australia

The development of robust object-based classification methods suitable for medium to high resolution satellite imagery provides a valid alternative to 'traditional' pixel-based methods. This paper compares the results of an object-based classification to a supervised per-pixel classification for mapping land cover in the tropical north of the Northern Territory of Australia. The object-based approach involved segmentation of image data into objects at multiple scale levels. objects were assigned classes using training objects and the Nearest Neighbour supervised and fuzzy classification algorithm. The supervised pixel-based classification involved the selection of training areas and a classification using the maximum likelihood classifier algorithm. Site-specific accuracy assessment using confusion matrices of both classifications were undertaken based on 256 reference sites. A comparison of the results shows a statistically significant higher overall accuracy of the object-based classification over the pixel-based classification. The incorporation of a digital elevation model (DEM) layer and associated class rules into the object-based classification produced slightly higher accuracies overall and for certain classes;however this was not statistically significant over the object-based using spectral information solely. The results indicate object-based analysis has good potential for extracting land cover information from satellite imagery captured over spatially heterogeneous land covers of tropical Australia. (C) 2011 Elsevier B.V. All rights reserved.

关键词： object-based image analysis Accuracy assessment Tropical savanna Northern Australia

来源：评论

学校读者我要写书评

暂无评论

Impacts of conservation buffers and grasslands on total phosphorus loads using hydrological modeling and remote sensing techniques

引用

CATENA 2011年第2期86卷 121-129页

作者： Larose, Myriam Heathman, Gary C. Norton, Darrell Smith, Douglas Purdue Univ USDA ARS Natl Soil Eros Res Lab W Lafayette IN 47907 USA Univ Michigan Sch Nat Resources Ann Arbor MI 48105 USA

To better assess the impacts of conservation buffers and grasslands on water quality at large spatial scales, development and integration of novel approaches are crucial to ensure that these land management practices are functioning properly and meeting their original goals. Recent developments in remote sensing technology have greatly enriched the availability of geospatial data that can be used in hydrological modeling to assess the potential hydrological response of conservation practices over larger areas. A methodology was developed using the object-based image analysis approach with Landsat-5 TM imagery of the year 2005 and thematic layers of streams to quantify conservation buffers and grasslands (OBIA-2005). The OBIA-2005 land cover data was used in the Soil and Water Assessment Tool hydrologic model to assess the impacts of vegetative conservation practices on total phosphorus (TP) loads. The model was calibrated and validated for discharge and TP loads in the Cedar Creek Watershed (CCW) in northeast Indiana. In general model efficiency for streamflow values was within acceptable statistical ranges. While calibration of TP loads was satisfactory for the total contributing area of two nested catchments within the upper CCW. Vegetative buffers of 30.5 m and 61 m combined with conservation grasslands generated from the OBIA-2005 resulted in a large reduction of TP loads as compared to no practices. The results also showed that including conservation grassland alone reduced TP loads by less than 2%. However, the combination of these practices with the width of edge-of-field buffer strips module of the SWAT model achieved the largest TP loads reduction. These findings demonstrate that improved representation of vegetative conservation practices in geospatial land cover data sets are more effective in assessing the impacts of conservation buffers and grasslands on water quality through hydrologic modeling. Published by Elsevier B.V.

关键词： Hydrological modeling object-based image analysis Landsat-5 TM Conservation practices Vegetative buffers Total phosphorus load

来源：评论

学校读者我要写书评

暂无评论

object-based gully feature extraction using high spatial resolution imagery

引用

GEOMORPHOLOGY 2011年第3-4期134卷 260-268页

作者： Shruthi, Rajesh B. V. Kerle, Norman Jetten, Victor Univ Twente Dept Earth Syst Anal Fac Geoinformat Sci & Earth Observat ITC Enschede Netherlands

Gully erosion is responsible for a substantial amount of soil loss and is generally considered an indicator of desertification. Hence, mapping these gully features provides essential information needed on sediment production, identification of vulnerable areas for gully formation, land degradation, and environmental and socio-economical effects. This paper investigates the use of object-oriented image analysis (OOA) to extract gully erosion features from satellite imagery, using a combination of topographic, spectral, shape (geometric) and contextual information obtained from IKONOS and GEOEYE-1 data. A rule-set was developed and tested for a semi-arid to sub-humid region in Morocco. The percentage of gully system area indicated negligible overestimations between the reference area and the OOA area in two sub-watersheds (0.03% and 1.77%). We also observed that finer gully-related edges within the complex gully systems were better identified semi-automatically than was possible by manual digitization, suggesting higher detection accuracy. OOA-based gully mapping is quicker and more objective than traditional methods, and is thus better suited to provide essential information for land managers to support their derision making processes, and for the erosion research community. (C) 2011 Elsevier B.V. All rights reserved.

关键词： Gully erosion object-based image analysis Land degradation High spatial resolution imagery

来源：评论

学校读者我要写书评

暂无评论

Impervious surface area extraction from IKONOS imagery using an object-based fuzzy method

引用

GEOCARTO INTERNATIONAL 2011年第1期26卷 3-20页

作者： Hu, Xuefei Weng, Qihao Indiana State Univ Dept Geog Geol & Anthropol Ctr Urban & Environm Change Terre Haute IN 47809 USA

The study of impervious surfaces is crucial to the sustainable development of urban areas due to its strong impact on urban environments. Remotely sensed high-resolution imagery has the advantage of providing more spatial details;however, digital image processing algorithms have not been well developed to accommodate this advantage and other characteristics of such imagery. In this article, an object-based fuzzy classification approach for impervious surface extraction was developed and applied to two pan-sharpened multi-spectral IKONOS images covering the residential and central business district (CBD) areas of Indianapolis, Indiana, USA. Fuzzy rules based on spectral, spatial and texture attributes, were developed to extract impervious surfaces. An accuracy assessment was performed for the final maps. The results indicated that the spatial patterns of extracted features were in accordance with those in the original images and the boundaries of features were appropriately delineated. Impervious surfaces were extracted with an accuracy of 95% in the residential area and 92% in the CBD area. Road extraction achieved accuracy a bit lower, with 93% and 90% from the residential and CBD area, respectively. Buildings were extracted with an accuracy of 94% from the residential area while 89% from the CBD area. It is suggested that the CBD area had a higher spectral complexity, building displacement and the shadow problem, leading to a more difficult estimation and mapping of impervious surfaces.

关键词： object-based image analysis fuzzy method impervious surfaces urban areas high-resolution satellite imagery

来源：评论

学校读者我要写书评

暂无评论

object-based analysis of CT images for automatic detection and segmentation of hypodense liver lesions

引用

INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY 2011年第6期6卷 737-747页

作者： Schwier, Michael Moltz, Jan Hendrik Peitgen, Heinz-Otto Fraunhofer MEVIS Inst Med Image Comp D-28359 Bremen Germany

Hypodense liver lesions are commonly detected in CT, so their segmentation and characterization are essential for diagnosis and treatment. Methods for automatic detection and segmentation of liver lesions were developed to support this task. The detection algorithm uses an object-based image analysis approach, allowing for effectively integrating domain knowledge and reasoning processes into the detection logic. The method is intended to succeed in cases typically difficult for computer-aided detection systems, especially low contrast of hypodense lesions relative to healthy tissue. The detection stage is followed by a dedicated segmentation algorithm needed to synthesize 3D segmentations for all true-positive findings. The automated method provides an overall detection rate of 77.8% with a precision of 0.53 and performs better than other related methods. The final lesion segmentation delivers appropriate quality in 89% of the detected cases, as evaluated by two radiologists. A new automated liver lesion detection algorithm employs the strengths of an object-based image analysis approach. The combination of automated detection and segmentation provides promising results with potential to improve diagnostic liver lesion evaluation.

关键词： Computer-aided detection Liver lesions Liver tumors object-based image analysis Lesion segmentation

来源：评论

学校读者我要写书评

暂无评论

Scale-Space Representation of Remote Sensing images using an object-Oriented Approach

Scale-Space Representation of Remote Sensing Images using an...

引用

Conference on the Geospatial InfoFusion Systems and Solutions for Defense and Security Applications

作者： Syed, Abdul Haleem Saber, Eli Messinger, David Rochester Inst Technol Chester F Carlson Ctr Imaging Sci Rochester NY 14623 USA

ISBN: (纸本)9780819486271

Today's high resolution remotely sensed images (<1m) pose several challenges which require solutions that go beyond the traditional spectral based methodologies. With the rapid increase in the level of detail present in these images, there is also an increase in the complexity. To deal with this complexity a consistent framework and image representation is needed. An object-based scale-space representation is proposed. Principles of object-based design are explained and the application of these principles to image regions is introduced. Given an input image, the scale-tree is automatically constructed using low-level information, starting with single pixels (as objects) and ending with the root node indicating the complete image. The scale-tree is a hierarchical structure where each level in the hierarchy differs from the next in the size of the objects/regions present at that level. Hence, the scale-tree reflects the scale-space breakdown of the image. From another point of view the scale-tree can also be seen as a collection of multiple segmentations with varying level of detail going from fine to coarse. Synthetic and real high resolution satellite images were used to evaluate our image representation. The goal of the proposed representation is to facilitate applications such as target/anomaly detection, image region classification and change detection.

关键词： image representation scale-space object-based image analysis segmentation region merging spatial processing scale-tree

来源：评论

学校读者我要写书评

暂无评论

TERRASAR-X AND RAPIDEYE DATA FOR THE PARAMETERISATION OF RELATIONAL CHARACTERISTICS OF URBAN ATKIS DLM objectS

TERRASAR-X AND RAPIDEYE DATA FOR THE PARAMETERISATION OF REL...

引用

ISPRS Hannover Workshop on High-Resolution Earth Imaging for Geospatial Information

作者： Hese, S. Lindner, M. Voltersen, M. Berger, C. Univ Jena Dept Geog D-07737 Jena Germany

This work presents a multi-sensor data analysis concept for the parameterisation of urban landuse in comparison to ATKIS DLM reference objects (digital landscape model). An object based top-down approach is implemented and the potential of multisensor data for a primary urban landcover object classification is assessed. Urban landuse structure is developed based on relational features applied to land cover objects and compared to an aggregated DLM class legend. For a better imperviousness description an advanced imperviousness measure - the build-up impervious intensity ratio is developed that takes building height and derived floor area (based on LiDAR data) and the amount of vegetation within a search radius to every building into account. The developed concept is parameterized with test areas in Rostock and transferability is investigated with data coverage in Cologne (Germany). The work is linked to the urban work package of the DLR funded ENVILAND-2 project that aims to develop operational concepts for the use of TerraSAR-X and Rapideye data in urban mapping scenarios.

关键词： Urban land use object-based image analysis RapidEye TerraSAR-X ENVILAND-2 DLM

来源：评论

学校读者我要写书评

暂无评论

DELINEATING PARAMETERS FOR object-based URBAN STRUCTURE MAPPING IN SANTIAGO DE CHILE USING QUICKBIRD DATA

DELINEATING PARAMETERS FOR OBJECT-BASED URBAN STRUCTURE MAPP...

引用

ISPRS Hannover Workshop on High-Resolution Earth Imaging for Geospatial Information

作者： Huck, A. Hese, S. Banzhaf, E. Univ Jena Dept Geog D-07737 Jena Germany UFZ Helmholtz Ctr Environm Res Dept Urban & Environm Sociol D-04318 Leipzig Germany

This work aims to parameterize the urban structure types (UST) in Santiago de Chile on statistical block level. In connotation of remote sensing UST are defined as land-use structure entities. Central input data for this object-oriented approach is spatially very high resolution panfused and atmospherically corrected Quickbird data. To analyse and assess the structural properties of urban land-cover objects within block level entities, basic and robust land-cover class descriptions are developed. For enhanced class descriptions several image object scales are created. based on defined UST and additional field data a set of test areas is selected for four municipalities assigned to different socio-spatial clusters in Santiago de Chile. In all test areas the distribution of the basic land-cover classes is parameterized using complex sub-object and relational image object descriptions. The central features to characterise the UST in this study are percentage area and density of subscale land-cover class objects. To carry out this analysis, the expert knowledge on UST is valuable to choose specific reference objects within the statistical block level. After the concept is implemented at the smallest scale, the approach can successfully be applied to the whole municipality once specific structural information are aggregated. The work is linked to activities of the project Risk Habitat Megacity and developed in close cooperation with the Helmholtz Centre for Environmental Research - UFZ in Leipzig, Germany. Finally, the resulting land-use structure entities will be linked to socio-spatial characteristics in the above mentioned cluster with respect to urban vulnerability.

关键词： urban structure types (UST) object-based image analysis Quickbird data Santiago de Chile land use/land cover Risk Habitat Megacity

来源：评论

学校读者我要写书评

暂无评论

Data fusion of extremely high resolution aerial imagery and LiDAR data for automated railroad centre line reconstruction

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2011年第6期66卷 S40-S51页

作者： Beger, Reinhard Gedrange, Claudia Hecht, Robert Neubert, Marco Leibniz Inst Ecol & Reg Dev IOER Dresden Germany

The quality of remotely sensed data in regards of accuracy and resolution has considerably improved in recent years. Very small objects are detectable by means of imaging and laser scanning, yet there are only few studies to use such data for large scale mapping of railroad infrastructure. In this paper, an approach is presented that integrates extremely high resolution ortho-imagery and dense airborne laser scanning point clouds. These data sets are used to reconstruct railroad track centre lines. A feature level data fusion is carried out in order to combine the advantages of both data sets and to achieve a maximum of accuracy and completeness. The workflow consists of three successive processing steps. First, object-based image analysis is used to derive a railroad track mask from ortho-imagery. This spatial location information is then combined with the height information to classify the laser points. Lastly, the location of railroad track centre lines from these classified points were approximated using a feature extraction method based on an adapted random sample consensus algorithm. This workflow is tested on two railroad sections and was found to deliver very accurate results in a quickly and highly automated manner. (C) 2011 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS) Published by Elsevier B.V. All rights reserved.

关键词： Multi-source data fusion object-based image analysis LiDAR Aerial imagery RANSAC object extraction

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：