Applied Imagery Pattern Recognition Workshop, 2002. Proceedings.最新文献_第3页

Use of physics based models in hyperspectral image exploitation 基于物理模型在高光谱图像开发中的应用

Applied Imagery Pattern Recognition Workshop, 2002. Proceedings. Pub Date : 2002-10-16 DOI: 10.1109/AIPR.2002.1182252

J. Schott, Kyungsuk Lee, R. Raqueño, Gary Hoffmann

引用次数: 2

A level set method for the extraction of roads from multispectral imagery 一种多光谱图像道路提取的水平集方法

Applied Imagery Pattern Recognition Workshop, 2002. Proceedings. Pub Date : 2002-10-16 DOI: 10.1109/AIPR.2002.1182268

T. Keaton, J. Brokish

{"title":"A level set method for the extraction of roads from multispectral imagery","authors":"T. Keaton, J. Brokish","doi":"10.1109/AIPR.2002.1182268","DOIUrl":"https://doi.org/10.1109/AIPR.2002.1182268","url":null,"abstract":"With the advances in remote sensing technologies, the extraction of roads and other linear features from satellite and aerial imagery has gained substantial interest in recent years. The introduction of satellite imagery characterized by high spectral and spatial resolutions has made possible the development of new viable approaches for the accurate, and cost-effective extraction of linear features with minimal human intervention. This paper presents a semi-automated method for the extraction of roads from high resolution (1 meter) pan-sharpened multispectral IKONOS imagery. An operator provides an initial seed point on the road of interest, then the region is grown using a level set method. Further analysis through iterative smoothing refines the extracted region to accurately estimate the road centerline despite the presence of cars on the road, changes in the pavement or surface properties of the road, or obstruction resulting from foliage or shadows cast on the road by neighboring trees. Initial results have demonstrated the utility of the algorithm in efficiently extracting roads from high resolution satellite imagery with minimal human interaction. Over 97 % delineation accuracy was achieved on manually ground truthed IKONOS image samples overlooking both urban and rural locations.","PeriodicalId":379110,"journal":{"name":"Applied Imagery Pattern Recognition Workshop, 2002. Proceedings.","volume":"29 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115685601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 41

Enhancing spatial resolution for exploitation in hyperspectral imagery 提高高光谱图像开发的空间分辨率

Applied Imagery Pattern Recognition Workshop, 2002. Proceedings. Pub Date : 2002-10-16 DOI: 10.1109/AIPR.2002.1182250

H. Rhody

引用次数: 3

The empire that was Russia: the Prokudin-Gorskii photographic record re-created 曾经的俄罗斯帝国:重现的普罗库丁-戈尔斯基摄影记录

Applied Imagery Pattern Recognition Workshop, 2002. Proceedings. Pub Date : 2002-10-16 DOI: 10.1109/AIPR.2002.1182269

L. E. Brooks

{"title":"The empire that was Russia: the Prokudin-Gorskii photographic record re-created","authors":"L. E. Brooks","doi":"10.1109/AIPR.2002.1182269","DOIUrl":"https://doi.org/10.1109/AIPR.2002.1182269","url":null,"abstract":"The story of the effort of the Library of Congress to preserve and make accessible color images taken by the innovative scientist-photographer Sergei Mikhailovich Prokudin-Gorskii begins a century ago in prerevolutionary Russia and ends with Internet access to stunning digital reproductions created by LC staffers and others. The story involves Tsar Nicholas II, the hiding of images in cellars deep below Paris during World War II, and the use of modern digital, high-resolution scanners and computer software to render more than 121 digital images in vibrant natural colors derived from Prokudin-Gorskii's glass-plate negatives. In 2000, as part of the effort to preserve the images, the Library of Congress scanned all 1,903 original glass-plate negatives at uninterpolated 1,000 pixels/inch, 16-bit grayscale mode, saving them as uncompressed TIFF format image files. Information Technology Services (ITS) staff located experts with the photography expertise and digital image technology to recover full-color digital images from these near-century-old \"color-separation\" negatives. Many Library divisions and two contractors collaborated on this project, which culminated in an exhibition in 2001. There is ready access to all the negatives and albums in the Prints and Photographs Online Catalog, http://lcweb2.loc.gov/pp/pphome.html.","PeriodicalId":379110,"journal":{"name":"Applied Imagery Pattern Recognition Workshop, 2002. Proceedings.","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122792041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Matched affine joint subspace detection in remote hyperspectral reconnaissance 远程高光谱侦察中的匹配仿射联合子空间检测

Applied Imagery Pattern Recognition Workshop, 2002. Proceedings. Pub Date : 2002-10-16 DOI: 10.1109/AIPR.2002.1182249

A. Schaum

引用次数: 2

Analysis of multispectral imagery and modeling contaminant transport 多光谱图像分析和污染物迁移建模

Applied Imagery Pattern Recognition Workshop, 2002. Proceedings. Pub Date : 2002-10-16 DOI: 10.1109/AIPR.2002.1182257

N. Becker, S. Brumby, N. David, J. Irvine

{"title":"Analysis of multispectral imagery and modeling contaminant transport","authors":"N. Becker, S. Brumby, N. David, J. Irvine","doi":"10.1109/AIPR.2002.1182257","DOIUrl":"https://doi.org/10.1109/AIPR.2002.1182257","url":null,"abstract":"A significant concern in the monitoring of hazardous waste is the potential for contaminants to migrate into locations where their presence poses greater environmental risks. The transport modeling performed in this study demonstrates the joint use of remotely sensed multispectral imagery and mathematical modeling to assess the surface migration of contaminants. KINEROS, an event-driven model of surface runoff and sediment transport, was used to assess uranium transport for various rain events. The model inputs include parameters related to the size and slope of watershed components, vegetation, and soil conditions. One distinct set of model inputs was derived from remotely sensed imagery data and another from site-specific knowledge. To derive the parameters of the KINEROS model from remotely sensed data, classification analysis was performed on IKONOS four-band multispectral imagery of the watershed. A system known as GENIE, developed by Los Alamos National Laboratory, employs genetic algorithms to evolve classifiers based on small, user-selected training samples. The classification analysis derived by employing GENIE provided insight into the correct KINEROS parameters for various sub-elements of the watershed. The model results offer valuable information about portions of the watershed that contributed the most to contaminant transport. These methods are applicable to numerous sites where possible transport of waste materials poses an environmental risk. Because the approach rests on the analysis of remote sensing data, the techniques can be used to monitor inaccessible waste sites, as well as reduce the amount of data that would need to be collected for model calibration.","PeriodicalId":379110,"journal":{"name":"Applied Imagery Pattern Recognition Workshop, 2002. Proceedings.","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131411481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sensor fusion for target detection and tracking 用于目标探测和跟踪的传感器融合

Applied Imagery Pattern Recognition Workshop, 2002. Proceedings. Pub Date : 2002-10-16 DOI: 10.1109/AIPR.2002.1182276

R. Bonneau, S. Ertan, J. Perretta, K. Shaw, B. Rahn

引用次数: 5

Unsupervised hyperspectral image segmentation using a new class of neuro-fuzzy systems based on weighted incremental neural networks 基于加权增量神经网络的一种新型神经模糊系统的无监督高光谱图像分割

Applied Imagery Pattern Recognition Workshop, 2002. Proceedings. Pub Date : 2002-10-16 DOI: 10.1109/AIPR.2002.1182272

H. Muhammed

{"title":"Unsupervised hyperspectral image segmentation using a new class of neuro-fuzzy systems based on weighted incremental neural networks","authors":"H. Muhammed","doi":"10.1109/AIPR.2002.1182272","DOIUrl":"https://doi.org/10.1109/AIPR.2002.1182272","url":null,"abstract":"Segmenting hyperspectral images is an important task for simplifying the analysis of the data by focusing on a certain part of the data set or on data samples of the same or at least \"nearby\" spectral properties. A new class of neuro-fuzzy systems, based on so-called weighted incremental neural networks (WINN), is briefly introduced, exemplified and finally used for unsupervised segmentation of hyperspectral images. The WINN algorithm produces a net of nodes connected by edges, which reflects and preserves the topology of the input data set. Additional weights, which are proportional to the local data densities in the input space, are associated with the resulting nodes and edges to store useful information about the topological relations in the given input data set. A fuzziness factor, related to the connectedness of the net, is introduced in the system. A watershed-like procedure is used to cluster the resulting net. The number of the resulting clusters is determined by this procedure. Experimental results underline the usefulness and efficiency of the proposed neuro-fuzzy system for multi-dimensional data clustering and image segmentation, especially hyperspectral images.","PeriodicalId":379110,"journal":{"name":"Applied Imagery Pattern Recognition Workshop, 2002. Proceedings.","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2002-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132880789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

Hyperspectral sensor testbed for real-time algorithm evaluation 高光谱传感器实时算法评估试验台

Applied Imagery Pattern Recognition Workshop, 2002. Proceedings. Pub Date : 2002-01-21 DOI: 10.1109/AIPR.2002.1182259

J. Jafolla, M. Dombrowski

引用次数: 1