发布求助
文献互助 智能选刊 最新文献

Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)最新文献

筛选
英文 中文
Hand-held acquisition of 3D models with a video camera 手持获取3D模型与视频摄像机
Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062) Pub Date : 1999-10-04 DOI: 10.1109/IM.1999.805330
M. Pollefeys, R. Koch, M. Vergauwen, L. Gool
{"title":"Hand-held acquisition of 3D models with a video camera","authors":"M. Pollefeys, R. Koch, M. Vergauwen, L. Gool","doi":"10.1109/IM.1999.805330","DOIUrl":"https://doi.org/10.1109/IM.1999.805330","url":null,"abstract":"Modeling of 3D objects from image sequences is a challenging problem and has been a research topic for many years. Important theoretical and algorithmic results were achieved that allow to extract even complex 3D scene models from images. One recent effort has been to reduce the amount of calibration and to avoid restrictions on the camera motion. In this contribution an approach is described which achieves this goal by combining state-of-the-art algorithms for uncalibrated projective reconstruction, self-calibration and dense correspondence matching.","PeriodicalId":110347,"journal":{"name":"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125939484","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: 76
Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room 基于外观的虚拟视图生成的时间变化事件从多相机图像在3D房间
Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062) Pub Date : 1999-10-04 DOI: 10.1109/IM.1999.805384
H. Saito, Shigeyuki Baba, M. Kimura, S. Vedula, T. Kanade
{"title":"Appearance-based virtual view generation of temporally-varying events from multi-camera images in the 3D room","authors":"H. Saito, Shigeyuki Baba, M. Kimura, S. Vedula, T. Kanade","doi":"10.1109/IM.1999.805384","DOIUrl":"https://doi.org/10.1109/IM.1999.805384","url":null,"abstract":"We present an \"appearance based\" virtual view generation method for temporally-varying events taken by multiple cameras of the \"3D Room\", developed by our group. With this method we can generate images from any virtual view point between two selected real views. The virtual appearance view generation method is based on simple interpolation between two selected views. The correspondence between the views are automatically generated from the multiple images by use of the volumetric model shape reconstruction framework. Since the correspondences are obtained by the recovered volumetric model, even occluded regions in the views can be correctly interpolated in the virtual view images. The virtual view image sequences are presented for demonstrating the performance of the virtual view image generation in the 3D Room.","PeriodicalId":110347,"journal":{"name":"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126732678","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: 69
Modeling structured environments by a single moving camera 通过单个移动摄像机建模结构化环境
Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062) Pub Date : 1999-10-04 DOI: 10.1109/IM.1999.805364
T. Repo, J. Röning
{"title":"Modeling structured environments by a single moving camera","authors":"T. Repo, J. Röning","doi":"10.1109/IM.1999.805364","DOIUrl":"https://doi.org/10.1109/IM.1999.805364","url":null,"abstract":"We address the problem of the recovery of motion and a 3D model of environment with moving monocular vision. The vision sensor developed here is able to model structured environments in real time. Features such as corners and straight lines are tracked from image sequences. Their location and the motion of the camera are estimated with Kalman filters. Unlike in the conventional solution, these estimations are separated. There is a Kalman filter for each feature of the model. With this separation, it is simple to insert new objects into the environment model as they appear in the camera view. In addition, it is possible to use several separate modelers that update the common environment model. It is shown with several tests that motion estimation works well even with rather difficult real world scenes, but to obtain better 3D models, centers and straight lines are not discriminating enough to model such scenes.","PeriodicalId":110347,"journal":{"name":"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121229361","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: 4
Generating smooth surfaces with bicubic splines over triangular meshes: toward automatic model building from unorganized 3D points 在三角形网格上生成具有双三次样条的光滑表面:从无组织的3D点自动建立模型
Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062) Pub Date : 1999-10-04 DOI: 10.1109/IM.1999.805360
T. Ueshiba, G. Roth
{"title":"Generating smooth surfaces with bicubic splines over triangular meshes: toward automatic model building from unorganized 3D points","authors":"T. Ueshiba, G. Roth","doi":"10.1109/IM.1999.805360","DOIUrl":"https://doi.org/10.1109/IM.1999.805360","url":null,"abstract":"The paper presents an algorithm for constructing tangent plane continuous (G/sup 1/) surfaces with piecewise polynomials over triangular meshes. The input mesh can be of arbitrary topological type, that is, any number of faces can meet at a mesh vertex. The mesh is first refined to one solely with quadrilateral cells. Rectangular Bezier patches are then assigned to each of the cells and control points are determined so that G/sup 1/ continuity across the patch boundaries is maintained. Since all the patches are rectangular, the resulting surface can be rendered efficiently by current commercial graphic hardware/software. In addition, by exploiting the fact that all the faces of the original mesh are triangular, the degree of each patch is optimized to three while a more general method dealing with arbitrary irregular meshes requires biquartic patches. Several surface examples generated from real 3D data are shown.","PeriodicalId":110347,"journal":{"name":"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124228773","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: 9
Progressive multilevel meshes from octree particles 八叉树粒子的渐进多级网格
Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062) Pub Date : 1999-10-04 DOI: 10.1109/IM.1999.805359
Y. Yemez, F. Schmitt
{"title":"Progressive multilevel meshes from octree particles","authors":"Y. Yemez, F. Schmitt","doi":"10.1109/IM.1999.805359","DOIUrl":"https://doi.org/10.1109/IM.1999.805359","url":null,"abstract":"We present a multilevel object modeling scheme adapted to storage and progressive transmission of complex 3D objects. Geometry and texture are encoded in terms of surface particles associated to a hierarchical space partitioning via an octree. Proper ordering of surface particles results in a compact multilevel representation without increasing the size of the uni-resolution model which provides the highest level of detail. This compact representation can be progressively decoded by the viewer and transformed by a fast direct triangulation technique into a sequence of triangle meshes of increasing levels of detail. The proposed scheme is demonstrated with 3D models of real objects constructed by a shape from silhouette technique.","PeriodicalId":110347,"journal":{"name":"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130009904","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: 20
Extraction and tracking of surfaces in range image sequences 距离图像序列中曲面的提取与跟踪
Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062) Pub Date : 1999-10-04 DOI: 10.1109/IM.1999.805355
Xiaoyi Jiang, S. Hofer, T. Stahs, I. Ahrns, H. Bunke
{"title":"Extraction and tracking of surfaces in range image sequences","authors":"Xiaoyi Jiang, S. Hofer, T. Stahs, I. Ahrns, H. Bunke","doi":"10.1109/IM.1999.805355","DOIUrl":"https://doi.org/10.1109/IM.1999.805355","url":null,"abstract":"Traditionally, feature extraction and correspondence determination are handled separately in motion analysis of (range) image sequences. The correspondence determination methods have typically an exponential computational complexity. We introduce a novel framework of motion analysis that unifies feature extraction and correspondence determination in a single process. Under the basic assumption of a small relative motion between the camera and the scene, feature extraction is solved by refining the segmentation result of the previous frame. In this way, correspondence information becomes directly available as a by-product of the feature extraction process. Due to the coupled processing of frames, we also force some degree of segmentation stability. First results on real range image sequences have demonstrated the potential of our approach.","PeriodicalId":110347,"journal":{"name":"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)","volume":"206 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133421555","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: 11
A 3D scanning system based on low-occlusion approach 基于低遮挡方法的三维扫描系统
Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062) Pub Date : 1999-10-04 DOI: 10.1109/IM.1999.805383
Bor-Tow Chen, W. Lou, Chia-Chen Chen, Hsien-Chang Lin
{"title":"A 3D scanning system based on low-occlusion approach","authors":"Bor-Tow Chen, W. Lou, Chia-Chen Chen, Hsien-Chang Lin","doi":"10.1109/IM.1999.805383","DOIUrl":"https://doi.org/10.1109/IM.1999.805383","url":null,"abstract":"In order to enhance the performance of a 3D laser scanning system, a low occlusion approach is analyzed to find the best view for scanning by considering the object position instead of the sensor position. Based on a 2-axis 3D color scanner developed by OES/ITRI, the best position (BP) of an object on the rotary table will be focused to meet the best view requirements for the low cost scanner. Since the 2-axis 3D scanner only consists of linear and rotary moving apparatuses, in general, it needs 2 or more scanning processes to capture multiple layers to register and merge to a complete 3D file. In order to optimize the scanned layers and minimize the amount of data, we propose an algorithm to effectively decrease the amount of scanned layers and to acquire best-view data in the 2-axis 3D scanner based on the proposed best-position criteria. In the experimental results, the emphasized problems of the worst case really occur when the object is set at an infeasible position. And the best-view scanning is illustrated after the object is reallocated suitably with the best position by the proposed algorithm. Hence, besides the NBV problem, the low-occlusion criteria proposed in the paper also play an important role for acquiring complete 3D data. In future, we will focus on the development of the automatic procedure to combine the NBV solution to achieve more efficient scanning for any complex 3D model.","PeriodicalId":110347,"journal":{"name":"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129843665","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: 11
Indoor scene reconstruction from sets of noisy range images 基于噪声范围图像的室内场景重建
Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062) Pub Date : 1999-10-04 DOI: 10.1109/IM.1999.805365
J. Gregor, R. Whitaker
{"title":"Indoor scene reconstruction from sets of noisy range images","authors":"J. Gregor, R. Whitaker","doi":"10.1109/IM.1999.805365","DOIUrl":"https://doi.org/10.1109/IM.1999.805365","url":null,"abstract":"The paper describes a system for indoor scene modeling from sets of noisy laser range images. We address several important aspects thereof: preprocessing, which includes image segmentation and planar model fitting; view registration, which is the method of determining the rigid transformation that describes the relative pose of the camera platform between views; and reconstruction, which is the subsequent integration or fusion of separate range images into a single 3D model. We give an empirical analysis, which demonstrates the efficacy of our plane-based registration strategy and results in real data that show the performance of the reconstruction system in its entirety.","PeriodicalId":110347,"journal":{"name":"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128324615","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: 47
On estimating the position of fragments on rotational symmetric pottery 关于旋转对称陶器碎片位置的估计
Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062) Pub Date : 1999-10-04 DOI: 10.1109/IM.1999.805377
Robert Sablatnig, C. Menard
{"title":"On estimating the position of fragments on rotational symmetric pottery","authors":"Robert Sablatnig, C. Menard","doi":"10.1109/IM.1999.805377","DOIUrl":"https://doi.org/10.1109/IM.1999.805377","url":null,"abstract":"The activation of ancient vessel-fragments is a time consuming but important task for archaeologists. The basis for classification and reconstruction is the profile which is the cross-section of the fragment in the direction of the rotational axis of symmetry. Hence the position of a fragment (orientation) on a vessel is important. In this work the estimation of the axis of rotation out of range data by using a Hough inspired method is proposed. In order to avoid outliers a robust method for estimation of the axis is used. Classification and reconstruction are performed in a bottom-up manner using a description language, which holds all features of the fragment as primitives and all properties among features as relations. Classification of newly found fragments of unknown type is performed by comparing the description of the new fragment with the description of already classified fragments by completing graph similarity. The sub-graph with the highest similarity is then used to reconstruct the complete vessel out of the fragment.","PeriodicalId":110347,"journal":{"name":"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)","volume":"28 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127296628","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: 7
Joined segmentation of cortical surface and brain volume in MRI using a homotopic deformable cellular model 使用同位可变形细胞模型的MRI皮质表面和脑体积的连接分割
Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062) Pub Date : 1999-10-04 DOI: 10.1109/IM.1999.805354
Y. Cointepas, I. Bloch, L. Garnero
{"title":"Joined segmentation of cortical surface and brain volume in MRI using a homotopic deformable cellular model","authors":"Y. Cointepas, I. Bloch, L. Garnero","doi":"10.1109/IM.1999.805354","DOIUrl":"https://doi.org/10.1109/IM.1999.805354","url":null,"abstract":"The paper presents a novel method to segment both the brain volume and the cortical surface from a MR image of the head using a single model. This method is based on an original deformable model which can handle jointly volumes and surfaces using a cellular complex based representation. The model is initialized on the outer brain surface and then deformed inside the cortex folds according to both volumic and surfacic constraints, while preserving topology.","PeriodicalId":110347,"journal":{"name":"Second International Conference on 3-D Digital Imaging and Modeling (Cat. No.PR00062)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132468826","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: 7
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信