Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004.最新文献_第2页

Surface height recovery using heat flow and manifold embedding 利用热流和流形嵌入法回收地表高度

Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004. Pub Date : 2004-09-06 DOI: 10.1109/3DPVT.2004.121

A. Robles-Kelly, E. Hancock

引用次数: 1

Efficient model creation of large structures based on range segmentation 基于距离分割的大型结构的高效模型创建

Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004. Pub Date : 2004-09-06 DOI: 10.1109/TDPVT.2004.1335272

I. Stamos, Marius Leordeanu

引用次数: 7

Heterogeneous deformation model for 3D shape and motion recovery from multi-viewpoint images 多视点图像三维形状和运动恢复的非均匀变形模型

Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004. Pub Date : 2004-09-06 DOI: 10.1109/TDPVT.2004.1335289

S. Nobuhara, T. Matsuyama

引用次数: 21

A non causal Bayesian framework for object tracking and occlusion handling for the synthesis of stereoscopic video 一个用于立体视频合成的目标跟踪和遮挡处理的非因果贝叶斯框架

Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004. Pub Date : 2004-09-06 DOI: 10.1109/TDPVT.2004.1335188

K. Moustakas, D. Tzovaras, M. Strintzis

引用次数: 6

Multi-spectral stereo image matching using mutual information 基于互信息的多光谱立体图像匹配

Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004. Pub Date : 2004-09-06 DOI: 10.1109/TDPVT.2004.1335420

C. Fookes, A. Maeder, S. Sridharan, Jamie Cook

{"title":"Multi-spectral stereo image matching using mutual information","authors":"C. Fookes, A. Maeder, S. Sridharan, Jamie Cook","doi":"10.1109/TDPVT.2004.1335420","DOIUrl":"https://doi.org/10.1109/TDPVT.2004.1335420","url":null,"abstract":"Mutual information (MI) has shown promise as an effective stereo matching measure for images affected by radiometric distortion. This is due to the robustness of MI against changes in illumination. However, MI-based approaches are particularly prone to the generation of false matches due to the small statistical power of the matching windows. Consequently, most previous MI approaches utilise large matching windows which smooth the estimated disparity field. This work proposes extensions to MI-based stereo matching in order to increase the robustness of the algorithm. Firstly, prior probabilities are incorporated into the MI measure in order to considerably increase the statistical power of the matching windows. These prior probabilities, which are calculated from the global joint histogram between the stereo pair, are tuned to a two level hierarchical approach. A 2D match surface, in which the match score is computed for every possible combination of template and matching window, is also utilised. This enforces left-right consistency and uniqueness constraints. These additions to MI-based stereo matching significantly enhance the algorithm's ability to detect correct matches while decreasing computation time and improving the accuracy. Results show that the MI measure does not perform quite as well for standard stereo pairs when compared to traditional area-based metrics. However, the MI approach is far superior when matching across multispectra stereo pairs.","PeriodicalId":191172,"journal":{"name":"Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004.","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123964859","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: 34

A graph cut based adaptive structured light approach for real-time range acquisition 一种基于图割的自适应结构光实时距离获取方法

Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004. Pub Date : 2004-09-06 DOI: 10.1109/TDPVT.2004.1335268

T. Koninckx, I. Geys, T. Jaeggli, L. Gool

{"title":"A graph cut based adaptive structured light approach for real-time range acquisition","authors":"T. Koninckx, I. Geys, T. Jaeggli, L. Gool","doi":"10.1109/TDPVT.2004.1335268","DOIUrl":"https://doi.org/10.1109/TDPVT.2004.1335268","url":null,"abstract":"This work describes a new algorithm that yields dense range maps in real-time. Reconstructions are based on a single frame structured light illumination. On-the-fly adaptation of the projection pattern renders the system more robust against scene variability. A continuous trade off between speed and quality is made. The correspondence problem is solved by using geometric pattern coding in combination with sparse color coding. Only local spatial and temporal continuity are assumed. This allows to construct a neighbor relationship within every frame and to track correspondences over time. All cues are integrated in one consistent labeling. This is achieved by reformulating the problem as a graph cut. Every cue is weighted based on its average consistency with the result within a small time window. Integration and weighting of additional cues is straightforward. The correctness of the range maps is not guaranteed, but an estimation of the uncertainty is provided for each part of the reconstruction. Our prototype is implemented using unmodified consumer hardware only. Frame rates vary between 10 and 25 fps dependent on scene complexity.","PeriodicalId":191172,"journal":{"name":"Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004.","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2004-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129283554","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: 29

3D image sensing for bit plane method of progressive transmission 三维图像传感的位平面渐进传输方法

Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004. Pub Date : 2004-09-06 DOI: 10.1109/TDPVT.2004.1335180

D. Loganathan, K. Mehata

引用次数: 1

A unified approach for motion analysis and view synthesis 运动分析和视图合成的统一方法

Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004. Pub Date : 2004-09-06 DOI: 10.1109/TDPVT.2004.1335386

A. Rav-Acha, Shmuel Peleg

引用次数: 12

Spacetime-coherent geometry reconstruction from multiple video streams 从多个视频流的时空相干几何重建

Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004. Pub Date : 2004-09-06 DOI: 10.1109/TDPVT.2004.1335231

M. Magnor, Bastian Goldlücke

引用次数: 16

Theoretical accuracy analysis of N-Ocular vision systems for scene reconstruction, motion estimation, and positioning n -眼视觉系统用于场景重建、运动估计和定位的理论精度分析

Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004. Pub Date : 2004-09-06 DOI: 10.1109/TDPVT.2004.1335409

P. Firoozfam, S. Negahdaripour

引用次数: 13