CVGIP: Image Understanding最新文献

Phase-Based Binocular Vergence Control and Depth Reconstruction Using Active Vision 基于相位的双目收敛控制与主动视觉深度重建

CVGIP: Image Understanding Pub Date : 1994-11-01 DOI: 10.1006/ciun.1994.1061

Theimer W.M., Mallot H.A.

引用次数: 104

Default Shape Theory: With Application to the Computation of the Direction of the Light Source 默认形状理论:在光源方向计算中的应用

CVGIP: Image Understanding Pub Date : 1994-11-01 DOI: 10.1006/ciun.1994.1058

Vega O.E., Yang Y.H.

{"title":"Default Shape Theory: With Application to the Computation of the Direction of the Light Source","authors":"Vega O.E., Yang Y.H.","doi":"10.1006/ciun.1994.1058","DOIUrl":"10.1006/ciun.1994.1058","url":null,"abstract":"<div><p>Humans appear to have the ability to infer the three-dimensional shape of an object from its outline or occluding contour. In computer vision, an occluding contour is an important clue in the shape recovery process. So far, only a small family of shapes, in particular, shapes generated by generalized cylinders, and shapes of polyhedrons, has been investigated in computer vision. However, there are many instances where these types of surfaces are not applicable, e.g., a solid with holes or a solid with no planar surfaces. This paper proposes a new concept called the <em>default shape theory</em> which includes the solid of revolution as a special case. A default shape is a function whose domain is a closed contour and whose range is a vector representation of a three-dimensional solid. The application of this new concept to recover the direction of the light source is demonstrated in this paper. Experimental results show that the default-shape-based method has comparable performance as the Pentland light source determination algorithm. This paper also proves the relationship between one particular type of default shape with the solid of revolution. Other possible definitions of default shape are also discussed.</p></div>","PeriodicalId":100350,"journal":{"name":"CVGIP: Image Understanding","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1994-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1006/ciun.1994.1058","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79298436","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: 18

Finding Planes and Clusters of Objects from 3D Line Segments with Application to 3D Motion Determination 从三维线段中寻找平面和物体簇及其在三维运动确定中的应用

CVGIP: Image Understanding Pub Date : 1994-11-01 DOI: 10.1006/ciun.1994.1057

Zhang Z.Y., Faugeras O.D.

引用次数: 5

Robust Methods for Estimating Pose and a Sensitivity Analysis 姿态估计的鲁棒方法及灵敏度分析

CVGIP: Image Understanding Pub Date : 1994-11-01 DOI: 10.1006/ciun.1994.1060

Kumar R., Hanson A.R.

{"title":"Robust Methods for Estimating Pose and a Sensitivity Analysis","authors":"Kumar R., Hanson A.R.","doi":"10.1006/ciun.1994.1060","DOIUrl":"10.1006/ciun.1994.1060","url":null,"abstract":"<div><p>This paper mathematically analyzes and proposes new solutions for the problem of estimating the camera 3D location and orientation (<em>pose determination</em>) from a matched set of 3D model and 2D image landmark features. Least-squares techniques for line tokens, which minimize both rotation and translation simultaneously, are developed and shown to be far superior to the earlier techniques which solved for rotation first and then translation. However, least-squares techniques fail catastrophically when outliers (or gross errors) are present in the match data. Outliers arise frequently due to incorrect correspondences or gross errors in the 3D model. Robust techniques for pose determination are developed to handle data contaminated by fewer than 50.0% outliers. Finally, the sensitivity of pose determination to incorrect estimates of camera parameters is analyzed. It is shown that for small field of view systems, offsets in the image center do not significantly affect the location of the camera in a world coordinate system. Errors in the focal length significantly affect only the component of translation along the optical axis in the pose computation.</p></div>","PeriodicalId":100350,"journal":{"name":"CVGIP: Image Understanding","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1994-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1006/ciun.1994.1060","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87995181","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: 243

Refining 3D Reconstructions: A Theoretical and Experimental Study of the Effect of Cross-Correlations 细化三维重建:相互关联效应的理论和实验研究

CVGIP: Image Understanding Pub Date : 1994-11-01 DOI: 10.1006/ciun.1994.1062

Thomas J.I., Hanson A., Oliensis J.

{"title":"Refining 3D Reconstructions: A Theoretical and Experimental Study of the Effect of Cross-Correlations","authors":"Thomas J.I., Hanson A., Oliensis J.","doi":"10.1006/ciun.1994.1062","DOIUrl":"https://doi.org/10.1006/ciun.1994.1062","url":null,"abstract":"<div><p>In robot navigation a model of the environment needs to be reconstructed for various applications, including path planning, obstacle avoidance, and determining where the robot is located. Traditionally, the model was acquired using two images (two-frame structure from motion) but the acquired models were unreliable and inaccurate. Recently, research has shifted to using several frames (multiframe structure from motion) instead of just two frames. However, almost none of the reported multiframe algorithms have produced accurate and stable reconstructions for general robot motion. The main reason seems to be that the primary source of error in the reconstruction-the error in the underlying motion-has been mostly ignored. Intuitively, if a reconstruction of the scene is made up of points, this motion error affects each reconstructed point in a systematic way. For example, if the translation of the robot is erroneous in a certain direction, all the reconstructed points would be shifted along the same direction. The contributions of this paper include mathematically isolating the effect of the motion error (as correlations in the structure error) and showing theoretically that these correlations can improve existing multiframe structure from motion techniques. Finally it is shown that new experimental results and previously reported work confirm the theoretical predictions.</p></div>","PeriodicalId":100350,"journal":{"name":"CVGIP: Image Understanding","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1994-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1006/ciun.1994.1062","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91983810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 15

Author Index for Volume 60 第60卷作者索引

CVGIP: Image Understanding Pub Date : 1994-11-01 DOI: 10.1006/ciun.1994.1066

引用次数: 0

Refining 3D reconstruction: a theoretical and experimental study of the effect of cross-correlations 细化三维重建:相互关系影响的理论和实验研究

CVGIP: Image Understanding Pub Date : 1994-11-01 DOI: 10.1006/CIUN.1994.1062

J. I. Thomas, A. Hanson, J. Oliensis

{"title":"Refining 3D reconstruction: a theoretical and experimental study of the effect of cross-correlations","authors":"J. I. Thomas, A. Hanson, J. Oliensis","doi":"10.1006/CIUN.1994.1062","DOIUrl":"https://doi.org/10.1006/CIUN.1994.1062","url":null,"abstract":"Abstract In robot navigation a model of the environment needs to be reconstructed for various applications, including path planning, obstacle avoidance, and determining where the robot is located. Traditionally, the model was acquired using two images (two-frame structure from motion) but the acquired models were unreliable and inaccurate. Recently, research has shifted to using several frames (multiframe structure from motion) instead of just two frames. However, almost none of the reported multiframe algorithms have produced accurate and stable reconstructions for general robot motion. The main reason seems to be that the primary source of error in the reconstruction-the error in the underlying motion-has been mostly ignored. Intuitively, if a reconstruction of the scene is made up of points, this motion error affects each reconstructed point in a systematic way. For example, if the translation of the robot is erroneous in a certain direction, all the reconstructed points would be shifted along the same direction. The contributions of this paper include mathematically isolating the effect of the motion error (as correlations in the structure error) and showing theoretically that these correlations can improve existing multiframe structure from motion techniques. Finally it is shown that new experimental results and previously reported work confirm the theoretical predictions.","PeriodicalId":100350,"journal":{"name":"CVGIP: Image Understanding","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1994-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82205917","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: 15

3D Structure Reconstruction from Point Correspondences between two Perspective Projections 从两个透视投影之间的点对应中重建三维结构

CVGIP: Image Understanding Pub Date : 1994-11-01 DOI: 10.1006/ciun.1994.1065

Kara A., Wilkes D.M., Kawamura K.

{"title":"3D Structure Reconstruction from Point Correspondences between two Perspective Projections","authors":"Kara A., Wilkes D.M., Kawamura K.","doi":"10.1006/ciun.1994.1065","DOIUrl":"10.1006/ciun.1994.1065","url":null,"abstract":"<div><p>An iterative algorithm for 3D structure reconstruction from two perspective projections is proposed. The basis of the method is the <em>eight-point algorithm</em> (Longuet-Higgins, <em>Nature</em> 293(10), 1981, 133-135; Tsai and Huang, <em>IEEE Trans. PAMI</em> 6, 1984, 13-27). A drawback of the eight-point algorithm is that it requires at least eight point correspondences. Further, there are certain point configurations for which the algorithm fails. For example, the eight corners of a cube on a quadratic surface passing through the focal points of the cameras form such a degenerate configuration. By combining the eight-point algorithm with an SVD (singular value decomposition) characterization of the so-called <em>E</em>-matrix (Faugeras and Maybank, <em>Internat. J. Comput. Vision</em> 4, 1990, 225-246; Huang and Faugeras, <em>IEEE Trans. PAMI</em> 11, 1989, 1310-1312), the proposed iterative algorithm solves the 3D reconstruction problem even from less than eight points. The algorithm is also free from the artificial degeneracy problem inherent to the eight-point algorithm. The iteration in the algorithm takes place only if the configuration is degenerate or violates the SVD characterization due to measurement error. Otherwise the computation is <em>O</em>(<em>N</em>) as in the eight-point algorithm.</p></div>","PeriodicalId":100350,"journal":{"name":"CVGIP: Image Understanding","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1994-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1006/ciun.1994.1065","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72611953","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: 3

Computational Cross Ratio for Computer Vision 计算机视觉的计算交叉比

CVGIP: Image Understanding Pub Date : 1994-11-01 DOI: 10.1006/ciun.1994.1063

Kanatani K.

引用次数: 19

Statistical Foundation for Hypothesis Testing of Image Data 图像数据假设检验的统计基础

CVGIP: Image Understanding Pub Date : 1994-11-01 DOI: 10.1006/ciun.1994.1064

Kanatani K.

引用次数: 5