Matching two perspective views

A computational approach to image matching is described. It uses multiple attributes associated with each image point to yield a generally overdetermined system of constraints, taking into account possible structural discontinuities and occlusions. In the algorithm implemented, intensity, edgeness, and cornerness attributes are used in conjunction with the constraints arising from intraregional smoothness, field continuity and discontinuity, and occlusions to compute dense displacement fields and occlusion maps along the pixel grids. The intensity, edgeness, and cornerness are invariant under rigid motion in the image plane. In order to cope with large disparities, a multiresolution multigrid structure is employed. Coarser level edgeness and cornerness measures are obtained by blurring the finer level measures. The algorithm has been tested on real-world scenes with depth discontinuities and occlusions. A special case of two-view matching is stereo matching, where the motion between two images is known. The algorithm can be easily specialized to perform stereo matching using the epipolar constraint     

Matching perspective views of a polyhedron using circuits

We present a novel approach for finding corresponding points between two line drawings extracted from perspective views of a moving object whose surface is composed of planar polygons. In our approach, each circuit of the drawings is encoded with a boundary shape code which we call the RLCC code (run length code of convex and concave strings), then a clustering technique is used to obtain the matching result recursively. A series of measures are taken to make the algorithm tolerate considerable dissimilarities which may exist between the two drawings, such as missing lines, scale differences, rotation, perspective shape distortions, etc. Experimental results are presented.     

Direction-based multiple views on data

World Wide Web - In this paper, we propose the direction heat maps to visualize the spreads of points w.r.t. different observers in the Euclidean space. It is a new way to look points....     

Infinite factorization of multiple non-parametric views

Combined analysis of multiple data sources has increasing application interest, in particular for distinguishing shared and source-specific aspects. We extend this rationale to the generative and non-parametric clustering setting by introducing a novel non-parametric hierarchical mixture model. The lower level of the model describes each source with a flexible non-parametric mixture, and the top level combines these to describe commonalities of the sources. The lower-level clusters arise from hierarchical Dirichlet Processes, inducing an infinite-dimensional contingency table between the sources. The commonalities between the sources are modeled by an infinite component model of the contingency table, interpretable as non-negative factorization of infinite matrices, or as a prior for infinite contingency tables. With Gaussian mixture components plugged in for continuous measurements, the model is applied to two views of genes, mRNA expression and abundance of the produced proteins, to expose groups of genes that are co-regulated in either or both of the views. We discover complex relationships between the marginals (that are multimodal in both marginals) that would remain undetected by simpler models. Cluster analysis of co-expression is a standard method of screening for co-regulation, and the two-view analysis extends the approach to distinguishing between pre- and post-translational regulation.     

On model checking multiple hybrid views

Many applications, for instance the MS .NET Global Assembly Cache (GAC), are naturally expressed as 3-valued models where an additional third truth value models uncertainty or under-specification. An example of under-specification is that a component in a GAC may or may not have a main method. Models described in this manner can then be analyzed to refute or verify properties about the concrete systems they intend to model. This approach to system validation traditionally considers only one model at a time, even though this model may evolve if subjected to analysis. Many applications, however, benefit from or require the simultaneous consideration of multiple models of systems. We mention here requirements from different stake holders, and data drawn from federated databases.     

Simultaneous registration of multiple views with markers

We propose a new model for simultaneous registration of multiple range views. The registration model minimizes a hybrid metric that is a combination of the tangent distance error and the sliding penalty. As a result, the proposed method is capable of reducing the sliding error in registration, especially for an object containing flat features. We used kinematical geometry to linearize rigid-body motions and approximate the registration model with a quadratic objective function, which leads to solving linear equations at each iteration. We also describe experiments indicating that our registration algorithm is insensitive to the initial alignment and maintains global stability.     

Model-based human shape reconstruction from multiple views

Image-based modelling allows the reconstruction of highly realistic digital models from real-world objects. This paper presents a model-based approach to recover animated models of people from multiple view video images. Two contributions are made, a multiple resolution model-based framework is introduced that combines multiple visual cues in reconstruction. Second, a novel mesh parameterisation is presented to preserve the vertex parameterisation in the model for animation. A prior humanoid surface model is first decomposed into multiple levels of detail and represented as a hierarchical deformable model for image fitting. A novel mesh parameterisation is presented that allows propagation of deformation in the model hierarchy and regularisation of surface deformation to preserve vertex parameterisation and animation structure. The hierarchical model is then used to fuse multiple shape cues from silhouette, stereo and sparse feature data in a coarse-to-fine strategy to recover a model that reproduces the appearance in the images. The framework is compared to physics-based deformable surface fitting at a single resolution, demonstrating an improved reconstruction accuracy against ground-truth data with a reduced model distortion. Results demonstrate realistic modelling of real people with accurate shape and appearance while preserving model structure for use in animation.     

Self-calibration of an affine camera from multiple views

A key limitation of all existing algorithms for shape and motion from image sequences under orthographic, weak perspective and para-perspective projection is that they require the calibration parameters of the camera. We present in this paper a new approach that allows the shape and motion to be computed from image sequences without having to know the calibration parameters. This approach is derived with the affine camera model, introduced by Mundy and Zisserman (1992), which is a more general class of projections including orthographic, weak perspective and para-perspective projection models. The concept of self-calibration, introduced by Maybank and Faugeras (1992) for the perspective camera and by Hartley (1994) for the rotating camera, is then applied for the affine camera.This paper introduces the 3 intrinsic parameters that the affine camera can have at most. The intrinsic parameters of the affine camera are closely related to the usual intrinsic parameters of the pin-hole perspective camera, but are different in the general case. Based on the invariance of the intrinsic parameters, methods of self-calibration of the affine camera are proposed. It is shown that with at least four views, an affine camera may be self-calibrated up to a scaling factor, leading to Euclidean (similarity) shape réconstruction up to a global scaling factor. Another consequence of the introduction of intrinsic and extrinsic parameters of the affine camera is that all existing algorithms using calibrated affine cameras can be assembled into the same framework and some of them can be easily extented to a batch solution.Experimental results are presented and compared with other methods using calibrated affine cameras.     

Behavior monitoring for assistive environments using multiple views

This work presents an approach to behavior understanding using multiple cameras. This approach is appropriate for monitoring people in an assistive environment for the purpose of issuing alerts in cases of abnormal behavior. The output of multiple classifiers is used to model and extract abnormal behavior from both the target trajectory and the target short-term activity (i.e., walking, running, abrupt motion, etc.). Spatial information is obtained after an offline camera registration using homography information. The proposed approach is verified experimentally in an indoor environment. The experiments are performed with a single moving target; however, the method can be generalized to multiple moving targets, which may occlude each other, due to the use of multiple cameras.     

Adaptive 3-D object recognition from multiple views

The authors address the problem of generating representations of 3-D objects automatically from exploratory view sequences of unoccluded objects. In building the models, processed frames of a video sequence are clustered into view categories called aspects, which represent characteristic views of an object invariant to its apparent position, size, 2-D orientation, and limited foreshortening deformation. The aspects as well as the aspect transitions of a view sequence are used to build (and refine) the 3-D object representations online in the form of aspect-transition matrices. Recognition emerges as the hypothesis that has accumulated the maximum evidence at each moment. The `winning' object continues to refine its representation until either the camera is redirected or another hypothesis accumulates greater evidence. This work concentrates on 3-D appearance modeling and succeeds under favorable viewing conditions by using simplified processes to segment objects from the scene and derive the spatial agreement of object features     

Robust multi-view feature matching from multiple unordered views

This paper explores the problem of multi-view feature matching from an unordered set of widely separated views. A set of local invariant features is extracted independently from each view. First we propose a new view-ordering algorithm that organizes all the unordered views into clusters of related (i.e. the same scene) views by efficiently computing the view-similarity values of all view pairs by reasonably selecting part of extracted features to match. Second a robust two-view matching algorithm is developed to find initial matches, then detect the outliers and finally incrementally find more reliable feature matches under the epipolar constraint between two views from dense to sparse based on an assumption that changes of both motion and feature characteristics of one match are consistent with those of neighbors. Third we establish the reliable multi-view matches across related views by reconstructing missing matches in a neighboring triple of views and efficiently determining the states of matches between view pairs. Finally, the reliable multi-view matches thus obtained are used to automatically track all the views by using a self-calibration method. The proposed methods were tested on several sets of real images. Experimental results show that it is efficient and can track a large set of multi-view feature matches across multiple widely separated views.     

Markerless tracking of complex human motions from multiple views

We present a method for markerless tracking of complex human motions from multiple camera views. In the absence of markers, the task of recovering the pose of a person during such motions is challenging and requires strong image features and robust tracking. We propose a solution which integrates multiple image cues such as edges, color information and volumetric reconstruction. We show that a combination of multiple image cues helps the tracker to overcome ambiguous situations such as limbs touching or strong occlusions of body parts. Following a model-based approach, we match an articulated body model built from superellipsoids against these image cues. Stochastic Meta Descent (SMD) optimization is used to find the pose which best matches the images. Stochastic sampling makes SMD robust against local minima and lowers the computational costs as a small set of predicted image features is sufficient for optimization. The power of SMD is demonstrated by comparing it to the commonly used Levenberg–Marquardt method. Results are shown for several challenging sequences showing complex motions and full articulation, with tracking of 24 degrees of freedom in ≈1 frame per second.     

Homogeneity of kappa statistics in multiple samples

The measurement of intra-observer agreement when the data are categorical has been the subject of several investigators since Cohen first proposed the kappa (kappa) as a chance-corrected coefficient of agreement for nominal scales. Subsequent procedures have been developed to assess the agreement of several raters using a dichotomous classification scheme, assess majority agreement among several raters using a polytomous classification scheme, and the use of kappa as an indicator of the quality of a measurement. Further developments include inference procedures for testing the homogeneity of k>/=2 independent kappa statistics. An executable FORTRAN code for testing the homogeneity of kappa statistics (kappa(h)) across multiple sites or studies is given. The FORTRAN program listing and/or executable programs are available from the author on request.     

Knowledge transfer across different domain data with multiple views

In many real-world applications in the areas of data mining, the distributions of testing data are different from that of training data. And on the other hand, many data are often represented by multiple views which are of importance to learning. However, little work has been done for it. In this paper, we explored to leverage the multi-view information across different domains for knowledge transfer. We proposed a novel transfer learning model which integrates the domain distance and view consistency into a 2-view support vector machine framework, namely DV2S. The objective of DV2S is to find the optimal feature mapping such that under the projections the classification margin is maximized, while both the domain distance and the disagreement between multiple views are minimized simultaneously. Experiments showed that DV2S outperforms a variety of state-of-the-art algorithms.     

Discrete contours in multiple views: approximation and recognition

Recognition of discrete planar contours under similarity transformations has received a lot of attention but little work has been reported on recognizing them under more general transformations. Planar object boundaries undergo projective or affine transformations across multiple views. We present two methods to recognize discrete curves in this paper. The first method computes a piecewise parametric approximation of the discrete curve that is projectively invariant. A polygon approximation scheme and a piecewise conic approximation scheme are presented here. The second method computes an invariant sequence directly from the sequence of discrete points on the curve in a Fourier transform space. The sequence is shown to be identical up to a scale factor in all affine related views of the curve. We present the theory and demonstrate its applications to several problems including numeral recognition, aircraft recognition, and homography computation.     

3D object pose form clustering with multiple views

A candidate pose algorithm is described which computes object pose from an assumed correspondence between a pair of 2D image points and a pair of 3D model points. By computing many pose candidates actual object pose can usually be determined by detecting a cluster in the space of all candidates. Cluster space can receive candidate pose parameters from independent computations in different camera views. It is shown that use of of geometric constraint can be sufficient for reliable pose detection, but use of other knowledge, such as edge presence and type, can be easily added for increased efficiency.     

Lighting transfer across multiple views through local color transforms

Computational Visual Media - We present a method for transferring lighting between photographs of a static scene. Our method takes as input a photo collection depicting a scene with varying...