A model based factorization approach for dense 3D recovery from monocular video

Feature track matrix factorization based methods have been attractive solutions to the Structure-front-motion (Sfnl) problem. Group motion of the feature points is analyzed to get the 3D information. It is well known that the factorization formulations give rise to rank deficient system of equations. Even when enough constraints exist, the extracted models are sparse due the unavailability of pixel level tracks. Pixel level tracking of 3D surfaces is a difficult problem, particularly when the surface has very little texture as in a human face. Only sparsely located feature points can be tracked and tracking error arc inevitable along rotating lose texture surfaces. However, the 3D models of an object class lie in a subspace of the set of all possible 3D models. We propose a novel solution to the Structure-from-motion problem which utilizes the high-resolution 3D obtained from range scanner to compute a basis for this desired subspace. Adding subspace constraints during factorization also facilitates removal of tracking noise which causes distortions outside the subspace. We demonstrate the effectiveness of our formulation by extracting dense 3D structure of a human face and comparing it with a well known Structure-front-motion algorithm due to Brand.

New phase unwrapping strategy for rapid and dense 3D data acquisition in structured light approach

Sinusoidal structured light projection (SSLP) technique, specifically-phase stepping method, is in widespread use to obtain accurate, dense 3-D data. But, if the object under investigation possesses surface discontinuities, phase unwrapping (an intermediate step in SSLP) stage mandatorily require several additional images, of the object with projected fringes (of different spatial frequencies), as input to generate a reliable 3D shape. On the other hand, Color-coded structured light projection (CSLP) technique is known to require a single image as in put, but generates sparse 3D data. Thus we propose the use of CSLP in conjunction with SSLP to obtain dense 3D data with minimum number of images as input. This approach is shown to be significantly faster and reliable than temporal phase unwrapping procedure that uses a complete exponential sequence. For example, if a measurement with the accuracy obtained by interrogating the object with 32 fringes in the projected pattern is carried out with both the methods, new strategy proposed requires only 5 frames as compared to 24 frames required by the later method.

Interior Medial Axis Transform computation of 3D objects bound by free-form surfaces

This paper presents an algorithm for generating the Interior Medial Axis Transform (iMAT) of 3D objects with free-form boundaries. The algorithm proposed uses the exact representation of the part and generates an approximate rational spline description of the iMAT. The algorithm generates the iMAT by a tracing technique that marches along the object's boundary. The level of approximation is controlled by the choice of the step size in the tracing procedure. Criteria based on distance and local curvature of boundary entities are used to identify the junction points and the search for these junction points is done in an efficient way. The algorithm works for multiply-connected objects as well. Results of the implementation are provided. (C) 2010 Elsevier Ltd. All rights reserved.

Novel gray coded pattern for unwrapping phase in fringe projection based 3D profiling

A method to reliably extract object profiles even with height discontinuities (that leads to 2n pi phase jumps) is proposed. This method uses Fourier transform profilometry to extract wrapped phase, and an additional image formed by illuminating the object of interest by a novel gray coded pattern for phase unwrapping. Simulation results suggest that the proposed approach not only retains the advantages of the original method, but also contributes significantly in the enhancement of its performance. Fundamental advantage of this method stems from the fact that both extraction of wrapped phase and unwrapping the same were done by gray scale images. Hence, unlike the methods that use colors, proposed method doesn't demand a color CCD camera and is ideal for profiling objects with multiple colors.

3D Image Reconstruction From Truncated Helical Cone Beam Projection Data - A Linear Prediction Approach

With the introduction of 2D flat-panel X-ray detectors, 3D image reconstruction using helical cone-beam tomography is fast replacing the conventional 2D reconstruction techniques. In 3D image reconstruction, the source orbit or scanning geometry should satisfy the data sufficiency or completeness condition for exact reconstruction. The helical scan geometry satisfies this condition and hence can give exact reconstruction. The theoretically exact helical cone-beam reconstruction algorithm proposed by Katsevich is a breakthrough and has attracted interest in the 3D reconstruction using helical cone-beam Computed Tomography.In many practical situations, the available projection data is incomplete. One such case is where the detector plane does not completely cover the full extent of the object being imaged in lateral direction resulting in truncated projections. This result in artifacts that mask small features near to the periphery of the ROI when reconstructed using the convolution back projection (CBP) method assuming that the projection data is complete. A number of techniques exist which deal with completion of missing data followed by the CBP reconstruction. In 2D, linear prediction (LP)extrapolation has been shown to be efficient for data completion, involving minimal assumptions on the nature of the data, producing smooth extensions of the missing projection data.In this paper, we propose to extend the LP approach for extrapolating helical cone beam truncated data. The projection on the multi row flat panel detectors has missing columns towards either ends in the lateral direction in truncated data situation. The available data from each detector row is modeled using a linear predictor. The available data is extrapolated and this completed projection data is backprojected using the Katsevich algorithm. Simulation results show the efficacy of the proposed method.

Dynamics of 3D view invariance in monkey inferotemporal cortex

Rotations in depth are challenging for object vision because features can appear, disappear, be stretched or compressed. Yet we easily recognize objects across views. Are the underlying representations view invariant or dependent? This question has been intensely debated in human vision, but the neuronal representations remain poorly understood. Here, we show that for naturalistic objects, neurons in the monkey inferotemporal (IT) cortex undergo a dynamic transition in time, whereby they are initially sensitive to viewpoint and later encode view-invariant object identity. This transition depended on two aspects of object structure: it was strongest when objects foreshortened strongly across views and were similar to each other. View invariance in IT neurons was present even when objects were reduced to silhouettes, suggesting that it can arise through similarity between external contours of objects across views. Our results elucidate the viewpoint debate by showing that view invariance arises dynamically in IT neurons out of a representation that is initially view dependent.

Avaliação Comparativa dos Scanners 3D Artec MHT e Cyberware WBX para aplicações em Antropometria e Ergonomia

A partir das dimensões dos indivíduos pode-se definir dimensionamentos adequados para os produtos e postos de trabalho, proporcionando segurança e conforto aos usuários. Com o avanço da tecnologia de digitalização de imagens (escaneamento) 3D, é possível tirar algumas medidas de maneira mais rápida e com a redução da presença do entrevistado durante o processo. No entanto, faltam estudos que avaliem estas tecnologias no Brasil, sendo necessária a realização de uma comparação das tecnologias e das respectivas precisões para que seu uso em pesquisas. Com o objetivo de oferecer métodos comparativos para escolha dos marcadores e equipamentos a serem utilizados em uma pesquisa antropométrica tridimensional da população brasileira, no presente estudo estão comparadas duas tecnologias de escaneamento: o sistema a laser WBX da empresa norte americana Cyberware e o sistema MHT da empresa russa Artec Group. O método para avaliação da precisão dimensional dos dados advindos desses equipamentos de digitalização de imagens 3D teve cinco etapas: Estudo dos processos de escaneamento; Escaneamento dos marcadores de pontos anatômicos; Escaneamento utilizando um corpo de prova cilíndrico; Escaneamento de um manequim; Escaneamento de um voluntário que teve seus pontos anatômicos marcados para a retirada de medidas. Foi feita uma comparação entre as medidas retiradas manualmente, por meio de antropômetro e virtualmente, com o auxílio do software de modelagem tridimensional Rhinoceros. Em relação aos resultados obtidos na avaliação do manequim e do voluntário, concluiu-se que a magnitude do erro absoluto é semelhante para ambos os scanners, e permanece constante independentemente das dimensões sob análise. As principais diferenças são em relação às funcionalidades dos equipamentos.

Testing of Depth-Encoded Hough Voting for Infrastructure Object Detection

The lack of viable methods to map and label existing infrastructure is one of the engineering grand challenges for the 21st century. For instance, over two thirds of the effort needed to geometrically model even simple infrastructure is spent on manually converting a cloud of points to a 3D model. The result is that few facilities today have a complete record of as-built information and that as-built models are not produced for the vast majority of new construction and retrofit projects. This leads to rework and design changes that can cost up to 10% of the installed costs. Automatically detecting building components could address this challenge. However, existing methods for detecting building components are not view and scale-invariant, or have only been validated in restricted scenarios that require a priori knowledge without considering occlusions. This leads to their constrained applicability in complex civil infrastructure scenes. In this paper, we test a pose-invariant method of labeling existing infrastructure. This method simultaneously detects objects and estimates their poses. It takes advantage of a recent novel formulation for object detection and customizes it to generic civil infrastructure scenes. Our preliminary experiments demonstrate that this method achieves convincing recognition results.

A performance evaluation of volumetric 3D interest point detectors

This paper presents the first performance evaluation of interest points on scalar volumetric data. Such data encodes 3D shape, a fundamental property of objects. The use of another such property, texture (i.e. 2D surface colouration), or appearance, for object detection, recognition and registration has been well studied; 3D shape less so. However, the increasing prevalence of 3D shape acquisition techniques and the diminishing returns to be had from appearance alone have seen a surge in 3D shape-based methods. In this work, we investigate the performance of several state of the art interest points detectors in volumetric data, in terms of repeatability, number and nature of interest points. Such methods form the first step in many shape-based applications. Our detailed comparison, with both quantitative and qualitative measures on synthetic and real 3D data, both point-based and volumetric, aids readers in selecting a method suitable for their application. © 2012 Springer Science+Business Media, LLC.

Obtaining the shape of a moving object with a specular surface

This paper addresses the basic problem of recovering the 3D surface of an object that is observed in motion by a single camera and under a static but unknown lighting condition. We propose a method to establish pixelwise correspondence between input images by way of depth search by investigating optimal subsets of intensities rather than employing all the relevant pixel values. The thrust of our algorithm is that it is capable of dealing with specularities which appear on the top of shading variance that is caused due to object motion. This is in terms of both stages of finding sparse point correspondence and dense depth search. We also propose that a linearised image basis can be directly computed by the procudure of finding the correspondence. We illustrate the performance of the theoretical propositions using images of real objects. © 2009. The copyright of this document resides with its authors.

A Self-Organizing Multiple-View Representation of 3D Objects

We explore representation of 3D objects in which several distinct 2D views are stored for each object. We demonstrate the ability of a two-layer network of thresholded summation units to support such representations. Using unsupervised Hebbian relaxation, we trained the network to recognise ten objects from different viewpoints. The training process led to the emergence of compact representations of the specific input views. When tested on novel views of the same objects, the network exhibited a substantial generalisation capability. In simulated psychophysical experiments, the network's behavior was qualitatively similar to that of human subjects.

Distance Metric Between 3D Models and 3D Images for Recognition and Classification

Similarity measurements between 3D objects and 2D images are useful for the tasks of object recognition and classification. We distinguish between two types of similarity metrics: metrics computed in image-space (image metrics) and metrics computed in transformation-space (transformation metrics). Existing methods typically use image and the nearest view of the object. Example for such a measure is the Euclidean distance between feature points in the image and corresponding points in the nearest view. (Computing this measure is equivalent to solving the exterior orientation calibration problem.) In this paper we introduce a different type of metrics: transformation metrics. These metrics penalize for the deformatoins applied to the object to produce the observed image. We present a transformation metric that optimally penalizes for "affine deformations" under weak-perspective. A closed-form solution, together with the nearest view according to this metric, are derived. The metric is shown to be equivalent to the Euclidean image metric, in the sense that they bound each other from both above and below. For Euclidean image metric we offier a sub-optimal closed-form solution and an iterative scheme to compute the exact solution.

3D Pose from Three Corresponding Points Under Weak-Perspective Projection

Model-based object recognition commonly involves using a minimal set of matched model and image points to compute the pose of the model in image coordinates. Furthermore, recognition systems often rely on the "weak-perspective" imaging model in place of the perspective imaging model. This paper discusses computing the pose of a model from three corresponding points under weak-perspective projection. A new solution to the problem is proposed which, like previous solutins, involves solving a biquadratic equation. Here the biquadratic is motivate geometrically and its solutions, comprised of an actual and a false solution, are interpreted graphically. The final equations take a new form, which lead to a simple expression for the image position of any unmatched model point.

Spatial Reference Frames for Object Recognition: Tuning for Rotations in Depth

The inferior temporal cortex (IT) of monkeys is thought to play an essential role in visual object recognition. Inferotemporal neurons are known to respond to complex visual stimuli, including patterns like faces, hands, or other body parts. What is the role of such neurons in object recognition? The present study examines this question in combined psychophysical and electrophysiological experiments, in which monkeys learned to classify and recognize novel visual 3D objects. A population of neurons in IT were found to respond selectively to such objects that the monkeys had recently learned to recognize. A large majority of these cells discharged maximally for one view of the object, while their response fell off gradually as the object was rotated away from the neuron"s preferred view. Most neurons exhibited orientation-dependent responses also during view-plane rotations. Some neurons were found tuned around two views of the same object, while a very small number of cells responded in a view- invariant manner. For five different objects that were extensively used during the training of the animals, and for which behavioral performance became view-independent, multiple cells were found that were tuned around different views of the same object. No selective responses were ever encountered for views that the animal systematically failed to recognize. The results of our experiments suggest that neurons in this area can develop a complex receptive field organization as a consequence of extensive training in the discrimination and recognition of objects. Simple geometric features did not appear to account for the neurons" selective responses. These findings support the idea that a population of neurons -- each tuned to a different object aspect, and each showing a certain degree of invariance to image transformations -- may, as an assembly, encode complex 3D objects. In such a system, several neurons may be active for any given vantage point, with a single unit acting like a blurred template for a limited neighborhood of a single view.

Virtual Visual Hulls: Example-Based 3D Shape Estimation from a Single Silhouette

Recovering a volumetric model of a person, car, or other object of interest from a single snapshot would be useful for many computer graphics applications. 3D model estimation in general is hard, and currently requires active sensors, multiple views, or integration over time. For a known object class, however, 3D shape can be successfully inferred from a single snapshot. We present a method for generating a ``virtual visual hull''-- an estimate of the 3D shape of an object from a known class, given a single silhouette observed from an unknown viewpoint. For a given class, a large database of multi-view silhouette examples from calibrated, though possibly varied, camera rigs are collected. To infer a novel single view input silhouette's virtual visual hull, we search for 3D shapes in the database which are most consistent with the observed contour. The input is matched to component single views of the multi-view training examples. A set of viewpoint-aligned virtual views are generated from the visual hulls corresponding to these examples. The 3D shape estimate for the input is then found by interpolating between the contours of these aligned views. When the underlying shape is ambiguous given a single view silhouette, we produce multiple visual hull hypotheses; if a sequence of input images is available, a dynamic programming approach is applied to find the maximum likelihood path through the feasible hypotheses over time. We show results of our algorithm on real and synthetic images of people.