3D face computational photography using PCA spaces

In this paper, we present a 3D face photography system based on a facial expression training dataset, composed of both facial range images (3D geometry) and facial texture (2D photography). The proposed system allows one to obtain a 3D geometry representation of a given face provided as a 2D photography, which undergoes a series of transformations through the texture and geometry spaces estimated. In the training phase of the system, the facial landmarks are obtained by an active shape model (ASM) extracted from the 2D gray-level photography. Principal components analysis (PCA) is then used to represent the face dataset, thus defining an orthonormal basis of texture and another of geometry. In the reconstruction phase, an input is given by a face image to which the ASM is matched. The extracted facial landmarks and the face image are fed to the PCA basis transform, and a 3D version of the 2D input image is built. Experimental tests using a new dataset of 70 facial expressions belonging to ten subjects as training set show rapid reconstructed 3D faces which maintain spatial coherence similar to the human perception, thus corroborating the efficiency and the applicability of the proposed system.

Depth estimation using multi-wavelet analysis based stereo vision approach

The problem of dimensional defects in aluminum die- casting is widespread throughout the foundry industry and their detection is of paramount importance in maintaining product quality. Due to the unpredictable factory environment and metallic, with highly reflective, nature of aluminum die-castings, it is extremely hard to estimate true dimensionality of the die-casting, autonomously. In this work, we propose a novel robust 3D reconstruction algorithm capable of reconstructing dimensionally accurate 3D depth models of the aluminum die-castings. The developed system is very simple and cost effective as it consists of only a stereo cameras pair and a simple fluorescent light. The developed system is capable of estimating surface depths within the tolerance of 1.5 mm. Moreover, the system is invariant to illuminative variations and orientation of the objects in the input image space, which makes the developed system highly robust. Due to its hardware simplicity and robustness, it can be implemented in different factory environments without a significant change in the setup.

Depth estimation using multiwavelet analysis based stereo vision approach

The problem of dimensional defects in aluminum die-casting is widespread throughout the foundry industry and their detection is of paramount importance in maintaining product quality. Due to the unpredictable factory environment and metallic, with highly reflective, nature of aluminum die-castings, it is extremely hard to estimate true dimensionality of the die-casting, autonomously. In this work, we propose a novel robust 3D reconstruction algorithm capable of reconstructing dimensionally accurate 3D depth models of the aluminum die-castings. The developed system is very simple and cost effective as it consists of only a stereo camera pair and a simple fluorescent light. The developed system is capable of estimating surface depths within the tolerance of 1.5 mm. Moreover, the system is invariant to illuminative variations and orientation of the objects in the input image space, which makes the developed system highly robust. Due to its hardware simplicity and robustness, it can be implemented in different factory environments without a significant change in the setup.

3D leadership for national renewal

A perpetual immigrant, Professor Frederick relates his life course that brought him to New Zealand and describes what he found here. One of the country’s early advocates of the “knowledge economy” path to economic development, Frederick outlines his vision of leadership for the new millennium that will help restore New Zealand to the top half of the OECD and grow the cake for the prosperity of all. He relates what we expect from our leaders as well as his personal vision to leadership in New Zealand.

Human action recognition based on 3D SIFT and LDA model

How to recognize human action from videos captured by modern cameras efficiently and effectively is a challenge in real applications. Traditional methods which need professional analysts are facing a bottleneck because of their shortcomings. To cope with the disadvantage, methods based on computer vision techniques, without or with only a few human interventions, have been proposed to analyse human actions in videos automatically. This paper provides a method combining the three dimensional Scale Invariant Feature Transform (SIFT) detector and the Latent Dirichlet Allocation (LDA) model for human motion analysis. To represent videos effectively and robustly, we extract the 3D SIFT descriptor around each interest point, which is sampled densely from 3D Space-time video volumes. After obtaining the representation of each video frame, the LDA model is adopted to discover the underlying structure-the categorization of human actions in the collection of videos. Public available standard datasets are used to test our method. The concluding part discusses the research challenges and future directions.

Hypothesis verification using parametric models and active vision strategies

This paper proposes a methodology for determining the shape and ultimately the functionality of objects from intensity images; 2D analytic functions are used to track 3D features during known camera motions. Three analytic functions are proposed that describe the relationship between pairs of points that are either stationary or moving depending on whether the points are on occluding boundaries or otherwise. Many of the problems of correspondence are reduced by using foveation, known camera motion, and active vision methods. The three analytic functions are shown to enable hypothesis refinement of the functionality of a number of 3D objects without full 3D information about the shape.

Obtaining functional parametric models using active vision strategies

This paper addresses the problem of determining which 3D shape is present, and more importantly, the dimensions of the shape in a scene. This is performed in an active vision system because it reduces the complexity of the problem through the use of gaze stabilization, choice of foveation point, and selective processing by adaptively processing regions of interest. In our case, only a small number of equations and parameters are needed for each shape and these are incorporated into functional descriptions of the shapes.

Emerging hypothesis verification using function-based geometric models and active vision strategies

This paper describes an investigation into the use of parametric 2D models describing the movement of edges for the determination of possible 3D shape and hence function of an object. An assumption of this research is that the camera can foveate and track particular features. It is argued that simple 2D analytic descriptions of the movement of edges can infer 3D shape while the camera is moved. This uses an advantage of foveation i.e. the problem becomes object centred. The problem of correspondence for numerous edge points is overcome by the use of a tree based representation for the competing hypotheses. Numerous hypothesis are maintained simultaneously and it does not rely on a single kinematic model which assumes constant velocity or acceleration. The numerous advantages of this strategy are described.

Obtaining function models using active vision strategies

This paper addresses the problem of determening which 3D shape is present, and more importantly, the dimensions of the shape within a scene. This is performed in an active vision system because it reduces the complexity of the problem through the use of gaze stabilisation, choice of foveation point and selective processing by adaptively processing regions of interest. In our case only a small number of equations and parameters are needed for each shape. For example, a container has width and height. These are incorporated into functional descriptions of the shapes.

Vision, ambiguity and perceptual possibility : why pictures matter in the critique of stereo-immersive VR

The acquisition of three-dimensional immersive space through advanced digitial imaging technology, suggests a profound shift from the relatively impoverished representational stratgies of two-dimensional pictorial imagery.  This entails an epistemological shift from pictorial representation, to the presentation of actual three-dimensional space through stereoscopic (3D) imagery.  Moreover, it suggests that visuality rather than 'virtuality' is the core issue in understanding the nature of the epistemological shift associated with stereo-immersive VR.

A shift in visual epistemology from 'flat' pictorial representation to three-dimensional stereo-immersion suggests a gainful move toward a visuality imbued with spatial possibilities.  In quantitative terms, these visual-spatial gains may seem self-evident.  However, certain aspects peculiar to pictorial representation are missing from stereo-immersive imaging.  That is lost in stereo-immersive imaging, and how it can be measured?

This thesis proposes that the inherent ambiguity of two-dimensional representations of three-dimensional spatial structure in pictures, invokes a perceptual response in which pictorial spaces elicit 'perceptual possibility'.  The robust three-dimentional spatiality of stereo-immersvie VR foreclosures such possibility.  Through examining stereo-immersive VR in terms of its visuality, the thesis develops a new appraoch to understanding VR that solves some of the issues associated with the problematic concept of 'virtuality'.  In addition, the thesis finds that by placing stereo-immersive VR and pictures within the shared paradigm of 'the visual', an important dimension of pictures that has been overlooked in past analyses re-emerges : the thesis proposes the concept of 'artifactuality' to account for the way pictures are fundamentally, and in the first instance, aesthetic objects for visual perception.  It is in their manner of appearing as pictures, that they are perceived as pictures of something.  It is from this fundamental basis that their many levels of meaning and signification - their manifold 'realisms' - can arise.

This thesis therefore addresses two intersecting problems within the paradigm of the visual: it proposes 1) that analyses of 'the virtual' be grounded in the 'artifactuality' of pictorial perception, and 2) that the spatiality of stereo-immersive VR be reinvigorated by purposefully 'under-contraining' its key percept - the robust, 'solid' stereoscopic structuring of visual space.  This approach opens up the discourse of stereo-immersive VR to new visual paradigms.  The thesis proposes that these be modelled not on the impossibility of 'the virtual', but on the possibilities of visual ambiguity drawn from the analysis of pictorial perception.

Instrumental vision

This chapter interrogates stereo-immersive ‘virtual reality’ (VR), the technology that enables a perceiver to experience what it is like to be immersed in a simulated environment. While the simulation is powered by the “geometry engine” (Cutting, 1997: 31) associated with high-end computer imaging technology, the visual experience itself is powered by ordinary human vision: the vision system’s innate capacity to see “in 3D”. To understand and critically appraise stereo-immersive VR, we should study not its purported ‘virtuality’, but its specific visuality, because the ‘reality’ of a so-called ‘virtual environment’ is afforded by the stereoacuity of binocular vision itself. By way of such a critique of the visuality of stereo-immersive VR, this chapter suggests that we think about the ‘practice’ of vision, and consider on what basis vision can have its own ‘materiality’. Pictorial perception is proposed as an exemplary visual mode in which the possibilities of perception might emerge. Against the ‘possibilities’ of vision associated with pictures, the visuality of stereo-immersive VR emerges as a harnessing, or ‘instrumentalisation’ of vision’s innate capabilities. James J. Gibson’s ‘ecological’ approach to vision studies is referenced to show the degree to which developers of VR have sought — and succeeded — to mimic the ‘realness’ of ordinary perceptual reality. This raises a question concerning whether the success of stereo-immersive VR is simultaneously the source of its own perceptual redundancy: for to bring into being the perceptual basis of ordinary ‘real’ reality, is to return the perceiver to what is already familiar and known.

Extracting 3D mesh skeletons using antipodal points locations

Finding the skeleton of a 3D mesh is an essential task for many applications such as mesh animation, tracking, and 3D registeration. In recent years, new technologies in computer vision such as Microsoft Kinect have proven that a mesh skeleton can be useful such as in the case of human machine interactions. To calculate the 3D mesh skeleton, the mesh properties such as topology and its components relations are utilized. In this paper, we propose the usage of a novel algorithm that can efficiently calculate a vertex antipodal point. A vertex antipodal point is the diametrically opposite point that belongs to the same mesh. The set of centers of the connecting lines between each vertex and its antipodal point represents the 3D mesh desired skeleton. Post processing is completed for smoothing and fitting centers into optimized skeleton parts. The algorithm is tested on different classes of 3D objects and produced efficient results that are comparable with the literature. The algorithm has the advantages of producing high quality skeletons as it preserves details. This is suitable for applications where the mesh skeleton mapping is required to be kept as much as possible.

3D reconstruction through photographs

Humans can perceive three dimension, our world is three dimensional and it is becoming increasingly digital too. We have the need to capture and preserve our existence in digital means perhaps due to our own mortality. We have also the need to reproduce objects or create small identical objects to prototype, test or study them. Some objects have been lost through time and are only accessible through old photographs. With robust model generation from photographs we can use one of the biggest human data sets and reproduce real world objects digitally and physically with printers. What is the current state of development in three dimensional reconstruction through photographs both in the commercial world and in the open source world? And what tools are available for a developer to build his own reconstruction software? To answer these questions several pieces of software were tested, from full commercial software packages to open source small projects, including libraries aimed at computer vision. To bring to the real world the 3D models a 3D printer was built, tested and analyzed, its problems and weaknesses evaluated. Lastly using a computer vision library a small software with limited capabilities was developed.

Utilizando mapas de conectividade fuzzy no desenvolvimento de algoritmos reparadores de imagens binárias 3D

A 3D binary image is considered well-composed if, and only if, the union of the faces shared by the foreground and background voxels of the image is a surface in R3. Wellcomposed images have some desirable topological properties, which allow us to simplify and optimize algorithms that are widely used in computer graphics, computer vision and image processing. These advantages have fostered the development of algorithms to repair bi-dimensional (2D) and three-dimensional (3D) images that are not well-composed. These algorithms are known as repairing algorithms. In this dissertation, we propose two repairing algorithms, one randomized and one deterministic. Both algorithms are capable of making topological repairs in 3D binary images, producing well-composed images similar to the original images. The key idea behind both algorithms is to iteratively change the assigned color of some points in the input image from 0 (background)to 1 (foreground) until the image becomes well-composed. The points whose colors are changed by the algorithms are chosen according to their values in the fuzzy connectivity map resulting from the image segmentation process. The use of the fuzzy connectivity map ensures that a subset of points chosen by the algorithm at any given iteration is the one with the least affinity with the background among all possible choices