VVG05
Permanent URI for this collection
Browse
Browsing VVG05 by Issue Date
Now showing 1 - 20 of 33
Results Per Page
Sort Options
Item Visual Recognition of Man-made Materials and Structures in an Office Environment(The Eurographics Association, 2005) Song, Y. Z.; Town, C. P.; Mike ChantlerThis paper demonstrates a new approach towards object recognition founded on the development of Neural Network classifiers and Bayesian Networks. The mapping from segmented image region descriptors to semantically meaningful class membership terms is achieved using Neural Networks. Bayesian Networks are then employed to probabilistically detect objects within an image by means of relating region class labels and their surrounding environments. Furthermore, it makes use of an intermediate level of image representation and demonstrates how object recognition can be achieved in this way.Item Use of Computer Vision/ Computer Graphics Collaboration for 3D Rotoscopy(The Eurographics Association, 2005) Gagalowicz, André; Mike ChantlerThis talk introduces 3D rotoscopy and its role in post-production applications, and the computer vision/computer graphics strategies used. The case of rigid objects is presented first, for which well-established approaches can be used. The case of articulated objects is considered next, with special attention to the case of a full human body tracking (ignoring significant shape deformations introduced by baggy clothes). Results related to the tracking of professional golfers and face tracking, a challenging case of deformable objects, will be presented. The talk will be concluded by a presentation of further, possible applications of research done at the MIRAGES laboratory at INRIA Rocquencourt.Item A New Framework for Trademark Retrieval Based on Size Functions(The Eurographics Association, 2005) Cerri, A.; Ferri, M.; Giorgi, D.; Mike ChantlerWe propose a new, effective system for Content Based trademark retrieval, which involves Size Functions. Three different classes of shape descriptors are combined, for a total amount of 25 measuring functions. The evaluation has been performed on a database of 1182 trademark images, provided by the UK Patent Office.Item Bitvectors for Robust Hierarchical Template Matching(The Eurographics Association, 2005) Tweed, David; Mike ChantlerMany target detection problems involve objects where the primary variability in appearance is due to changes amongst characteristic configurations (as opposed to the systematic variability of object rotation or illumination changes). It is then important to utilise as much of the correlation between features as possible. Detecting pedestrians is such a problem and was tackled by Gavrila [Gav98] using a large set of exemplar templates combined with hierarchical matching via Distance Transforms. We describe a variant using a robust distance function and explicit allowance for occlusions. Our innovation is using bitwise logical operators to test against multiple exemplars in parallel.Item Sensitivity Analysis in Image Synthesis(The Eurographics Association, 2005) Trujillo, M.; Izquierdo, E.; Mike ChantlerIntermediate virtual images are used in the evaluation of disparity estimations. The analysis is based on the effect of disparity inaccuracies in the relative quality of virtual images. The peak-signal-to-noise ratio and the percentage of visual errors are used to assess the quality of virtual images generated with distorted disparity fields. Computer simulation results show that the peak-signal-to-noise ratio is more affected by a small magnitude of perturbations two or three pixels than by a high frequency of perturbations 15% or 20%. However, the percentage of visual errors is more affected by the frequency of perturbations. By using distorted disparity fields, the deterioration in the quality of virtual images is imperceptible to the human eye.Item Regularised Anisotropic Nonlinear Diffusion for Rendering Refraction in Volume Graphics(The Eurographics Association, 2005) Rodgman, David; Chen, Min; Mike ChantlerRendering refraction in volume graphics requires smoothly distributed normals to synthesise good quality visual representations. Such refractive visualisation is more susceptible to noise in the data than visualisations that do not involve refraction. In this paper, we addresses the need for improving the continuity of voxel gradients in discretely sampled volume datasets using nonlinear diffusion methods, which was originally developed for image denoising. We consider the necessity for minimising unnecessary geometrical distortion, detail the functional specification of a volumetric filter for regularised anisotropic nonlinear diffusion (R-ANLD), discuss the further improvements of the filter, and compare the efficacy of the filter with an anisotropic nonlinear diffusion (ANLD) filter as well as a Gaussian filter and a linear diffusion filter. Our results indicate that it is possible to make significant improvements in image quality in refractive rendering without excessive distortion.Item Correspondenceless Stereo for 3-D Iris Location(The Eurographics Association, 2005) Anderson, Tom; Trucco, Emanuele; Razeto, Marco; Mike ChantlerWe present a correspondenceless stereo system locating the circular contour of an iris (limbus) in space, and therefore its 3-D plane. We avoid correspondence search completely by intersecting a bundle of conjugate epipolar lines with the elliptical images of the limbus in the stereo pair of images, which gives correspondences directly. The ellipses are located by active ellipse fitting. An efficient simulated annealing implementation achieves reliable iris location with uncontrolled illumination and eye or head movements. Tests with ground-truthed 3-D setups as well as real eye images indicate very good accuracy.Item Texture Mapping Volume Objects(The Eurographics Association, 2005) Shen, P.; Willis, P.; Mike ChantlerWe present a combination of image-based texture mapping and projective space (pseudo-solid) texture. This imagebased texture mapping is useful for objects defined from volume datasets. The paper makes three main contributions. First, it introduces the combination of the image-based two-part texture mapping and projective space texture mapping for volume objects. Second, it presents a multi-resolution technique to overcome problems with projecting at glancing angles and to eliminate artifacts due to the resolution limitations. Third, it presents the pixel-level data-dependent interpolation technique in projective image warping. The proposed approach leads to superior quality of texture and thus provides an optional solution for texturing volume objects.The results show the effectiveness and quality of rendered images.Item Merging Graphics and Vision for 3D Face Recognition(The Eurographics Association, 2005) Bai, Li; Song, Yi; Mike ChantlerThis paper presents a new approach to automatic 3D face modelling from unstructured point cloud data. An efficient B-Spline surface-fitting algorithm is used to obtain an initial parametric surface for each face point cloud data set. Knot vectors for each individual face surface are then standardised to produce a set of uniform knot vectors so that all the surfaces can be seen as fitted with the same set of knot vectors. Mapping from object space to shape space can then be established so that each 3D face can be described by a small number of shape descriptors. The use of shape descriptors allows automatic registration between face models. More importantly, it allows dynamic facial variation to be modelled and analysed via 3D warping, resulting in a powerful approach to quantifying the differences among individuals required for face recognition. 3D warping is often used in simulations in computer graphics. This paper explains, for the first time, how 3D warping can be exploited for face recognition based on multi-resolution analysis of warping fields. The methodology allows the quantitative study of variation in characteristics previously only described from a qualitative perspective.Item Talking Faces - Technologies and Applications(The Eurographics Association, 2005) Ostermann, Jörn; Weissenfeld, Axel; Liu, Kang; Mike ChantlerFacial animation has been combined with text-to-speech synthesis to create innovative multimodal interfaces. In this lecture, we present the technology and architecture in order to use this multimodal interface in an web-based environment to support education, entertainment and e-commerce applications. Modern text to speech synthesizers using concatenative speech synthesis are able to generate high quality speech. Face animation uses the phoneme and timing information provided by such a speech synthesizer in order to animate the mouth. There are 2 basic technologies that are used to render talking faces: 3D face models as described in MPEG-4 may be used to provide the impression of a talking cartoon or human-like character. Sample-based face models generated from recorded video enable the synthesis of a talking head that cannot be distinguished from a real person. Depending on the chosen face animation technology and latency requirements, different architectures for delivering the talking head over the Internet are required for interactive applications. Keywords: Face animation, visual speechItem Table of Contents and Preface(The Eurographics Association, 2005) Mike ChantlerItem Multi-View Image Coding with Wavelet Lifting Scheme(The Eurographics Association, 2005) Anantrasirichai, N.; Canagarajah, C. Nishan; Bull, David R.; Mike ChantlerIn this paper, we present a novel multi-view image codec based on a wavelet lifting scheme. The proposed algorithm applies the disparity estimation and compensation with the lifting scheme. It is very efficient in terms of compressions performance, memory requirements and fast computation. To get the highest multiview image coding efficiencies, two hybrid predictions are proposed; one for effective compression performance and one for compromising when more exact disparity values are required. Moreover, an adaptive weighing in update step and overlapped block disparity compensation are included to yield significant improvements in rate distortion performance. Experimental results show image quality gains of up to 2 dB and 1 dB against using well established methods such as the block-matching Haar and 5/3 wavelet lifting respectively.Item Advances in Shadow Removing for Motion Detection Algorithms(The Eurographics Association, 2005) Spagnolo, P.; D'Orazio, T.; Leo, M.; Distante, A.; Mike ChantlerDetecting moving objects is very important in many application contexts such as people detection and recognition, visual surveillance, automatic generation of video effects, and so on. Motion detection algorithms are very sensible to light conditions; in particular they suffer the presence of shadows and sudden changes due to light switches. Here we propose an additional module that can be applied to a generic gray-level motion detection algorithm. The only requirement is the presence of a reference image (background model). The main idea of the proposed approach is that variations in light conditions alter the intensity values of pixels in the image, but the basic structures in the scene remain unchanged. The algorithm we propose is based on the correlation between regions selected from the reference image and the current one. The experiments have been performed on image sequences acquired both in indoor and outdoor environments with natural and artificial lights.Item Color Reduction by Using a new Self-Growing and Self-Organized Neural Network(The Eurographics Association, 2005) Atsalakis, A.; Papamarkos, N.; Mike ChantlerA new method for the reduction of the number of colors in a digital image is proposed. The new method is based on the developed of a new neural network classifier that combines the advantages of the Growing Neural Gas (GNG) and the Kohonen Self-Organized Feature Map (SOFM) neural networks. We call the new neural network: Self-Growing and Self- Organized Neural Gas (SGONG). Its main advantage is that it defines the number of the created neurons and their topology in an automatic way. As a consecutive, isolated color classes, which may correspond to significant image details, can be obtained. The SGONG is fed by the color components and additional spatial features. To speed up the entire algorithm and to reduce memory requirements, a fractal scanning sub-sampling technique is used. The method is applicable to any type of color images and it can accommodate any type of color space.Item 3D Image Analysis and Synthesis at MPI Informatik(The Eurographics Association, 2005) Theobalt, Christian; Magnor, Marcus A.; Seidel, Hans-Peter; Mike ChantlerIn the talk, we give a brief overview of the research done in the Computer Graphics Group and the Graphics- Optics-Vision Group of the Max-Planck-Institut für Informatik in the area of 3D Image Analysis and Synthesis. In this context, we address the whole pipeline ranging from the acquisition of computational scene models, over the algorithmic processing of these scene descriptions, to their photo-realistic rendition in the computer. This paper illustrates the questions that we are trying to answer by means of one of our research projects, video-based rendering. We have developed a model-based system to acquire, reconstruct and render free-viewpoint videos of human actors that nicely illustrates the concept of 3D Image Analysis and Synthesis.Item Modeling Falling and Accumulating Snow(The Eurographics Association, 2005) Moeslund, T. B.; Madsen, C. B.; Aagaard, M.; Lerche, D.; Mike ChantlerThe use of computer graphics to produce special effects is currently being applied with great results in especially the entertainment and game industry. One area where computer graphics is not quite ready to replace all real effects is natural phenomena where a lack of general models exists. In this work we present a general model for falling and accumulating snow. The appearance and movement of falling snow are modeled in 3D based on the physics governing the real processes. The same goes for the accumulated snow where especially a correctly modeled wind field is important for producing realistically looking results. Intuitive weather parameters are used to control both models. The results show that both the appearance and movement of the snow, as well as the accumulated snow are very similar to real snow.Item On the Separation of Luminance from Colour in Images(The Eurographics Association, 2005) Woodland, Alan; Labrosse, Frédéric; Mike ChantlerMany computer vision and graphics related techniques rely upon illumination invariance of images to derive meaning from images of an object under varying lighting conditions. This is all the appearance-based methods. In practice however this assumption does not hold if one is not careful with either controlling the illumination of the object when capturing its appearance or with some post-processing of the images. This paper presents results of experiments designed to analyse the usefulness for illumination invariance of two colour models, CIE L*a*b* and YUV, that have been designed to provide separation of the luminance information from the colour information, and compare them with more traditional colour models, RGB and HSV. This is done by evaluating the variations in each of the components of the different colour spaces in real images taken in variable illumination conditions. We also present a simple application example.Item Realistic Real-Time Hair Simulation and Rendering(The Eurographics Association, 2005) Jung, Yvonne; Rettig, Alexander; Klar, Oliver; Lehr, Timo; Mike ChantlerWe present a method for realistic rendering and simulation of human hair in real-time, which is suitable for the use in complex virtual reality applications. Neighbouring hairs are combined into wisps and animated with our cantilever beam based simulation system, which runs numerically stable and with interactive update rates. The rendering algorithm utilizes latest graphics hardware features and can even handle light coloured hair by including anisotropic reflection and internal transmission.Item Learnt Inverse Kinematics for Animation Synthesis(The Eurographics Association, 2005) Ong, Eng-Jon; Hilton, Adrian; Mike ChantlerExisting work on animation synthesis can be roughly split into two approaches, those that combine segments of motion capture data, and those that perform inverse kinematics. In this paper, we present a method for performing animation synthesis of an articulated object (e.g. human body and a dog) from a minimal set of body joint positions, following the approach of inverse kinematics. We tackle this problem from a learning perspective. Firstly, we address the need for knowledge on the physical constraints of the articulated body, so as to avoid the generation of a physically impossible poses. A common solution is to heuristically specify the kinematic constraints for the skeleton model. In this paper however, the physical constraints of the articulated body are represented using a hierarchical cluster model learnt from a motion capture database. Additionally, we shall show that the learnt model automatically captures the correlation between different joints through the simultaneous modelling their angles. We then show how this model can be utilised to perform inverse kinematics in a simple and efficient manner. Crucially, we describe how IK is carried out from a minimal set of end-effector positions. Following this, we show how this "learnt inverse kinematics" framework can be used to perform animation syntheses of different types of articulated structures. To this end, the results presented include the retargeting of a flat surface walking animation to various uneven terrains to demonstrate the synthesis of a full human body motion from the positions of only the hands, feet and torso. Additionally, we show how the same method can be applied to the animation synthesis of a dog using only its feet and torso positions.Item SVD-Matching using SIFT Features(The Eurographics Association, 2005) Delponte, Elisabetta; Isgrò, Francesco; Odone, Francesca; Verri, Alessandro; Mike ChantlerThe paper tackles the problem of feature points matching between pair of images of the same scene. This is a key problem in computer vision. Among the many possible applications of feature matching we are motivated for helping in the initialisation of a 3D registration procedure. The method we discuss here is a version of the SVD matching proposed by Pilu, modified in order to cope with large scale variations. We detail the algorithm and present experimental evidence of the improvement in performance. The main contribution of this work is in showing that this compact and easy algorithm can be used for large-baseline matching.