VVG05

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/1030

Browse

Now showing 1 - 20 of 33

Table of Contents and Preface
(The Eurographics Association, 2005) Mike Chantler
Image classification using compression distance
(The Eurographics Association, 2005) Lan, Yuxuan; Harvey, Richard; Mike Chantler
The normalised compression distance measures the mutual compressibility of two signals. We show that this distance can be used for classification on real images. Furthermore, the same compressor can also operate on derived features with no further modification. We consider derived features consisting of trees indicating the containment and relative area of connected sets within the image. It had been previously postulated that such trees might be useful features, but they are too complicated for conventional classifiers. The new classifier operating on these trees produces results that are very similar to those obtained on the raw images thus allowing, for the first time, classification using the full trees.
Monte Carlo Noise Reduction Using Bayesian Method in Wavelet domain
(The Eurographics Association, 2005) Xu, Ruifeng; Pattanaik, Sumanta N.; Mike Chantler
A novel post-processing approach for removing Monte Carlo noises in synthetic images is presented in this paper. This paper first presents our findings on the statistical characteristics of the Monte Carlo noise, and then proposes a Bayesian method to remove this noise. The aim of this approach is to efficiently produce high quality synthetic images using Monte Carlo based rendering at low sampling rates.
Advances in Shadow Removing for Motion Detection Algorithms
(The Eurographics Association, 2005) Spagnolo, P.; D'Orazio, T.; Leo, M.; Distante, A.; Mike Chantler
Detecting 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.
Talking Faces - Technologies and Applications
(The Eurographics Association, 2005) Ostermann, Jörn; Weissenfeld, Axel; Liu, Kang; Mike Chantler
Facial 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 speech
Modeling Falling and Accumulating Snow
(The Eurographics Association, 2005) Moeslund, T. B.; Madsen, C. B.; Aagaard, M.; Lerche, D.; Mike Chantler
The 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.
Natural Image Matting
(The Eurographics Association, 2005) Hillman, Peter M.; Hannah, John M.; Mike Chantler
Matte pulling - generating greyscale images which indicate segmentation of images into elements with subpixel accuracy and where blur causes pixels to be a mixture of elements - has received attention in recent years. Many of the algorithms are too slow or too unpredictable to be of practical use in motion picture Post-production. Assessing the performance of different algorithms is also a complex task. This paper presents an optimisation which can be applied to many algorithms in order to allow them to run at interactive speeds, introduces a new algorithm based on Colour Lines, and presents a technique which can be used as a formal test-bench to measure the performance of matte algorithms.
Linear Hashtable Method and Predicted Hexagonal Search Algorithm with Moments Invariant
(The Eurographics Association, 2005) Wu, Yunsong; Megson, Graham; Nie, Zhengang; Liu, Xuan; Mike Chantler
This paper presents a novel Linear Hashtable Method Predicted Hexagonal Search (LHMPHS) method for block base motion compensation on the basis of research from previous algorithm. Hashtable is used in video compression. Motion vectors produced by Linear Hashtable Motion Estimation Algorithm (LHMEA) are used as predictors for HEXBS. Moments invariants are also tested in hashtable to prove the more information moments have, the better it is. Experimental results show that the proposed algorithm can offer the same compression rate as the Full Search and fastest than all investigated algorithms, while the PSNR is high. LHMPHS has significant improvement on HEXBS and shows a direction for improving other fast motion estimation algorithms.
Multi-View Image Coding with Wavelet Lifting Scheme
(The Eurographics Association, 2005) Anantrasirichai, N.; Canagarajah, C. Nishan; Bull, David R.; Mike Chantler
In 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.
Visual Recognition of Man-made Materials and Structures in an Office Environment
(The Eurographics Association, 2005) Song, Y. Z.; Town, C. P.; Mike Chantler
This 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.
Color Reduction by Using a new Self-Growing and Self-Organized Neural Network
(The Eurographics Association, 2005) Atsalakis, A.; Papamarkos, N.; Mike Chantler
A 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.
A New Framework for Trademark Retrieval Based on Size Functions
(The Eurographics Association, 2005) Cerri, A.; Ferri, M.; Giorgi, D.; Mike Chantler
We 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.
Bitvectors for Robust Hierarchical Template Matching
(The Eurographics Association, 2005) Tweed, David; Mike Chantler
Many 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.
Texture Mapping Volume Objects
(The Eurographics Association, 2005) Shen, P.; Willis, P.; Mike Chantler
We 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.
Merging Graphics and Vision for 3D Face Recognition
(The Eurographics Association, 2005) Bai, Li; Song, Yi; Mike Chantler
This 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.
On the Separation of Luminance from Colour in Images
(The Eurographics Association, 2005) Woodland, Alan; Labrosse, Frédéric; Mike Chantler
Many 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.
Realistic Real-Time Hair Simulation and Rendering
(The Eurographics Association, 2005) Jung, Yvonne; Rettig, Alexander; Klar, Oliver; Lehr, Timo; Mike Chantler
We 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.
3D Image Analysis and Synthesis at MPI Informatik
(The Eurographics Association, 2005) Theobalt, Christian; Magnor, Marcus A.; Seidel, Hans-Peter; Mike Chantler
In 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.
Different Medical Modelling Strategies in a Single Collaborative Immersive Virtual Environment
(The Eurographics Association, 2005) Al-khalifah, A.; McCrindle, R.; Alexandrov, V.; Mike Chantler
Visualisation and simulation systems are becoming increasingly popular nowadays in medical planning and training. These tools are built using various technologies, such as computer graphics, Virtual Reality, and three dimensional (3D) modelling. The latter is an important element to these systems, because it governs how models are represented and how they can be manipulated. In this paper, we investigate the use of various 3D modelling techniques in a virtual immersive collaborative environment. We highlight the merits and limitations of these techniques, explain how they can be used in a virtual medical context, and demonstrate a practical application.
Learnt Inverse Kinematics for Animation Synthesis
(The Eurographics Association, 2005) Ong, Eng-Jon; Hilton, Adrian; Mike Chantler
Existing 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.

Browse

Browsing VVG05 by Issue Date

Results Per Page

Sort Options