Browsing by Author "du Buf, J. M. H."
Now showing 1 - 10 of 119
Results Per Page
Sort Options
- A background-priority discrete boundary triangulation methodPublication . Loke, R. E.; Jansen, F. W.; du Buf, J. M. H.Discrete boundary triangulation methods generate triangular meshes through the centers of the boundary voxels of a volumetric object. At some voxel configurations it may be arbitrary whether a part of the volume should be included in the object or could be classified as background. Consequently, important details such as concave and convex edges and corners are not consistently preserved in the describing geometry. We present a "background priority" version of an existing "object priority" algorithm [6]. We show that the ad hoc configurations of the well-known Discretized Marching Cubes algorithm [13] can be derived from our method and that a combined triangulation with "object priority" and "background priority" better would preserve object details.
- A biological sound source localization modelPublication . Azarfar, A.; du Buf, J. M. H.In this paper we address sound source localization in the azimuthal plane. Various models, from the cochlear nuclei to the inferior colliculi, are implemented to achieve accurate and reliable localization. Coincidence detector cells in the medial nuclei and cells sensitive to interaural level difference in the lateral nuclei of the superior olive are combined with models of V-and I-type neurons plus azimuth map cells in the inferior colliculus. An advanced cell distribution in the inferior colliculus is proposed to keep ITD functions at any frequency within the physiological range of the head. Additional projections from the dorsal nucleus of the lateral lemniscus and the medial nucleus of the superior olive are modeled such that interaural time differences in different frequency bands converge to a single result. Experimental results demonstrate good performance in case of a variety of normal sounds.
- A deep neural network video framework for monitoring elderly personsPublication . Farrajota, Miguel; Rodrigues, João; du Buf, J. M. H.The rapidly increasing population of elderly persons is a phenomenon which affects almost the entire world. Although there are many telecare systems that can be used to monitor senior persons, none integrates one key requirement: detection of abnormal behavior related to chronic or new ailments. This paper presents a framework based on deep neural networks for detecting and tracking people in known environments, using one or more cameras. Video frames are fed into a convolutional network, and faces and upper/full bodies are detected in a single forward pass through the network. Persons are recognized and tracked by using a Siamese network which compares faces and/or bodies in previous frames with those in the current frame. This allows the system to monitor the persons in the environment. By taking advantage of parallel processing of ConvNets with GPUs, the system runs in real time on a NVIDIA Titan board, performing all above tasks simultaneously. This framework provides the basic infrastructure for future pose inference and gait tracking, in order to detect abnormal behavior and, if necessary, to trigger timely assistance by caregivers.
- A fast neural-dynamical approach to scale-invariant object detectionPublication . Terzic, Kasim; Lobato, D.; Saleiro, Mário; du Buf, J. M. H.We present a biologically-inspired method for object detection which is capable of online and one-shot learning of object appearance. We use a computationally efficient model of V1 keypoints to select object parts with the highest information content and model their surroundings by a simple binary descriptor based on responses of cortical cells. We feed these features into a dynamical neural network which binds compatible features together by employing a Bayesian criterion and a set of previously observed object views. We demonstrate the feasibility of our algorithm for cognitive robotic scenarios by evaluating detection performance on a dataset of common household items. © Springer International Publishing Switzerland 2014.
- A parametric spectral model for texture-based saliencePublication . Terzic, Kasim; Krishna, Sai; du Buf, J. M. H.; Gall, J.; Gehler, P.; Leibe, B.We present a novel saliency mechanism based on texture. Local texture at each pixel is characterised by the 2D spectrum obtained from oriented Gabor filters. We then apply a parametric model and describe the texture at each pixel by a combination of two 1D Gaussian approximations. This results in a simple model which consists of only four parameters. These four parameters are then used as feature channels and standard Difference-of-Gaussian blob detection is applied in order to detect salient areas in the image, similar to the Itti and Koch model. Finally, a diffusion process is used to sharpen the resulting regions. Evaluation on a large saliency dataset shows a significant improvement of our method over the baseline Itti and Koch model.
- A quantitative comparison of edge-preserving smoothing techniquesPublication . du Buf, J. M. H.; Campbell, T. G.Edge-preserving smoothing techniques are compared by considering a test image which contains a central disk-shaped region with a step or a ramp edge against a uniform background. Free parameters are the amplitude of Gaussian noise added, the edge slope and the number of filtering iterations. The quantitative comparison measure is the normalised squared error between the filtered noisy image and the noise-free image, on the uniform image regions and on the transition region separately. The filters considered are analysed with respect to their performance under variations in the free parameters and their computer-time consumption. Results obtained are compared with published data available. © 1990.
- A Review of Recent Texture Segmentation and Feature Extraction TechniquesPublication . Reed, T. R.; du Buf, J. M. H.The area of texture segmentation has undergone tremendous growth in recent years. There has been a great deal of activity both in the refinement of previously known approaches and in the development of completely new techniques. Although a wide variety of methodologies have been applied to this problem, there is a particularly strong concentration in the development of feature-based approaches and on the search for appropriate texture features. In this paper, we present a survey of current texture segmentation and feature extraction methods. Our emphasis is on techniques developed since 1980, particularly those with promise for unsupervised applications. © 1993 Academic Press. All rights reserved.
- Abstract processes in texture discriminationPublication . du Buf, J. M. H.In this study some experiments on texture segmentation are reported using the local Gabor power spectrum. The techniques applied are: (1) supervised pixel classification; (2) boundary detection by spectral dissimilarity estimation; (3) region-based segmentation based on Gaussian spectral estimation; and (4) the same as (3) but based on central moments of the local spectrum. It is shown that very-acceptable-to-excellent results can be obtained. It is argued, however, that the shortcomings of region-based and boundary-based approaches require that both processes should act in parallel, not only in digital image processing but also in the modelling of visual perception.
- Analysis of underwater acoustic data via 3-D segmentationPublication . Reed, Todd R.; Loke, R. E.; du Buf, J. M. H.The analysis of seabed structure is important in a wide variety of scientific and industrial applications. In this paper, underwater acoustic data produced by bottom-penetrating sonar (Topas) are analyzed using unsupervised volumetric segmentation, based on a three dimensional Gibbs-Markov model. The result is a concise and accurate description of the seabed, in which key structures are emphasized. This description is also very well suited to further operations, such as the enhancement and automatic recognition of important structures. Experimental results demonstrating the effectiveness of this approach are shown, using Topas data gathered in the North Sea off Horten, Norway.
- Arquitectura do córtex visual com aplicações na visão por computadorPublication . du Buf, J. M. H.; Rodrigues, J. M. F.O estudo da visão humana atrai o interesse de muitos cientistas ao longo dos séculos, como por exemplo em 1704 por Newton na visão a cores e 1910 por Helmholtz na óptica fisiológica. No entanto, as primeiras contribuições na visão computacional começaram por volta de 40 anos atrás quando os primeiros computadores apareceram. Por volta de 1980, David Marr estabeleceu as bases para a moderna teoria de visão computacional.