Search results for "METHODOLOGIE"
showing 10 items of 2141 documents
Spatio-Temporal Saliency Detection in Dynamic Scenes using Local Binary Patterns
2014
International audience; Visual saliency detection is an important step in many computer vision applications, since it reduces further processing steps to regions of interest. Saliency detection in still images is a well-studied topic. However, videos scenes contain more information than static images, and this additional temporal information is an important aspect of human perception. Therefore, it is necessary to include motion information in order to obtain spatio-temporal saliency map for a dynamic scene. In this paper, we introduce a new spatio-temporal saliency detection method for dynamic scenes based on dynamic textures computed with local binary patterns. In particular, we extract l…
Perceptually weighted optical flow for motion-based segmentation in MPEG-4 paradigm
2000
In the MPEG-4 paradigm, the sequence must be described in terms of meaningful objects. This meaningful, high-level representation should emerge from low-level primitives such as optical flow and prediction error which are the basic elements of previous-generation video coders. The accuracy of the high-level models strongly depends on the robustness of the primitives used. It is shown how perceptual weighting in optical flow computation gives rise to better motion estimates which consistently improve motion-based segmentation compared to equivalent unweighted motion estimates.
Semi-Supervised Remote Sensing Image Classification based on Clustering and the Mean Map Kernel
2008
This paper presents a semi-supervised classifier based on the combination of the expectation-maximization (EM) algorithm for Gaussian mixture models (GMM) and the mean map kernel. The proposed method uses the most reliable samples in terms of maximum likelihood to compute a kernel function that accurately reflects the similarity between clusters in the kernel space. The proposed method improves classification accuracy in situations where the available labeled information does not properly describe the classes in the test image.
Optical flow estimation from multichannel spherical image decomposition
2011
The problem of optical flow estimation is largely discussed in computer vision domain for perspective images. It was also proven that, in terms of optical flow analysis from these images, we have difficulty distinguishing between some motion fields obtained with little camera motion. The omnidirectional cameras provided images with large filed of view. These images contain global information about motion and allow to remove the ambiguity present in perspective case. Nevertheless, these images contain significant radial distortions that is necessary to take into account when treating these images to estimate the motion. In this paper, we shall describe new way to compute efficient optical fl…
Enhanced detection of contrast regions in echocardiograms by adaptive quantization
2002
The statistics of ultrasound echo images are governed by Rayleigh statistics. The authors derive some experimentally verifiable predictions of this theory, compare them with experimental results obtained from echocardiographic images, and derive a new color coding scheme, (adaptive quantization) that is adapted to the signal-dependent noise predicted by theory. This results in some technical advantages and in an improved discrimination of regions of the echo image that are enhanced by echo contrast material. >
<title>Human cell texture analysis with quincunx spline wavelet transform</title>
1999
Wavelet transforms are efficient tools for texture analysis and classification. Separable techniques are classically used but present several drawbacks. First, diagonal coefficients contain poor information. Second, the other coefficients contain useful information only if the texture is oriented in the vertical and horizontal directions. So an approach of texture analysis by non-separable transform is proposed. An improved interscale resolution is allowed by the quincunx scheme and this analysis leads to only one detail image where no particular orientation is favored. New orthogonal isotropic filters for the decomposition are constructed by applying McClellan transform on one dimension B-…
Hidden Markov Random Field model and BFGS algorithm for Brain Image Segmentation
2016
Brain MR images segmentation has attracted a particular focus in medical imaging. The automatic image analysis and interpretation became a necessity. Segmentation is one of the key operations to provide a crucial decision support to physicians. Its goal is to simplify the representation of an image into items meaningful and easier to analyze. Hidden Markov Random Fields (HMRF) provide an elegant way to model the segmentation problem. This model leads to the minimization problem of a function. BFGS (Broyden-Fletcher-Goldfarb-Shanno algorithm) is one of the most powerful methods to solve unconstrained optimization problem. This paper presents how we combine HMRF and BFGS to achieve a good seg…
<title>Multiresolution description of range images through 2D quincunx wavelet analysis</title>
1999
In this paper, we present a method for performing a multi- scale analysis on range images by using the wavelet transform, that is capable of revealing multi-resolution information. An accurate non-contact optical system based upon laser triangulation is used to determine the depth information of the object being scanned. The resulting range image is treated as a gray-level image by using a multi- resolution approach based on the generalization of the cascade algorithm using the quincunx wavelet transform. The quincunx wavelet assures very fine analysis. This method allows reconstruction of non-subsampled images that correspond to decompositions previously done at chosen scales. Multi-resolu…
A statistical model for magnitudes and angles of wavelet frame coefficients and its application to texture retrieval
2014
Abstract This paper presents a texture descriptor based on wavelet frame transforms. At each position in the image, and for each resolution level, we consider both vertical and horizontal wavelet detail coefficients as the components of a bivariate random vector. The magnitudes and angles of these vectors are computed. At each level the empirical histogram of magnitudes is modeled by a Generalized Gamma distribution, and the empirical histogram of angles is modeled by a different version of the von Mises distribution that accounts for histograms with 2 modes. Each texture is characterized by few parameters. A new distance is presented (based on the Kullback–Leibler divergence) that allows g…
A PROGRAM FOR THE AUTOMATIC COMPUTING OF SOLAR GAIN OF A PARALLELEPIPED VOLUME CONSIDERING THE SHADOWS CAST ON IT BY ANY SYSTEM OF SURROUNDING PARALL…
1985
A program is given, that computes solar gain on a parallelepiped volume taking in to consideration the shadows cast by any system of surrounding parallelepiped. It contains an algorithm for the quick discarding of non shadowing volumes, for the construction of the union polygon, without repetition of overlapping shadows, and for the intersection polygon of formerly found union polygon with the shadowed faces.