The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Recently, the use of object proposals has been much introduced in the field of salient object segmentation methods. Object proposal methods provide a limited set of proposals per image which can successively be analyzed on their saliency. In this context, we regard saliency map computation as a regression problem and we used object proposals (selective search) to compute the saliency map. Our method...
Chest wall mobility assessment is an important parameter in diagnosing pulmonary disorders. The purpose of this study is to examine and compare variations in thoracic and abdominal volumes based on changes in chest expansion that can be used as a clinical tool in pulmonary function studies. A newly proposed optical camera system utilizing a set of markers placed on subjects' thoracic and abdominal...
In this paper, we focus on modeling multichannel audio signals in the short-time Fourier transform domain for the purpose of source separation. We propose a probabilistic model based on a class of heavy-tailed distributions, in which the observed mixtures and the latent sources are jointly modeled by using a certain class of multivariate alpha-stable distributions. As opposed to the conventional Gaussian...
Shape Boltzmann machine (a type of Deep Boltzmann machine) is a powerful tool for shape modelling; however, has some drawbacks in representation of local shape parts. Disjunctive Normal Shape Model (DNSM) is a strong shape model that can effectively represent local parts of objects. In this paper, we propose a new shape model based on Shape Boltzmann Machine and Disjunctive Normal Shape Model which...
Inferring the pose and shape of vehicles in 3D from a movable platform still remains a challenging task due to the projective sensing principle of cameras, difficult surface properties e.g. reflections or transparency, and illumination changes between images. In this paper, we propose to use 3D shape and motion priors to regularize the estimation of the trajectory and the shape of vehicles in sequences...
We present scattering models of snow and ice hydrometeors and computation of full polarimetrie radar variables for winter precipitation using a higher order method of moments (MoM) in the surface integral equation (SIE) formulation. The studies of winter precipitation are based primarily on measurements by a multi-angle snowflake camera (MASC), reconstruction of 3D hydrometeor shapes by means of the...
The most standard approach to resolve the inherent ambiguities of the non-rigid structure from motion problem is using low-rank models that approximate deforming shapes by a linear combination of rigid basis. These models are typically global, i.e., each shape basis contributes equally to all points of the surface. While this approach has been shown effective to represent smooth deformations, its...
We have designed and implemented an unsupervised learning algorithm for finite mixture model using the scaled Dirichlet distribution for multivariate proportional data. In this paper, the task of learning finite mixture model involves estimation of model parameters as well as inferring the hidden class information of our observed data. We made use of the expectation maximization algorithm to find...
Construction of field lines for vector fields can be performed by a variety of analytical or graphical methods. Except for a small number of simple geometries, where closed analytical expressions can be obtained, the shape of the field lines is determined by numerical computation or evaluated approximately by physical modelling techniques [1]. In this paper, we consider irrotational vector fields...
Various applications have been developed during recent years which are based on the computer vision system. In this field, plant species recognition is a challenging task for researchers due to environmental and image acquisition condition of image. Leaf classification application can be used for various purpose such as remote sensing imaging, botanical characteristically analysis etc. Now a day,...
This paper deals with privacy protection in video surveillance. More specifically, the main goal of this work is to make the gender of people no more recognizable while preserving enough information concerning body shape and motion of people for action classification. We denote this processing as de-genderization. Regarding the current state-of-art methods, most of them have privacy filters only dedicated...
We extend a novel 2D shape descriptor called Distance Interior Ratio (DIR) [4] to describe a 3D shape represented by a volumetric model, called 3DDIR. The 3DDIR is defined as follow: Given a segment ab between two points a and b on the surface of an object O, the DIR of ab is the ratio of the total length of its fragments O ∩ ab to the length |ab|. To find the fragments O ∩ ab, we apply a simple ray...
This paper proposes a novel algorithm to determine the spatially varying reflectance of an arbitrary object based on per-pixel estimates of the bidirectional reflectance distribution function (BRDF). The proposed procedure is especially designed to work in environments that yield relatively sparse reflectance measurements, since the parameter estimation is initialized on regions of similar brightness...
We study the geometry of a 2-dimensional cyclic pursuit problem where n identical mobile agents modeled as unicycles are driven by a distributed control law. The agent i pursuits the agent i + 1 modulo n with the same constant forward speed. We propose, for the first time, a stable relative (1 : n)-periodic trajectory (RPT) for the polygonal chain formed by the system with a sufficiently large n....
In recent years, hand drawn sketch based 3D model retrieval method has become a popular research area due to the rapid growth of available 3D models on the Internet. However, most existing sketch based 3D model retrieval methods only consider using low-level visual features that cannot capture users'search intention. In this paper, we propose a novel sketch-based 3D model retrieval approach by using...
In this paper, we propose a new local descriptor for action recognition in depth images. The proposed descriptor relies on surface normals in 4D space of depth, time, spatial coordinates and higher-order partial derivatives of depth values along spatial coordinates. In order to classify actions, we follow the traditional Bag-of-words (BoW) approach, and propose two encoding methods termed Multi-Scale...
This paper presents a novel Robust Deep Appearance Models (RDAMs) approach to learn the non-linear correlation between shape and texture of face images. In this approach, two crucial components of face images, i.e. shape and texture, are represented by Deep Boltzmann Machines and Robust Deep Boltzmann Machines (RDBM), respectively. The RDBM, an alternative form of Robust Boltzmann Machines, can separate...
Discriminating probabilistic graphical models are reliable tools for a sequence labeling task. Conditional Random Fields (CRFs) are discriminative models which will enable us to label a sequence of input data. Other variations of CRFs have been proposed. Hidden Conditional Random Fields (HCRFs) incorporate hidden states to the CRF model and assign a label for the whole input sequence as the model's...
Level set-based contour tracking methods have generated recent interest in the computer vision community. In this paper, we propose a novel level set-based algorithm for tracking dynamic implicit contours that utilizes minimal prior information. Our solution consists of two main steps. In the first step, a simple first-order Markov chain model is employed for the coarse localization of a target object...
In this paper we propose a multi-modal object recognition system that uses a two-step hypothesis verification approach to improve runtime efficiency. The system uses local and global appearance and shape features, generating many possibly competing hypotheses, which are then verified such that the scene can be optimally explained in terms of recognized object models. The introduced modification in...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.