Thiago Lopes Trugillo da Silveira

Universidade Federal do Rio Grande do Sul | UFRGS · Departamento de Informática Aplicada

Omnidirectional media are becoming widespread with the increasing popularization of devices for capture and visualization. Unlike traditional pinhole-based images, omnidi-rectional images are defined on the surface of a sphere, present a full field of view, and store light intensities from a whole scene. In particular, applications exploring immers...

Programming is one of the most fundamental initial skills for engineering students. Institutions that offer engineering courses have the challenge of deciding how to deliver this subject since it requires unique thinking from students. This paper addresses the impact of adopting C and Python programming languages in introductory programming courses...

This paper introduced a matrix parametrization method based on the Loeffler discrete cosine transform (DCT) algorithm. As a result, a new class of eight-point DCT approximations was proposed, capable of unifying the mathematical formalism of several eight-point DCT approximations archived in the literature. Pareto-efficient DCT approximations are o...

In this paper, two 8-point multiplication-free DCT approximations based on the Chen's factorization are proposed and their fast algorithms are also derived. Both transformations are assessed in terms of computational cost, error energy, and coding gain. Experiments with a JPEG-like image compression scheme are performed and results are compared wit...

Pose estimation is a crucial problem in several computer vision and robotics applications. For the two-view scenario, the typical pipeline consists of finding point correspondences between the two views and using them to estimate the pose. However, most available keypoint extraction and matching methods were designed to work with perspective images...

The discrete cosine transform (DCT) is a relevant tool in signal processing applications, mainly known for its good decorrelation properties. Current image and video coding standards -- such as JPEG and HEVC -- adopt the DCT as a fundamental building block for compression. Recent works have introduced low-complexity approximations for the DCT, whic...

This paper provides a comprehensive survey on pioneer and state-of-the-art 3D scene geometry estimation methodologies based on single, two, or multiple images captured under omnidirectional optics. We first revisit the basic concepts of the spherical camera model and review the most common acquisition technologies and representation formats suitabl...

The discrete cosine transform (DCT) is a relevant tool in signal processing applications, mainly known for its good decorrelation properties. Current image and video coding standards—such as JPEG and HEVC—adopt the DCT as a fundamental building block for compression. Recent works have introduced low-complexity approximations for the DCT, which beco...

The Karhunen-Lo\`eve transform (KLT) is often used for data decorrelation and dimensionality reduction. The KLT is able to optimally retain the signal energy in only few transform components, being mathematically suitable for image and video compression. However, in practice, because of its high computational cost and dependence on the input signal...

Monocular depth inference methods based on 360° images allow 3D reconstruction of entire rooms with a single capture. However, most state-of-the-art approaches assume gravity aligned images and are highly sensitive to camera rotations. Such limitations result in poor depth estimates, which may jeopardize further 3D-based applications. Here, we pres...

Superpixels are fundamental in many visual computing applications, and most existingalgorithms are designed to work with pinhole-based images. However, immersiveapplications are gaining visibility with the growing number of devices for capturing andvisualizing 360º media. This paper introduces two fast and accurate superpixelalgorithms tailored to...

View synthesis allows observers to explore static scenes using aligned color images and depth maps captured in a preset camera path. Among the options, depth-image-based rendering (DIBR) approaches have been effective and efficient since only one pair of color and depth map is required, saving storage and bandwidth. The present work proposes a nove...

Techniques for 3D reconstruction of scenes based on images are popular and support a number of secondary applications. Traditional approaches require several captures for covering whole environments due to the narrow field of view (FoV) of the pinhole-based/perspective cameras. This paper summarizes the main contributions of the homonym Ph.D. Thesi...

This paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs (RAGs), in which regions are superpixels and edges connect neighboring superpixels. Our experiments suggest that Graph Attention Networks (GATs), which combine graph convolutions with self-at...

Discrete transforms play an important role in many signal processing applications, and low-complexity alternatives for classical transforms became popular in recent years. Particularly, the discrete cosine transform (DCT) has proven to be convenient for data compression, being employed in well-known image and video coding standards such as JPEG, H....

Discrete transforms play an important role in many signal processing applications, and low-complexity alternatives for classical transforms became popular in recent years. Particularly, the discrete cosine transform (DCT) has proven to be convenient for data compression, being employed in well-known image and video coding standards such as JPEG, H....

This document reports the use of Graph Attention Networks for classifying oversegmented images, as well as a general procedure for generating oversegmented versions of image-based datasets. The code and learnt models for/from the experiments are available on github. The experiments were ran from June 2019 until December 2019. We obtained better res...

The principal component analysis (PCA) is widely used for data decorrelation and dimensionality reduction. However, the use of PCA may be impractical in real-time applications, or in situations were energy and computing constraints are severe. In this context, the discrete cosine transform (DCT) becomes a low-cost alternative to data decorrelation....

This paper presents a perturbation analysis for the estimate of epipolar matrices using the 8-Point Algorithm (8-PA). Our approach explores existing bounds for singular subspaces and relates them to the 8-PA, without assuming any kind of error distribution for the matched features. In particular, if we use unit vectors as homogeneous image coordina...

In this paper we compare the quality of synthesized views produced by four DIBR methods when fed by depth maps estimated by five state-of-the-art stereo matching algorithms. Also, we compute the correlation between four popular metrics for ranking stereo matching algorithms and two metrics commonly used to evaluate synthesized views (PSNR and SSIM)...

This paper introduced a matrix parametrization method based on the Loeffler discrete cosine transform (DCT) algorithm. As a result, a new class of 8-point DCT approximations was proposed, capable of unifying the mathematical formalism of several 8-point DCT approximations archived in the literature. Pareto-efficient DCT approximations are obtained...

In this paper we propose a framework for inferring depth from a single spherical image, which can be coupled to any generic planar image monocular depth estimation algorithm. It consists of first inferring depth from overlapping planar patches extracted from the spherical image, and then using a regularized minimization scheme to stitch the patches...

In the pursuit of highly effective and efficient portable sleep classification systems, researchers have been testing a massive number of combinations of EEG features and classifiers. State of art sleep classification ensembles achieve accuracy in the order of 90%. However, there is presently no consensus regarding the best setof features for sleep...

Keypoint extraction and matching has been widely studied by the computer vision community, mostly focused on pinhole camera models. In this paper we perform a comparative analysis of four keypoint extraction algorithms applied to full spherical images, particularly in the context of pose estimation. Two of the methods chosen for the comparative stu...

In this paper, two 8-point multiplication-free DCT approximations based on the Chen's factorization are proposed and their fast algorithms are also derived. Both transformations are assessed in terms of computational cost, error energy, and coding gain. Experiments with a JPEG-like image compression scheme are performed and results are compared wit...

An orthogonal 16-point approximate discrete cosine transform (DCT) is introduced. The proposed transform requires neither multiplications nor bit-shifting operations. A fast algorithm based on matrix factorization is introduced, requiring only 44 additions---the lowest arithmetic cost in literature. To assess the introduced transform, computational...

The main objective of this study was to enhance the performance of sleep stage classification using single-channel electroencephalograms (EEGs), which are highly desirable for many emerging technologies, such as telemedicine and home care. The proposed method consists of decomposing EEGs by a discrete wavelet transform and computing the kurtosis, s...

Advances in materials engineering, electronic circuits, sensors, signal processing and classification techniques have allowed computational systems to interpret biological quantities, recognizing physiological conditions. The next scientific challenge is to turn those technologies portable, wearable or even implantable, above all, being energy effi...

A low-complexity orthogonal multiplierless approximation for the 16-point dis-crete cosine transform (DCT) was introduced. The proposed method was designed to possess a very low computational cost. A fast algorithm based on matrix factorization was proposed requiring only 60 additions. The proposed architecture outperforms classical and state-of-th...

Sleep deprivation is a public health problem which must be carefully examined and treated. Several studies have proposed automatic methods aiming to identify when a person falls asleep. The identification of the sleep state can help sleep experts to diagnose and prevent certain disorders such as apnea and insomnia. In the current work, the discrete...

The growing need for urban mobility implies new challenges for traffic management. Since vehicular networks (VANETs) will be available in future, new solutions can be applied to intersection control, offering more agility to transportation networks. While VANETs are not still widely deployed, this work explores the application of different intersec...

Monitoring and planning are interesting activities to help transit operator and to provide quality in public transportation. In fact, some computational tools and simulators play this role and assist humans in tasks and improving transportation. However, existing solutions are typically proprietary and, therefore , have prohibitive cost to be adopt...

The Simulation is a key element in efficient management and operation of public transport. This activity includes processing of dynamic data possibly obtained through sensors, as well dealing with static information including map digitalization. A fundamental problem is that, although available, systems that perform these activities are proprietary...