Search Results - "da Silveira, Thiago L. T."

A Hierarchical Superpixel-Based Approach for DIBR View Synthesis by de Oliveira, Adriano Q., Silveira, Thiago L. T. da, Walter, Marcelo, Jung, Claudio R.

“…View synthesis allows observers to explore static scenes using aligned color images and depth maps captured in a preset camera path. Among the options,…”
Get full text

Single-channel EEG sleep stage classification based on a streamlined set of statistical features in wavelet domain by da Silveira, Thiago L. T., Kozakevicius, Alice J., Rodrigues, Cesar R.

“…The main objective of this study was to enhance the performance of sleep stage classification using single-channel electroencephalograms (EEGs), which are…”
Get full text

Triangular matrix-based lossless compression algorithm for 3D mesh connectivity by Balreira, Dennis G., da Silveira, Thiago L. T.

“…Three-dimensional mesh compression is vital to support advances in many scenarios, such as 3D web-based applications. Existing 3D mesh methods usually require…”
Get full text

Investigating the impact of adopting Python and C languages for introductory engineering programming courses by Balreira, Dennis G., Silveira, Thiago L. T. da, Wickboldt, Juliano A.

“…Programming is one of the most fundamental initial skills for engineering students. Institutions that offer engineering courses have the challenge of deciding…”
Get full text

A Class of Low-Complexity DCT-Like Transforms for Image and Video Coding by da Silveira, Thiago L. T., Canterle, Diego Ramos, Coelho, Diego F. G., Coutinho, Vitor A., Bayer, Fabio M., Cintra, Renato J.

“…The discrete cosine transform (DCT) is a relevant tool in signal processing applications, mainly known for its good decorrelation properties. Current image and…”
Get full text

Omnidirectional 2.5D representation for COVID-19 diagnosis using chest CTs by da Silveira, Thiago L.T., Pinto, Paulo G.L., Lermen, Thiago S., Jung, Cláudio R.

“…The Coronavirus Disease 2019 (COVID-19) has drastically overwhelmed most countries in the last two years, and image-based approaches using computerized…”
Get full text

Automated drowsiness detection through wavelet packet analysis of a single EEG channel by da Silveira, Thiago L.T., Kozakevicius, Alice J., Rodrigues, Cesar R.

“…•Ratio indices computed from a single EEG channel used as drowsiness indicators.•Delta and gamma brain rhythms successfully used for drowsiness…”
Get full text

Data-independent low-complexity KLT approximations for image and video coding by Radünz, Anabeth P., da Silveira, Thiago L.T., Bayer, Fábio M., Cintra, Renato J.

“…The Karhunen–Loève transform (KLT) is often used for data decorrelation and dimensionality reduction. The KLT is able to optimally retain the signal energy in…”
Get full text

Superpixel Image Classification with Graph Attention Networks by Avelar, Pedro H. C., Tavares, Anderson R., da Silveira, Thiago L. T., Jung, Cliudio R., Lamb, Luis C.

“…This paper presents a methodology for image classification using Graph Neural Network (GNN) models. We transform the input images into region adjacency graphs…”
Get full text

Low-complexity 8-point DCT approximation based on angle similarity for image and video coding by Oliveira, Raíza S., Cintra, Renato J., Bayer, Fábio M., da Silveira, Thiago L. T., Madanayake, Arjuna, Leite, André

“…The principal component analysis (PCA) is widely used for data decorrelation and dimensionality reduction. However, the use of PCA may be impractical in…”
Get full text

A Temporally Coherent Background Model for DIBR View Synthesis by de Oliveira, Adriano Q., da Silveira, Thiago L. T., Walter, Marcelo, Jung, Claudio R.

“…Aligned color and depth images allow exploring a scene by projecting the virtual camera to arbitrary positions. Depth-image-based rendering (DIBR) methods are…”
Get full text

Perturbation Analysis of the 8-Point Algorithm: A Case Study for Wide FoV Cameras by da Silveira, Thiago L. T., Jung, Claudio R.

“…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…”
Get full text

Gravity Alignment for Single Panorama Depth Inference by Bergmann, Matheus A., Pinto, Paulo G. L., da Silveira, Thiago L. T., Jung, Claudio R.

“…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…”
Get full text

Multiplierless 16-point DCT approximation for low-complexity image and video coding by da Silveira, Thiago L. T., Oliveira, Raíza S., Bayer, Fábio M., Cintra, Renato J., Madanayake, Arjuna

“…An orthogonal 16-point approximate discrete cosine transform (DCT) is introduced. The proposed transform requires neither multiplications nor bit-shifting…”
Get full text

An orthogonal 16-point approximate DCT for image and video compression by da Silveira, Thiago L. T., Bayer, Fábio M., Cintra, Renato J., Kulasekera, Sunera, Madanayake, Arjuna, Kozakevicius, Alice J.

“…A low-complexity orthogonal multiplierless approximation for the 16-point discrete cosine transform (DCT) was introduced. The proposed method was designed to…”
Get full text

Pose Estimation for Two-View Panoramas based on Keypoint Matching: a Comparative Study and Critical Analysis by Murrugarra-Llerena, Jeffri, Da Silveira, Thiago L. T., Jung, Claudio R.

“…Pose estimation is a crucial problem in several computer vision and robotics applications. For the two-view scenario, the typical pipeline consists of finding…”
Get full text

Omnidirectional visual computing: Foundations, challenges, and applications by da Silveira, Thiago L.T., Jung, Cláudio R.

“…Omnidirectional images and videos are widespread due to the popularization of devices for capturing and visualization. Unlike pinhole-based imagery,…”
Get full text

A Multiparametric Class of Low-complexity Transforms for Image and Video Coding by Canterle, Diego Ramos, da Silveira, Thiago L.T., Bayer, Fábio M., Cintra, Renato J.

“…•We propose a multiparametric class of low-complexity transforms for image compression;•We introduce eleven novel 8-point low-complexity DCT approximations;•We…”
Get full text

Fast and accurate superpixel algorithms for 360∘ images by da Silveira, Thiago L.T., de Oliveira, Adriano Q., Walter, Marcelo, Jung, Cláudio R.

“…•We propose a method for multiscale, border-guided 360∘ image oversegmentation.•We propose a superpixel method for 360 ∘ images that concern borders and…”
Get full text

Spherically-Weighted Horizontally Dilated Convolutions for Omnidirectional Image Processing by Stringhini, Romulo M., da Silveira, Thiago L. T., Jung, Claudio R.

“…Traditional convolutional neural networks (CNNs) face significant challenges when applied to omnidirectional images due to the non-uniform sampling inherent in…”
Get full text