Mozart William Santos Almeida

Challenges in 3D Reconstruction from Images for Difficult Large-Scale Objects: A Study on the Modeling of Electrical Substations

In recent years, 3D reconstruction from images has played a major role in computer vision with a lot of improvements regarding both quality and performance. One of its main uses is the generation of 3D models of objects that are difficult to modeling. In the electrical sector, 3D reconstruction from images shows itself as a candidate to be used in specific scenarios with the advantage of its low price compared to laser scanning techniques. In fact, there are many industrial applications that can use the power of 3D reconstruction from images but no work has focused more deeply on their requirements yet. This paper analyzes the advantages and drawbacks in using 3D reconstruction from image techniques and tools in the uncontrolled environment of an electrical substation from the scenario characteristics and tools limitations points of view. Some representative available tools (commercial and academic) where evaluated and the relationship between scenario/object characteristics and reconstructed model quality could be pointed out for further improvements of the techniques in future work. This results can be used to create industrial applications with large scale difficult objects.

A High Performance Massively Parallel Approach for Real Time Deformable Body Physics Simulation

Single processor technology has been evolving across last decades, but due to physical limitations of chip manufacturing process, the industry is pursuing alternatives to sustain computational power growth,including the creation of multi-core systems. Parallel computing targets problems that are scalable and possibly distributed, dividing the problem into smaller pieces. This approach may be explored to satisfy real-time constraints required by real time physics simulation. This work introduces an optimal solution to implement accurate simulation of deformable bodies in real time. This is accomplished through the use of a meshless simulation technique, known as Point Based Animation, implemented using a parallel framework:the NVIDIA Compute Unified Device Architecture(CUDA). Our implementation showed significative improvements on performance in comparison to the former CPU one: impressive speedups around 20times could be achieved in the simulation of deformable bodies with 575 physical elements (phyxels) and53,504 surface elements (surfels).

Markerless tracking system for augmented reality in the automotive industry

Markerless tracking system for augmented reality targeting the automotive sector.System evaluation during the Volkswagen/ISMAR Tracking Challenge 2014.Additional studies in similar competition scenarios created by the authors.System suitable for tracking vehicle exterior / parts and high precision tracking. This paper presents a complete natural feature based tracking system that supports the creation of augmented reality applications focused on the automotive sector. The proposed pipeline encompasses scene modeling, system calibration and tracking steps. An augmented reality application was built on top of the system for indicating the location of 3D coordinates in a given environment which can be applied to many different applications in cars, such as a maintenance assistant, an intelligent manual, and many others. An analysis of the system was performed during the Volkswagen/ISMAR Tracking Challenge 2014, which aimed to evaluate state-of-the-art tracking approaches on the basis of requirements encountered in automotive industrial settings. A similar competition environment was also created by the authors in order to allow further studies. Evaluation results showed that the system allowed users to correctly identify points in tasks that involved tracking a rotating vehicle, tracking data on a complete vehicle and tracking with high accuracy. This evaluation allowed also to understand the applicability limits of texture based approaches in the textureless automotive environment, a problem not addressed frequently in the literature. To the best of the authors knowledge, this is the first work addressing the analysis of a complete tracking system for augmented reality focused on the automotive sector which could be tested and validated in a major benchmark like the Volkswagen/ISMAR Tracking Challenge, providing useful insights on the development of such expert and intelligent systems.

High Performance Computing: CUDA as a Supporting Technology for Next Generation Augmented Reality Applications

The main purpose of this survey is presenting the potential of GPGPU technology for real time markerless augmented reality related processing. CUDA is a GPGPU technology developed by NVIDIA that allows programmers to use the C programming language to code algorithms for execution on the GPU. Applications that require mathematically intensive computation of large amounts of data are ideal targets for GPU computing. In this survey, CUDA architecture will be depicted, together with an optimized programming model for obtaining better results using the parallel approach. A case study, mainly related to tracking algorithms, will also be shown in order to demonstrate the performance improvement in comparison to sequential approaches.

3D Tracking in Industrial Scenarios: A Case Study at the ISMAR Tracking Competition

One of the more challenging tasks in augmented reality is to develop a tracking system for the industrial scenario. It is due the fact that this environment has characteristics that defy most of the techniques available, such as texture less objects that in some case are too large and in others are very small. This work proposes the combination of established techniques for 3D reconstruction and tracking, as well as a calibration routine, that is suitable for this type of scenario. This complete tracking system was evaluated in the ISMAR Tracking Competition, a contest that simulates industrial scenarios and is promoted to test state of the art trackers. The system presented good results in the competition and a discussion regarding its performance is lodged, aiming to introduce an analysis that could help others during the development of their own tracking system for industrial scenario.

Improved Meshless Method for Simulating Incompressible Fluids on GPU

Meshless methods to simulate fluid flows have been increasingly evolving through the years since they are a great alternative to deal with large deformations, which is where mesh-based methods fail to perform efficiently. A well known meshless method is the Moving Particle Semi-implicit (MPS) method, which was designed to simulate free-surface truly incompressible fluid flows. Many variations and refinements of the methods accuracy and precision have been proposed since its creation and, due to these, it has proved to be very useful in a wide range of naval and mechanical engineering problems. However, one of its drawbacks is high computational load and some quite time-consuming functions, which prevents it to be more used in Computer Graphics and Virtual Reality applications. Graphics Processing Units (GPU) provide unprecedented capabilities for scientific computations. To promote the GPU-acceleration, the solution of the Poisson Pressure equation was brought into focus. This work benefits from some of the techniques presented in the related work and also from the CUDA language in order to get a stable, accurate and GPU-accelerated MPS method, which is this works main contribution. It is shown that the GPU version of the method developed can perform from, approximately, 6 to 10 times faster with the same reliability as the CPU version, both extended to three dimensions. Lastly, a simulation containing a total of 62,600 particles is fully rendered in 3D.

Tridimensional Visualization through Optical Illusion

Holography is a technique that uses the properties of light as a way of registering and representing three-dimensional scenes and objects. However, holography is not the only technique that makes it possible to visualize in three dimensions. In this work will be detailed another form of three-dimensional visualization based on an invention of the late 19th century. Different applications that use this approach will be presented, as well as their results that are quite similar to those of holography. A solution involving hardware/software for 3D visualization through optical illusion is proposed. Using a prism with specific geometric proportions, is possible project the generated content with the developed tool to visualize objects and even 3D point clouds relating to faces captured with the Microsoft Kinect sensor.