Nelson Duarte Filho

Achieving Turbidity Robustness on Underwater Images Local Feature Detection.

Methods to detect local features have been made to be invariant to many transformations. So far, the vast majority of feature detectors consider robustness just to over-land effects. However, when capturing pictures in underwater environments, there are media specific properties that can degrade the visual quality the captured images. Little work has been made in order to study the robustness that the popular feature detectors have to underwater environment image conditions. We develop a new dataset, called TURBID, where we produced real seabed images with different amounts of degradation. On this dataset, we search over multiple feature detectors from the literature to indicate the ones with more robust properties. We concluded that scale-invariant detectors are more robust to degradation of underwater images. Finally, we elected Center Surround Extremas, KAZE, Difference of Gaussians and the Hessian-Laplace as the best detectors for this environment on all tested scenes.

Parallel High Dimensional Self Organizing Maps Using CUDA

A common neural network used for complex data clustering is the Self Organizing Maps(SOM). This algorithm have a expensive training step, that occur mainly on high dimensional applications like image clustering. This makes impossible for some of these applications to be run in real time or even in a feasible time. On this paper we explore the use of GPUs with the NVIDIA CUDA language to decrease computational cost of SOM. We propose a three steps implementation able to reduce the computational complexity of the algorithm under SIMD paradigm and also making a good use of GPUs resources. At the end we were able to get a peak speed-up of 44 times against a C CPU implementation, fact that concludes about SOMs data parallelism.

An immersive and collaborative visualization system for digital manufacturing

In this paper, an approach on immersive multiprojection visualization of manufacturing processes is proposed. It admits scenarios with dynamic components and allows virtual reality collaborative visualization among geographically distributed users through multi-CAVE devices. A set of modules for modeling, converting, visualizing, and interacting are also proposed. The method can be applied to CAD projects, models, and simulations used in industry. The ideas discussed are then validated through the study of a real case related to the shipbuilding and offshore industries.

Underwater Single Image Restoration Using Dark Channel Prior

The underwater vision is highly spoiled by the underwater degradation effects. As light propagates in the water or other participative mediums, it suffers from a substantial scattering effect that produces poor image quality. Based on a physical model that describes this phenomenon it is possible to recover an haze-free image. But, for this procedure to succeed, it is necessary to obtain certain parameters from the model. With an adaptation of the Dark Channel Prior, proposed by this paper, we are able to obtain a rough distance map estimative. With this, and some model simplifications, we are able to successfully obtain the restoration of the image.

A General Purpose Cave-Like System for Visualization of Animated and 4D CAD Modeling

In the last decade, virtual reality (VR) systems have been used to enhance the visualization of CAD projects. The immersive VR techniques allow to the designer interacting and modeling in a more intuitive and efficient way. Current 4D and animated simulation CAD tools are a new challenge for immersive visualization. In this paper we propose a general purpose cave-like system that enables interactive visualization of 4D and animated CAD models. In an automated way, the system is able to treat static and dynamic 3D environments, allowing to share the experience of navigation in the scene among the users, even geographically distributed. The system proposed is validated through a case-study using dynamic 3D models created on digital manufacturing softwares of Shipbuilding and Offshore Industries.

Autonomous navigation for underground energy line inspection robot

This work proposes architecture of an inspection robots navigation system, aiming at monitoring underground energy lines. This architecture is composed of two modules: i. feature extraction from environment; ii navigation approach. The feature extraction module is based on the use of the edge detector by Canny algorithm and Hough transform for identification of lines from images of environment to monitoring. The lines identified correspond to cable conformation inside the duct. This information will serve to help the navigation system. For the implementation of the navigation system two approaches were proposed: navigation based on artificial neural network and navigation based on PID control. The navigation architecture can be used in real or simulated scenarios, and it was tested in a simulated environment.

Including operator's skill and environment conditions in IMS

This study intends to consider the operator skill and the environment conditions as variables of Intelligent Maintenance Systems (IMS). In this sense maintenance operations associated with the technical skills and environment factors through sensory perception can represent important strategy to improve the IMS. This approach considers the Cyber-Physical Systems (or CPS) paradigm to acquire human and context factors once that CPS system combines coordinates physical and computational elements. Thus this study proposes the CPS use for taking account the operators skill and environment conditions for maintenance strategies. This proposal aims the developing of Advanced Human Computer Interface for Intelligent Maintenance Systems that consider the operators skill and environment. The validation will be accomplished by interface named Toogle where two case studies will be tested.

Hyper-Environments: A Different Way to Think about IoT

The current technological scenario presents different mobile devices, which support wireless communication at an increasingly low cost. This all makes it possible to build systems thought to be impossible. The utilization of computational and natural elements, and the mixing of virtual and real elements, set up a complex relationship between elements. A good organization of these relations would enable the construction of complex systems that would bring countless benefits to users. This work presents an architecture to build hyper-environments, term proposed in this paper to define the interconnection between smart environments (which involve different elements, technological or not, real and/or virtual).The proposed architecture presents a taxonomy and a set of concepts for the organization of the hyper-environmental elements. It also offers directions to implement a middleware for building such systems. To validate the work, a hyper environment will be built using a middleware implemented based on the proposed architecture.

An Automated Platform for Immersive and Collaborative Visualization of Industrial Models

In this paper an automated platform for immersive multiprojection visualization of manufacturing processes is proposed. It admits scenarios with dynamic components and allows Virtual Reality collaborative visualization among geographically distributed users, through multi-CAVE devices. Modules for modeling, converting, visualizing and interacting composes the platform. The proposed system can be applied to CAD projects, models and simulations used in industry. The ideas discussed are then validated through the study of a real case related to the Shipbuilding and Offshore Industries.

Towards Intelligent Maintenance Systems: Rescuing Human Operator and Context Factors

Abstract Current technologies have used embedded devices for degradation monitoring based on Condition-Based Maintenance (CBM) paradigm for critical parts of equipments. Intelligent Maintenance Systems (IMS) have been proposed in order to autonomously provide failure predictions through data acquisition from sensors. This paper intends to discuss how to capture the operator skill and environment conditions into the IMS. We have adapted the data flow in CBM classical architecture in order to consider the resultant information from maintenance operations associated with the technical teams and their contexts. For this purpose was used a Cyber-Physical Systems (CPS) approach to consider human and context factors. Considering the CPS as system that combines and coordinates physical and computational elements, the CPS incorporates the ability to act in the physical world with the intelligence from cyber or virtual world. In this paper, we propose to use a CPS for taking account human/context factors applied maintenance strategies. The proposed tool, called Toogle-IMS, aims at developing an advanced Human-Computer Interaction (HCI) applied to Intelligent Maintenance System (IMS). We have applied the Toogle-IMS in two case studies associated with: i. mobile robots in maintenance and ii. mobile trucks in shipyards.