Silvia Silva da Costa Botelho

Transmission Estimation in Underwater Single Images

This paper proposes a methodology to estimate the transmission in underwater environments which consists on an adaptation of the Dark Channel Prior (DCP), a statistical prior based on properties of images obtained in outdoor natural scenes. Our methodology, called Underwater DCP (UDCP), basically considers that the blue and green color channels are the underwater visual information source, which enables a significant improvement over existing methods based in DCP. This is shown through a comparative study with state of the art techniques, we present a detailed analysis of our technique which shows its applicability and limitations in images acquired from real and simulated scenes.

Underwater Depth Estimation and Image Restoration Based on Single Images

In underwater environments, the scattering and absorption phenomena affect the propagation of light, degrading the quality of captured images. In this work, the authors present a method based on a physical model of light propagation that takes into account the most significant effects to image degradation: absorption, scattering, and backscattering. The proposed method uses statistical priors to restore the visual quality of the images acquired in typical underwater scenarios.

Appearance-based odometry and mapping with feature descriptors for underwater robots

The use of Autonomous Underwater Vehicles (AUVs) for underwater tasks is a promising robotic field. These robots can carry visual inspection cameras. Besides serving the activities of inspection and mapping, the captured images can also be used to aid navigation and localization of the robots. Visual odometry is the process of determining the position and orientation of a robot by analyzing the associated camera images. It has been used in a wide variety of non-standard locomotion robotic methods. In this context, this paper proposes an approach to visual odometry and mapping of underwater vehicles. Supposing the use of inspection cameras, this proposal is composed of two stages: i) the use of computer vision for visual odometry, extracting landmarks in underwater image sequences and ii) the development of topological maps for localization and navigation. The integration of such systems will allow visual odometry, localization and mapping of the environment. A set of tests with real robots was accomplished, regarding online and performance issues. The results reveals an accuracy and robust approach to several underwater conditions, as illumination and noise, leading to a promissory and original visual odometry and mapping technique.

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.

Applying Neural Networks to Study the Mesoscale Variability of Oceanic Boundary Currents

In this paper we apply a Neural Network (NN) to distill massive oceanographic datasets down to a new space of smaller dimension, thus characterizing the essential information contained in the data. Due to the natural nonlinearity of those data, traditional multivariate analysis may not represent reality. This work presents the methodology associated with the use of a multi-layer NN with a bottleneck to extract nonlinear information of the data.

Neural network for black-box fusion of underwater robot localization under unmodeled noise

Abstract The research on autonomous robotics has focused on the aspect of information fusion from redundant estimates. Choosing a convenient fusion policy, that reduces the impact of unmodeled noise, and is computationally efficient, is an open research issue. The objective of this work is to study the problem of underwater localization which is a challenging field of research, given the dynamic aspect of the environment. For this, we explore navigation task scenarios based on inertial and geophysical sensory. We propose a neural network framework named B-PR-F which heuristically performs adaptable fusion of information, based on the principle of contextual anticipation of the localization signal within an ordered processing neighborhood. In the framework black-box unimodal estimations are related to the task context, and the confidence on individual estimates is evaluated before fusing information. A study conducted in a virtual environment illustrates the relevance of the model in fusing information under multiple task scenarios. A real experiment shows that our model outperforms the Kalman Filter and the Augmented Monte Carlo Localization algorithms in the task. We believe that the principle proposed can be relevant to related application fields, involving the problem of state estimation from the fusion of redundant information.

A Topological Descriptor of Forward Looking Sonar Images for Navigation and Mapping

The automation of the monitoring, inspection and underwater maintenance tasks by underwater robots require a mapping and localization system. One challenge of these systems is how to recognize previously visited place in sensory information. This paper proposes a extended version of a method to detect loop closure dealing with acoustic images acquired by a forward looking sonar (FLS). The method builds a graph of Gaussian probability density function. This structure represents both shape and topological relation. We improve the image segmentation step adding a local parameters adjustment regard to intensity peak analyze of acoustic beams and changed the graph matching metric. We evaluate the method in a real dataset acquired by a underwater vehicle performing navigation in a harbor area.

Human Computer Interface (HCI) for Intelligent Maintenance Systems (IMS): The Role of Human and Context

This paper deals with advanced computational techniques for taking account the human factors in Intelligent Manufacture Systems. A Cyber-Physical Systems (or CPS) is a system that combines and coordinates physical and computational elements. The CPS incorporates the ability to act in the physical world with the intelligence of cyber world to add new features to real-world physical systems [1]. Among the various fields of activity of the CPS, can cite security systems, robotics, education, among others. Industrial environments are characterized by being favorable places for the introduction of technologies aimed to facilitate the interaction/mediation between human and machines. In this paper, we propose to use CPS for taking account human factors in Maintenance Estrategies. The proposal, called TOOGLE-IMS, aims at developing a Human Computer Interface (HCI) for Intelligent Maintenance Systems (IMS).

Simulating the Impacts of the Energy Consumption Using Multi-agent Systems

Simulation of home use of electric energy is a very powerful tool for the purpose of studying, planning and managing at electric energy distribution companies. This paper presents the initial results obtained considering the paradigm of multiagent systems (namely, the NetLogo tool) for the of energy consumption simulation as a common resource. Distinct profiles of possible behaviors of consumers and household appliances with different powers are modeled and simulated using computational agents.