Classification and characterization of places for mapping of environment using hierarchical neural network and omnivision

Mobile robots need autonomy to fulfill their tasks. Such autonomy is related whith their capacity to explorer and to recognize their navigation environments. In this context, the present work considers techniques for the classification and extraction of features from images, using artificial neural networks. This images are used in the mapping and localization system of LACE (Automation and Evolutive Computing Laboratory) mobile robot. In this direction, the robot uses a sensorial system composed by ultrasound sensors and a catadioptric vision system equipped with a camera and a conical mirror. The mapping system is composed of three modules; two of them will be presented in this paper: the classifier and the characterizer modules. Results of these modules simulations are presented in this paper.

Environment mapping for mobile robots navigation using hierarchical neural network and omnivision

Autonomous robots must be able to learn and maintain models of their environments. In this context, the present work considers techniques for the classification and extraction of features from images in joined with artificial neural networks in order to use them in the system of mapping and localization of the mobile robot of Laboratory of Automation and Evolutive Computer (LACE). To do this, the robot uses a sensorial system composed for ultrasound sensors and a catadioptric vision system formed by a camera and a conical mirror. The mapping system is composed by three modules. Two of them will be presented in this paper: the classifier and the characterizer module. The first module uses a hierarchical neural network to do the classification; the second uses techiniques of extraction of attributes of images and recognition of invariant patterns extracted from the places images set. The neural network of the classifier module is structured in two layers, reason and intuition, and is trained to classify each place explored for the robot amongst four predefine classes. The final result of the exploration is the construction of a topological map of the explored environment. Results gotten through the simulation of the both modules of the mapping system will be presented in this paper. © 2008 IEEE.

JSEG-based image segmentation in computer vision for agricultural mobile robot navigation

This project aims to apply image processing techniques in computer vision featuring an omnidirectional vision system to agricultural mobile robots (AMR) used for trajectory navigation problems, as well as localization matters. To carry through this task, computational methods based on the JSEG algorithm were used to provide the classification and the characterization of such problems, together with Artificial Neural Networks (ANN) for pattern recognition. Therefore, it was possible to run simulations and carry out analyses of the performance of JSEG image segmentation technique through Matlab/Octave platforms, along with the application of customized Back-propagation algorithm and statistical methods in a Simulink environment. Having the aforementioned procedures been done, it was practicable to classify and also characterize the HSV space color segments, not to mention allow the recognition of patterns in which reasonably accurate results were obtained.

ANN statistical image recognition method for computer vision in agricultural mobile robot navigation

The main application area in this project, is to deploy image processing and segmentation techniques in computer vision through an omnidirectional vision system to agricultural mobile robots (AMR) used for trajectory navigation problems, as well as localization matters. Thereby, computational methods based on the JSEG algorithm were used to provide the classification and the characterization of such problems, together with Artificial Neural Networks (ANN) for image recognition. Hence, it was possible to run simulations and carry out analyses of the performance of JSEG image segmentation technique through Matlab/Octave computational platforms, along with the application of customized Back-propagation Multilayer Perceptron (MLP) algorithm and statistical methods as structured heuristics methods in a Simulink environment. Having the aforementioned procedures been done, it was practicable to classify and also characterize the HSV space color segments, not to mention allow the recognition of segmented images in which reasonably accurate results were obtained. © 2010 IEEE.

Petroleum well drilling monitoring through cutting image analysis and artificial intelligence techniques

Petroleum well drilling monitoring has become an important tool for detecting and preventing problems during the well drilling process. In this paper, we propose to assist the drilling process by analyzing the cutting images at the vibrating shake shaker, in which different concentrations of cuttings can indicate possible problems, such as the collapse of the well borehole walls. In such a way, we present here an innovative computer vision system composed by a real time cutting volume estimator addressed by support vector regression. As far we know, we are the first to propose the petroleum well drilling monitoring by cutting image analysis. We also applied a collection of supervised classifiers for cutting volume classification. (C) 2010 Elsevier Ltd. All rights reserved.

Pattern recognition structured heuristics methods for image processing in mobile robot navigation

In this project, the main focus is to apply image processing techniques in computer vision through an omnidirectional vision system to agricultural mobile robots (AMR) used for trajectory navigation problems, as well as localization matters. To carry through this task, computational methods based on the JSEG algorithm were used to provide the classification and the characterization of such problems, together with Artificial Neural Networks (ANN) for pattern recognition. Therefore, it was possible to run simulations and carry out analyses of the performance of JSEG image segmentation technique through Matlab/Octave platforms, along with the application of customized Back-propagation algorithm and statistical methods as structured heuristics methods in a Simulink environment. Having the aforementioned procedures been done, it was practicable to classify and also characterize the HSV space color segments, not to mention allow the recognition of patterns in which reasonably accurate results were obtained. ©2010 IEEE.

Formação de imagens multiespectrais por meio de fusão de imagens adquiridas por múltiplas câmaras

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

SPECT (Single photon emission tomography): Gama câmara, reconstrução tomográfica e características funcional

The SPECT (Single Photon Emission Computed Tomography) systems are part of a medical image acquisition technology which has been outstanding, because the resultant images are functional images complementary to those that give anatomic information, such as X-Ray CT, presenting a high diagnostic value. These equipments acquire, in a non-invasive way, images from the interior of the human body through tomographic mapping of radioactive material administered to the patient. The SPECT systems are based on the Gamma Camera detection system, and one of them being set on a rotational gantry is enough to obtain the necessary data for a tomographic image. The images obtained from the SPECT system consist in a group of flat images that describe the radioactive distribution on the patient. The trans-axial cuts are obtained from the tomographic reconstruction techniques. There are analytic and iterative methods to obtain the tomographic reconstruction. The analytic methods are based on the Fourier Cut Theorem (FCT), while the iterative methods search for numeric solutions to solve the equations from the projections. Within the analytic methods, the filtered backprojection (FBP) method maybe is the simplest of all the tomographic reconstruction techniques. This paper's goal is to present the operation of the SPECT system, the Gamma Camera detection system, some tomographic reconstruction techniques and the requisites for the implementation of this system in a Nuclear Medicine service

Análise de regiões em cenários agrícolas utilizando um sistema de visão catadióptrico

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Line based camera calibration in machine vision dynamic applications

The problem of dynamic camera calibration considering moving objects in close range environments using straight lines as references is addressed. A mathematical model for the correspondence of a straight line in the object and image spaces is discussed. This model is based on the equivalence between the vector normal to the interpretation plane in the image space and the vector normal to the rotated interpretation plane in the object space. In order to solve the dynamic camera calibration, Kalman Filtering is applied; an iterative process based on the recursive property of the Kalman Filter is defined, using the sequentially estimated camera orientation parameters to feedback the feature extraction process in the image. For the dynamic case, e.g. an image sequence of a moving object, a state prediction and a covariance matrix for the next instant is obtained using the available estimates and the system model. Filtered state estimates can be computed from these predicted estimates using the Kalman Filtering approach and based on the system model parameters with good quality, for each instant of an image sequence. The proposed approach was tested with simulated and real data. Experiments with real data were carried out in a controlled environment, considering a sequence of images of a moving cube in a linear trajectory over a flat surface.

Accuracy assessment of a photogrammetric close-range reconstruction system

Geometric accuracy of a close-range photogrammetric system is assessed in this paper considering surface reconstruction with structured light as its main purpose. The system is based on an off-the-shelf digital camera and a pattern projector. The mathematical model for reconstruction is based on the parametric equation of the projected straight line combined with collinearity equations. A sequential approach for system calibration was developed and is presented. Results obtained from real data are also presented and discussed. Experiments with real data using a prototype have indicated 0.5mm of accuracy in height determination and 0.2mm in the XY plane considering an application where the object was 1630mm distant from the camera.

A low cost structured light system

The aim of this paper is to present the current development status of a low cost system for surface reconstruction with structured light. The acquisition system is composed of a single off-the-shelf digital camera and a pattern projector. A pattern codification strategy was developed to allow the pattern recognition automatically and a calibration methodology ensures the determination of the direction vector of each pattern. The experiments indicated that an accuracy of 0.5mm in depth could be achieved for typical applications.

A low-cost 3D reconstruction system using a single-shot projection of a pattern matrix

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

A Single Intraoperative Sub-Tenon's Capsule Injection of Triamcinolone and Ciprofloxacin in a Controlled-Release System for Cataract Surgery

PURPOSE. To compare intraoperative injection of triamcinolone and ciprofloxacin in a controlled-release system (DuoCat) with prednisolone and ciprofloxacin eye drops after cataract surgery.METHODS. In this randomized, double-masked, controlled trial, a total of 135 patients undergoing cataract surgery were randomly allocated to two groups: 67 patients treated after surgery with prednisolone 1% and ciprofloxacin 3% eye drops four times daily (week 1), three times daily (week 2), twice daily (week 3), and once daily (week 4) and 0.3% ciprofloxacin drops four times daily (weeks 1 and 2), and 68 patients treated at the end of surgery with a sub-Tenon's injection of 25 mg triamcinolone and 2 mg ciprofloxacin in biodegradable microspheres. The patients were examined on postoperative days 1, 3, 7, 14, and 28. The main outcome measures were postoperative anterior chamber cell and flare, intraocular pressure (IOP), lack of anti-inflammatory response, and presence of infection.RESULTS. No significant differences were observed between the groups in anterior chamber cell (P > 0.14) and flare (P > 0.02) at any postoperative visits. The mean (99% confidence interval) differences in IOP between the prednisolone and triamcinolone groups on days 1, 3, 7, 14, and 28 were -0.4 mm Hg (-2.1 to 1.3), 0.0 mm Hg (-1.4 to 1.3), 0.0 mm Hg (-1.1 to 1.1), -0.2 mm Hg (-1.1 to 0.8), and -0.1 mm Hg (-1.1 to 0.9), respectively. No patient had a postoperative infection.CONCLUSIONS. One injection of DuoCat had a therapeutic response and ocular tolerance that were equivalent to conventional eye drops in controlling inflammation after cataract surgery. (Clinical-Trials. gov number, NCT00431028.) (Invest Ophthalmol Vis Sci. 2009; 50: 3041-3047) DOI: 10.1167/iovs.08-2920

Scintigraphy of the hepatobiliar system in patients with pulmonary tuberculosis

The objective of this paper was to evaluate the hepatobiliary function of patients with pulmonary tuberculosis under triple treatment, using the technetium-99m-DISIDA (99mTc-DISIDA) hepatobiliary scintigraphy. Ten men and three women with pulmonary tuberculosis were subjected to hepatobiliary scintigraphy at the beginning of triple treatment (M1) and two months after it (M2). Patients were from the urban area, of low socioeconomic level, malnourished, and chronic alcohol and/or tobacco users. Ten normal individuals were evaluated as controls. Radiotracer images were acquired on a computerized gamma camera (Orbiter-Siemens) and T1/2 uptake and excretion values were calculated. Nutritional status and serum hepatic enzyme levels for each patient were evaluated at M1 and M2. None presented clinical or laboratory antecedent of hepatobiliary disease. At M1, there were no hepatic serum or kinetic alterations of the 99mTc-DISIDA. At M2, patients presented better nutritional conditions than at M1; there was increased serum aspartate aminotransferase (AST) and reduced excretion time for 99mTc-DISIDA, which was interpreted as a more adaptive than toxic phenomenon, yet not all alterations were significant and none manifested clinically. Apparently, triple treatment acted on the liver inducing the P450 cytochrome enzymatic system, accelerating radiotracer excretion, which follows the same path as the bilirubins.