No description available.

Sustaining the safety and operability of civil infrastructure assets, including buildings, is a complex undertaking that requires a perpetual cycle involving inspection, and further decisions for renewal fund allocation. However, inspection, which is the basis for all subsequent decisions, is a complex task to manage, particularly when a large number of assets are involved. The current lack of a structured process with visual referencing as well as the high subjectivity and inflexibility to changing inspection requirements make current inspections very costly and time consuming. This research improves the building inspection process by introducing a 3D system for inspection management that has four unique features: (1) a structured assessment approach that considers multiple organizations, buildings and inspectors, using a GIS interface; (2) a 3D visual referencing method for marking problem areas during inspections to facilitate all on-site inspections, thus reducing time and cost; (3) a visual guidance module to reduce inspection subjectivity; and (4) a flexible module for designing different assessment types. The proposed inspection management system creates 3D building plans from 2D Computer-Aided Drawing (CAD) to provide location referencing that enhances inspection effectiveness. The visual guidance system allows inspectors with various experience levels to perform consistent inspections and requires less training, thus reducing costs. Flexible inspection generation also allows a variety of inspection types, such as condition and level of service, to be readily incorporated. A computerized prototype system has been developed using the Windows Presentation Foundation’s XAML markup language with underlying C# programming on a tablet computer for experimentation. The thesis provides a detailed description of system development and reports the benefits of the system on a sample inspection. Accordingly, the system has proven most useful for large organizations that own a large number of building assets that require frequent inspections.

Sustaining the safety and operability of civil infrastructure assets, including buildings, is a complex undertaking that requires a perpetual cycle involving inspection, and further decisions for renewal fund allocation. However, inspection, which is the basis for all subsequent decisions, is a complex task to manage, particularly when a large number of assets are involved. The current lack of a structured process with visual referencing as well as the high subjectivity and inflexibility to changing inspection requirements make current inspections very costly and time consuming. This research improves the building inspection process by introducing a 3D system for inspection management that has four unique features: (1) a structured assessment approach that considers multiple organizations, buildings and inspectors, using a GIS interface; (2) a 3D visual referencing method for marking problem areas during inspections to facilitate all on-site inspections, thus reducing time and cost; (3) a visual guidance module to reduce inspection subjectivity; and (4) a flexible module for designing different assessment types. The proposed inspection management system creates 3D building plans from 2D Computer-Aided Drawing (CAD) to provide location referencing that enhances inspection effectiveness. The visual guidance system allows inspectors with various experience levels to perform consistent inspections and requires less training, thus reducing costs. Flexible inspection generation also allows a variety of inspection types, such as condition and level of service, to be readily incorporated. A computerized prototype system has been developed using the Windows Presentation Foundation’s XAML markup language with underlying C# programming on a tablet computer for experimentation. The thesis provides a detailed description of system development and reports the benefits of the system on a sample inspection. Accordingly, the system has proven most useful for large organizations that own a large number of building assets that require frequent inspections.

In this work a machine vision system for inspecting pharmaceutical color tablets is presented and implemented. Nonparametric clustering based segmentation is faster and thus more appropriate for real-time applications. Two nonparametric clustering based methods, Nearest Neighbor algorithm and MaxShift algorithm are worked in RGB and HSV color spaces as the segmentation step. The implemented algorithm allows the system to detect the missing and broken tablets, tablet fragments, and the color, size, and shape of individual tablets in pharmaceutical blisters, in real-time. System has two operation modes called &amp / #8216 / &amp / #8216 / training&amp / #8217 / &amp / #8217 / and &amp / #8216 / &amp / #8216 / inspection&amp / #8217 / &amp / #8217 / mode, respectively. Operator selects one point on any tablet in a defect-free training captured image in the &amp / #8216 / &amp / #8216 / training&amp / #8217 / &amp / #8217 / mode. In the correction step an optimization algorithm is required, for which Powell and Downhill Simplex methods are used. Captured image is then corrected for spatial color nonuniformity, segmented, and the position, size, shape, and color of each tablet are extracted in the training mode. The correction and segmentation models / the extracted features generated in the training mode is saved with the user defined values to form the model. Each acquired image in the inspection mode is corrected and segmented according to the blister model and then the blisters are classified as &amp / #8216 / &amp / #8216 / good&amp / #8217 / &amp / #8217 / or &amp / #8216 / &amp / #8216 / bad&amp / #8217 / &amp / #8217 / by comparing the extracted feature values with the user defined tolerances stored in the blister model.

L'apparence d'un produit joue un rôle important dans la perception de sa qualité par le client. Au-delà des fonctionnalités qu'il doit remplir, un produit doit désormais avoir un aspect irréprochable. Il n'y a cependant pas de surface parfaite car, à un niveau de grossissement donné, un écart par rapport à une surface idéale peut toujours être identifié. Pour détecter cet écart et évaluer son impact sur la qualité perçue du produit, les entreprises mettent généralement en place un contrôle visuel d'aspect de surface de leurs produits. Une première thèse a été réalisée au Laboratoire SYMME afin de proposer une méthodologie permettant de réduire la variabilité généralement observée sur les résultats de ce type de contrôle. Nos travaux se situent dans la continuité de ces travaux avec l'objectif de proposer des méthodes et des outils pour la maîtrise des trois étapes d'un contrôle visuel d'aspect : exploration, évaluation et décision. Le projet de thèse réalisé dans le cadre d'un programme européen de recherche INTERREG IV réunissait différentes Universités et Entreprises. Les pratiques des entreprises partenaires ont procurés un terrain d'expérimentation des recherches proposées. Partant de cette observation, nous avons proposé une conceptualisation du contrôle visuel humain débouchant sur des propositions de méthodes et outils adaptés aux trois étapes. Ces propositions ont été testées dans les entreprises partenaires pour vérifier leur robustesse à la variété des situations industriels. Nous avons par exemple proposé un nouveau test R2&E2 Conformité qui mesure la variabilité d'un contrôle visuel et contribue à l'identification des sources possibles de cette variabilité. Outre cette conceptualisation pour la création d'outils, nous listons un ensemble de recommandations à suivre par les entreprises pour une meilleure exploration des anomalies. Nous proposons également un ensemble d'attributs sensoriels permettant de caractériser, en vue de l'évaluer, toute anomalie d'aspect. Enfin, nous montrons comment, en formalisant le processus d'expertise, un contrôleur peut évaluer une anomalie d'aspect et juger de son impact sur la qualité perçue du produit. / The product appearance plays an important role in the perception of quality by the customer. Beyond the features that must be satisfied, now a product must have a flawless appearance. However, there is no perfect surface, because a given level of magnification, a deviation from an ideal surface can always be identified. To detect this deviation and assess its impact on perceived product quality, companies usually set up a visual inspection of the surface appearance of their products. A first PhD thesis was carried out at the Laboratoire SYMME to propose a methodology to reduce the variability generally observed on the results of this type of inspection. Our work is in the continuity of this thesis with the aim to propose methods and tools for the control of three stages of visual inspection of surface appearance: exploration, evaluation and decision. The thesis project carried out under of a European research program INTERREG IV brought together different Universities and Companies. The practices of corporate partners have brought a testing field for the proposed researches. Based on this observation, we proposed a conceptualization of human visual inspection leading to proposals for methods and tools adapted to the three stages. These proposals were tested in the partner companies to verify their robustness to a variety of industrial situations. For example, we proposed a new test R2&E2 Compliance which measures the variability of a visual inspection and helps to identify possible sources of this variability. In addition to this conceptualization for the development of tools, we list a set of recommendations to be followed by companies for a better exploration of anomalies. We also propose a set of sensory attributes to characterize, with a view to evaluate any anomaly appearance. Finally, we show how to formalize the expertise process, a controller can evaluate an anomaly appearance and judge its impact on the perceived quality of the product.

O objetivo deste trabalho é o desenvolvimento de um método dedicado de classificação para placas de madeira utilizadas na fabricação de lápis, utilizando procedimentos de visão computacional. O processo aqui proposto, foi idealizado buscando uma metodologia que pudesse ser realizada com baixa complexidade computacional, ou seja, os cálculos dos algoritmos utilizando apenas operações simples - do tipo soma, subtração, multiplicação e divisão - em imagens em níveis de cinza. A intenção em utilizar apenas as operações básicas citadas, tem o objetivo de tornar o método implementável em arquiteturas com tecnologia VLSI, notadamente em Arquiteturas Sistólicas. O trabalho descreve o ciclo de produção do lápis localizando a etapa onde é proposta a metodologia de classificação das placas de madeira. Nesta etapa, há uma seqüência de procedimentos, descritos ao longo do trabalho, que compreendem a aquisição da imagem das placas, a extração de características das imagens, o processamento dessas características e por fim os algoritmos de classificação. Na etapa de extração de características, buscou-se com a aplicação de um método de Limiar automático que utiliza a entropia de Shannon, extrair informações suficientes para classificar adequadamente as placas de madeiras em diferentes classes, fornecendo dessa forma, um sistema ágil, repetitivo e de baixo custo para aproveitamento da madeira em diferentes produtos finais. / The objective of this work was to develop a dedicated computer vision method for the classification of wooden plates used in pencil manufacturing. The process here proposed was idealized looking for a low computational complexity methodology that could be accomplished in VLSI, as for instance using Systolic Computer Architectures made of logic arrays. The pencil cycle of production is described, locating the stage where the proposed classification methodology should be used. There is a sequence of procedures, along the work, that describe the acquisition, extraction of the characteristics and the processing of the images, and finally the classification algorithms. For the extraction of characteristics of the images, it was used an automatic method for the threshold determination, based on Shannon\'s entropy. The information supplied by the threshold determination method allows classifying the plates in different classes. The analysis of the results showed that the method performs well is repetitive and efficient on the classification and its use can be extended to classifying other final products.

This project deals with the optical control of welding glass blank. The blank consists two small parts of made of special glass. This blank is an essential part of the measuring device density of oxygen. Measuring device algorithm is based on paramagnetic properties of oxygen. It is a small and precise piece of the whole mechanism therefore the precision and perfection made strict criteria. For checking compliance with those criteria, developed a computer program written in C# programming language. Its task is to rule on perfection produced parts. It also serves to back up data on individual production units.

As avaliações de postura craniocervical podem ser realizadas através de métodos qualitativos e quantitativos. Apesar das vantagens no emprego das análises quantitativas, a ausência de valores clínicos de referência para determinação da presença/ausência de desalinhamentos posturais é uma limitação para uso do recurso na prática clínica. Objetivo: Identificar os valores de acurácia, sensibilidade e especificidade da fotogrametria em relação inspeção visual para avaliação da postura craniocervical através da análise de fotografias no plano sagital, além de verificar a confiabilidade destes métodos. Método: Foram avaliadas 157 imagens no plano sagital de mulheres (35,6 DP:10,36 anos). As imagens foram analisadas através da avaliação qualitativa (inspeção visual) e através da análise quantitativa (fotogrametria) considerando-se dois ângulos: ângulo craniovertebral (ACV) e lordose cervical (ALC). Os voluntários com dor cervical também foram submetidos a avaliação de intensidade de dor e incapacidade relacionada à dor cervical. A inspeção visual foi realizada por 5 fisioterapeutas experientes. Da mesma forma a avaliação por fotogrametria foi realizada por 2 avaliadores. Todas as avaliações foram repetidas após uma semana. Para análise estatística foi utilizado o Coeficiente de Correlação Intraclasse (CCI) para analisar a confiabilidade e o Kappa de Cohen para a concordância. Além disso, os valores de acurácia, sensibilidade e especificidade foram identificados através do Receiver Operating Characteristic (ROC). Resultados: Foram observados níveis aceitáveis de confiabilidade para o ACV e ALC (CCI<0,98) por meio da fotogrametria e valores de PABAK para a concordância intra-examinador entre 0,63-0,91 (ACV) e 0,46-0,89 (ALC) e para a concordância interexaminadores de 0,51-0,85 (ACV) e 0,16-0,59 (ALC). Foi observada uma acurácia moderada (0,7 ROC<0,9) para os valores de corte do ACV (42°, EPM±0,73º) e ALC (12º-15º, EPM±0,42º) com níveis aceitáveis de sensibilidade e especificidade (<0,63). Assim, foi encontrada uma acurácia moderada (0,7<ROC<0,9) para os valores de corte dos ACV (± 42°) e ALC (± 13°) estabelecidos pelo estudo, com níveis adequados de sensibilidade e especificidade dos mesmos. Também não foram verificados níveis aceitáveis de sensibilidade, especificidade e acurácia dos ângulos de postura craniocervical para detecção dos grupos sintomático vs. assintomático para dor cervical, e para identificação dos subgrupos com e sem incapacidade relacionda a dor cervical. Conclusão: Nossos resultados dão suporte para o uso de ângulos na análise postural quantitativa que discriminam indivíduos com protrusão da cabeça moderada/severa e indivíduos com alterações da postura cervical em hiperlordose e retificação/cifose cervical em relação à postura considerada normal através da avaliação qualitativa. Entretanto, ambos os ângulos estudados não demonstraram bons índices para discriminar indivíduos sintomáticos vs. assintomáticos para dor cervical ou subgrupos com e sem incapacidade relacionda à dor cervical. / Evaluations of craniocervical posture can be performed through qualitative and quantitative methods. Although the advantages in the use of quantitative analyzes, the absence of clinical reference values to determine the presence / absence of postural misalignments is a limitation for the use of the resource in clinical practice. Objective: To identify the accuracy, sensitivity and specificity values of the photogrammetry in relation to the visual inspection to evaluate the craniocervical posture through the analysis of photographs in the sagittal plane, besides verifying the reliability of these methods. Method: 157 images were evaluated in the sagittal plane of women (35.6 SD: 10.36 years). The images were analyzed through qualitative evaluation (visual inspection) and quantitative analysis (photogrammetry) considering two angles: craniovertebral angle (CVA) and cervical lordosis (LCA). Cervical pain volunteers were also assessed for pain intensity and disability related to cervical pain. Visual inspection was performed by 5 experienced physiotherapists. Likewise, the evaluation by photogrammetry was performed by 2 evaluators. All evaluations were repeated after one week. For statistical analysis, the Intraclass Correlation Coefficient (ICC) was used to analyze reliability and Cohen\'s Kappa for agreement. In addition, the values of accuracy, sensitivity and specificity were identified through the Receiver Operating Characteristic (ROC). Results: Acceptable levels of reliability for CVA and LCA (ICC <0.98) were observed by photogrammetry and PABAK values for intra-examiner agreement between 0.63-0.91 (CVA) and 0.46- 0.89 (LCA) and for the inter-examiner agreement of 0.51-0.85 (CVA) and 0.16-0.59 (LCA). A moderate accuracy (0.7 < ROC <0.9) was observed for the cut values of the CVA (42 °, SME ± 0.73 °) and LCA (12 ° -15 °, SME ± 0.42 °) with acceptable levels of Sensitivity and specificity (<0.63). Thus, a moderate accuracy (0.7 <ROC <0.9) was found for the cutoff values of the CVA (±42°) and LCA (± 13 °) established by the study, with adequate levels of sensitivity and specificity. Also, no acceptable levels of sensitivity, specificity and accuracy of the craniocervical posture angles were detected for symptomatic groups vs. Asymptomatic for cervical pain, and to identify the subgroups with and without disability related to cervical pain. Conclusion: Our results support the use of angles in the quantitative postural analysis that discriminate individuals with moderate / severe head protrusion and individuals with altered cervical posture in hyperlordosis and rectification / cervical kyphosis in relation to the posture considered normal through the qualitative evaluation. However, both angles studied did not show good indices to discriminate symptomatic individuals vs. Asymptomatic for cervical pain or subgroups with and without disability related to cervical pain.

Os objetivos do presente estudo foram avaliar, em superfícies oclusais de dentes decíduos, o desempenho de dois índices visuais (Nyvad e International Caries Detection and Assessment System + activity lesions assessment ICDAS-II+ALA) para verificar: a) a profundidade e atividade de lesões de cárie, b) a habilidade do aparelho de fluorescência a laser de diferenciar lesões ativas e inativas e c) a associação de variáveis explicativas ligadas ao dente e à criança com a atividade de lesões de cárie. O estudo foi dividido em etapas: (1) avaliação dos índices visuais in vitro; (2) e em etapa in vivo; (3) avaliação da fluorescência a laser na detecção da atividade da lesão; (4) avaliação de variáveis relacionados à atividade de lesões de cárie. Para a etapa 1, 107 molares decíduos foram examinados por dois examinadores utilizando os índices visuais acima mencionados. Parte da amostra (n=69) foi submetida ao exame histológico para avaliação da profundidade das lesões. Foram calculados a reprodutibilidade dos índices e parâmetros associados à validade dos mesmos para estimativa da profundidade das lesões, além da associação entre os índices e com o exame histológico. Para a etapa 2, foram selecionadas 139 crianças entre 3 e 12 anos. Os molares decíduos dessas crianças (n=763) foram também examinados por dois examinadores usando os mesmos índices visuais. Os dentes exfoliados ou extraídos dessa amostra (n=50) foram examinados histologicamente para profundidade e atividade das lesões (com uso de corante indicar de pH). A reprodutibilidade e validade de critério dos índices foram verificadas. Para a etapa 3, os molares decíduos foram examinados com o aparelho de fluorescência a laser (DIAGNOdent) após 3s e 15s de secagem. A diferença entre as medidas nos dois tempos foi calculada. A associação das leituras com a severidade, atividade e pigmentação das lesões foi verificada. A validade do método foi verificada para os dentes exfoliados ou extraídos. Por fim, para a etapa 4, alguns parâmetros possivelmente relacionados com a atividade das lesões de cárie foram coletados por questionário e clinicamente. Uma análise multinível foi feita para verificar a associação desses parâmetros com a atividade das lesões de cárie classificadas pelos índices. Observou-se que os índices de cárie são comparáveis, apresentando boa reprodutibilidade e validade de critério para detectar lesões de cárie e estimar sua profundidade, tanto in vitro, como in vivo. Os sistemas também apresentam associação satisfatória para a avaliação da atividade das lesões, sendo que o ICDAS-II + ALA mostra uma tendência de superestimar essa atividade das lesões quando comparado ao índice de Nyvad. O método de fluorescência a laser é capaz de diferenciar lesões ativas de inativas classificadas pelo índice de Nyvad, sendo que a pigmentação não influencia isoladamente, a avaliação da atividade das lesões por esse método. Por fim, o tipo de dente e o acúmulo de placa madura, assim como a experiência de cárie e visita anterior ao dentista são variáveis, respectivamente do dente e da criança, associadas à presença de lesões ativas. / The aims of this study were to evaluate, in occlusal surfaces of primary teeth, the performance of two visual scoring systems (Nyvad e International Caries Detection and Assessment System + activity lesions assessment ICDAS-II+ALA) in assessing a) lesions depth and activity, b) the laser fluorescence ability in distinguishing active from inactive lesions and c) the association between independent variables related to the tooth and the child concerning caries activity status. This study was divided into stages: (1) evaluation of visual indices in vitro; (2) and also in an in vivo stage; (3) evaluation of laser fluorescence in caries lesion assessment; (4) evaluation of other variables related to caries activity. For phase 1, 107 primary molars were examined by two independent examiners using the scoring systems mentioned above. Some teeth (n=69) were evaluated concerning lesions depth in the histological examination. The reproducibility of the methods and some parameters related to their validity were calculated. Additionally, association between the indices and between each index and the histological examination were assessed. For the phase 2, 139 children aged 3 to 12-years were selected. Primary molars (n=763) were also examined by two independent examiners using the same visual systems. Exfoliated or extracted teeth from this sample (n=50) were examined histologically regarding the lesion depth and activity status (using a pH detector dye). The reproducibility and validity for both indices were assessed. For the phase 3, laser fluorescence examinations (DIAGNOdent) were performed after air-drying for 3s and 15s. The difference between the readings in these two periods of drying was calculated. The association between the laser fluorescence measurements and lesions severity, activity and staining was assessed. The validity was verified in the sample of extracted or exfoliated teeth. Finally, in the phase 4, some parameters possibly related to caries activity were collected clinically or by questionnaire. Multilevel analyses were performed to verify the association among these parameters and the lesions activity status classified by the visual systems. It was observed that the visual scoring indices are comparable and present good reproducibility and criterion validity in detecting caries lesions and estimating their depths, both in vitro and in vivo. The systems also show acceptable association concerning caries activity assessment. Besides, the ICDAS-II + ALA tends to overestimate lesions activity comparing to Nyvads system. The laser fluorescence is able to differentiate active from arrested lesions classified by the Nyvads criteria and the fissure discoloration does not interfere by itself in the caries activity assessment by this method. Finally, the tooth type and the presence of mature dental plaque on the lesions site, as well the anterior caries experience and the visit to the dentist are variables, respectively related to the tooth and the child, associated with the presence of active caries lesions.

<p></p><p>Visual inspection is the primary means of ensuring the safety and functionality of in-service bridges in the United States and owners spend considerable resources on such inspections. While the Federal Highway Administration (FHWA) and many state departments of transportation have guidelines related to inspector qualification, training, and certification, an inspector’s actual capability to identify defects in the field under these guidelines is unknown. This research aimed to address the knowledge gap surrounding visual inspection performance for steel bridges in order to support future advances in inspection and design procedures. Focusing primarily on fatigue crack detection, this research also considered the ability of inspectors to accurately and consistently estimate section loss in steel bridge members. </p> <p> </p> <p>Inspection performance was evaluated through a series of simulated bridge inspections performed in representative in-situ conditions. First, this research describes the results from 30 hands-on, visual inspections performed on full size bridge specimens with known fatigue cracks. Probability of Detection (POD) curves were fit to the inspection results and the 50% and 90% detection rate crack lengths were determined. The variability in performance was large, and only a small amount of the variance could be explained by individual characteristics or environmental conditions. Based on the results, recommendations for improved training methods, inspection procedures, and equipment were developed. Above all, establishment of a performance based qualification system for bridge inspectors is recommended to confirm that a satisfactory level of performance is consistently achieved in the field. </p> <p> </p> <p>Long term, managing agencies may eschew traditional hands-on bridge inspection methods in favor of emerging technologies imagined to provide improved results and fewer logistical challenges. This research investigated the potential for unmanned aircraft system (UAS) assistance during visual inspection of steel bridges. Using the same specimens as in the hands-on inspections, four UAS-assisted field inspections and 19 UAS-assisted desk inspections were performed. A direct comparison was made between performance in the hands-on and UAS-assisted inspections, as well as between performance in the two types of UAS-assisted inspections. Again, significant variability was present in the results suggesting that human factors continue to have a substantial influence on inspection performance, regardless of inspection method. </p> <p> </p> <p>Finally, to expand the findings from the crack detection inspections, the lower chord from a deck truss was used to investigate variability in the inspection of severely corroded steel tension members. Five inspectors performed a hands-on inspection of the specimen and four engineers calculated the load rating for the same specimen. Significant variability was observed in how inspectors recorded thickness measurements during the inspections and engineers interpreted the inspection reports and applied the code requirements. </p><br><p></p>