Towards intelligent aquaculture. Development of an early Biological Warning System to monitor exposure to contaminants and fish welfare: from artificial vision to systems modelling

161 p.

Vision-Based Solutions for Human-Robot Collaboration in Industrial Workcells

Industrial robots are both versatile and high performant, enabling the flexible automation typical of the modern Smart Factories. For safety reasons, however, they must be relegated inside closed fences and/or virtual safety barriers, to keep them strictly separated from human operators. This can be a limitation in some scenarios in which it is useful to combine the human cognitive skill with the accuracy and repeatability of a robot, or simply to allow a safe coexistence in a shared workspace. Collaborative robots (cobots), on the other hand, are intrinsically limited in speed and power in order to share workspace and tasks with human operators, and feature the very intuitive hand guiding programming method. Cobots, however, cannot compete with industrial robots in terms of performance, and are thus useful only in a limited niche, where they can actually bring an improvement in productivity and/or in the quality of the work thanks to their synergy with human operators. The limitations of both the pure industrial and the collaborative paradigms can be overcome by combining industrial robots with artificial vision. In particular, vision can be exploited for a real-time adjustment of the pre-programmed task-based robot trajectory, by means of the visual tracking of dynamic obstacles (e.g. human operators). This strategy allows the robot to modify its motion only when necessary, thus maintain a high level of productivity but at the same time increasing its versatility. Other than that, vision offers the possibility of more intuitive programming paradigms for the industrial robots as well, such as the programming by demonstration paradigm. These possibilities offered by artificial vision enable, as a matter of fact, an efficacious and promising way of achieving human-robot collaboration, which has the advantage of overcoming the limitations of both the previous paradigms yet keeping their strengths.

Sistema de detecção e localização de veículos subaquáticos

Mestrado em Engenharia Electrotécnica e de Computadores.Área de Especialização de Sistemas Autónomos

Navegação de robôs móveis por marcas artificiais em ambientes semi-estruturados

Mestrado em engenharia electrotécnica e de computadores - Área de Especialização de Sistemas Autónomos

Sistema de mapeamento e localização simultânea para inspecção subaquática

A sequente dissertação resulta do desenvolvimento de um sistema de navegação subaquático para um Remotely Operated Vehicle (ROV). A abordagem proposta consiste de um algoritmo em tempo real baseado no método de Mapeamento e Localização Simultâneo (SLAM) a partir de marcadores em ambientes marinhos não estruturados. SLAM introduz dois principais desafios: (i) reconhecimento dos marcadores provenientes dos dados raw do sensor, (ii) associação de dados. Na detecção dos marcadores foram aplicadas técnicas de visão artificial baseadas na extracção de pontos e linhas. Para testar o uso de features no visual SLAM em tempo real nas operações de inspecção subaquáticas foi desenvolvida uma plataforma modicada do RT-SLAM que integra a abordagem EKF SLAM. A plataforma é integrada em ROS framework e permite estimar a trajetória 3D em tempo real do ROV VideoRay Pro 3E até 30 fps. O sistema de navegação subaquático foi caracterizado num tanque instalado no Laboratório de Sistemas Autónomos através de um sistema stereo visual de ground truth. Os resultados obtidos permitem validar o sistema de navegação proposto para veículos subaquáticos. A trajetória adquirida pelo VideoRay em ambiente controlado é validada pelo sistema de ground truth. Dados para ambientes não estruturados, como um gasoduto, foram adquiridos e obtida respectiva trajetória realizada pelo robô. Os dados apresentados comprovam uma boa precisão e exatidão para a estimativa da posição.

Automatização de sistemas de inspeção COGNEX

Com um mercado automóvel cada vez mais competitivo e com os construtores automóveis à procura de atingir os zero defeitos nos seus produtos, a Bosch Car Multimédia Portugal S.A, fabricante de sistemas multimédia para o mercado automóvel, tem como objetivo a qualidade perfeita dos seus produtos. Tal perfeição exige processos de fabrico cada vez mais evoluídos e com melhores sistemas de auxílio à montagem. Nesse sentido, a incorporação de sistemas de visão artificial para verificação da montagem correta dos componentes em sistemas multimédia tem vindo a crescer largamente. Os sistemas de inspeção visual da Cognex tornaram-se o standard da Bosch para a verifi-cação da montagem de componentes por serem sistemas bastante completos, fáceis de con-figurar e com um suporte técnico bastante completo. Estes sistemas têm vindo a ser inte-grados em diversas máquinas (postos) de montagem e nunca foi desenvolvida uma ferra-menta normalizada para integração destes sistemas com as máquinas. A ideia principal deste projeto passou por desenvolver um sistema (uma aplicação informá-tica) que permita controlar os indicadores de qualidade destes sistemas de visão, garantir o seguimento dos produtos montados e, ao mesmo tempo, efetuar cópias de segurança de todo o sistema para utilização em caso de avaria ou de troca de equipamento. Tal sistema foi desenvolvido recorrendo à programação de uma Dynamic Link Library (DLL), através da linguagem VisualBasic.NET, que permite às aplicações dos equipamen-tos (máquinas) da Bosch Car Multimédia comunicarem de uma forma universal e transpa-rente com os sistemas de inspeção visual da marca Cognex. Os objetivos a que o autor se propôs no desenvolvimento deste sistema foram na sua maioria alcançados e o projeto encontra-se atualmente implementado e em execução nas linhas de produção da Bosch Car Multimédia.

Segmentación interactiva multi-clase de personas

La segmentació de persones es molt difícil a causa de la variabilitat de les diferents condicions, com la postura que aquestes adoptin, color del fons, etc. Per realitzar aquesta segmentació existeixen diferents tècniques, que a partir d'una imatge ens retornen un etiquetat indicant els diferents objectes presents a la imatge. El propòsit d'aquest projecte és realitzar una comparativa de les tècniques recents que permeten fer segmentació multietiqueta i que son semiautomàtiques, en termes de segmentació de persones. A partir d'un etiquetatge inicial idèntic per a tots els mètodes utilitzats, s'ha realitzat una anàlisi d'aquests, avaluant els seus resultats sobre unes dades publiques, analitzant 2 punts: el nivell de interacció i l'eficiència.

Segmentación interactiva multi-clase de personas

La segmentació de persones es molt difícil a causa de la variabilitat de les diferents condicions, com la postura que aquestes adoptin, color del fons, etc. Per realitzar aquesta segmentació existeixen diferents tècniques, que a partir d'una imatge ens retornen un etiquetat indicant els diferents objectes presents a la imatge. El propòsit d'aquest projecte és realitzar una comparativa de les tècniques recents que permeten fer segmentació multietiqueta i que son semiautomàtiques, en termes de segmentació de persones. A partir d'un etiquetatge inicial idèntic per a tots els mètodes utilitzats, s'ha realitzat una anàlisi d'aquests, avaluant els seus resultats sobre unes dades publiques, analitzant 2 punts: el nivell de interacció i l'eficiència.

Estudi fonamental i aplicat de l'etapa d'eliminació de tinta per flotació

La tesi realitza un estudi detallat dels principals processos que tenen lloc durant l'eliminació de tinta tòner per flotació. L'estudi del procés d'adhesió de tinta a la superfície de bombolles d'aire s'ha realitzat mitjançant visió artificial. Els resultats obtinguts han mostrat que un excés de tensioactiu provoca una disminució de la quantitat de tinta unida a la bombolla d'aire i per tant una disminució de l'eficàcia del procés de flotació. La caracterització de les bombolles d'aire presents en una cel·la de flotació ha posat de manifest que tant el cabal d'aire com la velocitat de l'agitador configuren la distribució de diàmetres final. L'estudi del procés d'eliminació de tinta per flotació en absència de fibres cel·lulòsiques ha mostrat que les variables físico-químiques estudiades són les que tenen una major influència en el procés d'eliminació de tinta tòner per flotació. Finalment s'han addicionat fibres cel·lulòsiques a la suspensió. S'ha pogut comprovar que s'aconsegueix una bona eliminació de tinta sempre i quan les condicions hidrodinàmiques siguin les adequades.

An approach to coded structured light to obtain three dimensional information

The human visual ability to perceive depth looks like a puzzle. We perceive three-dimensional spatial information quickly and efficiently by using the binocular stereopsis of our eyes and, what is mote important the learning of the most common objects which we achieved through living. Nowadays, modelling the behaviour of our brain is a fiction, that is why the huge problem of 3D perception and further, interpretation is split into a sequence of easier problems. A lot of research is involved in robot vision in order to obtain 3D information of the surrounded scene. Most of this research is based on modelling the stereopsis of humans by using two cameras as if they were two eyes. This method is known as stereo vision and has been widely studied in the past and is being studied at present, and a lot of work will be surely done in the future. This fact allows us to affirm that this topic is one of the most interesting ones in computer vision. The stereo vision principle is based on obtaining the three dimensional position of an object point from the position of its projective points in both camera image planes. However, before inferring 3D information, the mathematical models of both cameras have to be known. This step is known as camera calibration and is broadly describes in the thesis. Perhaps the most important problem in stereo vision is the determination of the pair of homologue points in the two images, known as the correspondence problem, and it is also one of the most difficult problems to be solved which is currently investigated by a lot of researchers. The epipolar geometry allows us to reduce the correspondence problem. An approach to the epipolar geometry is describes in the thesis. Nevertheless, it does not solve it at all as a lot of considerations have to be taken into account. As an example we have to consider points without correspondence due to a surface occlusion or simply due to a projection out of the camera scope. The interest of the thesis is focused on structured light which has been considered as one of the most frequently used techniques in order to reduce the problems related lo stereo vision. Structured light is based on the relationship between a projected light pattern its projection and an image sensor. The deformations between the pattern projected into the scene and the one captured by the camera, permits to obtain three dimensional information of the illuminated scene. This technique has been widely used in such applications as: 3D object reconstruction, robot navigation, quality control, and so on. Although the projection of regular patterns solve the problem of points without match, it does not solve the problem of multiple matching, which leads us to use hard computing algorithms in order to search the correct matches. In recent years, another structured light technique has increased in importance. This technique is based on the codification of the light projected on the scene in order to be used as a tool to obtain an unique match. Each token of light is imaged by the camera, we have to read the label (decode the pattern) in order to solve the correspondence problem. The advantages and disadvantages of stereo vision against structured light and a survey on coded structured light are related and discussed. The work carried out in the frame of this thesis has permitted to present a new coded structured light pattern which solves the correspondence problem uniquely and robust. Unique, as each token of light is coded by a different word which removes the problem of multiple matching. Robust, since the pattern has been coded using the position of each token of light with respect to both co-ordinate axis. Algorithms and experimental results are included in the thesis. The reader can see examples 3D measurement of static objects, and the more complicated measurement of moving objects. The technique can be used in both cases as the pattern is coded by a single projection shot. Then it can be used in several applications of robot vision. Our interest is focused on the mathematical study of the camera and pattern projector models. We are also interested in how these models can be obtained by calibration, and how they can be used to obtained three dimensional information from two correspondence points. Furthermore, we have studied structured light and coded structured light, and we have presented a new coded structured light pattern. However, in this thesis we started from the assumption that the correspondence points could be well-segmented from the captured image. Computer vision constitutes a huge problem and a lot of work is being done at all levels of human vision modelling, starting from a)image acquisition; b) further image enhancement, filtering and processing, c) image segmentation which involves thresholding, thinning, contour detection, texture and colour analysis, and so on. The interest of this thesis starts in the next step, usually known as depth perception or 3D measurement.

The implementation of a low-cost production-line inspection system

This article describes an application of computers to a consumer-based production engineering environment. Particular consideration is given to the utilisation of low-cost computer systems for the visual inspection of components on a production line in real time. The process of installation is discussed, from identifying the need for artificial vision and justifying the cost, through to choosing a particular system and designing the physical and program structure.

A network of integrate and fire neurons for visual selection

Biological systems have facility to capture salient object(s) in a given scene, but it is still a difficult task to be accomplished by artificial vision systems. In this paper a visual selection mechanism based on the integrate and fire neural network is proposed. The model not only can discriminate objects in a given visual scene, but also can deliver focus of attention to the salient object. Moreover, it processes a combination of relevant features of an input scene, such as intensity, color, orientation, and the contrast of them. In comparison to other visual selection approaches, this model presents several interesting features. It is able to capture attention of objects in complex forms, including those linearly nonseparable. Moreover, computer simulations show that the model produces results similar to those observed in natural vision systems.

Influência das características dos anéis de crescimento na densidade, resistência e rigidez da madeira de Pinus taeda L

Pós-graduação em Agronomia (Energia na Agricultura) - FCA

Classificazione di oggetti in immagini attraverso il modello Bag of Visual Words

Generic object recognition is an important function of the human visual system and everybody finds it highly useful in their everyday life. For an artificial vision system it is a really hard, complex and challenging task because instances of the same object category can generate very different images, depending of different variables such as illumination conditions, the pose of an object, the viewpoint of the camera, partial occlusions, and unrelated background clutter. The purpose of this thesis is to develop a system that is able to classify objects in 2D images based on the context, and identify to which category the object belongs to. Given an image, the system can classify it and decide the correct categorie of the object. Furthermore the objective of this thesis is also to test the performance and the precision of different supervised Machine Learning algorithms in this specific task of object image categorization. Through different experiments the implemented application reveals good categorization performances despite the difficulty of the problem. However this project is open to future improvement; it is possible to implement new algorithms that has not been invented yet or using other techniques to extract features to make the system more reliable. This application can be installed inside an embedded system and after trained (performed outside the system), so it can become able to classify objects in a real-time. The information given from a 3D stereocamera, developed inside the department of Computer Engineering of the University of Bologna, can be used to improve the accuracy of the classification task. The idea is to segment a single object in a scene using the depth given from a stereocamera and in this way make the classification more accurate.

Autonomous vehicle control systems for safe crossroads

This article presents a cooperative manoeuvre among three dual mode cars – vehicles equipped with sensors and actuators, and that can be driven either manually or autonomously. One vehicle is driven autonomously and the other two are driven manually. The main objective is to test two decision algorithms for priority conflict resolution at intersections so that a vehicle autonomously driven can take their own decision about crossing an intersection mingling with manually driven cars without the need for infrastructure modifications. To do this, the system needs the position, speeds, and turning intentions of the rest of the cars involved in the manoeuvre. This information is acquired via communications, but other methods are also viable, such as artificial vision. The idea of the experiments was to adjust the speed of the manually driven vehicles to force a situation where all three vehicles arrive at an intersection at the same time.