Large quantities of bulk grain are moved using graincars in Canada and other parts of the world. Automation has not progressed significantly in the grain industry probably because the market is limited for automated systems. A prototype of a robot (“Grain-o-bot”) using machine vision to automatically open and close graincar hopper gates and detect the contents of the graincar was built and studied. The “Grain-o-bot” was a Cartesian robot equipped with two cameras and an opening tool as the end-effector. One camera acted as the eye to determine the sprocket location, and guided the end-effector to the sprocket opening. For most applications, machine vision solutions based on pattern recognition were developed using images acquired in a laboratory setting. Major constraints with these solutions occurred when implementing them in real world applications. So the first step for this automation was to correctly identify the hopper gate sprocket on the grain car. Algorithms were developed to detect and identify the sprocket under proper lighting conditions with 100% accuracy. The performance of the algorithms was also evaluated for the identification of the sprocket on a grain car exposed to different lighting conditions, which are expected to occur in typical grain unloading facilities. Monochrome images of the sprocket from a model system were acquired using different light. Correlation and pattern recognition techniques using a template image combined with shape detection were used for sprocket identification. The images were pre-processed using image processing techniques, prior to template matching. The template image developed from the light source that was similar to the light source used to acquire ii images was more successful in identifying the sprocket than the template image developed using different light sources. A sample of the graincar content was taken by slightly opening and immediately closing the hopper gates. The sample was identified by taking an image using the second camera and performing feature matching. An accuracy of 99% was achieved in identifying Canada Western Red Spring (CWRS) wheat and 100% for identifying barley and canola.

Zugl.: Aachen, Techn. Hochsch., Diss., 2007

Stuttgart, Univ., Diss., 2003.

Universiẗat, Diss., 2004--Frankfurt (Main).

Techn. University, Diss., 2004--Dresden.

Made available in DSpace on 2016-08-29T15:33:17Z (GMT). No. of bitstreams: 1 tese_5110_.pdf: 2498862 bytes, checksum: dedd1a12ee1994a236252576fadedc20 (MD5) Previous issue date: 2012-04-16 / A crescente utilização dos ambientes virtuais colaborativos nas mais variadas formas destaca lacunas nos suportes tecnológicos atuais no que diz respeito à customização do ambiente e de sua interface. Esse fato incita a criação de novas propostas que atendam às necessidades ou preferências dos usuários de espaços virtuais. Este trabalho apresenta uma arquitetura de software que apoia a autoria na criação e edição de interfaces visuais dos espaços virtuais desenvolvidos a partir do MOrFEu, favorecendo a personalização dos ambientes e consequentemente gerando sua melhor adaptação aos estilos cognitivos de seus usuários. Os templates, instâncias de interfaces gráficas, são criados individualmente ou em conjunto. Seus usuários são ainda beneficiados com a possibilidade de sua reutilização e customização.

Due to the amount of flow simulation and measurement data, automatic detection, classification and visualization of features is necessary for an inspection. Therefore, many automated feature detection methods have been developed in recent years. However, one feature class is visualized afterwards in most cases, and many algorithms have problems in the presence of noise or superposition effects. In contrast, image processing and computer vision have robust methods for feature extraction and computation of derivatives of scalar fields. Furthermore, interpolation and other filter can be analyzed in detail. An application of these methods to vector fields would provide a solid theoretical basis for feature extraction. The authors suggest Clifford algebra as a mathematical framework for this task. Clifford algebra provides a unified notation for scalars and vectors as well as a multiplication of all basis elements. The Clifford product of two vectors provides the complete geometric information of the relative positions of these vectors. Integration of this product results in Clifford correlation and convolution which can be used for template matching on vector fields. Furthermore, for frequency analysis of vector fields and the behavior of vector-valued filters, a Clifford Fourier transform has been derived for 2 and 3 dimensions. Convolution and other theorems have been proved, and fast algorithms for the computation of the Clifford Fourier transform exist. Therefore the computation of Clifford convolution can be accelerated by computing it in Clifford Fourier domain. Clifford convolution and Fourier transform can be used for a thorough analysis and subsequent visualization of vector fields

The formalization of natural language contracts can make the prescriptions found in these contracts more precise, promoting the development of smart contracts, which are digitized forms of the documents where the monitoring and execution can be partially automated. Full formalization remains a difficult problem, and this thesis makes steps towards solving this challenge by focusing on a narrow sub-problem of formalizing contract refinements. We want to allow a contract author to customize a contract template, and automatically convert the resulting contract to a formal specification language called Symboleo, created specifically for the legal contract domain. The hope is that research towards partial formalization can be useful on its own, as well as useful towards the full formalization of contracts. The main questions addressed by this thesis involve asking what linguistic forms these refinements will take. Answering these questions involves both linguistic analysis and empirical analysis on a set of real contracts to construct a controlled natural language (CNL). This language is expressive and natural enough to be adopted by contract authors, and it is precise enough that it can reliably be converted into the proper formal specification. We also design a tool, SymboleoNLP, that demonstrates this functionality on realistic contracts. This involves ensuring that the contract author can input contract refinements that adhere to our CNL, and that the refinements are properly formalized with Symboleo. In addition to contributing an evidence-based CNL for contract refinements, this thesis also outlines a very clear methodology for constructing this CNL, which may need to go through iterations as requirements change and as the Symboleo language evolves. The SymboleoNLP tool is another contribution, and is designed for iterative improvement. We explore a number of potential areas where further NLP techniques may be integrated to improve performance, and the tool is designed for easy integration of these modules to adapt to emerging technologies and changing requirements.

No description available.

No description available.