A FAST assembly simulation analysis method for hull blocks with engineering constraints

In order to effectively improve the assembly efficiency for hull blocks, an assembly simulation analysis method considering engineering constraints is proposed in this paper, and an integrated system of shipbuilding accuracy analysis and assembly analysis considering multi-constraints is developed. The method is divided into pre-matching model and fine matching model. In the pre-matching model, an Improved Coherent Point Drift (ICPD) algorithm is used to obtain more accurate initial matching values. The fine matching model firstly uses the Analytic Hierarchy Process (AHP) algorithm to automatically obtain the constrained weights, then the weights vector is used to add the assembly constraints for hull blocks such as straightness, hard point constraints etc. into the multi-objective optimization function. By solving the function, the optimum positioning location and the most reasonable adjustment scheme are obtained. This method shortens the occupancy time of the equipment used to build the hull, reduces the workload of the staff, and improves the efficiency and quality of shipbuilding. The integrated system adds engineering constraints analysis module and the function of automatically finding and eliminating error measurement points. Through the verification of the examples, the integrated system realizes the automation and intellectualization of the assembly for hull blocks.

Avaliação do Desempenho dos Métodos ICP, CPD e SVR para Registro Automático de Nuvens de Pontos Relativas a Telhados Extraídas de Dados LiDAR Aerotransportados

A partir dos anos 2000, houve um aumento na aquisição de dados LiDAR (Light Detection and Ranging) em áreas urbanas, o que possibilitou diversos estudos e aplicações nas mais variadas áreas, verificando-se um crescimento dos acervos históricos. Com isso, são necessários métodos de processamento robustos para manipulação desses dados. Os métodos de registro de dados laser inserem-se nesse contexto, essenciais para promover a utilização de dados oriundos de distintos equipamentos e datas. Este estudo consiste em avaliar o desempenho de três métodos de registro: Iterative Closest Point (ICP), Coherent Point Drift (CPD) e Support Vector Registration (SVR). A metodologia contempla o pré-processamento dos dados LiDAR para a extração de três telhados de edifícios com características distintas, localizados no campus da UFPR, em Curitiba – PR. Foram utilizados dados do sensor Optech ALTM Pegasus HD 500, com frequência de 300 kHz e altura de voo de 1.600 m, densidade média de 1,71 pontos por m² e IFOV de 25°. Os métodos foram implementados na linguagem Python. Como resultados, foram obtidos os registros, dos quais foram extraídas suas acurácias e tempos de processamento. Os resultados evidenciaram que os métodos CPD e SVR são ótimas alternativas para superar as limitações do ICP, ressaltando-se o desempenho do CPD e a eficiência computacional do SVR, sendo que este último é particularmente adequado para lidar com dados ruidosos.

Sea Turtle Facial Recognition Using Map Graphs of Scales

Individual identification of sea turtles is important to study their biology and aide in conservation efforts. Traditional methods for identifying sea turtles that rely on physical or GPS tags can be expensive, and difficult to implement. Alternatively, the scale structure on the side of a turtle's head has been shown to be specific to the individual and stable over its lifetime, and therefore can be used as the individual's "fingerprint". Here we propose a novel facial recognition method where an image of a sea turtle is converted into a graph (network) with nodes representing scales, and edges connecting two scales that share a border. The topology of the graph is used to differentiate species. We additionally develop a robust metric to compare turtles based on a correspondence between nodes generated by a coherent point drift algorithm and computing a graph edit distance to identify individual turtles with over 94% accuracy. By representing the special and topological features of sea turtle scales as a graph, we perform more accurate individual identification which is robust under different imaging conditions and may be adapted for a wider number of species.

Landmark-free, parametric hypothesis tests regarding two-dimensional contour shapes using coherent point drift registration and statistical parametric mapping

This paper proposes a computational framework for automated, landmark-free hypothesis testing of 2D contour shapes (i.e., shape outlines), and implements one realization of that framework. The proposed framework consists of point set registration, point correspondence determination, and parametric full-shape hypothesis testing. The results are calculated quickly (<2 s), yield morphologically rich detail in an easy-to-understand visualization, and are complimented by parametrically (or nonparametrically) calculated probability values. These probability values represent the likelihood that, in the absence of a true shape effect, smooth, random Gaussian shape changes would yield an effect as large as the observed one. This proposed framework nevertheless possesses a number of limitations, including sensitivity to algorithm parameters. As a number of algorithms and algorithm parameters could be substituted at each stage in the proposed data processing chain, sensitivity analysis would be necessary for robust statistical conclusions. In this paper, the proposed technique is applied to nine public datasets using a two-sample design, and an ANCOVA design is then applied to a synthetic dataset to demonstrate how the proposed method generalizes to the family of classical hypothesis tests. Extension to the analysis of 3D shapes is discussed.