Trois hypothèses principales existent quant aux indices locaux du contour étant les plus informatifs pour le processus de structuration de la forme, et permettant l’identification visuelle des objets : les angles et les indices de tridimensionnalité (Biederman, 1987 ; Boucart et al, 1995), les éléments mi-segments (Kennedy & Domander, 1985, Singh & Fulvio, 2005), et l’interaction entre le type de fragmentation et le degré de spécificité de la forme globale (Panis & Wagemans, 2009). L’objectif de ce travail consiste donc à confronter ces trois hypothèses, en tentant de déterminer par ailleurs le niveau (conscient ou non conscient) auquel s’opèrent la détection et le traitement de ces indices. Les paradigmes d’amorçage supra et infraliminaire sont employés. Des dessins d’objets fragmentés selon deux modes (angles et indices de tridimensionnalité versus éléments mi-segments) sont insérés en tant qu’amorce, précédant une image cible du même objet, elle-même fragmentée et présentant des zones de contours strictement identiques ou complémentaires à l’amorce. Aucune des quatre expériences proposées ne met en évidence un effet « qualitatif » du type de fragmentation. En revanche, certaines conditions temporelles permettent un effet d’amorçage de type lié à la quantité de contour présenté. Nos résultats confirment l’ambiguïté émergeant de la littérature relative aux zones de contours les plus informatives, et semblent conforter la nécessité d’un haut degré d’automaticité des processus impliqués dans la perspective de mettre en évidence des effets d’amorçage perceptif / Three main hypotheses exist concerning the most informative local features of contour for binding processes, allowing visual object identification: vertices and 3D features (Biederman, 1987 ; Boucart et al, 1995), midsegments elements (Kennedy R& Domander, 1985, Singh & Fulvio, 2005), and the interaction betweenfragmentation type and complexity of the global form (Panis & Wagemans, 2009). The aim of this work is to confront these hypotheses, while trying to determine the level (conscious or unconscious) at which the detection and the processing of these features occur. Conscious and unconscious priming paradigms are employed. Drawings of fragmented objects contain either vertices and 3D features or midsegment elements. They are used as primes, preceding a fragmented target image of the same object containing identical or complementary contour features. None of these four experiments highlight a qualitative effect of fragmentation types. However, a quantitative priming effect can be observed under certain timing conditions. Our results confirm the ambiguity emerging from literature concerning the most informative contour features and the necessity of a high degree of automatism of the processes involved in order to highlight perceptual priming effects

Recent advances in technology have increased awareness of the necessity for automated systems in people’s everyday lives. Artificial systems are more frequently being introduced into environments previously thought to be too perilous for humans to operate in. Some robots can be used to extract potentially hazardous materials from sites inaccessible to humans, while others are being developed to aid humans with laborious tasks. A crucial aspect of all artificial systems is the manner in which they interact with their immediate surroundings. Developing such a deceivingly simply aspect has proven to be significantly challenging, as it not only entails the methods through which the system perceives its environment, but also its ability to perform critical tasks. These undertakings often involve the coordination of numerous subsystems, each performing its own complex duty. To complicate matters further, it is nowadays becoming increasingly important for these artificial systems to be able to perform their tasks in real-time. The task of object recognition is typically described as the process of retrieving the object in a database that is most similar to an unknown, or query, object. Pose estimation, on the other hand, involves estimating the position and orientation of an object in three-dimensional space, as seen from an observer’s viewpoint. These two tasks are regarded as vital to many computer vision techniques and and regularly serve as input to more complex perception algorithms. An approach is presented which regards the object recognition and pose estimation procedures as mutually dependent. The core idea is that dissimilar objects might appear similar when observed from certain viewpoints. A feature-based conceptualisation, which makes use of a database, is implemented and used to perform simultaneous object recognition and pose estimation. The design incorporates data compression techniques, originally suggested by the image-processing community, to facilitate fast processing of large databases. System performance is quantified primarily on object recognition, pose estimation and execution time characteristics. These aspects are investigated under ideal conditions by exploiting three-dimensional models of relevant objects. The performance of the system is also analysed for practical scenarios by acquiring input data from a structured light implementation, which resembles that obtained from many commercial range scanners. Practical experiments indicate that the system was capable of performing simultaneous object recognition and pose estimation in approximately 230 ms once a novel object has been sensed. An average object recognition accuracy of approximately 73% was achieved. The pose estimation results were reasonable but prompted further research. The results are comparable to what has been achieved using other suggested approaches such as Viewpoint Feature Histograms and Spin Images. / Dissertation (MEng)--University of Pretoria, 2013. / gm2014 / Electrical, Electronic and Computer Engineering / unrestricted

Recent advances in technology have increased awareness of the necessity for automated systems in people’s everyday lives. Artificial systems are more frequently being introduced into environments previously thought to be too perilous for humans to operate in. Some robots can be used to extract potentially hazardous materials from sites inaccessible to humans, while others are being developed to aid humans with laborious tasks. A crucial aspect of all artificial systems is the manner in which they interact with their immediate surroundings. Developing such a deceivingly simply aspect has proven to be significantly challenging, as it not only entails the methods through which the system perceives its environment, but also its ability to perform critical tasks. These undertakings often involve the coordination of numerous subsystems, each performing its own complex duty. To complicate matters further, it is nowadays becoming increasingly important for these artificial systems to be able to perform their tasks in real-time. The task of object recognition is typically described as the process of retrieving the object in a database that is most similar to an unknown, or query, object. Pose estimation, on the other hand, involves estimating the position and orientation of an object in three-dimensional space, as seen from an observer’s viewpoint. These two tasks are regarded as vital to many computer vision techniques and regularly serve as input to more complex perception algorithms. An approach is presented which regards the object recognition and pose estimation procedures as mutually dependent. The core idea is that dissimilar objects might appear similar when observed from certain viewpoints. A feature-based conceptualisation, which makes use of a database, is implemented and used to perform simultaneous object recognition and pose estimation. The design incorporates data compression techniques, originally suggested by the image-processing community, to facilitate fast processing of large databases. System performance is quantified primarily on object recognition, pose estimation and execution time characteristics. These aspects are investigated under ideal conditions by exploiting three-dimensional models of relevant objects. The performance of the system is also analysed for practical scenarios by acquiring input data from a structured light implementation, which resembles that obtained from many commercial range scanners. Practical experiments indicate that the system was capable of performing simultaneous object recognition and pose estimation in approximately 230 ms once a novel object has been sensed. An average object recognition accuracy of approximately 73% was achieved. The pose estimation results were reasonable but prompted further research. The results are comparable to what has been achieved using other suggested approaches such as Viewpoint Feature Histograms and Spin Images. / Dissertation (MEng)--University of Pretoria, 2013. / gm2014 / Electrical, Electronic and Computer Engineering / unrestricted