3D model reconstruction using neural gas accelerated on GPU

In this work, we propose the use of the neural gas (NG), a neural network that uses an unsupervised Competitive Hebbian Learning (CHL) rule, to develop a reverse engineering process. This is a simple and accurate method to reconstruct objects from point clouds obtained from multiple overlapping views using low-cost sensors. In contrast to other methods that may need several stages that include downsampling, noise filtering and many other tasks, the NG automatically obtains the 3D model of the scanned objects. To demonstrate the validity of our proposal we tested our method with several models and performed a study of the neural network parameterization computing the quality of representation and also comparing results with other neural methods like growing neural gas and Kohonen maps or classical methods like Voxel Grid. We also reconstructed models acquired by low cost sensors that can be used in virtual and augmented reality environments for redesign or manipulation purposes. Since the NG algorithm has a strong computational cost we propose its acceleration. We have redesigned and implemented the NG learning algorithm to fit it onto Graphics Processing Units using CUDA. A speed-up of 180× faster is obtained compared to the sequential CPU version.

3D model based map building

Comunicación presentada en el IX Workshop de Agentes Físicos (WAF'2008), Vigo, 11-12 septiembre 2008.

Augmented and Virtual Reality techniques for footwear

The use of 3D imaging techniques has been early adopted in the footwear industry. In particular, 3D imaging could be used to aid commerce and improve the quality and sales of shoes. Footwear customization is an added value aimed not only to improve product quality, but also consumer comfort. Moreover, customisation implies a new business model that avoids the competition of mass production coming from new manufacturers settled mainly in Asian countries. However, footwear customisation implies a significant effort at different levels. In manufacturing, rapid and virtual prototyping is required; indeed the prototype is intended to become the final product. The whole design procedure must be validated using exclusively virtual techniques to ensure the feasibility of this process, since physical prototypes should be avoided. With regard to commerce, it would be desirable for the consumer to choose any model of shoes from a large 3D database and be able to try them on looking at a magic mirror. This would probably reduce costs and increase sales, since shops would not require storing every shoe model and the process of trying several models on would be easier and faster for the consumer. In this paper, new advances in 3D techniques coming from experience in cinema, TV and games are successfully applied to footwear. Firstly, the characteristics of a high-quality stereoscopic vision system for footwear are presented. Secondly, a system for the interaction with virtual footwear models based on 3D gloves is detailed. Finally, an augmented reality system (magic mirror) is presented, which is implemented with low-cost computational elements that allow a hypothetical customer to check in real time the goodness of a given virtual footwear model from an aesthetical point of view.

Contributions to 3D Data Registration and Representation

Nowadays, new computers generation provides a high performance that enables to build computationally expensive computer vision applications applied to mobile robotics. Building a map of the environment is a common task of a robot and is an essential part to allow the robots to move through these environments. Traditionally, mobile robots used a combination of several sensors from different technologies. Lasers, sonars and contact sensors have been typically used in any mobile robotic architecture, however color cameras are an important sensor due to we want the robots to use the same information that humans to sense and move through the different environments. Color cameras are cheap and flexible but a lot of work need to be done to give robots enough visual understanding of the scenes. Computer vision algorithms are computational complex problems but nowadays robots have access to different and powerful architectures that can be used for mobile robotics purposes. The advent of low-cost RGB-D sensors like Microsoft Kinect which provide 3D colored point clouds at high frame rates made the computer vision even more relevant in the mobile robotics field. The combination of visual and 3D data allows the systems to use both computer vision and 3D processing and therefore to be aware of more details of the surrounding environment. The research described in this thesis was motivated by the need of scene mapping. Being aware of the surrounding environment is a key feature in many mobile robotics applications from simple robotic navigation to complex surveillance applications. In addition, the acquisition of a 3D model of the scenes is useful in many areas as video games scene modeling where well-known places are reconstructed and added to game systems or advertising where once you get the 3D model of one room the system can add furniture pieces using augmented reality techniques. In this thesis we perform an experimental study of the state-of-the-art registration methods to find which one fits better to our scene mapping purposes. Different methods are tested and analyzed on different scene distributions of visual and geometry appearance. In addition, this thesis proposes two methods for 3d data compression and representation of 3D maps. Our 3D representation proposal is based on the use of Growing Neural Gas (GNG) method. This Self-Organizing Maps (SOMs) has been successfully used for clustering, pattern recognition and topology representation of various kind of data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models without considering time constraints. Self-organising neural models have the ability to provide a good representation of the input space. In particular, the Growing Neural Gas (GNG) is a suitable model because of its flexibility, rapid adaptation and excellent quality of representation. However, this type of learning is time consuming, specially for high-dimensional input data. Since real applications often work under time constraints, it is necessary to adapt the learning process in order to complete it in a predefined time. This thesis proposes a hardware implementation leveraging the computing power of modern GPUs which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). Our proposed geometrical 3D compression method seeks to reduce the 3D information using plane detection as basic structure to compress the data. This is due to our target environments are man-made and therefore there are a lot of points that belong to a plane surface. Our proposed method is able to get good compression results in those man-made scenarios. The detected and compressed planes can be also used in other applications as surface reconstruction or plane-based registration algorithms. Finally, we have also demonstrated the goodness of the GPU technologies getting a high performance implementation of a CAD/CAM common technique called Virtual Digitizing.

Modelo geológico 3D del NO de la Cuenca del Bajo Segura (Alicante, SE de España)

Se ha realizado un modelo geológico en 3D de la porción NO de la Cuenca del Bajo Segura, por ser esta la que mostraba una menor complicación geológica. La cuenca se ha dividido en 7 sintemas (nombrados Ab,M1, M2, P1, P2, Pc y Q) y se ha utilizado como base de la cuenca el techo de la Formación Calizas de Las Ventanas (Ve). La construcción del modelo 3D permite un mejor conocimiento geológico de la cuenca. El modelo apunta a una mayor complicación tectónica de lo supuesto en un principio.

3D geometry of growth strata in a fault-propagation fold: insights into space–time evolution of the Crevillente Fault (Abanilla-Alicante sector), Betic Cordillera, Spain

This work presents a 3D geometric model of growth strata cropping out in a fault-propagation fold associated with the Crevillente Fault (Abanilla-Alicante sector) from the Bajo Segura Basin (eastern Betic Cordillera, southern Spain). The analysis of this 3D model enables us to unravel the along-strike and along-section variations of the growth strata, providing constraints to assess the fold development, and hence, the fault kinematic evolution in space and time. We postulate that the observed along-strike dip variations are related to lateral variation in fault displacement. Along-section variations of the progressive unconformity opening angles indicate greater fault slip in the upper Tortonian–Messinian time span; from the Messinian on, quantitative analysis of the unconformity indicate a constant or lower tectonic activity of the Crevillente Fault (Abanilla-Alicante sector); the minor abundance of striated pebbles in the Pliocene-Quaternary units could be interpreted as a decrease in the stress magnitude and consequently in the tectonic activity of the fault. At a regional scale, comparison of the growth successions cropping out in the northern and southern limits of the Bajo Segura Basin points to a southward migration of deformation in the basin. This means that the Bajo Segura Fault became active after the Crevillente Fault (Abanilla-Alicante sector), for which activity on the latter was probably decreasing according to our data. Consequently, we propose that the seismic hazard at the northern limit of the Bajo Segura Basin should be lower than at the southern limit.

3D numerical modelling of acoustic horns using the method of fundamental solutions

In the present work, a three-dimensional (3D) formulation based on the method of fundamental solutions (MFS) is applied to the study of acoustic horns. The implemented model follows and extends previous works that only considered two-dimensional and axisymmetric horn configurations. The more realistic case of 3D acoustic horns with symmetry regarding two orthogonal planes is addressed. The use of the domain decomposition technique with two interconnected sub-regions along a continuity boundary is proposed, allowing for the computation of the sound pressure generated by an acoustic horn installed on a rigid screen. In order to reduce the model discretization requirements for these cases, Green’s functions derived with the image source methodology are adopted, automatically accounting for the presence of symmetry conditions. A strategy for the calculation of an optimal position of the virtual sources used by the MFS to define the solution is also used, leading to improved reliability and flexibility of the proposed method. The responses obtained by the developed model are compared to reference solutions, computed by well-established models based on the boundary element method. Additionally, numerically calculated acoustic parameters, such as directivity and beamwidth, are compared with those evaluated experimentally.