GPGPU implementation of growing neural gas: application to 3D scene reconstruction

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, especially 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 paper proposes a Graphics Processing Unit (GPU) parallel implementation of the GNG with Compute Unified Device Architecture (CUDA). In contrast to existing algorithms, the proposed GPU implementation allows the acceleration of the learning process keeping a good quality of representation. Comparative experiments using iterative, parallel and hybrid implementations are carried out to demonstrate the effectiveness of CUDA implementation. The results show that GNG learning with the proposed implementation achieves a speed-up of 6× compared with the single-threaded CPU implementation. GPU implementation has also been applied to a real application with time constraints: acceleration of 3D scene reconstruction for egomotion, in order to validate the proposal.

Studies on the ecology of Carybdea marsupialis (Cubozoa) and jellyfish sting risk management

Programa LIFE Comisión Europea (LIFE NAT 080064 CUBOMED; Ministerio de Agricultura, Alimentación y Medio Ambiente; Fundación Biodiversidad; Dirección General del Agua, Generalitat Valenciana; Fundació Baleària; El Portet de Denia.

Evaluating the Effectiveness of Post Fire Emergency Rehabilitation Treatments on Soil Degradation and Erosion Control in Semi-Arid Mediterranean Areas of the Spanish South East

In this study, we seeded a native plant species and applied a mulch of chopped wood originating from the same burned area to avoid the establishment of invasive species. We evaluated four treatments: (1) seeding, (2) mulch, (3) seeding and mulch, and (4) control. Our objective was to increase plant recovery and to minimize the soil erosion and degradation. The study was conducted in Alicante, Spain in Torremanzanas forest of the semi-arid Mediterranean bioclimatic area after the wildfire of November, 2002. During three years of monitoring, we find that combined treatment: seeding and mulch increased the post fire plant recovery 20% approximately more than the rest of treatments and the control plots. We also found that seven months after treating mulch and seeding and mulch treatments presented a gain of soil: +5.18 to + 5.24 mm while the seeding treatment and control plots presented soil loss rates of: −0.48 to −0.49 mm. In addition, mulch treatment significantly decreased soil compaction to the half, and increased the infiltration capacity to 40 ml.mn−1 more than in plots without mulch, as well as increased the soil respiration to the double compared with no mulch plots. Work in progress confirms the positive effect of chopped wood as mulching treatment with or without seeding on the soil protection against soil erosion, and the amelioration of bio-physical properties after wildfires in the Mediterranean semi-arid burned areas.

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.