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.

Reversible holographic 3D data storage in oxide glasses using visible lasers

Antimony based glasses have been investigated for the first time regarding the possibility of holographic data storage using visible lasers sources. Changes in both refractive index and the absorption coefficient were measured using a holographic setup. The modulation of the optical constants is reversible by heat treatment. Bragg gratings were written under visible light of an Ar laser and erased thermally.

VIRTOPSY--scientific documentation, reconstruction and animation in forensic: individual and real 3D data based geo-metric approach including optical body/object surface and radiological CT/MRI scanning.

Until today, most of the documentation of forensic relevant medical findings is limited to traditional 2D photography, 2D conventional radiographs, sketches and verbal description. There are still some limitations of the classic documentation in forensic science especially if a 3D documentation is necessary. The goal of this paper is to demonstrate new 3D real data based geo-metric technology approaches. This paper present approaches to a 3D geo-metric documentation of injuries on the body surface and internal injuries in the living and deceased cases. Using modern imaging methods such as photogrammetry, optical surface and radiological CT/MRI scanning in combination it could be demonstrated that a real, full 3D data based individual documentation of the body surface and internal structures is possible in a non-invasive and non-destructive manner. Using the data merging/fusing and animation possibilities, it is possible to answer reconstructive questions of the dynamic development of patterned injuries (morphologic imprints) and to evaluate the possibility, that they are matchable or linkable to suspected injury-causing instruments. For the first time, to our knowledge, the method of optical and radiological 3D scanning was used to document the forensic relevant injuries of human body in combination with vehicle damages. By this complementary documentation approach, individual forensic real data based analysis and animation were possible linking body injuries to vehicle deformations or damages. These data allow conclusions to be drawn for automobile accident research, optimization of vehicle safety (pedestrian and passenger) and for further development of crash dummies. Real 3D data based documentation opens a new horizon for scientific reconstruction and animation by bringing added value and a real quality improvement in forensic science.

A robust and fast method for 6DoF motion estimation from generalized 3D data

Nowadays, there is an increasing number of robotic applications that need to act in real three-dimensional (3D) scenarios. In this paper we present a new mobile robotics orientated 3D registration method that improves previous Iterative Closest Points based solutions both in speed and accuracy. As an initial step, we perform a low cost computational method to obtain descriptions for 3D scenes planar surfaces. Then, from these descriptions we apply a force system in order to compute accurately and efficiently a six degrees of freedom egomotion. We describe the basis of our approach and demonstrate its validity with several experiments using different kinds of 3D sensors and different 3D real environments.

Analysis of Local Search Methods for 3D Data

In questa tesi sono stati analizzati alcuni metodi di ricerca per dati 3D. Viene illustrata una panoramica generale sul campo della Computer Vision, sullo stato dell’arte dei sensori per l’acquisizione e su alcuni dei formati utilizzati per la descrizione di dati 3D. In seguito è stato fatto un approfondimento sulla 3D Object Recognition dove, oltre ad essere descritto l’intero processo di matching tra Local Features, è stata fatta una focalizzazione sulla fase di detection dei punti salienti. In particolare è stato analizzato un Learned Keypoint detector, basato su tecniche di apprendimento di machine learning. Quest ultimo viene illustrato con l’implementazione di due algoritmi di ricerca di vicini: uno esauriente (K-d tree) e uno approssimato (Radial Search). Sono state riportate infine alcune valutazioni sperimentali in termini di efficienza e velocità del detector implementato con diversi metodi di ricerca, mostrando l’effettivo miglioramento di performance senza una considerabile perdita di accuratezza con la ricerca approssimata.

A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional 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. It is proposed 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). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.

Improving 3D Keypoint Detection from Noisy Data Using Growing Neural Gas

3D sensors provides valuable information for mobile robotic tasks like scene classification or object recognition, but these sensors often produce noisy data that makes impossible applying classical keypoint detection and feature extraction techniques. Therefore, noise removal and downsampling have become essential steps in 3D data processing. In this work, we propose the use of a 3D filtering and down-sampling technique based on a Growing Neural Gas (GNG) network. GNG method is able to deal with outliers presents in the input data. These features allows to represent 3D spaces, obtaining an induced Delaunay Triangulation of the input space. Experiments show how the state-of-the-art keypoint detectors improve their performance using GNG output representation as input data. Descriptors extracted on improved keypoints perform better matching in robotics applications as 3D scene registration.

Automated 3D Lumbar Intervertebral Disc Segmentation from MRI Data Sets

This paper proposed an automated three-dimensional (3D) lumbar intervertebral disc (IVD) segmentation strategy from Magnetic Resonance Imaging (MRI) data. Starting from two user supplied landmarks, the geometrical parameters of all lumbar vertebral bodies and intervertebral discs are automatically extracted from a mid-sagittal slice using a graphical model based template matching approach. Based on the estimated two-dimensional (2D) geometrical parameters, a 3D variable-radius soft tube model of the lumbar spine column is built by model fitting to the 3D data volume. Taking the geometrical information from the 3D lumbar spine column as constraints and segmentation initialization, the disc segmentation is achieved by a multi-kernel diffeomorphic registration between a 3D template of the disc and the observed MRI data. Experiments on 15 patient data sets showed the robustness and the accuracy of the proposed algorithm.

Pre-processing for noise detection in gene expression classification data

Due to the imprecise nature of biological experiments, biological data is often characterized by the presence of redundant and noisy data. This may be due to errors that occurred during data collection, such as contaminations in laboratorial samples. It is the case of gene expression data, where the equipments and tools currently used frequently produce noisy biological data. Machine Learning algorithms have been successfully used in gene expression data analysis. Although many Machine Learning algorithms can deal with noise, detecting and removing noisy instances from the training data set can help the induction of the target hypothesis. This paper evaluates the use of distance-based pre-processing techniques for noise detection in gene expression data classification problems. This evaluation analyzes the effectiveness of the techniques investigated in removing noisy data, measured by the accuracy obtained by different Machine Learning classifiers over the pre-processed data.

Design and implementation of 3D buildings integration for a Webgl-Based Virtual Globe: a case study of Valencian Cadastre and Fide Building Mode

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Overview of coded light projection techniques for automatic 3D profiling

Obtaining automatic 3D profile of objects is one of the most important issues in computer vision. With this information, a large number of applications become feasible: from visual inspection of industrial parts to 3D reconstruction of the environment for mobile robots. In order to achieve 3D data, range finders can be used. Coded structured light approach is one of the most widely used techniques to retrieve 3D information of an unknown surface. An overview of the existing techniques as well as a new classification of patterns for structured light sensors is presented. This kind of systems belong to the group of active triangulation method, which are based on projecting a light pattern and imaging the illuminated scene from one or more points of view. Since the patterns are coded, correspondences between points of the image(s) and points of the projected pattern can be easily found. Once correspondences are found, a classical triangulation strategy between camera(s) and projector device leads to the reconstruction of the surface. Advantages and constraints of the different patterns are discussed

Evolution of a debris flow channel monitored using a 3D terrestrial laser scanner

Like numerous torrents in mountainous regions, the Illgraben creek (canton of Wallis, SW Switzerland) produces almost every year several debris flows. The total area of the active catchment is only 4.7 km², but large events ranging from 50'000 to 400'000 m³ are common (Zimmermann 2000). Consequently, the pathway of the main channel often changes suddenly. One single event can for instance fill the whole river bed and dig new several-meters-deep channels somewhere else (Bardou et al. 2003). The quantification of both, the rhythm and the magnitude of these changes, is very important to assess the variability of the bed's cross section and long profile. These parameters are indispensable for numerical modelling, as they should be considered as initial conditions. To monitor the channel evolution an Optech ILRIS 3D terrestrial laser scanner (LIDAR) was used. LIDAR permits to make a complete high precision 3D model of the channel and its surroundings by scanning it from different view points. The 3D data are treated and interpreted with the software Polyworks from Innovmetric Software Inc. Sequential 3D models allow for the determination of the variation in the bed's cross section and long profile. These data will afterwards be used to quantify the erosion and the deposition in the torrent reaches. To complete the chronological evolution of the landforms, precise digital terrain models, obtained by high resolution photogrammetry based on old aerial photographs, will be used. A 500 m long section of the Illgraben channel was scanned on 18th of August 2005 and on 7th of April 2006. These two data sets permit identifying the changes of the channel that occurred during the winter season. An upcoming scanning campaign in September 2006 will allow for the determination of the changes during this summer. Preliminary results show huge variations in the pathway of the Illgraben channel, as well as important vertical and lateral erosion of the river bed. Here we present the results of a river bank on the left (north-western) flank of the channel (Figure 1). For the August 2005 model the scans from 3 viewpoints were superposed, whereas the April 2006 3D image was obtained by combining 5 separate scans. The bank was eroded. The bank got eroded essentially on its left part (up to 6.3 m), where it is hit by the river and the debris flows (Figures 2 and 3). A debris cone has also formed (Figure 3), which suggests that a part of the bank erosion is due to shallow landslides. They probably occur when the river erosion creates an undercut slope. These geometrical data allow for the monitoring of the alluvial dynamics (i.e. aggradation and degradation) on different time scales and the influence of debris flows occurrence on these changes. Finally, the resistance against erosion of the bed's cross section and long profile will be analysed to assess the variability of these two key parameters. This information may then be used in debris flow simulation.

Quantitative analysis of crystal/grain sizes and their distributions in 2D and 3D

We review methods to estimate the average crystal (grain) size and the crystal (grain) size distribution in solid rocks. Average grain sizes often provide the base for stress estimates or rheological calculations requiring the quantification of grain sizes in a rock's microstructure. The primary data for grain size data are either 1D (i.e. line intercept methods), 2D (area analysis) or 3D (e.g., computed tomography, serial sectioning). These data have been used for different data treatments over the years, whereas several studies assume a certain probability function (e.g., logarithm, square root) to calculate statistical parameters as the mean, median, mode or the skewness of a crystal size distribution. The finally calculated average grain sizes have to be compatible between the different grain size estimation approaches in order to be properly applied, for example, in paleo-piezometers or grain size sensitive flow laws. Such compatibility is tested for different data treatments using one- and two-dimensional measurements. We propose an empirical conversion matrix for different datasets. These conversion factors provide the option to make different datasets compatible with each other, although the primary calculations were obtained in different ways. In order to present an average grain size, we propose to use the area-weighted and volume-weighted mean in the case of unimodal grain size distributions, respectively, for 2D and 3D measurements. The shape of the crystal size distribution is important for studies of nucleation and growth of minerals. The shape of the crystal size distribution of garnet populations is compared between different 2D and 3D measurements, which are serial sectioning and computed tomography. The comparison of different direct measured 3D data; stereological data and direct presented 20 data show the problems of the quality of the smallest grain sizes and the overestimation of small grain sizes in stereological tools, depending on the type of CSD. (C) 2011 Published by Elsevier Ltd.