Plane detection from monocular image sequences

AIRES, Kelson R. T. ; ARAÚJO, Hélder J. ; MEDEIROS, Adelardo A. D. . Plane Detection from Monocular Image Sequences. In: VISUALIZATION, IMAGING AND IMAGE PROCESSING, 2008, Palma de Mallorca, Spain. Proceedings..., Palma de Mallorca: VIIP, 2008

Plane Detection Using Affine Homography

AIRES, Kelson R. T.; ARAÚJO, Hélder J.; MEDEIROS, Adelardo A. D. Plane Detection Using Affine Homography. In: CONGRESSO BRASILEIRO DE AUTOMÁTICA, 2008, Juiz de Fora, MG: Anais... do CBA 2008.

Homography-based ground plane detection using a single on-board camera

This study presents a robust method for ground plane detection in vision-based systems with a non-stationary camera. The proposed method is based on the reliable estimation of the homography between ground planes in successive images. This homography is computed using a feature matching approach, which in contrast to classical approaches to on-board motion estimation does not require explicit ego-motion calculation. As opposed to it, a novel homography calculation method based on a linear estimation framework is presented. This framework provides predictions of the ground plane transformation matrix that are dynamically updated with new measurements. The method is specially suited for challenging environments, in particular traffic scenarios, in which the information is scarce and the homography computed from the images is usually inaccurate or erroneous. The proposed estimation framework is able to remove erroneous measurements and to correct those that are inaccurate, hence producing a reliable homography estimate at each instant. It is based on the evaluation of the difference between the predicted and the observed transformations, measured according to the spectral norm of the associated matrix of differences. Moreover, an example is provided on how to use the information extracted from ground plane estimation to achieve object detection and tracking. The method has been successfully demonstrated for the detection of moving vehicles in traffic environments.

Plane detection from monocular image sequences

AIRES, Kelson R. T. ; ARAÚJO, Hélder J. ; MEDEIROS, Adelardo A. D. . Plane Detection from Monocular Image Sequences. In: VISUALIZATION, IMAGING AND IMAGE PROCESSING, 2008, Palma de Mallorca, Spain. Proceedings..., Palma de Mallorca: VIIP, 2008

Plane Detection Using Affine Homography

AIRES, Kelson R. T.; ARAÚJO, Hélder J.; MEDEIROS, Adelardo A. D. Plane Detection Using Affine Homography. In: CONGRESSO BRASILEIRO DE AUTOMÁTICA, 2008, Juiz de Fora, MG: Anais... do CBA 2008.

Plane detection from monocular image sequences

AIRES, Kelson R. T. ; ARAÚJO, Hélder J. ; MEDEIROS, Adelardo A. D. . Plane Detection from Monocular Image Sequences. In: VISUALIZATION, IMAGING AND IMAGE PROCESSING, 2008, Palma de Mallorca, Spain. Proceedings..., Palma de Mallorca: VIIP, 2008

Plane Detection Using Affine Homography

AIRES, Kelson R. T.; ARAÚJO, Hélder J.; MEDEIROS, Adelardo A. D. Plane Detection Using Affine Homography. In: CONGRESSO BRASILEIRO DE AUTOMÁTICA, 2008, Juiz de Fora, MG: Anais... do CBA 2008.

Sperimentazione con algoritmi per l'analisi di nuvole di punti per applicazioni di guida autonoma

Al giorno d’oggi quasi tutte le persone possiedono un mezzo motorizzato che utilizzano per spostarsi. Tale operazione, che risulta semplice per una persona, può essere compiuta da un robot o un autoveicolo in modo autonomo? La risposta a questa domanda è si, ma se ad una persona serve solo un po’ di pratica per guidare, questa azione non risulta altrettanto immediata per dei veicoli motorizzati. In soccorso ad essi vi è la Computer Vision, un ramo dell’informatica che, in un certo senso, rende un elaboratore elettronico in grado di percepire l’ambiente circostante, nel modo in cui una persona fa con i propri occhi. Oggi ci concentreremo su due campi della computer vision, lo SLAM o Simultaneous Localization and Mapping, che rende un robot in grado di mappare, attraverso una camera, il mondo in cui si trova ed allo stesso tempo di localizzare, istante per istante, la propria posizione all’interno di esso, e la Plane Detection, che permette di estrapolare i piani presenti all’interno di una data immagine.

A deep learning-based approach for 3D people tracking

Questa tesi si occupa dell’estensione di un framework software finalizzato all'individuazione e al tracciamento di persone in una scena ripresa da telecamera stereoscopica. In primo luogo è rimossa la necessità di una calibrazione manuale offline del sistema sfruttando algoritmi che consentono di individuare, a partire da un fotogramma acquisito dalla camera, il piano su cui i soggetti tracciati si muovono. Inoltre, è introdotto un modulo software basato su deep learning con lo scopo di migliorare la precisione del tracciamento. Questo componente, che è in grado di individuare le teste presenti in un fotogramma, consente ridurre i dati analizzati al solo intorno della posizione effettiva di una persona, escludendo oggetti che l’algoritmo di tracciamento sarebbe portato a individuare come persone.

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.

Holographic optical tweezers combined with back-focal-plane displacement detection

A major problem with holographic optical tweezers (HOTs) is their incompatibility with laser-based position detection methods, such as back-focal-plane interferometry (BFPI). The alternatives generally used with HOTs, like high-speed video tracking, do not offer the same spatial and temporal bandwidths. This has limited the use of this technique in precise quantitative experiments. In this paper, we present an optical trap design that combines digital holography and back-focal-plane displacement detection. We show that, with a particularly simple setup, it is possible to generate a set of multiple holographic traps and an additional static non-holographic trap with orthogonal polarizations and that they can be, therefore, easily separated for measuring positions and forces with the high positional and temporal resolutions of laser-based detection. We prove that measurements from both polarizations contain less than 1% crosstalk and that traps in our setup are harmonic within the typical range. We further tested the instrument in a DNA stretching experiment and we discuss an interesting property of this configuration: the small drift of the differential signal between traps.

Detection of high-velocity material from the wind-wind collision zone of Eta Carinae across the 2009.0 periastron passage

We report near-infrared spectroscopic observations of the Eta Carinae massive binary system during 2008-2009 using the CRIRES spectrograph mounted on the 8m UT 1 Very Large Telescope (VLT Antu). We detect a strong, broad absorption wing in He I lambda 10833 extending up to -1900 km s(-1) across the 2009.0 spectroscopic event. Analysis of archival Hubble Space Telescope/Space Telescope Imaging Spectrograph ultraviolet and optical data identifies a similar high-velocity absorption (up to -2100 km s(-1)) in the ultraviolet resonance lines of Si IV lambda lambda 1394, 1403 across the 2003.5 event. Ultraviolet resonance lines from low-ionization species, such as Si II lambda lambda 1527, 1533 and CII lambda lambda 1334, 1335, show absorption only up to -1200 km s(-1), indicating that the absorption with velocities -1200 to -2100 km s(-1) originates in a region markedly more rapidly moving and more ionized than the nominal wind of the primary star. Seeing-limited observations obtained at the 1.6m OPD/LNA telescope during the last four spectroscopic cycles of Eta Carinae (1989-2009) also show high-velocity absorption in He I lambda 10833 during periastron. Based on the large OPD/LNA dataset, we determine that material with velocities more negative than -900 km s(-1) is present in the phase range 0.976 <= phi <= 1.023 of the spectroscopic cycle, but absent in spectra taken at phi <= 0.947 and phi >= 1.049. Therefore, we constrain the duration of the high-velocity absorption to be 95 to 206 days (or 0.047 to 0.102 in phase). We propose that the high-velocity absorption component originates in shocked gas in the wind-wind collision zone, at distances of 15 to 45 AU in the line-of-sight to the primary star. With the aid of three-dimensional hydrodynamical simulations of the wind-wind collision zone, we find that the dense high-velocity gas is along the line-of-sight to the primary star only if the binary system is oriented in the sky such that the companion is behind the primary star during periastron, corresponding to a longitude of periastron of omega similar to 240 degrees-270 degrees. We study a possible tilt of the orbital plane relative to the Homunculus equatorial plane and conclude that our data are broadly consistent with orbital inclinations in the range i = 40 degrees-60 degrees.

LADAR based mapping and obstacle detection system for service robots

Dissertação apresentada na Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa para a obtenção do grau de Mestre em Engenharia Electrotécnica e de Computadores

Correlation postprocessing-based method for the detection of de focused images

We present a method to detect patterns in defocused scenes by means of a joint transform correlator. We describe analytically the correlation plane, and we also introduce an original procedure to recognize the target by postprocessing the correlation plane. The performance of the methodology when the defocused images are corrupted by additive noise is also considered.