Aerial video geo-registration using terrain models from dense and coherent stereo matching

In the context of aerial imagery, one of the first steps toward a coherent processing of the information contained in multiple images is geo-registration, which consists in assigning geographic 3D coordinates to the pixels of the image. This enables accurate alignment and geo-positioning of multiple images, detection of moving objects and fusion of data acquired from multiple sensors. To solve this problem there are different approaches that require, in addition to a precise characterization of the camera sensor, high resolution referenced images or terrain elevation models, which are usually not publicly available or out of date. Building upon the idea of developing technology that does not need a reference terrain elevation model, we propose a geo-registration technique that applies variational methods to obtain a dense and coherent surface elevation model that is used to replace the reference model. The surface elevation model is built by interpolation of scattered 3D points, which are obtained in a two-step process following a classical stereo pipeline: first, coherent disparity maps between image pairs of a video sequence are estimated and then image point correspondences are back-projected. The proposed variational method enforces continuity of the disparity map not only along epipolar lines (as done by previous geo-registration techniques) but also across them, in the full 2D image domain. In the experiments, aerial images from synthetic video sequences have been used to validate the proposed technique.

Fast stereo matching by iterated dynamic programming and quadtree subregioning

The application of energy minimisation methods for stereo matching has been demonstrated to produce high quality disparity maps. However the majority of these methods are known to be computationally expensive, requiring minutes or even hours of computation. We propose a fast minimisation scheme that produces strongly competitive results for significantly reduced computation, requiring only a few seconds of computation. In this paper, we present our iterated dynamic programming algorithm along with a quadtree subregioning process for fast stereo matching.

Mitigating non-Lambertian surfaces issues in Stereo Matching with Neural Radiance Fields

Depth estimation from images has long been regarded as a preferable alternative compared to expensive and intrusive active sensors, such as LiDAR and ToF. The topic has attracted the attention of an increasingly wide audience thanks to the great amount of application domains, such as autonomous driving, robotic navigation and 3D reconstruction. Among the various techniques employed for depth estimation, stereo matching is one of the most widespread, owing to its robustness, speed and simplicity in setup. Recent developments has been aided by the abundance of annotated stereo images, which granted to deep learning the opportunity to thrive in a research area where deep networks can reach state-of-the-art sub-pixel precision in most cases. Despite the recent findings, stereo matching still begets many open challenges, two among them being finding pixel correspondences in presence of objects that exhibits a non-Lambertian behaviour and processing high-resolution images. Recently, a novel dataset named Booster, which contains high-resolution stereo pairs featuring a large collection of labeled non-Lambertian objects, has been released. The work shown that training state-of-the-art deep neural network on such data improves the generalization capabilities of these networks also in presence of non-Lambertian surfaces. Regardless being a further step to tackle the aforementioned challenge, Booster includes a rather small number of annotated images, and thus cannot satisfy the intensive training requirements of deep learning. This thesis work aims to investigate novel view synthesis techniques to augment the Booster dataset, with ultimate goal of improving stereo matching reliability in presence of high-resolution images that displays non-Lambertian surfaces.

Stereo matching su GPU

La Stereo Vision è un popolare argomento di ricerca nel campo della Visione Artificiale; esso consiste nell’usare due immagini di una stessa scena,prodotte da due fotocamere diverse, per estrarre informazioni in 3D. L’idea di base della Stereo Vision è la simulazione della visione binoculare umana:le due fotocamere sono disposte in orizzontale per fungere da “occhi” che guardano la scena in 3D. Confrontando le due immagini ottenute, si possono ottenere informazioni riguardo alle posizioni degli oggetti della scena.In questa relazione presenteremo un algoritmo di Stereo Vision: si tratta di un algoritmo parallelo che ha come obiettivo di tracciare le linee di livello di un area geografica. L’algoritmo in origine era stato implementato per la Connection Machine CM-2, un supercomputer sviluppato negli anni 80, ed era espresso in *Lisp, un linguaggio derivato dal Lisp e ideato per la macchina stessa. Questa relazione tratta anche la traduzione e l’implementazione dell’algoritmo in CUDA, ovvero un’architettura hardware per l’elaborazione pa- rallela sviluppata da NVIDIA, che consente di eseguire codice parallelo su GPU. Si darà inoltre uno sguardo alle difficoltà che sono state riscontrate nella traduzione da *Lisp a CUDA.

On precise three-dimensional environment modeling via UAV-based photogrammetric systems

Abstract : Images acquired from unmanned aerial vehicles (UAVs) can provide data with unprecedented spatial and temporal resolution for three-dimensional (3D) modeling. Solutions developed for this purpose are mainly operating based on photogrammetry concepts, namely UAV-Photogrammetry Systems (UAV-PS). Such systems are used in applications where both geospatial and visual information of the environment is required. These applications include, but are not limited to, natural resource management such as precision agriculture, military and police-related services such as traffic-law enforcement, precision engineering such as infrastructure inspection, and health services such as epidemic emergency management. UAV-photogrammetry systems can be differentiated based on their spatial characteristics in terms of accuracy and resolution. That is some applications, such as precision engineering, require high-resolution and high-accuracy information of the environment (e.g. 3D modeling with less than one centimeter accuracy and resolution). In other applications, lower levels of accuracy might be sufficient, (e.g. wildlife management needing few decimeters of resolution). However, even in those applications, the specific characteristics of UAV-PSs should be well considered in the steps of both system development and application in order to yield satisfying results. In this regard, this thesis presents a comprehensive review of the applications of unmanned aerial imagery, where the objective was to determine the challenges that remote-sensing applications of UAV systems currently face. This review also allowed recognizing the specific characteristics and requirements of UAV-PSs, which are mostly ignored or not thoroughly assessed in recent studies. Accordingly, the focus of the first part of this thesis is on exploring the methodological and experimental aspects of implementing a UAV-PS. The developed system was extensively evaluated for precise modeling of an open-pit gravel mine and performing volumetric-change measurements. This application was selected for two main reasons. Firstly, this case study provided a challenging environment for 3D modeling, in terms of scale changes, terrain relief variations as well as structure and texture diversities. Secondly, open-pit-mine monitoring demands high levels of accuracy, which justifies our efforts to improve the developed UAV-PS to its maximum capacities. The hardware of the system consisted of an electric-powered helicopter, a high-resolution digital camera, and an inertial navigation system. The software of the system included the in-house programs specifically designed for camera calibration, platform calibration, system integration, onboard data acquisition, flight planning and ground control point (GCP) detection. The detailed features of the system are discussed in the thesis, and solutions are proposed in order to enhance the system and its photogrammetric outputs. The accuracy of the results was evaluated under various mapping conditions, including direct georeferencing and indirect georeferencing with different numbers, distributions and types of ground control points. Additionally, the effects of imaging configuration and network stability on modeling accuracy were assessed. The second part of this thesis concentrates on improving the techniques of sparse and dense reconstruction. The proposed solutions are alternatives to traditional aerial photogrammetry techniques, properly adapted to specific characteristics of unmanned, low-altitude imagery. Firstly, a method was developed for robust sparse matching and epipolar-geometry estimation. The main achievement of this method was its capacity to handle a very high percentage of outliers (errors among corresponding points) with remarkable computational efficiency (compared to the state-of-the-art techniques). Secondly, a block bundle adjustment (BBA) strategy was proposed based on the integration of intrinsic camera calibration parameters as pseudo-observations to Gauss-Helmert model. The principal advantage of this strategy was controlling the adverse effect of unstable imaging networks and noisy image observations on the accuracy of self-calibration. The sparse implementation of this strategy was also performed, which allowed its application to data sets containing a lot of tie points. Finally, the concepts of intrinsic curves were revisited for dense stereo matching. The proposed technique could achieve a high level of accuracy and efficiency by searching only through a small fraction of the whole disparity search space as well as internally handling occlusions and matching ambiguities. These photogrammetric solutions were extensively tested using synthetic data, close-range images and the images acquired from the gravel-pit mine. Achieving absolute 3D mapping accuracy of 11±7 mm illustrated the success of this system for high-precision modeling of the environment.

Sharpness Matching in Stereo Images

When stereo images are captured under less than ideal conditions, there may be inconsistencies between the two images in brightness, contrast, blurring, etc. When stereo matching is performed between the images, these variations can greatly reduce the quality of the resulting depth map. In this paper we propose a method for correcting sharpness variations in stereo image pairs which is performed as a pre-processing step to stereo matching. Our method is based on scaling the 2D discrete cosine transform (DCT) coefficients of both images so that the two images have the same amount of energy in each of a set of frequency bands. Experiments show that applying the proposed correction method can greatly improve the disparity map quality when one image in a stereo pair is more blurred than the other.

Interocular suppression is gated by interocular feature matching

We present a new form of contrast masking in which the target is a patch of low spatial frequency grating (0.46 c/deg) and the mask is a dark thin ring that surrounds the centre of the target patch. In matching and detection experiments we found little or no effect for binocular presentation of mask and test stimuli. But when mask and test were presented briefly (33 or 200 ms) to different eyes (dichoptic presentation), masking was substantial. In a 'half-binocular' condition the test stimulus was presented to one eye, but the mask stimulus was presented to both eyes with zero-disparity. This produced masking effects intermediate to those found in dichoptic and full-binocular conditions. We suggest that interocular feature matching can attenuate the potency of interocular suppression, but unlike in previous work (McKee, S. P., Bravo, M. J., Taylor, D. G., & Legge, G. E. (1994) Stereo matching precedes dichoptic masking. Vision Research, 34, 1047) we do not invoke a special role for depth perception. © 2004 Elsevier Ltd. All rights reserved.

Sistema di visione stereo su architettura ZYNQ

Lo scopo della tesi è creare un’architettura in FPGA in grado di ricavare informazioni 3D da una coppia di sensori stereo. La pipeline è stata realizzata utilizzando il System-on-Chip Zynq, che permette una stretta interazione tra la parte hardware realizzata in FPGA e la CPU. Dopo uno studio preliminare degli strumenti hardware e software, è stata realizzata l’architettura base per la scrittura e la lettura di immagini nella memoria DDR dello Zynq. In seguito l’attenzione si è spostata sull’implementazione di algoritmi stereo (rettificazione e stereo matching) su FPGA e nella realizzazione di una pipeline in grado di ricavare accurate mappe di disparità in tempo reale acquisendo le immagini da una camera stereo.

Correspondência estéreo usando imagens em multiresolução com profundidade variável

We propose a multi-resolution, coarse-to-fine approach for stereo matching, where the first matching happens at a different depth for each pixel. The proposed technique has the potential of attenuating several problems faced by the constant depth algorithm, making it possible to reduce the number of errors or the number of comparations needed to get equivalent results. Several experiments were performed to demonstrate the method efficiency, including comparison with the traditional plain correlation technique, where the multi-resolution matching with variable depth, proposed here, generated better results with a smaller processing time

Uma proposição para o cálculo de mapas de disparidade de imagens estéreo usando um interpolador neural baseado em funções de base radial

This study aims to seek a more viable alternative for the calculation of differences in images of stereo vision, using a factor that reduces heel the amount of points that are considered on the captured image, and a network neural-based radial basis functions to interpolate the results. The objective to be achieved is to produce an approximate picture of disparities using algorithms with low computational cost, unlike the classical algorithms

Semi-automatic modeling of buildings from digital surface models

Semi-automatic building detection and extraction is a topic of growing interest due to its potential application in such areas as cadastral information systems, cartographic revision, and GIS. One of the existing strategies for building extraction is to use a digital surface model (DSM) represented by a cloud of known points on a visible surface, and comprising features such as trees or buildings. Conventional surface modeling using stereo-matching techniques has its drawbacks, the most obvious being the effect of building height on perspective, shadows, and occlusions. The laser scanner, a recently developed technological tool, can collect accurate DSMs with high spatial frequency. This paper presents a methodology for semi-automatic modeling of buildings which combines a region-growing algorithm with line-detection methods applied over the DSM.

Metodologie di apprendimento automatico applicate alla generazione di dati 3D

Il framework in oggetto, è un ambiente ideato con lo scopo di applicare tecniche di Machine Learning (in particolare le Random Forest) alle funzionalità dell'algoritmo di stereo matching SGM (Semi Global Matching), al fine di incrementarne l'accuratezza in versione standard. Scopo della presente tesi è quello di modificare alcune impostazioni di tale framework rendendolo un ambiente che meglio si adatti alla direzionalità delle scanline (introducendo finestre di supporto rettangolari e ortogonali e il training di foreste separate in base alla singola scanline) e ampliarne le funzionalità tramite l'aggiunta di alcune nuove feature, quali la distanza dal più vicino edge direzionale e la distintività calcolate sulle immagini Left della stereo pair e gli edge direzionali sulle mappe di disparità. Il fine ultimo sarà quello di eseguire svariati test sui dataset Middlebury 2014 e KITTI e raccogliere dati che descrivano l'andamento in positivo o negativo delle modifiche effettuate.

Desarrollo de un sistema de estimación de mapas de profundidad densos a partir de secuencias reales de vídeo 3D.

Este proyecto fín de carrera describe el desarrollo de un sistema de estimación de mapas de profundidad densos a partir de secuencias reales de vídeo 3D. Está motivado por la necesidad de utilizar la información de profundidad de un vídeo estéreo para calcular las oclusiones en el módulo de inserción de objetos sintéticos interactivos desarrollado en el proyecto ImmersiveTV. En el receptor 3DTV, el sistema debe procesar en tiempo real secuencias estéreo de escenas reales en alta resolución con formato Side-by-Side. Se analizan las características del contenido para conocer los problemas a enfrentar. Obtener un mapa de profundidad denso mediante correspondencia estéreo (stereo matching) permite calcular las oclusiones del objeto sintético con la escena. No es necesario que el valor de disparidad asignado a cada píxel sea preciso, basta con distinguir los distintos planos de profundidad ya que se trabaja con distancias relativas. La correspondencia estéreo exige que las dos vistas de entrada estén alineadas. Primero se comprueba si se deben rectificar y se realiza un repaso teórico de calibración y rectificación, resumiendo algunos métodos a considerar en la resolución del problema. Para estimar la profundidad, se revisan técnicas de correspondencia estéreo densa habituales, seleccionando un conjunto de implementaciones con el fin de valorar cuáles son adecuadas para resolver el problema, incluyendo técnicas locales, globales y semiglobales, algunas sobre CPU y otras para GPU; modificando algunas para soportar valores negativos de disparidad. No disponer de ground truth de los mapas de disparidad del contenido real supone un reto que obliga a buscar métodos indirectos de comparación de resultados. Para una evaluación objetiva, se han revisado trabajos relacionados con la comparación de técnicas de correspondencia y entornos de evaluación existentes. Se considera el mapa de disparidad como error de predicción entre vistas desplazadas. A partir de la vista derecha y la disparidad de cada píxel, puede reconstruirse la vista izquierda y, comparando la imagen reconstruida con la original, se calculan estadísticas de error y las tasas de píxeles con disparidad inválida y errónea. Además, hay que tener en cuenta la eficiencia de los algoritmos midiendo la tasa de cuadros por segundo que pueden procesar. Observando los resultados, atendiendo a los criterios de maximización de PSNR y minimización de la tasa de píxeles incorrectos, se puede elegir el algoritmo con mejor comportamiento. Como resultado, se ha implementado una herramienta que integra el sistema de estimación de mapas de disparidad y la utilidad de evaluación de resultados. Trabaja sobre una imagen, una secuencia o un vídeo estereoscópico. Para realizar la correspondencia, permite escoger entre un conjunto de algoritmos que han sido adaptados o modificados para soportar valores negativos de disparidad. Para la evaluación, se ha implementado la reconstrucción de la vista de referencia y la comparación con la original mediante el cálculo de la RMS y PSNR, como medidas de error, además de las tasas de píxeles inválidos e incorrectos y de la eficiencia en cuadros por segundo. Finalmente, se puede guardar las imágenes (o vídeos) generados como resultado, junto con un archivo de texto en formato csv con las estadísticas para su posterior comparación.

Dynamic breast MRI: Image registration and its impact on enhancement curve estimation

A novel algorithm for performing registration of dynamic contrast-enhanced (DCE) MRI data of the breast is presented. It is based on an algorithm known as iterated dynamic programming originally devised to solve the stereo matching problem. Using artificially distorted DCE-MRI breast images it is shown that the proposed algorithm is able to correct for movement and distortions over a larger range than is likely to occur during routine clinical examination. In addition, using a clinical DCE-MRI data set with an expertly labeled suspicious region, it is shown that the proposed algorithm significantly reduces the variability of the enhancement curves at the pixel level yielding more pronounced uptake and washout phases.

Il Vestibolo di Piazza d'Oro - Rilievi per la modellazione 3D ed il texturing

Il caso studio del vestibolo ottagonale di Villa Adriana ha dato la possibilità di applicare ad un edificio di notevole valore storico e artistico tecniche di restituzione digitale e di modellazione tridimensionale basate su applicativi di modellazione geometrica, con lo scopo di generarne il modello 3D digitale fotorealistico e polifunzionale. Nel caso specifico del vestibolo, un modello tridimensionale di questo tipo risulta utile a fini documentativi, a sostegno di ipotesi costruttive e come strumento per la valutazione di interventi di restauro. Il percorso intrapreso ha permesso di valutare le criticità nelle tecniche di acquisizione, modellazione e foto-modellazione tridimensionale applicate in ambito archeologico, tecniche usate abitualmente anche in settori quali l’architettura, il design industriale ma anche nel cinema (effetti speciali e film d’animazione) e in ambito videoludico, con obiettivi differenti: nel settore del design e della progettazione industriale il Reverse Modeling viene impiegato per eseguire controlli di qualità e rispetto delle tolleranze sul prodotto finale, mentre in ambito cinematografico e videoludico (in combinazione con altri software) permette la creazione di modelli realistici da inserire all’interno di film o videogiochi, (modelli non solo di oggetti ma anche di persone). La generazione di un modello tridimensionale ottenuto tramite Reverse Modeling è frutto di un processo opposto alla progettazione e può avvenire secondo diverse strategie, ognuna delle quali presenta vantaggi e svantaggi specifici che la rendono più indicata in alcuni casi piuttosto che in altri. In questo studio sono state analizzate acquisizioni tridimensionali effettuate tramite Laser Scan e tramite applicazioni Structure from Motion/Dense Stereo View.