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.

Collection and real-time analysis of images from aircraft to support civil protection operational activities

This report describes the realization of a system, in which an object detection model will be implemented, whose aim is to detect the presence of people in images. This system could be used for several applications: for example, it could be carried on board an aircraft or a drone. In this case, the system is designed in such a way that it can be mounted on light/medium weight helicopters, helping the operator to find people in emergency situations. In the first chapter the use of helicopters for civil protection is analysed and applications similar to this case study are listed. The second chapter describes the choice of the hardware devices that have been used to implement a prototype of a system to collect, analyse and display images. At first, the PC necessary to process the images was chosen, based on the characteristics of the algorithms that are necessary to run the analysis. In the further, a camera that could be compatible with the PC was selected. Finally, the battery pack was chosen taking into account the electrical consumption of the devices. The third chapter illustrates the algorithms used for image analysis. In the fourth, some of the requirements listed in the regulations that must be taken into account for carrying on board all the devices have been briefly analysed. In the fifth chapter the activity of design and modelling, with the CAD Solidworks, the devices and a prototype of a case that will house them is described. The sixth chapter discusses the additive manufacturing, since the case was printed exploiting this technology. In the seventh chapter, part of the tests that must be carried out on the equipment to certificate it have been analysed, and some simulations have been carried out. In the eighth chapter the results obtained once loaded the object detection model on a hardware for image analyses were showed. In the ninth chapter, conclusions and future applications were discussed.

Machine learning and convolutional neural networks for melanomas identification

Il machine learning negli ultimi anni ha acquisito una crescente popolarità nell’ambito della ricerca scientifica e delle sue applicazioni. Lo scopo di questa tesi è stato quello di studiare il machine learning nei suoi aspetti generali e applicarlo a problemi di computer vision. La tesi ha affrontato le difficoltà del dover spiegare dal punto di vista teorico gli algoritmi alla base delle reti neurali convoluzionali e ha successivamente trattato due problemi concreti di riconoscimento immagini: il dataset MNIST (immagini di cifre scritte a mano) e un dataset che sarà chiamato ”MELANOMA dataset” (immagini di melanomi e nevi sani). Utilizzando le tecniche spiegate nella sezione teorica si sono riusciti ad ottenere risultati soddifacenti per entrambi i dataset ottenendo una precisione del 98% per il MNIST e del 76.8% per il MELANOMA dataset

Neural Radiance Fields for Relighting and View Synthesis

Neural scene representation and neural rendering are new computer vision techniques that enable the reconstruction and implicit representation of real 3D scenes from a set of 2D captured images, by fitting a deep neural network. The trained network can then be used to render novel views of the scene. A recent work in this field, Neural Radiance Fields (NeRF), presented a state-of-the-art approach, which uses a simple Multilayer Perceptron (MLP) to generate photo-realistic RGB images of a scene from arbitrary viewpoints. However, NeRF does not model any light interaction with the fitted scene; therefore, despite producing compelling results for the view synthesis task, it does not provide a solution for relighting. In this work, we propose a new architecture to enable relighting capabilities in NeRF-based representations and we introduce a new real-world dataset to train and evaluate such a model. Our method demonstrates the ability to perform realistic rendering of novel views under arbitrary lighting conditions.

Miglioramento della qualità di algoritmi di face morphing generation

L'obiettivo principale di questo lavoro di tesi è quello di migliorare gli algoritmi di morphing generation in termini di qualità visiva e di potenzialità di attacco dei sistemi automatici di riconoscimento facciale.

Generative Neural Networks for image iper-resolution and improvement of Optical Character Recognition's performances

The usage of Optical Character Recognition’s (OCR, systems is a widely spread technology into the world of Computer Vision and Machine Learning. It is a topic that interest many field, for example the automotive, where becomes a specialized task known as License Plate Recognition, useful for many application from the automation of toll road to intelligent payments. However, OCR systems need to be very accurate and generalizable in order to be able to extract the text of license plates under high variable conditions, from the type of camera used for acquisition to light changes. Such variables compromise the quality of digitalized real scenes causing the presence of noise and degradation of various type, which can be minimized with the application of modern approaches for image iper resolution and noise reduction. Oneclass of them is known as Generative Neural Networks, which are very strong ally for the solution of this popular problem.

Antibody-Antigen Interface Characterization with Contextualized Pre-trained Embeddings

Artificial Intelligence (AI) has substantially influenced numerous disciplines in recent years. Biology, chemistry, and bioinformatics are among them, with significant advances in protein structure prediction, paratope prediction, protein-protein interactions (PPIs), and antibody-antigen interactions. Understanding PPIs is critical since they are responsible for practically everything living and have several uses in vaccines, cancer, immunology, and inflammatory illnesses. Machine Learning (ML) offers enormous potential for effectively simulating antibody-antigen interactions and improving in-silico optimization of therapeutic antibodies for desired features, including binding activity, stability, and low immunogenicity. This research looks at the use of AI algorithms to better understand antibody-antigen interactions, and it further expands and explains several difficulties encountered in the field. Furthermore, we contribute by presenting a method that outperforms existing state-of-the-art strategies in paratope prediction from sequence data.

Robotic grasping: State of the art and modular real-world implementation

Robotic Grasping is an important research topic in robotics since for robots to attain more general-purpose utility, grasping is a necessary skill, but very challenging to master. In general the robots may use their perception abilities like an image from a camera to identify grasps for a given object usually unknown. A grasp describes how a robotic end-effector need to be positioned to securely grab an object and successfully lift it without lost it, at the moment state of the arts solutions are still far behind humans. In the last 5–10 years, deep learning methods take the scene to overcome classical problem like the arduous and time-consuming approach to form a task-specific algorithm analytically. In this thesis are present the progress and the approaches in the robotic grasping field and the potential of the deep learning methods in robotic grasping. Based on that, an implementation of a Convolutional Neural Network (CNN) as a starting point for generation of a grasp pose from camera view has been implemented inside a ROS environment. The developed technologies have been integrated into a pick-and-place application for a Panda robot from Franka Emika. The application includes various features related to object detection and selection. Additionally, the features have been kept as generic as possible to allow for easy replacement or removal if needed, without losing time for improvement or new testing.

Intelligent automatic overtaking system using vision for vehicle detection

There is clear evidence that investment in intelligent transportation system technologies brings major social and economic benefits. Technological advances in the area of automatic systems in particular are becoming vital for the reduction of road deaths. We here describe our approach to automation of one the riskiest autonomous manœuvres involving vehicles – overtaking. The approach is based on a stereo vision system responsible for detecting any preceding vehicle and triggering the autonomous overtaking manœuvre. To this end, a fuzzy-logic based controller was developed to emulate how humans overtake. Its input is information from the vision system and from a positioning-based system consisting of a differential global positioning system (DGPS) and an inertial measurement unit (IMU). Its output is the generation of action on the vehicle’s actuators, i.e., the steering wheel and throttle and brake pedals. The system has been incorporated into a commercial Citroën car and tested on the private driving circuit at the facilities of our research center, CAR, with different preceding vehicles – a motorbike, car, and truck – with encouraging results.

Combining human perception and geometric restrictions for automatic pedestrian detection

[EN]Automatic detection systems do not perform as well as human observers, even on simple detection tasks. A potential solution to this problem is training vision systems on appropriate regions of interests (ROIs), in contrast to training on predefined and arbitrarily selected regions. Here we focus on detecting pedestrians in static scenes. Our aim is to answer the following question: Can automatic vision systems for pedestrian detection be improved by training them on perceptually-defined ROIs?

Automatic sleep apnea detection and sleep classification using the ECG and the SpO2 signals

Dissertation for a Masters Degree in Computer and Electronic Engineering

Detection of purkinje images for automatic positioning of fixation target and interferometric measurements of anterior eye chamber

In cataract surgery, the eye’s natural lens is removed because it has gone opaque and doesn’t allow clear vision any longer. To maintain the eye’s optical power, a new artificial lens must be inserted. Called Intraocular Lens (IOL), it needs to be modelled in order to have the correct refractive power to substitute the natural lens. Calculating the refractive power of this substitution lens requires precise anterior eye chamber measurements. An interferometry equipment, the AC Master from Zeiss Meditec, AG, was in use for half a year to perform these measurements. A Low Coherence Interferometry (LCI) measurement beam is aligned with the eye’s optical axis, for precise measurements of anterior eye chamber distances. The eye follows a fixation target in order to make the visual axis align with the optical axis. Performance problems occurred, however, at this step. Therefore, there was a necessity to develop a new procedure that ensures better alignment between the eye’s visual and optical axes, allowing a more user friendly and versatile procedure, and eventually automatizing the whole process. With this instrument, the alignment between the eye’s optical and visual axes is detected when Purkinje reflections I and III are overlapped, as the eye follows a fixation target. In this project, image analysis is used to detect these Purkinje reflections’ positions, eventually automatically detecting when they overlap. Automatic detection of the third Purkinje reflection of an eye following a fixation target is possible with some restrictions. Each pair of detected third Purkinje reflections is used in automatically calculating an acceptable starting position for the fixation target, required for precise measurements of anterior eye chamber distances.

Automatic eye blink detection using consumer web cameras

This research aims to advance blinking detection in the context of work activity. Rather than patients having to attend a clinic, blinking videos can be acquired in a work environment, and further automatically analyzed. Therefore, this paper presents a methodology to perform the automatic detection of eye blink using consumer videos acquired with low-cost web cameras. This methodology includes the detection of the face and eyes of the recorded person, and then it analyzes the low-level features of the eye region to create a quantitative vector. Finally, this vector is classified into one of the two categories considered —open and closed eyes— by using machine learning algorithms. The effectiveness of the proposed methodology was demonstrated since it provides unbiased results with classification errors under 5%

An approach to vision-based station keeping for an unmanned underwater vehicle

This paper presents an automatic vision-based system for UUV station keeping. The vehicle is equipped with a down-looking camera, which provides images of the sea-floor. The station keeping system is based on a feature-based motion detection algorithm, which exploits standard correlation and explicit textural analysis to solve the correspondence problem. A visual map of the area surveyed by the vehicle is constructed to increase the flexibility of the system, allowing the vehicle to position itself when it has lost the reference image. The testing platform is the URIS underwater vehicle. Experimental results demonstrating the behavior of the system on a real environment are presented