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.

Study of recycled Rap and Ra as alternative aggregates for pavements' sub-base and base

Nowadays, an important world’s population growth forecast establish that an increase of 2 billion people is expected by 2050. (UN,2019). This increment of people worldwide involves more humans, as well as growth of the demand for the construction of new residential, institutional, industrial, and infrastructural areas, prompting to a higher consumption of natural resources as required for construction materials. In addition, an effect of this population growth is the production and accumulation of waste causing a serious environmental and economic issue around the world. As an alternative to just producing more waste at the final stage of a building, house, road, among other concrete-based structures, adequate techniques must be applied for recycling and reusing these potential materials. The main priority of the thesis is to foment and evaluate the sustainable construction work leading to environmental-friendly actions that promote the reuse and recycling of construction waste, focusing on the use of construction recycled construction materials as an alternative for sub-base and base of road structure application. This thesis is committed to the analysis of the several laboratory tests carried out for achieving the physical-mechanical properties of the studied materials (recycled concrete aggregates + reclaimed asphalt pavement (RCA+RAP) and stabilized crushed sleepers). All these tests have been carried out in the Laboratory of Roads from the University of Bologna and in the experimental site in CAR srl., at Imola. The results are reported in tables, graphs, and are discussed. The mechanical properties values obtained from the laboratory tests are analysed and compared with standard values declared in the Italian and European normative for roads construction and to the results obtained from in-situ tests in the experimentation field (CAR srl in Imola) with the same materials. This to analyse the performance of them under natural conditions.

Introducing CHIMeRA: from the development of a comprehensive biomedical database to the analysis of its sub-components.

In this thesis we discuss the expansion of an existing project, called CHIMeRA, which is a comprehensive biomedical network, and the analysis of its sub-components by using graph theory. We describe how it is structured internally, what are the existing databases from which it retrieves information and what machine learning techniques are used in order to produce new knowledge. We also introduce a new technique for graph exploration that is aimed to speed-up the network cover time under the condition that the analyzed graph is stellar; if this condition is satisfied, the improvement in the performance compared to the conventional exploration technique is extremely appealing. We show that the stellar structure is highly recurrent for sub-networks in CHIMeRA generated by queries, which made this technique even more interesting. Finally, we describe the convenience in using the CHIMeRA network for research purposes and what it could become in a very near future.