Abstract: This paper presents a preliminary study on the registration and fusion of cross-spectral imaging. The objective is to evaluate the validity of widely used computer vision approaches when they are applied at different
spectral bands. In particular, we are interested in merging images from the infrared (both long wave infrared: LWIR and near infrared: NIR) and visible spectrum (VS). Experimental results with different data sets are presented.

Abstract: On-board pedestrian detection is crucial for Advanced Driver Assistance Systems
(ADAS). An accurate classication is fundamental for vision-based pedestrian detection.
The underlying assumption for learning classiers is that the training set and the deployment environment (testing) follow the same probability distribution regarding the features used by the classiers. However, in practice, there are dierent reasons that can break this constancy assumption. Accordingly, reusing existing classiers by adapting them from the previous training environment (source domain) to the new testing one (target domain) is an approach with increasing acceptance in the computer vision community. In this thesis we focus on the domain adaptation of deformable part-based models (DPMs) for pedestrian detection. As a prof of concept, we use a computer graphic based synthetic dataset, i.e. a virtual world, as the source domain, and adapt the virtual-world trained DPM detector to various real-world dataset.
We start by exploiting the maximum detection accuracy of the virtual-world
trained DPM. Even though, when operating in various real-world datasets, the virtualworld trained detector still suer from accuracy degradation due to the domain gap of virtual and real worlds. We then focus on domain adaptation of DPM. At the rst step, we consider single source and single target domain adaptation and propose two batch learning methods, namely A-SSVM and SA-SSVM. Later, we further consider leveraging multiple target (sub-)domains for progressive domain adaptation and propose a hierarchical adaptive structured SVM (HA-SSVM) for optimization. Finally, we extend HA-SSVM for the challenging online domain adaptation problem, aiming at making the detector to automatically adapt to the target domain online, without any human intervention. All of the proposed methods in this thesis do not require
revisiting source domain data. The evaluations are done on the Caltech pedestrian detection benchmark. Results show that SA-SSVM slightly outperforms A-SSVM and avoids accuracy drops as high as 15 points when comparing with a non-adapted detector. The hierarchical model learned by HA-SSVM further boosts the domain adaptation performance. Finally, the online domain adaptation method has demonstrated that it can achieve comparable accuracy to the batch learned models while not requiring manually label target domain examples. Domain adaptation for pedestrian detection is of paramount importance and a relatively unexplored area. We humbly hope the work in this thesis could provide foundations for future work in this area.

Abstract: Building a visual summary from an egocentric photostream captured by a lifelogging wearable camera is of high interest for different applications (e.g. memory reinforcement). In this paper, we propose a new summarization method based on keyframes selection that uses visual features extracted bymeans of a convolutional neural network. Our method applies an unsupervised clustering for dividing the photostreams into events, and finally extracts the most relevant keyframe for each event. We assess the results by applying a blind-taste test on a group of 20 people who assessed the quality of the
summaries.

Abstract: In this paper, we will discuss the most common challenges in electoral document processing and study the different solutions from the document analysis community that can be applied in each case. We will cover Optical Mark Recognition techniques to detect voter selections in the Australian Ballot, handwritten number recognition for preferential elections and handwriting recognition for write-in areas. We will also propose some particular adjustments that can be made to those general techniques in the specific context of electoral documents.

Abstract: Pedestrian detection for autonomous driving has gained a lot of prominence during the last few years. Besides the fact that it is one of the hardest tasks within computer vision, it involves huge computational costs. The real-time constraints in the field are tight, and regular processors are not able to handle the workload obtaining an acceptable ratio of frames per second (fps). Moreover, multiple cameras are required to obtain accurate results, so the need to speed up the process is even higher. Taking the work in [1] as our baseline, we propose a CUDA implementation of a pedestrian detection system. Further, we introduce significant algorithmic adjustments and optimizations to adapt the problem to the GPU architecture. The aim is to provide a system capable of running in real-time obtaining reliable results.

Abstract: Action recognition systems mostly work with videos of proper quality and resolution. Even most challenging benchmark databases for action recognition, hardly include videos of low-resolution from, e.g., surveillance cameras. In videos recorded by such cameras, due to the distance between people and cameras, people are pictured very small and hence challenge action recognition algorithms. Simple upsampling methods, like bicubic interpolation, cannot retrieve all the detailed information that can help the recognition. To deal with this problem, in this paper we combine results of bicubic interpolation with results of a state-ofthe-art deep learning-based super-resolution algorithm, through an alpha-blending approach. The experimental results obtained on down-sampled version of a large subset of Hoolywood2 benchmark database show the importance of the proposed system in increasing the recognition rate of a state-of-the-art action recognition system for handling low-resolution videos.