Abstract: Computer vision technologies are at the core of different advanced driver assistance systems (ADAS) and will play a key role in oncoming autonomous vehicles too. One of the main challenges for such technologies is to perceive the driving environment, i.e. to detect and track relevant driving information in a reliable manner (e.g. pedestrians in the vehicle route, free space to drive through). Nowadays it is clear that machine learning techniques are essential for developing such a visual perception for driving. In particular, the standard working pipeline consists of collecting data (i.e. on-board images), manually annotating the data (e.g. drawing bounding boxes around pedestrians), learning a discriminative data representation taking advantage of such annotations (e.g. a deformable part-based model, a deep convolutional neural network), and then assessing the reliability of such representation with the acquired data. In the last two decades most of the research efforts focused on representation learning (first, designing descriptors and learning classifiers; later doing it end-to-end). Hence, collecting data and, especially, annotating it, is essential for learning good representations. While this has been the case from the very beginning, only after the disruptive appearance of deep convolutional neural networks that it became a serious issue due to their data hungry nature. In this context, the problem is that manual data annotation is a tiresome work prone to errors. Accordingly, in the late 00’s we initiated a research line consisting of training visual models using photo-realistic computer graphics, especially focusing on assisted and autonomous driving. In this paper, we summarize such a work and show how it has become a new tendency with increasing acceptance.

Abstract: The original idea of this project was to study the role of colour in the challenging task of object recognition. We started by extending previous research on colour naming showing that it is feasible to capture colour terms through parsimonious ellipsoids. Although, the results of our model exceeded state-of-the-art in two benchmark datasets, we realised that the two phenomena of metameric lights and colour constancy must be addressed prior to any further colour processing. Our investigation of metameric pairs reached the conclusion that they are infrequent in real world scenarios. Contrary to that, the illumination of a scene often changes dramatically. We addressed this issue by proposing a colour constancy model inspired by the dynamical centre-surround adaptation of neurons in the visual cortex. This was implemented through two overlapping asymmetric Gaussians whose variances and heights are adjusted according to the local contrast of pixels. We complemented this model with a generic contrast-variant pooling mechanism that inversely connect the percentage of pooled signal to the local contrast of a region. The results of our experiments on four benchmark datasets were indeed promising: the proposed model, although simple, outperformed even learning-based approaches in many cases. Encouraged by the success of our contrast-variant surround modulation, we extended this approach to detect boundaries of objects. We proposed an edge detection model based on the first derivative of the Gaussian kernel. We incorporated four types of surround: full, far, iso- and orthogonal-orientation. Furthermore, we accounted for the pooling mechanism at higher cortical areas and the shape feedback sent to lower areas. Our results in three benchmark datasets showed significant improvement over non-learning algorithms.
To summarise, we demonstrated that biologically-inspired models offer promising solutions to computer vision problems, such as, colour naming, colour constancy and edge detection. We believe that the greatest contribution of this Ph.D dissertation is modelling the concept of dynamic surround modulation that shows the significance of contrast-variant surround integration. The models proposed here are grounded on only a portion of what we know about the human visual system. Therefore, it is only natural to complement them accordingly in future works.

Abstract: The human visual system and most digital cameras sample the continuous spectral power distribution through three classes of receptors. This implies that two distinct spectral reflectances can result in identical tristimulus values under one illuminant and differ under another – the problem of metamer mismatching. It is still debated how frequent this issue arises in the real world, using naturally occurring reflectance functions and common illuminants.
We gathered more than ten thousand spectral reflectance samples from various sources, covering a wide range of environments (e.g., flowers, plants, Munsell chips) and evaluated their responses under a number of natural and artificial source of lights. For each pair of reflectance functions, we estimated the perceived difference using the CIE-defined distance ΔE2000 metric in Lab color space.
The degree of metamer mismatching depended on the lower threshold value l when two samples would be considered to lead to equal sensor excitations (ΔE < l), and on the higher threshold value h when they would be considered different. For example, for l=h=1, we found that 43.129 comparisons out of a total of 6×107 pairs would be considered metameric (1 in 104). For l=1 and h=5, this number reduced to 705 metameric pairs (2 in 106). Extreme metamers, for instance l=1 and h=10, were rare (22 pairs or 6 in 108), as were instances where the two members of a metameric pair would be assigned to different color categories. Not unexpectedly, we observed variations among different reflectance databases and illuminant spectra with more frequency under artificial illuminants than natural ones.
Overall, our numbers are not very different from those obtained earlier (Foster et al, JOSA A, 2006). However, our results also show that the degree of metamerism is typically not very strong and that category switches hardly ever occur.

Abstract: Optical Music Recognition is the task of transcribing a music score into a machine readable format. Many music scores are written in a single staff, and therefore, they could be treated as a sequence. Therefore, this work explores the use of Long Short-Term Memory (LSTM) Recurrent Neural Networks for reading the music score sequentially, where the LSTM helps in keeping the context. For training, we have used a synthetic dataset of more than 40000 images, labeled at primitive level

Abstract: Deep learning for human action recognition in videos is making significant progress, but is slowed down by its dependency on expensive manual labeling of large video collections. In this work, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for ”Procedural Human Action Videos”. It contains a total of 39, 982 videos, with more than 1, 000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We introduce a deep multi-task representation learning architecture to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF101 and HMDB51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, significantly
outperforming fine-tuning state-of-the-art unsupervised generative models of videos.

Abstract: Hundreds of millions of figures are available in the biomedical literature, representing important biomedical experimental evidence. Since text is a rich source of information in figures, automatically extracting such text may assist in the task of mining figure information and understanding biomedical documents. Unlike images in the open domain, biomedical figures present a variety of unique challenges. For example, biomedical figures typically have complex layouts, small font sizes, short text, specific text, complex symbols and irregular text arrangements. This paper presents the final results of the ICDAR 2017 Competition on Text Extraction from Biomedical Literature Figures (ICDAR2017 DeTEXT Competition), which aims at extracting (detecting and recognizing) text from biomedical literature figures. Similar to text extraction from scene images and web pictures, ICDAR2017 DeTEXT Competition includes three major tasks, i.e., text detection, cropped word recognition and end-to-end text recognition. Here, we describe in detail the data set, tasks, evaluation protocols and participants of this competition, and report the performance of the participating methods.

Abstract: Over the last few years, the number of consumer computer vision applications has increased dramatically. Today, computer vision solutions can be found in video game consoles, smartphone applications, driving assistance – just to name a few. Ideally, we require the performance of those applications, particularly those that are safety critical to remain constant under any external environment factors, such as changes in illumination or weather conditions. However, this is not always possible or very difficult to obtain by only using visible imagery, due to the inherent limitations of the images from that spectral band. For that reason, the use of images from different or multiple spectral bands is becoming more appealing.
The aforementioned possible advantages of using images from multiples spectral bands on various vision applications make multi-spectral image processing a relevant topic for research and development. Like in visible image processing, multi-spectral image processing needs tools and algorithms to handle information from various spectral bands. Furthermore, traditional tools such as local feature detection, which is the basis of many vision tasks such as visual odometry, image registration, or structure from motion, must be adjusted or reformulated to operate under new conditions. Traditional feature detection, description, and matching methods tend to underperform in multi-spectral settings, in comparison to mono-spectral settings, due to the natural differences between each spectral band.
The work in this thesis is focused on the local feature description problem when cross-spectral images are considered. In this context, this dissertation has three main contributions. Firstly, the work starts by proposing the usage of a combination of frequency and spatial information, in a multi-scale scheme, as feature description. Evaluations of this proposal, based on classical hand-made feature descriptors, and comparisons with state of the art cross-spectral approaches help to find and understand limitations of such strategy. Secondly, different convolutional neural network (CNN) based architectures are evaluated when used to describe cross-spectral image patches. Results showed that CNN-based methods, designed to work with visible monocular images, could be successfully applied to the description of images from two different spectral bands, with just minor modifications. In this framework, a novel CNN-based network model, specifically intended to describe image patches from two different spectral bands, is proposed. This network, referred to as Q-Net, outperforms state of the art in the cross-spectral domain, including both previous hand-made solutions as well as L2 CNN-based architectures. The third contribution of this dissertation is in the cross-spectral feature description application domain. The multispectral odometry problem is tackled showing a real application of cross-spectral descriptors
In addition to the three main contributions mentioned above, in this dissertation, two different multi-spectral datasets are generated and shared with the community to be used as benchmarks for further studies.