Search

Computer Vision in Vehicle Technology focuses on computer vision as on-board technology, bringing together fields of research where computer vision is progressively penetrating: the automotive sector, unmanned aerial and underwater vehicles. It also serves as a reference for researchers of current developments and challenges in areas of the application of computer vision, involving vehicles such as advanced driver assistance (pedestrian detection, lane departure warning, traffic sign recognition), autonomous driving and robot navigation (with visual simultaneous localization and mapping) or unmanned aerial vehicles (obstacle avoidance, landscape classification and mapping, fire risk assessment).

Vision-based semantic segmentation in urban scenarios is a key functionality for autonomous driving. Recent revolutionary results of deep convolutional neural networks (CNNs) foreshadow the advent of reliable classifiers to perform such visual tasks. However, CNNs require learning of many parameters from raw images; thus, having a sufficient amount of diverse images with class annotations is needed. These annotations are obtained via cumbersome, human labor which is particularly challenging for semantic segmentation since pixel-level annotations are required. In this chapter, we propose to use a combination of a virtual world to automatically generate realistic synthetic images with pixel-level annotations, and domain adaptation to transfer the models learned to correctly operate in real scenarios. We address the question of how useful synthetic data can be for semantic segmentation—in particular, when using a CNN paradigm. In order to answer this question we have generated a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations and object identifiers. We use SYNTHIA in combination with publicly available real-world urban images with manually provided annotations. Then, we conduct experiments with CNNs that show that combining SYNTHIA with simple domain adaptation techniques in the training stage significantly improves performance on semantic segmentation.

Copper-based chalcogenides that comprise abundant, low-cost, and environmental friendly elements are excellent materials for a number of energy conversion applications, including photovoltaics, photocatalysis, and thermoelectrics (TE). In such applications, the use of solution-processed nanocrystals (NCs) to produce thin films or bulk nanomaterials has associated several potential advantages, such as high material yield and throughput, and composition control with unmatched spatial resolution and cost. Here we report on the production of Cu3SbSe4 (CASe) NCs with tuned amounts of Sn and Bi dopants. After proper ligand removal, as monitored by nuclear magnetic resonance and infrared spectroscopy, these NCs were used to produce dense CASe bulk nanomaterials for solid state TE energy conversion. By adjusting the amount of extrinsic dopants, dimensionless TE figures of merit (ZT) up to 1.26 at 673 K were reached. Such high ZT values are related to an optimized carrier concentration by Sn doping, a minimized lattice thermal conductivity due to efficient phonon scattering at point defects and grain boundaries, and to an increase of the Seebeck coefficient obtained by a modification of the electronic band structure with Bi doping. Nanomaterials were further employed to fabricate ring-shaped TE generators to be coupled to hot pipes, which provided 20 mV and 1 mW per TE element when exposed to a 160 ºC temperature gradient. The simple design and good thermal contact associated with the ring geometry and the potential low cost of the material solution processing may allow the fabrication of TE generators with short payback times.

Colorectal cancer (CRC) is the third cause of cancer death worldwide. Currently, the standard approach to reduce CRC-related mortality is to perform regular screening in search for polyps and colonoscopy is the screening tool of choice. The main limitations of this screening procedure are polyp miss rate and the inability to perform visual assessment of polyp malignancy. These drawbacks can be reduced by designing decision support systems (DSS) aiming to help clinicians in the different stages of the procedure by providing endoluminal scene segmentation. Thus, in this paper, we introduce an extended benchmark of colonoscopy image segmentation, with the hope of establishing a new strong benchmark for colonoscopy image analysis research. The proposed dataset consists of 4 relevant classes to inspect the endoluminal scene, targeting different clinical needs. Together with the dataset and taking advantage of advances in semantic segmentation literature, we provide new baselines by training standard fully convolutional networks (FCNs). We perform a comparative study to show that FCNs significantly outperform, without any further postprocessing, prior results in endoluminal scene segmentation, especially with respect to polyp segmentation and localization.

Supervised learning tends to produce more accurate classifiers than unsupervised learning in general. This implies that training data is preferred with annotations. When addressing visual perception challenges, such as localizing certain object classes within an image, the learning of the involved classifiers turns out to be a practical bottleneck. The reason is that, at least, we have to frame object examples with bounding boxes in thousands of images. A priori, the more complex the model is regarding its number of parameters, the more annotated examples are required. This annotation task is performed by human oracles, which ends up in inaccuracies and errors in the annotations (aka ground truth) since the task is inherently very cumbersome and sometimes ambiguous. As an alternative, we have pioneered the use of virtual worlds for collecting such annotations automatically and with high precision. However, since the models learned with virtual data must operate in the real world, we still need to perform domain adaptation (DA). In this chapter, we revisit the DA of a Deformable Part-Based Model (DPM) as an exemplifying case of virtual- to real-world DA. As a use case, we address the challenge of vehicle detection for driver assistance, using different publicly available virtual-world data. While doing so, we investigate questions such as how does the domain gap behave due to virtual-vs-real data with respect to dominant object appearance per domain, as well as the role of photo-realism in the virtual world .

Trabajo presentado a la IEEE International Conference on Image Processing (ICIP), celebrada en Beijing (China) del 17 al 20 de septiembre de 2017., We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning. The coarse reasoning is performed over a discrete classification space to obtain a general rough solution, while the fine details of the solution are obtained over a continuous regression space. In our approach both components are jointly estimated, which proved to be beneficial for improving estimation accuracy. Additionally, we propose a new network architecture, which combines coarse and fine components by treating the fine estimation as a refinement built on top of the coarse solution, and therefore adding details to the general prediction. We apply our approach to the challenging problem of optical flow estimation and empirically validate it against state-of-the-art CNN-based solutions trained from scratch and tested on large optical flow datasets., This work was partially supported by European AEROARMS project (H2020-ICT-2014-1-644271) and CICYT projects ColRobTransp (DPI2016-78957-R), ROBINSTRUCT (TIN2014-58178-R).

Purpose Financial stress features frequently as an explanatory factor in research into decisions concerning the contracting out, or decentralisation, of local public services, though existing empirical studies are not unanimous in their conclusions. The understanding of how financial crises influence these processes could be enhanced by the use of a dynamic methodology that takes into account the following three aspects: the duration of the financial stress, the effectiveness of the action taken and the time‐lag between the crisis and the response. The paper aims to discuss these issues. Design/methodology/approach This study introduces three important innovations in the methodology employed to study financial stress: the consideration of the duration of a financial stress episode as a key factor in promoting changes in the provision of public services; the effectiveness of the measures taken; and time‐lag, which takes into account the extended time horizon over which the local authority may implement business‐like and organisational changes. Findings To date, the techniques used to measure the effects of changes in service delivery methods implemented to alleviate financial stress, have not reflected the true nature of the phenomenon. The results obtained when the new approach proposed in this paper was used to examine Spanish local government responses to financial stress during the period 1999‐2007 confirm that the methodology is well‐judged and effective. Originality/value This study reveals that local authorities facing financial stress of two, three or four years’ duration present percentages of decentralisation and contracting‐out that are significantly higher than is the case for local authorities that implement the same processes in response to crises of one year. These findings confirm the need to carry out studies that include the duration of financial crises as a determinant factor in change processes.

Detecting pedestrians with on-board vision systems is of paramount interest for assisting drivers to prevent vehicle-to-pedestrian accidents. The core of a pedestrian detector is its classification module, which aims at deciding if a given image window contains a pedestrian. Given the difficulty of this task, many classifiers have been proposed during the last 15 years. Among them, the so-called (deformable) part-based classifiers, including multiview modeling, are usually top ranked in accuracy. Training such classifiers is not trivial since a proper aspect clustering and spatial part alignment of the pedestrian training samples are crucial for obtaining an accurate classifier. In this paper, the authors first perform automatic aspect clustering and part alignment by using virtual-world pedestrians, i.e., human annotations are not required. Second, the authors use a mixture-of-parts approach that allows part sharing among different aspects. Third, these proposals are integrated in a learning framework, which also allows incorporating real-world training data to perform domain adaptation between virtual- and real-world cameras. Overall, the obtained results on four popular on-board data sets show that the proposal clearly outperforms the state-of-the-art deformable part-based detector known as latent support vector machine.

The aim of this article is to analyse the level of public financial information disclosed by certain Arab countries in the Middle East, in view of calls for greater transparency and international trends in this respect. Accordingly, we examined the financial reports published online by the selected countries, contrasting them with the financial statements and contents proposed in the International Public Sector Accounting Standards (IPSAS) issued by the International Federation of Accountants. The results show that the Arab countries analysed present a low level of public financial information. They all present similar degrees of compliance with IPSAS 1 and 2. Nonetheless, we can observe that aid-receiving countries are implementing the policies stipulated in the international recommendations in response to the demands of donors and international agencies. Countries with oil revenues experience less pressure to implement the IPSAS. Points for practitioners The findings of this article may be of interest to public managers in all the selected Arab countries, especially those in the public administrations of the Gulf Cooperation Council countries and to consulting companies in the Gulf region. The analysis made of financial legislation and of the IPSAS 1 and 2 indexes for the selected countries may encourage them to initiate a process of financial reforms.

Nowadays, photovoltaic solar energy is a clean and reliable source for producing electric power. Most photovoltaic systems have been designed and built up for use in applications with low power requirements. The efficiency of solar cells is quite low, obtaining best results in monocrystalline silicon structures, with an efficiency of about 18%. When temperature rises, photovoltaic cell efficiency decreases, given that the short-circuit current is slightly increased, and the open-circuit voltage, fill factor and power output are reduced. To ensure that this does not affect performance, this paper describes how to interconnect photovoltaic and thermoelectric technology into a single structure. The temperature gradient in the solar panel is used to supply thermoelectric cells, which generate electricity, achieving a positive contribution to the total balance of the complete system.

Pedestrian detection is of paramount interest for many applications. Most promising detectors rely on discriminatively learnt classifiers, i.e., trained with annotated samples. However, the annotation step is a human intensive and subjective task worth to be minimized. By using virtual worlds we can automatically obtain precise and rich annotations. Thus, we face the question: can a pedestrian appearance model learnt in realistic virtual worlds work successfully for pedestrian detection in real-world images? Conducted experiments show that virtual-world based training can provide excellent testing accuracy in real world, but it can also suffer the data set shift problem as real-world based training does. Accordingly, we have designed a domain adaptation framework, V-AYLA, in which we have tested different techniques to collect a few pedestrian samples from the target domain (real world) and combine them with the many examples of the source domain (virtual world) in order to train a domain adapted pedestrian classifier that will operate in the target domain. V-AYLA reports the same detection accuracy than when training with many human-provided pedestrian annotations and testing with real-world images of the same domain. To the best of our knowledge, this is the first work demonstrating adaptation of virtual and real worlds for developing an object detector.

Finding solutions to the unfavourable economic and financial situation that the local authorities are currently facing is of crucial importance. One such solution is to adopt mechanisms for restructuring local public services, through new management approaches to reduce costs and thereby reduce fiscal stress. The aim of this article is to determine the probability of a city council changing the way it manages services, selecting from different options, in response to situations of fiscal stress. To address this issue, we studied a sample of 1572 Spanish municipalities for the period 2002–2009, using a random-effects panel multinomial logit model. The results obtained show that outsourcing and inter-municipal cooperation are the management formulas that councils are most likely to choose in response to a financial crisis, especially the ones arising from insufficient transfers, negative cash flow, debt or budget deficit.

Detecting the free road surface ahead of a moving vehicle is an important research topic in different areas of computer vision, such as autonomous driving or car collision warning. Current vision-based road detection methods are usually based solely on low-level features. Furthermore, they generally assume structured roads, road homogeneity, and uniform lighting conditions, constraining their applicability in real-world scenarios. In this paper, road priors and contextual information are introduced for road detection. First, we propose an algorithm to estimate road priors online using geographical information, providing relevant initial information about the road location. Then, contextual cues, including horizon lines, vanishing points, lane markings, 3-D scene layout, and road geometry, are used in addition to low-level cues derived from the appearance of roads. Finally, a generative model is used to combine these cues and priors, leading to a road detection method that is, to a large degree, robust to varying imaging conditions, road types, and scenarios.

The contract audit is an instrument facilitating the evaluation of prices offered and costs incurred in non-competitive defence contracts. In this study we analyse the degree of harmonization of contract auditing models among four European countries by means of a comparative analysis of the characteristics of contract auditing in these countries. We identify similarities and differences among the contract auditing models applied in these countries, and conclude that they do not present a high degree of harmonization of defence contract cost evaluation. Points for practitioners This comparative study highlights the similarities and differences among the audit models for defence contracts in four European countries (the UK, France, Spain and Norway). The authors present the main characteristics of each model and systematize the features inherent to a possible common model that could be achieved by harmonizing audit practices and the rules applicable to the corresponding cost calculations. Finally, the authors recommend further progress be made in harmonizing the audit practices applied in NATO countries for defence contracts.

The Organisation for Economic Co-Operation and Development emphasizes the e-government process as a tool for promoting budget transparency making all fiscal reports publicly available on the Internet. Nonetheless, the particular approach adopted to New Public Management models may influence different policies concerning the concepts of information quality and transparency. Based on an administrative culture approach, the aim of this article is to analyze whether the new technologies are being used by central governments for improving their accountability and democracy making their budgetary figures transparent for all stakeholders. The results of this study confirm that differences do exist across countries under different administrative cultures.

Video alignment is important in different areas of computer vision such as wide baseline matching, action recognition, change detection, video copy detection and frame dropping prevention. Current video alignment methods usually deal with a relatively simple case of fixed or rigidly attached cameras or simultaneous acquisition. Therefore, in this paper we propose a joint video alignment for bringing two video sequences into a spatio-temporal alignment. Specifically, the novelty of the paper is to formulate the video alignment to fold the spatial and temporal alignment into a single alignment framework. This simultaneously satisfies a frame-correspondence and frame-alignment similarity; exploiting the knowledge among neighbor frames by a standard pairwise Markov random field (MRF). This new formulation is able to handle the alignment of sequences recorded at different times by independent moving cameras that follows a similar trajectory, and also generalizes the particular cases that of fixed geometric transformation and/or linear temporal mapping. We conduct experiments on different scenarios such as sequences recorded simultaneously or by moving cameras to validate the robustness of the proposed approach. The proposed method provides the highest video alignment accuracy compared to the state-of-the-art methods on sequences recorded from vehicles driving along the same track at different times.

Gulf Cooperation Council countries are seeking to develop their governmental financial information systems to make them more informative and transparent. The aim of this article is to determine the extent to which Qatar has developed its governmental financial information systems in response to the enormous degree of economic and administrative development in recent decades, and to identify the most important factors that have influenced the reforms made in this area. For this purpose, Luder's Financial Management Reform Process Model (2001) was referred to and semi-structured interviews were carried out with governmental accounting officials in Qatar in June 2011.

This paper presents a graduate course project on computer vision. The aim of the project is to detect and recognize traffic signs in video sequences recorded by an on-board vehicle camera. This is a demanding problem, given that traffic sign recognition is one of the most challenging problems for driving assistance systems. Equally, it is motivating for the students given that it is a real-life problem. Furthermore, it gives them the opportunity to appreciate the difficulty of real-world vision problems and to assess the extent to which this problem can be solved by modern computer vision and pattern classification techniques taught in the classroom. The learning objectives of the course are introduced, as are the constraints imposed on its design, such as the diversity of students' background and the amount of time they and their instructors dedicate to the course. The paper also describes the course contents, schedule, and how the project-based learning approach is applied. The outcomes of the course are discussed, including both the students' marks and their personal feedback.

We have recently observed an increased risk for vertebral fractures (VF) in a randomized controlled trial comparing the analgesic effect of vertebroplasty (VP) versus conservative treatment in symptomatic VF. The aim of the present study was to evaluate the risk factors related to the development of VF after VP in these patients. We evaluated risk factors including age, gender, bone mineral density, the number, type, and severity of vertebral deformities at baseline, the number of vertebral bodies treated, the presence and location of disk cement leakage, bone remodeling (determining bone turnover markers) and 25 hydroxyvitamin D [25(OH)D] levels at baseline in all patients. Twenty-nine radiologically new VF were observed in 17 of 57 patients undergoing VP, 72% adjacent to the VP. Patients developing VF after VP showed an increased prevalence of 25(OH)D deficiency ( 80 years (RR, 3.20; 95% CI, 1.70–6.03, p = 0.0007) and glucocorticoid therapy (RR, 3.64; 95% CI, 1.61–8.26, p = 0.0055) constituted the principal factors in the overall study population. Increased risk of VF after VP was also associated with cement leakage into the inferior disk (RR, 6.14; 95% CI, 1.65–22.78, p = 0.044) and more than one vertebral body treated during VP (RR, 4.19; 95% CI, 1.03–34.3, p = 0.044). In conclusion, nearly 30% of patients with osteoporotic VF treated with VP had a new VF after the procedure. Age, especially >80 years, the presence of inferior disk cement leakage after the procedure, the number of cemented vertebrae, and low 25(OH)D serum levels were related to the development of new VF in these patients, with the latter indicating the need to correct vitamin D deficiency prior to performing VP.

We present a method for the cost estimation of custom hoses from CAD models. They can come in two formats, which are easy to generate: a STL file or the image of a CAD drawing showing several orthogonal projections. The challenges in either cases are, first, to obtain from them a high level 3D description of the shape, and second, to learn a regression function for the prediction of the manufacturing time, based on geometric features of the reconstructed shape. The chosen description is the 3D line along the medial axis of the tube and the diameter of the circular sections along it. In order to extract it from STL files, we have adapted RANSAC, a robust parametric fitting algorithm. As for CAD drawing images, we propose a new technique for 3D reconstruction from data entered on any number of orthogonal projections. The regression function is a Gaussian process, which does not constrain the function to adopt any specific form and is governed by just two parameters. We assess the accuracy of the manufacturing time estimation by k-fold cross validation on 171 STL file models for which the time is provided by an expert. The results show the feasibility of the method, whereby the relative error for 80% of the testing samples is below 15%.

Con el fin de realizar una comparación descriptiva de los sistemas de contabilidad gubernamental de los países de la región centroamericana, el presente artículodesarrolla y aplica una metodología de comparación adaptada al entorno en el que operan estos sistemas. A tal efecto, se analizan los atributos que caracterizan el sistema de contabilidad gubernamental dividiéndolo en tres subsistemas, a saber: el de regulación contable, el de capital humano y el de prácticas contables. Este último, por su amplitud, se secciona en prácticas contables de selección y elaboración, y prácticas contables de comunicación.

Contract auditing, or cost and price auditing, has been applied in Spain as a means of determining prices in non-competitive defense contracts since 1989. Factors such as Spain's participation in international defense organizations, the characteristics of the defense market and the contractual legal framework for the procurement of defense goods and services help underscore the need for the Spanish Ministry of Defense to implement cost and price auditing. With the evolution of cost and price auditing in Spain in mind, this paper analyses the entire process, describes the audit procedures that are most commonly used today and assesses the main results achieved, in terms of financial savings. The results obtained show that cost and price auditing does indeed contribute to a more efficient use of public resources. Resumo A auditoria de contratos, ou auditoria de custos e preços, aplica-se na Espanha como uma ferramenta para a fixação dos preços dos contratos de defesa não competitivos desde 1989. A participação da Espanha em organismos internacionais de defesa, as características do mercado de defesa e o quadro normativo contratual em que se realizam as aquisições de bens e serviços para a defesa têm propiciado a necessidade da implementação da auditoria de custos e preços por parte do Departamento de Defesa da Espanha. Tendo em conta a evolução que sua aplicação tem tido na Espanha, os objetivos deste artigo são: analisar no seu conjunto o processo da auditoria de custos e preços e as modalidades de auditoria mais usadas atualmente, assim como os principais resultados alcançados em termos de poupanças monetárias. Os resultados obtidos mostram que a auditoria de custos e preços contribui para um uso mais eficiente dos recursos públicos. Resumen La auditoría de contratos o auditoría de costes y precios se aplica en España como herramienta para la fijación de los precios de los contratos de defensa no competitivos desde 1989. La participación de España en organismos internacionales de defensa, las características del mercado de defensa y el marco normativo contractual en el que se realizan las adquisiciones de bienes y servicios para la defensa han propiciado la necesidad de la implantación de la auditoria de costes y precios por parte del Departamento de Defensa de España. Teniendo en cuenta la evolución que su aplicación ha tenido en España, los objetivos de este artículo son: analizar en su conjunto el proceso de la auditoria de costes y precios y las modalidades de auditoría más utilizadas en la actualidad, así como los principales resultados alcanzados en términos de ahorros monetarios. Los resultados obtenidos muestran que la auditoría de costes y precios contribuye a un uso más eficiente de los recursos públicos.

Contract auditing, or cost and price auditing, has been applied in Spain as a means of determining prices in non-competitive defense contracts since 1989. Factors such as Spain's participation in international defense organizations, the characteristics of the defense market and the contractual legal framework for the procurement of defense goods and services help underscore the need for the Spanish Ministry of Defense to implement cost and price auditing. With the evolution of cost and price auditing in Spain in mind, this paper analyses the entire process, describes the audit procedures that are most commonly used today and assesses the main results achieved, in terms of financial savings. The results obtained show that cost and price auditing does indeed contribute to a more efficient use of public resources.

Passive Millimeter Wave Images currently used to detect hidden threats suffer from low resolution, blur, and a very low signal-to-noise-ratio. These shortcomings render threat detection, both visual and automatic, very challenging. Furthermore, due to the presence of very severe noise, most of the blind image restoration methods fail to recover the system blurring kernel from a single image. In this paper we propose a robust Bayesian multiframe blind image deconvolution method that approximates the posterior distribution of the blur by a Dirichlet distribution. We show that this approach naturally incorporates the non-negativity and normalization constraints for the blur and cope well with the image noise. The performance of the proposed method is tested on both synthetic and real images.

Vision-based semantic segmentation in urban scenarios is a key functionality for autonomous driving. Recent revolutionary results of deep convolutional neural networks (DCNNs) foreshadow the advent of reliable classifiers to perform such visual tasks. However, DCNNs require learning of many parameters from raw images, thus, having a sufficient amount of diverse images with class annotations is needed. These annotations are obtained via cumbersome, human labour which is particularly challenging for semantic segmentation since pixel-level annotations are required. In this paper, we propose to use a virtual world to automatically generate realistic synthetic images with pixel-level annotations. Then, we address the question of how useful such data can be for semantic segmentation – in particular, when using a DCNN paradigm. In order to answer this question we have generated a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations. We use SYNTHIA in combination with publicly available real-world urban images with manually provided annotations. Then, we conduct experiments with DCNNs that show how the inclusion of SYNTHIA in the training stage significantly improves performance on the semantic segmentation task.

This paper presents the comparison of two nonlinear model-based control strategies for autonomous cars. A control oriented model of vehicle based on a bicycle model is used. The two control strategies use a model reference approach. Using this approach, the error dynamics model is developed. Both controllers receive as input the longitudinal, lateral and orientation errors generating as control outputs the steering angle and the velocity of the vehicle. The first control approach is based on a non-linear control law that is designed by means of the Lyapunov direct approach. The second approach is based on a sliding mode-control that defines a set of sliding surfaces over which the error trajectories will converge. The main advantage of the sliding-control technique is the robustness against non-linearities and parametric uncertainties in the model. However, the main drawback of first ordersliding mode is the chattering, so it has been implemented a high order sliding mode control. To test and compare the proposed control strategies, different path following scenarios are used in simulation.

The eye acts as a dipole between the cornea (positive potential) and the retina (negative potential) which causes an electric field around the eyeball. Therefore, when humans make saccadic eye movements, they generate signals relative to this potential called electrooculography (EOG) signals. These signals can be measured by placing electrodes near the eye. Different electrode configurations can be employed to acquire the EOG signals. The properties of these signals change depending on the number and placement of the electrodes. Therefore, this paper presents a comparative study of electrode placement used to measure EOG signals. In order to support this study a low-cost signal acquisition hardware was developed. It enables the comparison of different electrode placements while showing the particularities of each one. The aim of this study is to analyse which electrode configuration could be best for medical applications.

We propose an online domain adaptation method for the deformable part-based model (DPM). The online domain adaptation is based on a two-level hierarchical adaptation tree, which consists of instance models in the leaf nodes and a category model at the root node. Moreover, combined with a multiple object tracking procedure (MOT), our proposal neither requires target-domain annotated data nor revisiting the source-domain data for performing the source-to-target domain adaptation of the DPM. From a practical point of view this means that, given a source-domain DPM and new video for training on a new domain without object annotations, our procedure outputs a new DPM adapted to the domain represented by the video. As proof-of-concept we apply our proposal to the challenging task of pedestrian detection. In this case, each instance model is an exemplar classifier trained online with only one pedestrian per frame. The pedestrian instances are collected by MOT and the hierarchical model is constructed dynamically according to the pedestrian trajectories. Our experimental results show that the adapted model achieves the accuracy of recent supervised domain adaptation methods (i.e., requiring manually annotated target-domain data), and improves the source model more than 10 percentage points.

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., Comment: Accepted for publication at CVPR 2017. http://adas.cvc.uab.es/phav/

Photorealistic virtual environments are crucial for developing and testing automated driving systems in a safe way during trials. As commercially available simulators are expensive and bulky, this paper presents a low-cost, extendable, and easy-to-use (LEE) virtual environment with the aim to highlight its utility for level 3 driving automation. In particular, an experiment is performed using the presented simulator to explore the influence of different variables regarding control transfer of the car after the system was driving autonomously in a highway scenario. The results show that the speed of the car at the time when the system needs to transfer the control to the human driver is critical.

The countries in the Central American region, Costa Rica, El Salvador, Guatemala, Honduras, Nicaragua and Panama, have carried out a reform process of their public financial management systems, seeking to guarantee higher-quality, reliable and timely information, using mainly the International Public Sector Accounting Standards (IPSAS). In this context, the chapter has a double objective. On the one hand, valuing from the Model of Contingency of the Professor Lüder, the influence of the environment in the implementation of processes of innovation in systems of government financial management in the Central American region. On the other hand analyze the main implementation strategies in the process of adoption or adaptation of IPSAS in these countries. For this purpose, interviews have been made with those responsible for the process of implementation of IPSAS in the countries of the region, as well as an in-depth review of the documents and legislation issued in government financial administration in these countries.

Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image classification and showing promise for videos, has still not clearly superseded action recognition methods using hand-crafted features, even when training on massive datasets. In this paper, we introduce hybrid video classification architectures based on carefully designed unsupervised representations of hand-crafted spatio-temporal features classified by supervised deep networks. As we show in our experiments on five popular benchmarks for action recognition, our hybrid model combines the best of both worlds: it is data efficient (trained on 150 to 10000 short clips) and yet improves significantly on the state of the art, including recent deep models trained on millions of manually labelled images and videos., Comment: Accepted for publication in the 14th European Conference on Computer Vision (ECCV), Amsterdam, 2016, plus supplementary material

The Stixel World is a medium-level, compact representation of road scenes that abstracts millions of disparity pixels into hundreds or thousands of stixels. The goal of this work is to implement and evaluate a complete multi-stixel estimation pipeline on an embedded, energy-efficient, GPU-accelerated device. This work presents a full GPU-accelerated implementation of stixel estimation that produces reliable results at 26 frames per second (real-time) on the Tegra X1 for disparity images of 1024x440 pixels and stixel widths of 5 pixels, and achieves more than 400 frames per second on a high-end Titan X GPU card.

Arrays of electrodeposited ZnO nanowires (NWs) were used to illustrate the dependence of the ZnO visible photoluminescence (PL) emission on the extension of the surface depletion layer and obtain further insight into the localization of the related states. With this goal in mind, three sets of measurements were carried out: (i) analysis of the PL spectra of ZnO:Cl NWs as a function of their carrier concentration; (ii) analysis of the PL spectra of ZnO:Cl/ZnO core−shell NWs as a function of the thickness of their intrinsic ZnO shell; (iii) in situ analysis of the PL dependence on the polarization of ZnO:Cl photoelectrodes. The obtained experimental results evidenced that the yellow and orange emissions from electrodeposited ZnO NWs are correlated with the extension of the NWs surface depletion region. This result points out the surface localization of the states at the origin of these transitions. On the other hand, the green emission that dominates the visible part of the PL spectra in annealed ZnO NWs showed no dependence on the surface band bending, thus pointing toward its origin in the bulk.

We present a waist-worn personal navigation system based on inertial measurement units. The device makes use of the human bipedal pattern to reduce position errors. We describe improved algorithms, based on detailed description of the heel strike biomechanics and its translation to accelerations of the body waist to estimate the periods of zero velocity, the step length, and the heading estimation. The experimental results show that we are able to support pedestrian navigation with the high-resolution positioning required for most applications.

Intelligent vehicle lighting systems aim at automatically regulating the headlights' beam to illuminate as much of the road ahead as possible while avoiding dazzling other drivers. A key component of such a system is computer vision software that is able to distinguish blobs due to vehicles' headlights and rear lights from those due to road lamps and reflective elements such as poles and traffic signs. In a previous work, we have devised a set of specialized supervised classifiers to make such decisions based on blob features related to its intensity and shape. Despite the overall good performance, there remain challenging that have yet to be solved: notably, faint and tiny blobs corresponding to quite distant vehicles. In fact, for such distant blobs, classification decisions can be taken after observing them during a few frames. Hence, incorporating tracking could improve the overall lighting system performance by enforcing the temporal consistency of the classifier decision. Accordingly, this paper focuses on the problem of constructing blob tracks, which is actually one of multiple-target tracking (MTT), but under two special conditions: We have to deal with frequent occlusions, as well as blob splits and merges. We approach it in a novel way by formulating the problem as a maximum a posteriori inference on a Markov random field. The qualitative (in video form) and quantitative evaluation of our new MTT method shows good tracking results. In addition, we will also see that the classification performance of the problematic blobs improves due to the proposed MTT algorithm.

The current economic crisis is increasingly affecting the public sector, requiring stricter control of deficits, and local administrations are not exempt from these requirements. Therefore, it is essential to consider management forms that may produce cost savings in the provision of public services. In this article we propose an evaluation of municipal waste collection and disposal services to determine whether single/joint or public/private municipal service provision, together with other factors including quality, political aspects, and the socio-economic environment, most contribute to reducing costs. The results obtained for the period 2002–08 show that joint management (inter-municipal cooperation) and public management (in relation to single and private management systems, respectively) have a greater effect on reducing the costs of this service. Thus, small and medium-sized local authorities can identify formulas for reducing costs and thus be in a better position to overcome the economic crisis.

Vision-based road detection is important for different applications in transportation, such as autonomous driving, vehicle collision warning, and pedestrian crossing detection. Common approaches to road detection are based on low-level road appearance (e.g., color or texture) and neglect of the scene geometry and context. Hence, using only low-level features makes these algorithms highly depend on structured roads, road homogeneity, and lighting conditions. Therefore, the aim of this paper is to classify road geometries for road detection through the analysis of scene composition and temporal coherence. Road geometry classification is proposed by building corresponding models from training images containing prototypical road geometries. We propose adaptive shape models where spatial pyramids are steered by the inherent spatial structure of road images. To reduce the influence of lighting variations, invariant features are used. Large-scale experiments show that the proposed road geometry classifier yields a high recognition rate of 73.57% $pm$ 13.1, clearly outperforming other state-of-the-art methods. Including road shape information improves road detection results over existing appearance-based methods. Finally, it is shown that invariant features and temporal information provide robustness against disturbing imaging conditions.

In this paper, a modified mechanical grip fitting is used to perform double cantilever beam (DCB) tests. The advantage of using mechanical grips instead of piano hinges or end blocks lies in the fact that the use of adhesive bonding is not required to fix the sample. Adhesive bonding can be an important source of uncertainty and unexpected debondings in fatigue tests. Mechanical fittings are also well suited for high temperature applications where adhesive bonds usually undergo premature failure. An experimental programme has been developed in order to compare the performance of the modified mechanical hinges with classical hinges and end blocks. The highest GIc values and scattering were found for the end block system, while hinges and mechanical hinges furnished similar results. The material used to perform the experimental study was a Hexcel AS4/3501-6 unidirectional laminate.

This paper proposes a new framework for real-time estimation of the onboard stereo head's position and orientation relative to the road surface, which is required for any advanced driver-assistance application. This framework can be used with all road types: highways, urban, etc. Unlike existing works that rely on feature extraction in either the image domain or 3-D space, we propose a framework that directly estimates the unknown parameters from the stream of stereo pairs' brightness. The proposed approach consists of two stages that are invoked for every stereo frame. The first stage segments the road region in one monocular view. The second stage estimates the camera pose using a featureless registration between the segmented monocular road region and the other view in the stereo pair. This paper has two main contributions. The first contribution combines a road segmentation algorithm with a registration technique to estimate the online stereo camera pose. The second contribution solves the registration using a featureless method, which is carried out using two different optimization techniques: 1) the differential evolution algorithm and 2) the Levenberg-Marquardt (LM) algorithm. We provide experiments and evaluations of performance. The results presented show the validity of our proposed framework.

In this work, we address the problem of aligning two video sequences. Such alignment refers to synchronization, i.e., the establishment of temporal correspondence between frames of the first and second video, followed by spatial registration of all the temporally corresponding frames. Video synchronization and alignment have been attempted before, but most often in the relatively simple cases of fixed or rigidly attached cameras and simultaneous acquisition. In addition, restrictive assumptions have been applied, including linear time correspondence or the knowledge of the complete trajectories of corresponding scene points; to some extent, these assumptions limit the practical applicability of any solutions developed. We intend to solve the more general problem of aligning video sequences recorded by independently moving cameras that follow similar trajectories, based only on the fusion of image intensity and GPS information. The novelty of our approach is to pose the synchronization as a MAP inference problem on a Bayesian network including the observations from these two sensor types, which have been proved complementary. Alignment results are presented in the context of videos recorded from vehicles driving along the same track at different times, for different road types. In addition, we explore two applications of the proposed video alignment method, both based on change detection between aligned videos. One is the detection of vehicles, which could be of use in ADAS. The other is online difference spotting videos of surveillance rounds.

By using an onboard camera, it is possible to detect the free road surface ahead of the ego-vehicle. Road detection is of high relevance for autonomous driving, road departure warning, and supporting driver-assistance systems such as vehicle and pedestrian detection. The key for vision-based road detection is the ability to classify image pixels as belonging or not to the road surface. Identifying road pixels is a major challenge due to the intraclass variability caused by lighting conditions. A particularly difficult scenario appears when the road surface has both shadowed and nonshadowed areas. Accordingly, we propose a novel approach to vision-based road detection that is robust to shadows. The novelty of our approach relies on using a shadow-invariant feature space combined with a model-based classifier. The model is built online to improve the adaptability of the algorithm to the current lighting and the presence of other vehicles in the scene. The proposed algorithm works in still images and does not depend on either road shape or temporal restrictions. Quantitative and qualitative experiments on real-world road sequences with heavy traffic and shadows show that the method is robust to shadows and lighting variations. Moreover, the proposed method provides the highest performance when compared with hue-saturation-intensity (HSI)-based algorithms.

A novel technique for missing data matrix rank estimation is presented. It is focused on matrices of trajectories, where every element of the matrix corresponds to an image coordinate from a feature point of a rigid moving object at a given frame; missing data are represented as empty entries. The objective of the proposed approach is to estimate the rank of a missing data matrix in order to fill in empty entries with some matrix completion method, without using or assuming neither the number of objects contained in the scene nor the kind of their motion. The key point of the proposed technique consists in studying the frequency behaviour of the individual trajectories, which are seen as 1D signals. The main assumption is that due to the rigidity of the moving objects, the frequency content of the trajectories will be similar after filling in their missing entries. The proposed rank estimation approach can be used in different computer vision problems, where the rank of a missing data matrix needs to be estimated. Experimental results with synthetic and real data are provided in order to empirically show the good performance of the proposed approach.

In recent years, significant changes have produced in the organisational culture of the public sector, bringing accountability and sustainability to the foreground and highlighting the definition of corporate social responsibility (CSR) in public administrations. In this respect, state-owned enterprises (SOEs) are well placed to provide an important example to other companies and society and could be of crucial importance in the promotion and development of socially responsible policies. With these considerations in mind, we analyse the state of research into the practice of CSR within SOEs, seeking to identify the main theoretical and empirical contributions made in this respect, that it will be a useful base for studies in the future. Our results show that research attention has been paid to this issue but significantly less than the large body of work carried out in this respect in the private sector. Most of the studies we identify are descriptive, although a growing body of explanatory research is now appearing. Few studies have been made of the impact of CSR practices on users and this constitutes a possible area for research in the future. Our review shows that research into CSR in SOEs is particularly significant in countries where the state has a strong presence in these companies.

Detection of lane markings based on a camera sensor can be a low-cost solution to lane departure and curve-over-speed warnings. A number of methods and implementations have been reported in the literature. However, reliable detection is still an issue because of cast shadows, worn and occluded markings, variable ambient lighting conditions, for example. We focus on increasing detection reliability in two ways. First, we employed an image feature other than the commonly used edges: ridges, which we claim addresses this problem better. Second, we adapted RANSAC, a generic robust estimation method, to fit a parametric model of a pair of lane lines to the image features, based on both ridgeness and ridge orientation. In addition, the model was fitted for the left and right lane lines simultaneously to enforce a consistent result. Four measures of interest for driver assistance applications were directly computed from the fitted parametric model at each frame: lane width, lane curvature, and vehicle yaw angle and lateral offset with regard the lane medial axis. We qualitatively assessed our method in video sequences captured on several road types and under very different lighting conditions. We also quantitatively assessed it on synthetic but realistic video sequences for which road geometry and vehicle trajectory ground truth are known.

The delamination energy and fracture behaviour under static and dynamic mode I loading of two composites, made of the same unidirectional carbon reinforcement embedded in two different matrices, one tough and the other brittle, was investigated with the aim of analyzing the influence of the employed resin on the fatigue delamination behaviour of both composites. In the case of dynamic loading, the number of cycles necessary for the onset of delamination was determined for a given elastic energy release rate and crack growth rate for different critical energy rates. The double cantilever beam (DCB) test was found to be suitable for promoting the initial delamination. The experimental results confirm the enhanced performance of the tough resin both in terms of crack initiation and growth rate.