With the ongoing Industry 4.0 (I4.0) revolution, plant management and supervision play a key role in the development and (re-)design of industrial plants. In the arising scenarios, the need to coordinate human workers and autonomous systems, sharing the same environment, teaming together, becomes a fundamental requirement. Indeed, even though automation in standard assembly lines has reached high efficiency and reliability, for complex and new applications, a certain amount of failure must be considered for future addressing. This paper presents a framework for the flexible coordination of such a complex and heterogeneous cyber-physical system. A digital Ttwin mirrors in real-time the plant system, while a dashboard displays plant status, providing the human operators with fundamental tools for supervision and prompt intervention in case of failure. The framework was developed and tested in an industrially relevant environment, specifically for the assembly of the interior of an aircraft fuselage.

The future of autonomous driving is slowly approaching, but there are still many steps to take before it can become a reality. It is crucial to pay attention to road infrastructure, because without it, intelligent vehicles will not be able to operate reliably, and it will never be possible to dispense of driver's control. This paper presents the work carried out for the detection of road markings damage using computer vision techniques. This is a complex task for which there are currently not many papers and large image sets in the literature. This study uses images from the public Road Damage Detection dataset for the D44 defect and also provides 971 new labelled images for Spanish roads. For this purpose, three detectors based on deep learning architectures (Faster RCNN, SDD and EfficientDet) have been used and single-source and mixed-source models have been studied to find the model that best fits the target images. Finally, F1-score values reaching 0.929 and 0.934 have been obtained for Japanese and Spanish images respectively which improve the state-of-the-art results by 25%. It can be concluded that the results of this study are promising, although the collection of many more images will be necessary for the scientific community to continue advancing in the future in this field of research.

Industrial vision highlights a growing trend in industrial systems. As camera sensors become smarter, the quality of data produced increases and it improves the accuracy results. One of the most decisive steps for getting accurate measurements is the calibration process. This paper aims to analyze the effect of four calibration parameters: camera focus, exposure time, calibration plate tilt and number of images, on the calibration accuracy. Endocentric and telecentric lenses are used in the image acquisition and a comparative quality analysis of the calibration result is obtained using statistical methods. A sample of 2176 images is used to generate the population and the calibration error is obtained for the different values of the parameters of interest. To study the influence of each parameter in the calibration error, a multivariable statistical analysis is performed. Statistically significant results were obtained for all parameters, except in the exposure time parameter, leading to the conclusion that the calibration results (and hence the measurement accuracy) can be improved by choosing the appropriate calibration parameters.

Due to changes and movements during a measurement process, the need to have an alignment system becomes imperative, in order to avoid all possible errors that may arise from a lack of alignment. In the effort to obtain the best possible conditions for alignment, it is necessary to check whether the object to be measured is well-positioned. Good alignment reduces down-time and should be part of the quality control process. The aim of this paper is the study of light and object alignments to monitor and achieve an optimal alignment system, in order to eliminate the effects of misalignment. The algorithms were tested with a not-optimal system to ascertain its efficiency. Besides, calibration parameters that have been studied in a previous work have been added to the whole experiment in order to quantify which impact has every single optimization in the measurement error of each stage.

Objectives The method of drug delivery directly into the cochlea with an implantable pump connected to a CI electrode array ensures long-term delivery and effective dose control, and also provides the possibility to use different drugs. The objective is to develop a model of inner ear pharmacokinetics of an implanted cochlea, with the delivery of FITC-Dextran, in the non-human primate model. Design A preclinical cochlear electrode array (CI Electrode Array HL14DD, manufactured by Cochlear Ltd.) attached to an implantable peristaltic pump filled with FITC-Dextran was implanted unilaterally in a total of 15 Macaca fascicularis (Mf). Three groups were created (5 Mf in each group), according to three different drug delivery times: 2 hours, 24 hours and 7 days. Perilymph (10 samples, 1¿L each) was sampled from the apex of the cochlea and measured immediately after extraction with a spectrofluorometer. After scarifying the specimens, x-Rays and histological analysis were performed. Results Surgery, sampling and histological analysis were performed successfully in all specimens. FITC-Dextran quantification showed different patterns, depending on the delivery group. In the 2 hours injection experiment, an increase in FITC-Dextran concentrations over the sample collection time was seen, reaching maximum concentration peaks (420-964µM) between samples 5 and 7, decreasing in successive samples, without returning to baseline ...

Background: Technological developments to treat hearing loss with different types of hearing aids and auditory implants have improved the auditory perception of patients, particularly in highly complex listening conditions. These devices can be fitted and adapted to enhance speech perception. Audiological tests that assess hearing with and without auditory devices have traditionally taken place in sound-attenuated audiometric booths. Although the insights gained from these tests are extremely useful, they do not accurately reflect everyday listening situations, and accurate information about the potential benefits of the hearing device in real acoustic scenarios cannot be established. Consequently, it is difficult to optimise this technology since fitting cannot be customised. Objectives: The aim of this study was to validate an audiological testing method using a new development, the Realistic Environment Audiometric Booth (REAB), in clinical practice. Materials: We used specifically designed software to perform audiological tests in an 8 m(2) sound-attenuated booth. The REAB was designed to conduct audiological tests in standard testing conditions and in new hearing scenarios that simulate real-life situations since sound can be emitted simultaneously or alternately 360 degrees around the patient, along with 3D images. Methods: Prospective study in which subjects were tested randomly in the REAB and the conventional booth (CB) in free field. Results: 150 subjects were recruited, mean age 56 +/- 20.7 years. Auditory outcomes for pure-tone audiometry showed a high correlation; this was also the case for speech audiometries in quiet and in noise. The outcome of the new scenarios with real-life noise was plotted, including the mean values and their confidence intervals. A decreasing trend was observed in the results obtained by the different groups, according to their hearing levels. Conclusions: We have developed and validated a new audiological testing method that enables hearing ability to be assessed in listening conditions similar to those found in real life. The REAB complements the tests performed in CBs, thereby aiding the diagnostic process by reproducing acoustic and visual scenarios that conventional tests do not offer.

European road safety has improved greatly in recent decades. However, the current numbers are still far away to reach the European Commission's road safety targets. In this context, Cooperative Intelligent Transport Systems (C-ITS) are expected to significantly improve road safety, traffic efficiency and comfort of driving, by helping the driver to make better decisions and adapt to the traffic situation. This paper puts forward two vision-based applications for traffic sign recognition (TSR) and real-time weather alerts, such as for fog-banks. These modules will support operators in road infrastructure maintenance tasks as well as drivers, giving them valuable information via C-ITS messages. Different state-of-the-art methods are analysed using both publicly available datasets (GTSB) as well as our own image databases (Ceit-TSR and Ceit-Foggy). The selected models for TSR implementation are based on Aggregated Chanel Features (ACF) and Convolutional Neural Networks (CNN) that reach more than 90% accuracy in real time. Regarding fog detection, an image feature extraction method on different colour spaces is proposed to differentiate sunny, cloudy and foggy scenes, as well as its visibility level. Both applications are already running in an onboard probe vehicle system.

Aeronautics, in the context of industry 4.0, is continuously evolving to respond to the market dynamics and has incorporated automation to many stages of aircraft manufacturing. However, most of the final assembly line processes are still done manually and remain a challenge. Virtual Reality (VR) technologies can be leveraged to study the incorporation of automation systems involving Human-Robot Coexistence (HRC) in assembly processes before the physical system is available, which is beneficial for increasing the productivity and identifying issues beforehand, thus, preventing unexpected costs. In this context, a VR simulation environment was developed with two innovative factors: (1) The possibility to evaluate multiple new automated and semi-automated cabin and position processes and select the best one in terms of specific Key Performance Indicators (KPIs) for a future implementation in the physical system and (2) the capability to study the ergonomics of the human worker inside the narrow space of the fuselage while assembling the parts and coexisting with robots, without compromising the worker's safety. The results show that most of the new proposed strategies improve the assembly time, worker cost, or ergonomics of the process, with an investment varying between 100 K and 200 K euros and ROI of 1-2 years.

Featured Application Comparison two digital solutions (tablet based and Augmented Reality based) for bus maintenance against the traditional solution based on paper. This paper shows two developed digital systems as an example of intelligent garage and maintenance that targets the applicability of augmented reality and wearable devices technologies to the maintenance of bus fleets. Both solutions are designed to improve the maintenance process based on verification of tasks checklist. The main contribution of the paper focuses on the implementation of the prototypes in the company's facilities in an operational environment with real users and address the difficulties inherent in the transfer of a technology to a real work environment, such as a mechanical workshop. The experiments have been conducted in real operation thanks to the involvement of the public transport operator DBUS, which operates public transport buses in the city of Donostia-San Sebastian (Spain). Two solutions have been developed and compared against the traditional process: one based on Tablet and another one based on Microsoft HoloLens. The results show objective metrics (Key Performance Indicators, KPI) as well as subjective metrics based on questionnaires comparing the two technological approaches against the traditional one based on guide work and paper.

Quality control has become a priority in the inspection processes of industrial manufacturing of gears. Due to the advancement of technology and the realisations of Industry 4.0, smart factories demand high precision and accuracy in the measurements and inspection of industrial gears. Machine vision technology provides image-based inspection and analysis for such demanding applications. With the use of software, sensors, cameras, and robot guidance, such integrated systems can be realised. The aim of this paper is to deploy an improved machine vision application to determine the precise measurement of industrial gears, at subpixel level, with the potential to improve quality control, reduce downtime, and optimise the inspection process. A machine vision application (Vision2D) has been developed to acquire and analyze captured images to implement the process of measurement and inspection. Firstly, a very minimum calibration error of 0.06 pixel was obtained after calibration. The calibrated vision system was verified by measuring a ground-truth sample gear in a Coordinate Measuring Machine (CMM), using the parameter generated as the nominal value of the outer diameter. A methodical study of the global uncertainty associated with the process is carried out in order to know better the admissible zone for accepting gears. After that, the proposed system analyzed twelve other samples with a nominal tolerance threshold of +/- 0.020 mm. Amongst the gears inspected, the Vision2D application identified eight gears which are accepted and four bad gears which are rejected. The inspection result demonstrates an improvement in the algorithm of the Vision2D system application when compared with the previous existing algorithms.

This chapter describes a surface reconstruction method that mixes interpolating and approximating features and its implementation in graphics hardware. Hybrid methods are useful in areas such sculpting, medicine, and cultural heritage, where details must be preserved. Such cases may also contain noise (due to sampling inaccuracies) or duplicated points (in the case of the scan is done from multiple points of view), where hybrid methods provide an interesting solution. The proposed method makes use of a point projection operator to create a regular distributed and noise free set of points, which is reconstructed using local Delaunay triangulations. Both points projection and triangulation methods are studied in its basic serial version, but aiming to design parallel versions (more specifically GPU implementations) that increase their performance. The adaptations required for the parallel reconstruction are discussed, and several implementation details are given.