Design and Characterization of a Wearable Inertial Measurement Unit.

The utilization of inertial measurement units as wearable sensors is proliferating across various domains, such as health care, sports, and rehabilitation. This expansion has produced a market of devices tailored to accommodate very specific ranges of operational demands. Simultaneously, this growth is creating opportunities for the development of a new class of devices more oriented towards general-purpose use and capable of capturing both high-frequency signals for short-term, event-driven motion analysis and low-frequency signals for extended monitoring. For such a design, which combines flexibility and low cost, a rigorous evaluation of the device in terms of deviation, noise levels, and precision is essential. This evaluation is crucial for identifying potential improvements and refining the design accordingly, yet it is rarely addressed in the literature. This paper presents the development process of such a device. The results of the design process demonstrate acceptable performance in optimizing energy consumption and storage capacity while highlighting the most critical optimizations needed to advance the device towards the goal of a smart, general-purpose unit for human motion monitoring.

Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models.

Semantic image segmentation is a core task for autonomous driving, which is performed by deep models. Since training these models draws to a curse of human-based image labeling, the use of synthetic images with automatically generated labels together with unlabeled real-world images is a promising alternative. This implies addressing an unsupervised domain adaptation (UDA) problem. In this paper, we propose a new co-training procedure for synth-to-real UDA of semantic segmentation models. It performs iterations where the (unlabeled) real-world training images are labeled by intermediate deep models trained with both the (labeled) synthetic images and the real-world ones labeled in previous iterations. More specifically, a self-training stage provides two domain-adapted models and a model collaboration loop allows the mutual improvement of these two models. The final semantic segmentation labels (pseudo-labels) for the real-world images are provided by these two models. The overall procedure treats the deep models as black boxes and drives their collaboration at the level of pseudo-labeled target images, i.e., neither modifying loss functions is required, nor explicit feature alignment. We test our proposal on standard synthetic and real-world datasets for onboard semantic segmentation. Our procedure shows improvements ranging from approximately 13 to 31 mIoU points over baselines.

Estimation of Ground Contact Time with Inertial Sensors from the Upper Arm and the Upper Back.

Ground contact time (GCT) is one of the most relevant factors when assessing running performance in sports practice. In recent years, inertial measurement units (IMUs) have been widely used to automatically evaluate GCT, since they can be used in field conditions and are friendly and easy to wear devices. In this paper we describe the results of a systematic search, using the Web of Science, to assess what reliable options are available to GCT estimation using inertial sensors. Our analysis reveals that estimation of GCT from the upper body (upper back and upper arm) has rarely been addressed. Proper estimation of GCT from these locations could permit an extension of the analysis of running performance to the public, where users, especially vocational runners, usually wear pockets that are ideal to hold sensing devices fitted with inertial sensors (or even using their own cell phones for that purpose). Therefore, in the second part of the paper, an experimental study is described. Six subjects, both amateur and semi-elite runners, were recruited for the experiments, and ran on a treadmill at different paces to estimate GCT from inertial sensors placed at the foot (for validation purposes), the upper arm, and upper back. Initial and final foot contact events were identified in these signals to estimate the GCT per step, and compared to times estimated from an optical MOCAP (Optitrack), used as the ground truth. We found an average error in GCT estimation of 0.01 s in absolute value using the foot and the upper back IMU, and of 0.05 s using the upper arm IMU. Limits of agreement (LoA, 1.96 times the standard deviation) were [-0.01 s, 0.04 s], [-0.04 s, 0.02 s], and [0.0 s, 0.1 s] using the sensors on the foot, the upper back, and the upper arm, respectively.

Real-Time Short-Term Pedestrian Trajectory Prediction Based on Gait Biomechanics.

The short-term prediction of a person's trajectory during normal walking becomes necessary in many environments shared by humans and robots. Physics-based approaches based on Newton's laws of motion seem best suited for short-term predictions, but the intrinsic properties of human walking conflict with the foundations of the basic kinematical models compromising their performance. In this paper, we propose a short-time prediction method based on gait biomechanics for real-time applications. This method relays on a single biomechanical variable, and it has a low computational burden, turning it into a feasible solution to implement in low-cost portable devices. We evaluate its performance from an experimental benchmark where several subjects walked steadily over straight and curved paths. With this approach, the results indicate a performance good enough to be applicable to a wide range of human-robot interaction applications.

Co-Training for Deep Object Detection: Comparing Single-Modal and Multi-Modal Approaches.

Top-performing computer vision models are powered by convolutional neural networks (CNNs). Training an accurate CNN highly depends on both the raw sensor data and their associated ground truth (GT). Collecting such GT is usually done through human labeling, which is time-consuming and does not scale as we wish. This data-labeling bottleneck may be intensified due to domain shifts among image sensors, which could force per-sensor data labeling. In this paper, we focus on the use of co-training, a semi-supervised learning (SSL) method, for obtaining self-labeled object bounding boxes (BBs), i.e., the GT to train deep object detectors. In particular, we assess the goodness of multi-modal co-training by relying on two different views of an image, namely, appearance (RGB) and estimated depth (D). Moreover, we compare appearance-based single-modal co-training with multi-modal. Our results suggest that in a standard SSL setting (no domain shift, a few human-labeled data) and under virtual-to-real domain shift (many virtual-world labeled data, no human-labeled data) multi-modal co-training outperforms single-modal. In the latter case, by performing GAN-based domain translation both co-training modalities are on par, at least when using an off-the-shelf depth estimation model not specifically trained on the translated images.

Metrological Evaluation of Human-Robot Collaborative Environments Based on Optical Motion Capture Systems.

In the context of human-robot collaborative shared environments, there has been an increase in the use of optical motion capture (OMC) systems for human motion tracking. The accuracy and precision of OMC technology need to be assessed in order to ensure safe human-robot interactions, but the accuracy specifications provided by manufacturers are easily influenced by various factors affecting the measurements. This article describes a new methodology for the metrological evaluation of a human-robot collaborative environment based on optical motion capture (OMC) systems. Inspired by the ASTM E3064 test guide, and taking advantage of an existing industrial robot in the production cell, the system is evaluated for mean error, error spread, and repeatability. A detailed statistical study of the error distribution across the capture area is carried out, supported by a Mann-Whitney U-test for median comparisons. Based on the results, optimal capture areas for the use of the capture system are suggested. The results of the proposed method show that the metrological characteristics obtained are compatible and comparable in quality to other methods that do not require the intervention of an industrial robot.

Recognizing New Classes with Synthetic Data in the Loop: Application to Traffic Sign Recognition.

On-board vision systems may need to increase the number of classes that can be recognized in a relatively short period. For instance, a traffic sign recognition system may suddenly be required to recognize new signs. Since collecting and annotating samples of such new classes may need more time than we wish, especially for uncommon signs, we propose a method to generate these samples by combining synthetic images and Generative Adversarial Network (GAN) technology. In particular, the GAN is trained on synthetic and real-world samples from known classes to perform synthetic-to-real domain adaptation, but applied to synthetic samples of the new classes. Using the Tsinghua dataset with a synthetic counterpart, SYNTHIA-TS, we have run an extensive set of experiments. The results show that the proposed method is indeed effective, provided that we use a proper Convolutional Neural Network (CNN) to perform the traffic sign recognition (classification) task as well as a proper GAN to transform the synthetic images. Here, a ResNet101-based classifier and domain adaptation based on CycleGAN performed extremely well for a ratio ∼ 1 / 4 for new/known classes; even for more challenging ratios such as ∼ 4 / 1 , the results are also very positive.

Accelerometry-Based Distance Estimation for Ambulatory Human Motion Analysis.

In human motion science, accelerometers are used as linear distance sensors by attaching them to moving body parts, with their measurement axes its measurement axis aligned in the direction of motion. When double integrating the raw sensor data, multiple error sources are also integrated integrated as well, producing inaccuracies in the final position estimation which increases fast with the integration time. In this paper, we make a systematic and experimental comparison of different methods for position estimation, with different sensors and in different motion conditions. The objective is to correlate practical factors that appear in real applications, such as motion mean velocity, path length, calibration method, or accelerometer noise level, with the quality of the estimation. The results confirm that it is possible to use accelerometers to estimate short linear displacements of the body with a typical error of around 4.5% in the general conditions tested in this study. However, they also show that the motion kinematic conditions can be a key factor in the performance of this estimation, as the dynamic response of the accelerometer can affect the final results. The study lays out the basis for a better design of distance estimations, which are useful in a wide range of ambulatory human motion monitoring applications.

On-Board Detection of Pedestrian Intentions.

Avoiding vehicle-to-pedestrian crashes is a critical requirement for nowadays advanced driver assistant systems (ADAS) and future self-driving vehicles. Accordingly, detecting pedestrians from raw sensor data has a history of more than 15 years of research, with vision playing a central role. During the last years, deep learning has boosted the accuracy of image-based pedestrian detectors. However, detection is just the first step towards answering the core question, namely is the vehicle going to crash with a pedestrian provided preventive actions are not taken? Therefore, knowing as soon as possible if a detected pedestrian has the intention of crossing the road ahead of the vehicle is essential for performing safe and comfortable maneuvers that prevent a crash. However, compared to pedestrian detection, there is relatively little literature on detecting pedestrian intentions. This paper aims to contribute along this line by presenting a new vision-based approach which analyzes the pose of a pedestrian along several frames to determine if he or she is going to enter the road or not. We present experiments showing 750 ms of anticipation for pedestrians crossing the road, which at a typical urban driving speed of 50 km/h can provide 15 additional meters (compared to a pure pedestrian detector) for vehicle automatic reactions or to warn the driver. Moreover, in contrast with state-of-the-art methods, our approach is monocular, neither requiring stereo nor optical flow information.

Pedestrian Detection at Day/Night Time with Visible and FIR Cameras: A Comparison.

Despite all the significant advances in pedestrian detection brought by computer vision for driving assistance, it is still a challenging problem. One reason is the extremely varying lighting conditions under which such a detector should operate, namely day and nighttime. Recent research has shown that the combination of visible and non-visible imaging modalities may increase detection accuracy, where the infrared spectrum plays a critical role. The goal of this paper is to assess the accuracy gain of different pedestrian models (holistic, part-based, patch-based) when training with images in the far infrared spectrum. Specifically, we want to compare detection accuracy on test images recorded at day and nighttime if trained (and tested) using (a) plain color images; (b) just infrared images; and (c) both of them. In order to obtain results for the last item, we propose an early fusion approach to combine features from both modalities. We base the evaluation on a new dataset that we have built for this purpose as well as on the publicly available KAIST multispectral dataset.

Oleogels and reverse emulsions stabilized by acetylated Kraft lignins.

Acetylated Kraft lignins were evaluated for their ability of structuring vegetable oils into oleogels. Microwave-assisted acetylation was used to adjust lignin's degree of substitution according to reaction temperature (130 to 160 °C), and its effect in improving the viscoelasticity of the oleogels, which was related to the hydroxyl group content. The results were compared with those obtained by Kraft lignins acetylated using conventional methods at room temperature. A higher microwave temperature resulted in gel-like oil dispersions with improved viscoelastic properties, and stronger shear-thinning character, along with enhanced long-term stability. Lignin nanoparticles structured castor oil by enhancing hydrogen bonding between the hydroxyl groups of the oil and the nanoparticles. The oil structuring capacity of the modified lignins enhanced the stability of water-in-oil Pickering emulsions that resulted from low-energy mixing.

Consensus document for lipid profile determination and reporting in Spanish clinical laboratories. What parameters should be included in a basic lipid profile?

Cardiovascular diseases (CVD) continue to be the main cause of death in our country. Adequate control of lipid metabolism disorders is a key challenge in cardiovascular prevention that is far from being achieved in real clinical practice. There is a great heterogeneity in the reports of lipid metabolism from Spanish clinical laboratories, which may contribute to its poor control. For this reason, a working group of the main scientific societies involved in the care of patients at vascular risk, has prepared this document with a consensus proposal on the determination of the basic lipid profile in cardiovascular prevention, recommendations for its realization and unification of criteria to incorporate the lipid control goals appropriate to the vascular risk of the patients in the laboratory reports.

Consensus document for lipid profile testing and reporting in Spanish clinical laboratories: what parameters should a basic lipid profile include?

Cardiovascular diseases (CVD) continue to be the main cause of death in our country. Adequate control of lipid metabolism disorders is a key challenge in cardiovascular prevention that is far from being achieved in real clinical practice. There is a great heterogeneity in the reports of lipid metabolism from Spanish clinical laboratories, which may contribute to its poor control. For this reason, a working group of the main scientific societies involved in the care of patients at vascular risk, has prepared this document with a consensus proposal on the determination of the basic lipid profile in cardiovascular prevention, recommendations for its realization and unification of criteria to incorporate the lipid control goals appropriate to the vascular risk of the patients in the laboratory reports.

Consensus document for lipid profile testing and reporting in Spanish clinical laboratories.

Cardiovascular diseases (CVD) continue to be the main cause of death in our country. Adequate control of lipid metabolism disorders is a key challenge in cardiovascular prevention that is far from being achieved in real clinical practice. There is a great heterogeneity in the reports of lipid metabolism from Spanish clinical laboratories, which may contribute to its poor control. For this reason, a working group of the main scientific societies involved in the care of patients at vascular risk, has prepared this document with a consensus proposal on the determination of the basic lipid profile in cardiovascular prevention, recommendations for its realization and unification of criteria to incorporate the lipid control goals appropriate to the vascular risk of the patients in the laboratory reports.

Slope estimation during normal walking using a shank-mounted inertial sensor.

In this paper we propose an approach for the estimation of the slope of the walking surface during normal walking using a body-worn sensor composed of a biaxial accelerometer and a uniaxial gyroscope attached to the shank. It builds upon a state of the art technique that was successfully used to estimate the walking velocity from walking stride data, but did not work when used to estimate the slope of the walking surface. As claimed by the authors, the reason was that it did not take into account the actual inclination of the shank of the stance leg at the beginning of the stride (mid stance). In this paper, inspired by the biomechanical characteristics of human walking, we propose to solve this issue by using the accelerometer as a tilt sensor, assuming that at mid stance it is only measuring the gravity acceleration. Results from a set of experiments involving several users walking at different inclinations on a treadmill confirm the feasibility of our approach. A statistical analysis of slope estimations shows in first instance that the technique is capable of distinguishing the different slopes of the walking surface for every subject. It reports a global RMS error (per-unit difference between actual and estimated inclination of the walking surface for each stride identified in the experiments) of 0.05 and this can be reduced to 0.03 with subject-specific calibration and post processing procedures by means of averaging techniques.

Lignocellulosic Materials for the Production of Biofuels, Biochemicals and Biomaterials and Applications of Lignocellulose-Based Polyurethanes: A Review.

The present review is devoted to the description of the state-of-the-art techniques and procedures concerning treatments and modifications of lignocellulosic materials in order to use them as precursors for biomaterials, biochemicals and biofuels, with particular focus on lignin and lignin-based products. Four different main pretreatment types are outlined, i.e., thermal, mechanical, chemical and biological, with special emphasis on the biological action of fungi and bacteria. Therefore, by selecting a determined type of fungi or bacteria, some of the fractions may remain unaltered, while others may be decomposed. In this sense, the possibilities to obtain different final products are massive, depending on the type of microorganism and the biomass selected. Biofuels, biochemicals and biomaterials derived from lignocellulose are extensively described, covering those obtained from the lignocellulose as a whole, but also from the main biopolymers that comprise its structure, i.e., cellulose, hemicellulose and lignin. In addition, special attention has been paid to the formulation of bio-polyurethanes from lignocellulosic materials, focusing more specifically on their applications in the lubricant, adhesive and cushioning material fields. High-performance alternatives to petroleum-derived products have been reported, such as adhesives that substantially exceed the adhesion performance of those commercially available in different surfaces, lubricating greases with tribological behaviour superior to those in lithium and calcium soap and elastomers with excellent static and dynamic performance.

Development of Bio-Based Materials: Synthesis, Characterization and Applications.

The need to find suitable biomaterials and procedures from alternative products able to imitate or even enhance the performance of currently used products has become an important focus of research today due to the depletion of non-renewable resources and the increasing concern related to climate change, sustainability and environmental preservation [...].

A Review of Rigid Polymeric Cellular Foams and Their Greener Tannin-Based Alternatives.

This review focuses on the description of the main processes and materials used for the formulation of rigid polymer foams. Polyurethanes and their derivatives, as well as phenolic systems, are described, and their main components, foaming routes, end of life, and recycling are considered. Due to environmental concerns and the need to find bio-based alternatives for these products, special attention is given to a recent class of polymeric foams: tannin-based foams. In addition to their formulation and foaming procedures, their main structural, thermal, mechanical, and fire resistance properties are described in detail, with emphasis on their advanced applications and recycling routes. These systems have been shown to possess very interesting properties that allow them to be considered as potential substitutes for non-renewable rigid polymeric cellular foams.

Lignin-enriched residues from bioethanol production: Chemical characterization, isocyanate functionalization and oil structuring properties.

Lignin-enriched waste products from bioethanol production of agriculture residues were tested as structuring agents in castor oil once functionalized with hexamethylene diisocyanate. Cane bagasse, barley and wheat straw were processed through steam explosion, pre-saccharification and simultaneous saccharification and fermentation (PSSF). Alternatively, cane bagasse was submitted to steam explosion and enzymatic hydrolysis (EH). Several Nuclear Magnetic Resonance techniques were used to characterize both residues and NCO-functionalized counterparts. The ß-O-4'/resinol/phenylcoumaran content and hydroxyphenyl/guaiacyl/syringyl distribution depend on biomass source, pretreatment, and enzymatic hydrolysis. Total hydroxyl content (from 1.23 for cane bagasse to 1.85 for wheat straw residues), aromatic/aliphatic hydroxyl ratio (0.78 for cane bagasse and 0.61 and 0.49 for barley and wheat straw residues, respectively) and S/G ratio (ranging from 0.25 to 0.86) influence the NCO-functionalization and oleogel rheological response. Oleogels obtained with barley straw residues exhibited the highest values of the storage modulus; around 2 × 105 Pa and 104 Pa for 25% and 20% contents, respectively. PSSF process showed weaker modification, leading to softer viscoelastic response compared to EH. These oleogels exhibited rheological properties similar to lubricating greases of different NLGI grades. Therefore, we herein show an integrative protocol for the valorization of lignin-enriched residues from bioethanol production as potential thickeners of lubricating greases.

Distributed Learning and Inference With Compressed Images.

Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are increasingly common (e.g. autonomous vehicles, cloud computing, smartphones). In addition, many devices suffer from limited resources to store or transmit data (e.g. storage space, channel capacity). In these scenarios, lossy image compression plays a crucial role to effectively increase the number of images collected under such constraints. However, lossy compression entails some undesired degradation of the data that may harm the performance of the downstream analysis task at hand, since important semantic information may be lost in the process. Moreover, we may only have compressed images at training time but are able to use original images at inference time (i.e. test), or vice versa, and in such a case, the downstream model suffers from covariate shift. In this paper, we analyze this phenomenon, with a special focus on vision-based perception for autonomous driving as a paradigmatic scenario. We see that loss of semantic information and covariate shift do indeed exist, resulting in a drop in performance that depends on the compression rate. In order to address the problem, we propose dataset restoration, based on image restoration with generative adversarial networks (GANs). Our method is agnostic to both the particular image compression method and the downstream task; and has the advantage of not adding additional cost to the deployed models, which is particularly important in resource-limited devices. The presented experiments focus on semantic segmentation as a challenging use case, cover a broad range of compression rates and diverse datasets, and show how our method is able to significantly alleviate the negative effects of compression on the downstream visual task.