Search

Data-driven algorithms have surpassed traditional techniques in almost every aspect in robotic vision problems. Such algorithms need vast amounts of quality data to be able to work properly after their training process. Gathering and annotating that sheer amount of data in the real world is a time-consuming and error-prone task. Those problems limit scale and quality. Synthetic data generation has become increasingly popular since it is faster to generate and automatic to annotate. However, most of the current datasets and environments lack realism, interactions, and details from the real world. UnrealROX is an environment built over Unreal Engine 4 which aims to reduce that reality gap by leveraging hyperrealistic indoor scenes that are explored by robot agents which also interact with objects in a visually realistic manner in that simulated world. Photorealistic scenes and robots are rendered by Unreal Engine into a virtual reality headset which captures gaze so that a human operator can move the robot and use controllers for the robotic hands; scene information is dumped on a per-frame basis so that it can be reproduced offline to generate raw data and ground truth annotations. This virtual reality environment enables robotic vision researchers to generate realistic and visually plausible data with full ground truth for a wide variety of problems such as class and instance semantic segmentation, object detection, depth estimation, visual grasping, and navigation., Published in Virtual Reality journal

Registration is the process that computes the transformation that aligns sets of data. Commonly, a registration process can be divided into four main steps: target selection, feature extraction, feature matching, and transform computation for the alignment. The accuracy of the result depends on multiple factors, the most significant are the quantity of input data, the presence of noise, outliers and occlusions, the quality of the extracted features, real-time requirements and the type of transformation, especially those ones defined by multiple parameters, like non-rigid deformations. Recent advancements in machine learning could be a turning point in these issues, particularly with the development of deep learning (DL) techniques, which are helping to improve multiple computer vision problems through an abstract understanding of the input data. In this paper, a review of deep learning-based registration methods is presented. We classify the different papers proposing a framework extracted from the traditional registration pipeline to analyse the new learning-based proposal strengths. Deep Registration Networks (DRNs) try to solve the alignment task either replacing part of the traditional pipeline with a network or fully solving the registration problem. The main conclusions extracted are, on the one hand, 1) learning-based registration techniques cannot always be clearly classified in the traditional pipeline. 2) These approaches allow more complex inputs like conceptual models as well as the traditional 3D datasets. 3) In spite of the generality of learning, the current proposals are still ad hoc solutions. Finally, 4) this is a young topic that still requires a large effort to reach general solutions able to cope with the problems that affect traditional approaches., Published in Applied Sciences

In the last years, the care of dependent people, either by disease, accident, disability, or age, is one of the current priority research topics in developed countries. Moreover, such care is intended to be at patients home, in order to minimize the cost of therapies. Patients rehabilitation will be fulfilled when their integration in society is achieved, either in the family or in a work environment. To address this challenge, we propose the development and evaluation of an assistant for people with acquired brain injury or dependents. This assistant is twofold: in the patient’s home is based on the design and use of an intelligent environment with abilities to monitor and active learning, combined with an autonomous social robot for interactive assistance and stimulation. On the other hand, it is complemented with an outdoor assistant, to help patients under disorientation or complex situations. This involves the integration of several existing technologies and provides solutions to a variety of technological challenges. Deep leaning-based techniques are proposed as core technology to solve these problems. This work has been funded by the Spanish Government TIN2016-76515-R grant for the COMBAHO project, supported with Feder funds. It has also been supported by the University of Alicante project GRE16-19 and the Valencian Government GV/2018/022. This work has also been supported by Spanish grants for PhD studies FPU15/04516 and ACIF/2017/243. Experiments were made possible by a generous hardware donation from NVIDIA.

The ability to predict, anticipate and reason about future outcomes is a key component of intelligent decision-making systems. In light of the success of deep learning in computer vision, deep-learning-based video prediction emerged as a promising research direction. Defined as a self-supervised learning task, video prediction represents a suitable framework for representation learning, as it demonstrated potential capabilities for extracting meaningful representations of the underlying patterns in natural videos. Motivated by the increasing interest in this task, we provide a review on the deep learning methods for prediction in video sequences. We firstly define the video prediction fundamentals, as well as mandatory background concepts and the most used datasets. Next, we carefully analyze existing video prediction models organized according to a proposed taxonomy, highlighting their contributions and their significance in the field. The summary of the datasets and methods is accompanied with experimental results that facilitate the assessment of the state of the art on a quantitative basis. The paper is summarized by drawing some general conclusions, identifying open research challenges and by pointing out future research directions., Submitted to TPAMI

Image semantic segmentation is more and more being of interest for computer vision and machine learning researchers. Many applications on the rise need accurate and efficient segmentation mechanisms: autonomous driving, indoor navigation, and even virtual or augmented reality systems to name a few. This demand coincides with the rise of deep learning approaches in almost every field or application target related to computer vision, including semantic segmentation or scene understanding. This paper provides a review on deep learning methods for semantic segmentation applied to various application areas. Firstly, we formulate the semantic segmentation problem and define the terminology of this field as well as interesting background concepts. Next, the main datasets and challenges are exposed to help researchers decide which are the ones that best suit their needs and goals. Then, existing methods are reviewed, highlighting their contributions and their significance in the field. We also devote a part of the paper to review common loss functions and error metrics for this problem. Finally, quantitative results are given for the described methods and the datasets in which they were evaluated, following up with a discussion of the results. At last, we point out a set of promising future works and draw our own conclusions about the state of the art of semantic segmentation using deep learning techniques. This work has been funded by the Spanish Government TIN2016-76515-R funding for the COMBAHO project, supported with Feder funds. It has also been supported by a Spanish national grant for PhD studies FPU15/04516 (Alberto Garcia-Garcia). In addition, it was also funded by the grant Ayudas para Estudios de Master e Iniciacion a la Investigacion from the University of Alicante.

This article describes how the human activity recognition in videos is a very attractive topic among researchers due to vast possible applications. This article considers the analysis of behaviors and activities in videos obtained with low-cost RGB cameras. To do this, a system is developed where a video is input, and produces as output the possible activities happening in the video. This information could be used in many applications such as video surveillance, disabled person assistance, as a home assistant, employee monitoring, etc. The developed system makes use of the successful techniques of Deep Learning. In particular, convolutional neural networks are used to detect features in the video images, meanwhile Recurrent Neural Networks are used to analyze these features and predict the possible activity in the video. This work has been funded by the Spanish Government TIN2016-76515-R grant for the COMBAHO project, supported with Feder funds.

This article describes how the human activity recognition in videos is a very attractive topic among researchers due to vast possible applications. This article considers the analysis of behaviors and activities in videos obtained with low-cost RGB cameras. To do this, a system is developed where a video is input, and produces as output the possible activities happening in the video. This information could be used in many applications such as video surveillance, disabled person assistance, as a home assistant, employee monitoring, etc. The developed system makes use of the successful techniques of Deep Learning. In particular, convolutional neural networks are used to detect features in the video images, meanwhile Recurrent Neural Networks are used to analyze these features and predict the possible activity in the video.

State-of-the-art deep learning-based models used to address hand challenges, e.g. 3D hand joint estimation, need a vast amount of annotated data to achieve a good performance. The lack of data is a problem of paramount importance. Consequently, the use of synthetic datasets for training deep learning models is a trend and represents a promising avenue to improve existing approaches. Nevertheless, currently existing synthetic datasets lack of accurate and complete annotations, realism, and also rich hand-object interactions. For this purpose, in our work we present a synthetic dataset featuring rich hand-object interactions in photorealistic scenarios. The applications of our dataset for hand-related challenges are unlimited. To validate our data, we propose an initial approach to 3D hand joint estimation using a graph convolutional network feeded with point cloud data. Another point in favour of our dataset is that interactions are performed using realistic objects extracted from the YCB dataset. This could allow to test trained systems with our synthetic dataset using images/videos manipulating the same objects in real life.

Interaction in virtual reality (VR) environments (e.g. grasping and manipulating virtual objects) is essential to ensure a pleasant and immersive experience. In this work, we propose a visually realistic, flexible and robust grasping system that enables real-time interactions in virtual environments. Resulting grasps are visually realistic because hand is automatically fitted to the object shape from a position and orientation determined by the user using the VR handheld controllers (e.g. Oculus Touch motion controllers). Our approach is flexible because it can be adapted to different hand meshes (e.g. human or robotic hands) and it is also easily customizable. Moreover, it enables interaction with different objects regardless their geometries. In order to validate our proposal, an exhaustive qualitative and quantitative performance analysis has been carried out. On one hand, qualitative evaluation was used in the assessment of abstract aspects, such as motor control, finger movement realism, and interaction realism. On the other hand, for the quantitative evaluation a novel metric has been proposed to visually analyze the performed grips. Performance analysis results indicate that previous experience with our grasping system is not a prerequisite for an enjoyable, natural and intuitive VR interaction experience. This work has been funded by the Spanish Government TIN2016-76515-R grant for the COMBAHO project, supported with Feder funds. This work has also been supported by three Spanish national grants for PhD studies (FPU15/04516, FPU17/00166, and ACIF/2018/197), by the University of Alicante project GRE16- 19, and by the Valencian Government project GV/2018/022. Experiments were made possible by a generous hardware donation from NVIDIA.

Enter the RobotriX, an extremely photorealistic indoor dataset designed to enable the application of deep learning techniques to a wide variety of robotic vision problems. The RobotriX consists of hyperrealistic indoor scenes which are explored by robot agents which also interact with objects in a visually realistic manner in that simulated world. Photorealistic scenes and robots are rendered by Unreal Engine into a virtual reality headset which captures gaze so that a human operator can move the robot and use controllers for the robotic hands; scene information is dumped on a per-frame basis so that it can be reproduced offline using UnrealCV to generate raw data and ground truth labels. By taking this approach, we were able to generate a dataset of 38 semantic classes across 512 sequences totaling 8M stills recorded at +60 frames per second with full HD resolution. For each frame, RGB-D and 3D information is provided with full annotations in both spaces. Thanks to the high quality and quantity of both raw information and annotations, the RobotriX will serve as a new milestone for investigating 2D and 3D robotic vision tasks with large-scale data-driven techniques.

Electro-optical measurements, i.e., optical waveguides and plasmonic based electrochemical impedance spectroscopy (P-EIS), are based on the sensitive dependence of refractive index of electro-optical sensors on surface charge density, modulated by an AC electrical field applied to the sensor surface. Recently, P-EIS has emerged as a new analytical tool that can resolve local impedance with high, optical spatial resolution, without using microelectrodes. This study describes a high speed image acquisition and processing system for electro-optical measurements, based on a high speed complementary metal-oxide semiconductor (CMOS) sensor and a field-programmable gate array (FPGA) board. The FPGA is used to configure CMOS parameters, as well as to receive and locally process the acquired images by performing Fourier analysis for each pixel, deriving the real and imaginary parts of the Fourier coefficients for the AC field frequencies. An AC field generator, for single or multi-sine signals, is synchronized with the high speed acquisition system for phase measurements. The system was successfully used for real-time angle-resolved electro-plasmonic measurements from 30 Hz up to 10 kHz, providing results consistent to ones obtained by a conventional electrical impedance approach. The system was able to detect amplitude variations with a relative variation of ±1%, even for rather low sampling rates per period (i.e., 8 samples per period). The PC (personal computer) acquisition and control software allows synchronized acquisition for multiple FPGA boards, making it also suitable for simultaneous angle-resolved P-EIS imaging.

This paper contains a solution for a digital PI controller implemented in a synchronous Buck converter used in Constant Voltage configuration. In such applications, a digital PI controller can replace a traditional PI compensation network made with analog components. This is an approachable solution because Proportional and Integral blocks can be easily defined following a transfer function which can tune the respectively coefficients until a stable DC/DC converter is obtained. The PI terms can be digitally implemented using a microcontroller, and then added to the entire system which must provide an adequate response time, maintain system stability and reduce the output voltage steady-state error. A closed loop control system simulation will confirm the above statements. The main advantage of the digital PI control is that no additional analog components are required, resulting in a higher level of integration, also device calibration can be done more smoothly.

The resonant controllers offer significant advantages for control of power converters that operate with time-vary reference signals. However, this kind of control is affected by the errors introduced by discretization and quantization and may require floating-point Digital Signal Processors (DSP) for proper implementation. This paper addresses the issues related to the implementation of resonant current control using low-cost, 16-bit, fixed-point DSPs for cost-sensitive applications like the low-power residential microgrids. The performance of the proposed resonant controller is evaluated using a single-phase inverter that can be part of a grid-connected Uninterruptible Power Supply (UPS).

Object grasping in domestic environments using social robots has an enormous potential to help dependant people with certain degree of disability. In this work, we made use of the well-known Pepper social robot to carry out such task. We provide an integrated solution using ROS to recognize and grasp simple objects. That system was deployed on an accelerator platform (Jetson TX1) to be able to perform object recognition in real time using RGB-D sensors attached to the robot. By using our system, we proved that the Pepper robot shows a great potential for such kind of domestic assistance tasks.

In this work, a Schaeffer language recognition system is proposed in order to help autistic children overcome communicative disorders. Using Schaeffer language as a speech and language therapy, improves children communication skills and at the same time the understanding of language productions. Nevertheless, the teaching process of children in performing gestures properly is not straightforward. For this purpose, this system will teach children with autism disorder the correct way to communicate using gestures in combination with speech reproduction. The main purpose is to accelerate the learning process and increase children interest by using a technological approach. Several recurrent neural network‐based approaches have been tested, such as vanilla recurrent neural networks, long short‐term memory networks,and gated recurrent unit‐based models. In order to select the most suitable model, an extensive comparison has been conducted reporting a 93.13% classification success rate over a subset of 25 Schaeffer gestures by using an long short‐term memory‐based approach. Our dataset consists on pose‐based features such as angles and euclidean distances extracted from the raw skeletal data provided by a Kinect v2 sensor. This work has been funded by the Spanish Government TIN2016-76515-R grant for the COMBAHO project, supported with Feder funds. This work has also been supported by a Spanish national grant for PhD studies FPU15/04516 and the grant "Ayudas para Estudios de Máster e Iniciación a la Investigación" from the University of Alicante. Experiments were made possible by a generous hardware donation from NVIDIA (Tesla K40).

In this work, we carry out a study of the effect of adverse conditions, which characterize real-world scenes, on the accuracy of a Convolutional Neural Network applied to 3D object class recognition. Firstly, we discuss possible ways of representing 3D data to feed the network. In addition, we propose a set of representations to be tested. Those representations consist of a grid-like structure (fixed and adaptive) and a measure for the occupancy of each cell of the grid (binary and normalized point density). After that, we propose and implement a Convolutional Neural Network for 3D object recognition using Caffe. At last, we carry out an in-depth study of the performance of the network over a 3D CAD model dataset, the Princeton ModelNet project, synthetically simulating occlusions and noise models featured by common RGB-D sensors. The results show that the volumetric representations for 3D data play a key role on the recognition process and Convolutional Neural Network can be considerably robust to noise and occlusions if a proper representation is chosen. This work has been supported by the Spanish Government DPI2013-40534-R grant for the SIRMAVED project, also supported with FEDER funds. This work has also been funded by the grant “Ayudas para Estudios de Máster e Iniciación a la Investigación” from the University of Alicante.

Schaeffer language is considered an effective method to help autistic children overcome communicative disorders. Speech and language therapy results in an improvement in communication skills and understanding of language productions. In this work, a Schaeffer language recognition system is presented with the purpose of teaching children with autism disorder the correct way to communicate using gestures in combination with speech reproduction. The purpose is to accelerate the learning process and increase children interest using a technological approach. A Long Short-Term Memory (LSTM) model has been implemented for this purpose reporting a 93.13% classification success rate over a subset of 25 Schaeffer gestures. A comparison with vanilla RNNs and GRU-based models has been also carried out. Pose-based features such as angles and euclidean distances have been extracted from our gesture dataset by processing raw skeletal data from a Kinect v2 sensor.

Cell culture assays have become a routine testing method in the medical and pharmaceutical research. Real-time monitoring of cells on a substrate using electrical impedance is a convenient and non-invasive method of analysis. Cell proliferation and apoptosis can be quantified and characterized by electrical impedance in a time-dependent manner. Unfortunately monitoring several cell cultures at the same time is challenging because of the prohibitive costs of impedance analysis equipment or rather slow response if multiplexing the front-end of an impedance analyzer. We propose a low cost high performance impedance analyzer based on a two channel delta-sigma 16-bit ADC. The device can handle frequencies between 30 Hz and 10 kHz with input impedances ranging: 100mOhms - 10Mohms. The Automatic Level Control (ALC) algorithm allows for steady non-invasive voltage levels on the measured impedance independent of measuring frequency and impedance value. The device prototype performance is compared to commercial analyzers used for monitoring cell growth and related cell based e.g. biosensing applications. Low production cost and robustness to component tolerances owed to special digital processing inside the Digital Signal Controller (DSC) make this device very suitable to mass production, the first step in becoming a readily available tool.

Intentional oil pollution damages marine ecosystems. Therefore, society and governments require maritime surveillance for early oil spill detection. The fast response in the detection process helps to identify the offenders in the vast majority of cases. Nowadays, it is a human operator whom is trained for carrying out oil spill detection. Operators usually use image processing techniques and data analysis from optical, thermal or radar acquired from aerial vehicles or spatial satellites. The current trend is to automate the oil spill detection process so that this can filter candidate oil spill from an aircraft as a decision support system for human operators. In this work, a robust and automated system for candidate oil spill based on Recurrent Neural Network (RNN) is presented. The aim is to provide a faster identification of the candidate oil spills from SLAR scanned sequences. So far, the majority of the research works about oil spill detection are focused on the classification b etween real oil spills and look-alikes, and they use SAR or optical images but not SLAR. Furthermore, the overall decision is usually taken by an operator in the research works of state-of-art, mainly due to the wide variety of types of look-alikes which cause false positives in the detection process when traditional NN are used. This work provides a RRN-based approach for candidate oil spill detection using SLAR data in contrast with the traditional Multilayer Perceptron Neural Network (MPNN). The system is tested with temporary data acquired from a SLAR sensor mounted on an aircraft. It achieves a success rate in detecting of 97%. This work was supported by the Spanish Ministry of Economy and Competitiveness through the research project ONTIME (RTC-2014-1863-8).