toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Marjorie Chalen; Boris X. Vintimilla pdf  openurl
  Title Towards Action Prediction Applying Deep Learning Type Journal Article
  Year 2019 Publication Latin American Conference on Computational Intelligence (LA-CCI); Guayaquil, Ecuador; 11-15 Noviembre 2019 Abbreviated Journal  
  Volume Issue Pages (down) pp. 1-3  
  Keywords action prediction, early recognition, early detec- tion, action anticipation, cnn, deep learning, rnn, lstm.  
  Abstract Considering the incremental development future action prediction by video analysis task of computer vision where it is done based upon incomplete action executions. Deep learning is playing an important role in this task framework. Thus, this paper describes recently techniques and pertinent datasets utilized in human action prediction task.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number cidis @ cidis @ Serial 129  
Permanent link to this record
 

 
Author Cristhian A. Aguilera, Cristhian Aguilera, Cristóbal A. Navarro, & Angel D. Sappa pdf  openurl
  Title Fast CNN Stereo Depth Estimation through Embedded GPU Devices Type Journal Article
  Year 2020 Publication Sensors 2020 Abbreviated Journal  
  Volume Vol. 2020-June Issue 11 Pages (down) pp. 1-13  
  Keywords stereo matching; deep learning; embedded GPU  
  Abstract Current CNN-based stereo depth estimation models can barely run under real-time

constraints on embedded graphic processing unit (GPU) devices. Moreover, state-of-the-art

evaluations usually do not consider model optimization techniques, being that it is unknown what is

the current potential on embedded GPU devices. In this work, we evaluate two state-of-the-art models

on three different embedded GPU devices, with and without optimization methods, presenting

performance results that illustrate the actual capabilities of embedded GPU devices for stereo depth

estimation. More importantly, based on our evaluation, we propose the use of a U-Net like architecture

for postprocessing the cost-volume, instead of a typical sequence of 3D convolutions, drastically

augmenting the runtime speed of current models. In our experiments, we achieve real-time inference

speed, in the range of 5–32 ms, for 1216  368 input stereo images on the Jetson TX2, Jetson Xavier,

and Jetson Nano embedded devices.
 
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language English Summary Language English Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 14248220 ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number cidis @ cidis @ Serial 132  
Permanent link to this record
 

 
Author Ángel Morera, Ángel Sánchez, A. Belén Moreno, Angel D. Sappa, & José F. Vélez pdf  isbn
openurl 
  Title SSD vs. YOLO for Detection of Outdoor Urban Advertising Panels under Multiple Variabilities. Type Journal Article
  Year 2020 Publication Abbreviated Journal In Sensors  
  Volume Vol. 2020-August Issue 16 Pages (down) pp. 1-23  
  Keywords object detection; urban outdoor panels; one-stage detectors; Single Shot MultiBox Detector (SSD); You Only Look Once (YOLO); detection metrics; object and scene imaging variabilities  
  Abstract This work compares Single Shot MultiBox Detector (SSD) and You Only Look Once (YOLO)

deep neural networks for the outdoor advertisement panel detection problem by handling multiple

and combined variabilities in the scenes. Publicity panel detection in images o ers important

advantages both in the real world as well as in the virtual one. For example, applications like Google

Street View can be used for Internet publicity and when detecting these ads panels in images, it could

be possible to replace the publicity appearing inside the panels by another from a funding company.

In our experiments, both SSD and YOLO detectors have produced acceptable results under variable

sizes of panels, illumination conditions, viewing perspectives, partial occlusion of panels, complex

background and multiple panels in scenes. Due to the diculty of finding annotated images for the

considered problem, we created our own dataset for conducting the experiments. The major strength

of the SSD model was the almost elimination of False Positive (FP) cases, situation that is preferable

when the publicity contained inside the panel is analyzed after detecting them. On the other side,

YOLO produced better panel localization results detecting a higher number of True Positive (TP)

panels with a higher accuracy. Finally, a comparison of the two analyzed object detection models

with di erent types of semantic segmentation networks and using the same evaluation metrics is

also included.
 
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language English Summary Language English Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 14248220 Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number cidis @ cidis @ Serial 133  
Permanent link to this record
 

 
Author Cristhian A. Aguilera; Cristhian Aguilera; Angel D. Sappa pdf  openurl
  Title Melamine faced panels defect classification beyond the visible spectrum. Type Journal Article
  Year 2018 Publication In Sensors 2018 Abbreviated Journal  
  Volume Vol. 11 Issue Issue 11 Pages (down)  
  Keywords  
  Abstract In this work, we explore the use of images from different spectral bands to classify defects in melamine faced panels, which could appear through the production process. Through experimental evaluation, we evaluate the use of images from the visible (VS), near-infrared (NIR), and long wavelength infrared (LWIR), to classify the defects using a feature descriptor learning approach together with a support vector machine classifier. Two descriptors were evaluated, Extended Local Binary Patterns (E-LBP) and SURF using a Bag of Words (BoW) representation. The evaluation was carried on with an image set obtained during this work, which contained five different defect categories that currently occurs in the industry. Results show that using images from beyond

the visual spectrum helps to improve classification performance in contrast with a single visible spectrum solution.
 
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number gtsi @ user @ Serial 89  
Permanent link to this record
 

 
Author Xavier Soria; Angel D. Sappa; Riad Hammoud pdf  openurl
  Title Wide-Band Color Imagery Restoration for RGB-NIR Single Sensor Image. Sensors 2018 ,2059. Type Journal Article
  Year 2018 Publication Abbreviated Journal  
  Volume Vol. 18 Issue Issue 7 Pages (down)  
  Keywords  
  Abstract Multi-spectral RGB-NIR sensors have become ubiquitous in recent years. These sensors allow the visible and near-infrared spectral bands of a given scene to be captured at the same time. With such cameras, the acquired imagery has a compromised RGB color representation due to near-infrared bands (700–1100 nm) cross-talking with the visible bands (400–700 nm). This paper proposes two deep learning-based architectures to recover the full RGB color images, thus removing the NIR information from the visible bands. The proposed approaches directly restore the high-resolution RGB image by means of convolutional neural networks. They are evaluated with several outdoor images; both architectures reach a similar performance when evaluated in different scenarios and using different similarity metrics. Both of them improve the state of the art approaches.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number gtsi @ user @ Serial 96  
Permanent link to this record
 

 
Author Marta Diaz; Dennys Paillacho; Cecilio Angulo pdf  openurl
  Title Evaluating Group-Robot Interaction in Crowded Public Spaces: A Week-Long Exploratory Study in the Wild with a Humanoid Robot Guiding Visitors Through a Science Museum. Type Journal Article
  Year 2015 Publication International Journal of Humanoid Robotics Abbreviated Journal  
  Volume Vol. 12 Issue Pages (down)  
  Keywords Group-robot interaction; robotic-guide; social navigation; space management; spatial formations; group walking behavior; crowd behavior  
  Abstract This paper describes an exploratory study on group interaction with a robot-guide in an open large-scale busy environment. For an entire week a humanoid robot was deployed in the popular Cosmocaixa Science Museum in Barcelona and guided hundreds of people through the museum facilities. The main goal of this experience is to study in the wild the episodes of the robot guiding visitors to a requested destination focusing on the group behavior during displacement. The walking behavior follow-me and the face to face communication in a populated environment are analyzed in terms of guide- visitors interaction, grouping patterns and spatial formations. Results from observational data show that the space configurations spontaneously formed by the robot guide and visitors walking together did not always meet the robot communicative and navigational requirements for successful guidance. Therefore additional verbal and nonverbal prompts must be considered to regulate effectively the walking together and follow-me behaviors. Finally, we discuss lessons learned and recommendations for robot’s spatial behavior in dense crowded scenarios.  
  Address  
  Corporate Author Thesis  
  Publisher International Journal of Humanoid Robotics Place of Publication Editor  
  Language English Summary Language English Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number cidis @ cidis @ Serial 34  
Permanent link to this record
 

 
Author Santos V.; Angel D. Sappa.; Oliveira M. & de la Escalera A. pdf  openurl
  Title Special Issue on Autonomous Driving and Driver Assistance Systems Type Journal Article
  Year 2019 Publication In Robotics and Autonomous Systems Abbreviated Journal  
  Volume 121 Issue Pages (down)  
  Keywords  
  Abstract  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number gtsi @ user @ Serial 119  
Permanent link to this record
 

 
Author Charco, J.L., Sappa, A.D., Vintimilla, B.X., Velesaca, H.O. pdf  openurl
  Title Camera pose estimation in multi-view environments:from virtual scenarios to the real world Type Journal Article
  Year 2021 Publication In Image and Vision Computing Journal. (Article number 104182) Abbreviated Journal  
  Volume Vol. 110 Issue Pages (down)  
  Keywords Relative camera pose estimation, Domain adaptation, Siamese architecture, Synthetic data, Multi-view environments  
  Abstract This paper presents a domain adaptation strategy to efficiently train network architectures for estimating the relative camera pose in multi-view scenarios. The network architectures are fed by a pair of simultaneously acquired

images, hence in order to improve the accuracy of the solutions, and due to the lack of large datasets with pairs of

overlapped images, a domain adaptation strategy is proposed. The domain adaptation strategy consists on transferring the knowledge learned from synthetic images to real-world scenarios. For this, the networks are firstly

trained using pairs of synthetic images, which are captured at the same time by a pair of cameras in a virtual environment; and then, the learned weights of the networks are transferred to the real-world case, where the networks are retrained with a few real images. Different virtual 3D scenarios are generated to evaluate the

relationship between the accuracy on the result and the similarity between virtual and real scenarios—similarity

on both geometry of the objects contained in the scene as well as relative pose between camera and objects in the

scene. Experimental results and comparisons are provided showing that the accuracy of all the evaluated networks for estimating the camera pose improves when the proposed domain adaptation strategy is used,

highlighting the importance on the similarity between virtual-real scenarios.
 
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language English Summary Language English Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number cidis @ cidis @ Serial 147  
Permanent link to this record
 

 
Author Rubio, G.A., Agila, W.E pdf  openurl
  Title A fuzzy model to manage water in polymer electrolyte membrane fuel cells Type Journal Article
  Year 2021 Publication In Processes Journal. (Article number 904) Abbreviated Journal  
  Volume Vol. 9 Issue Issue 6 Pages (down)  
  Keywords PEM fuel cell, fuzzy, neural network, electrical response, flooding, drying.  
  Abstract In this paper, a fuzzy model is presented to determine in real-time the degree of dehydration or flooding of a proton exchange membrane of a fuel cell, to optimize its electrical response and consequently, its autonomous operation. By applying load, current and flux variations in the dry, normal, and flooded states of the membrane, it was determined that the temporal evolution of the fuel cell voltage is characterized by changes in slope and by its voltage oscillations. The results were validated using electrochemical impedance spectroscopy and show slope changes from 0.435 to 0.52 and oscillations from 3.6 mV to 5.2 mV in the dry state, and slope changes from 0.2 to 0.3 and oscillations from 1 mV to 2 mV in the flooded state. The use of fuzzy logic is a novelty and constitutes a step towards the progressive automation of the supervision, perception, and intelligent control of fuel cells, allowing them to reduce their risks and increase their economic benefits.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language English Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number cidis @ cidis @ Serial 153  
Permanent link to this record
 

 
Author Rafael E. Rivadeneira, Angel Domingo Sappa, Vintimilla B. X. and Hammoud R. pdf  openurl
  Title A Novel Domain Transfer-Based Approach for Unsupervised Thermal Image Super- Resolution. Type Journal Article
  Year 2022 Publication Sensors Abbreviated Journal Sensors  
  Volume Vol. 22 Issue Issue 6 Pages (down)  
  Keywords  
  Abstract  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number cidis @ cidis @ Serial 170  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: