|
|
Cristhian A. Aguilera, C. A., Cristóbal A. Navarro, & Angel D. Sappa. (2020). Fast CNN Stereo Depth Estimation through Embedded GPU Devices. Sensors 2020, Vol. 2020-June(11), pp. 1–13.
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.
|
|
|
|
Ángel Morera, Á. S., A. Belén Moreno, Angel D. Sappa, & José F. Vélez. (2020). SSD vs. YOLO for Detection of Outdoor Urban Advertising Panels under Multiple Variabilities. In Sensors, Vol. 2020-August(16), pp. 1–23.
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.
|
|
|
|
Cristhian A. Aguilera, Cristhian Aguilera, & Angel D. Sappa. (2018). Melamine faced panels defect classification beyond the visible spectrum. In Sensors 2018, Vol. 11(Issue 11).
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.
|
|
|
|
Xavier Soria, Angel D. Sappa, & Riad Hammoud. (2018). Wide-Band Color Imagery Restoration for RGB-NIR Single Sensor Image. Sensors 2018 ,2059.Vol. 18(Issue 7).
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.
|
|
|
|
Marta Diaz, Dennys Paillacho, & Cecilio Angulo. (2015). 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. International Journal of Humanoid Robotics, Vol. 12.
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.
|
|
|
|
Santos V., Angel D. Sappa., & Oliveira M. & de la Escalera A. (2019). Special Issue on Autonomous Driving and Driver Assistance Systems. In Robotics and Autonomous Systems, 121.
|
|
|
|
Charco, J. L., Sappa, A.D., Vintimilla, B.X., Velesaca, H.O. (2021). Camera pose estimation in multi-view environments:from virtual scenarios to the real world. In Image and Vision Computing Journal. (Article number 104182), Vol. 110.
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.
|
|
|
|
Rubio, G. A., Agila, W.E. (2021). A fuzzy model to manage water in polymer electrolyte membrane fuel cells. In Processes Journal. (Article number 904), Vol. 9(Issue 6).
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.
|
|
|
|
Rafael E. Rivadeneira, A. D. S., Vintimilla B. X. and Hammoud R. (2022). A Novel Domain Transfer-Based Approach for Unsupervised Thermal Image Super- Resolution. Sensors, Vol. 22(Issue 6).
|
|
|
|
Santos, V., Sappa, A.D., Oliveira, M. & de la Escalera, A. (2021). Editorial: Special Issue on Autonomous Driving and Driver Assistance Systems – Some Main Trends. In Journal: Robotics and Autonomous Systems. (Article number 103832), Vol. 144.
|
|
