|
|
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.
|
|
|
|
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.
|
|
|
|
Del Pino, J., Salazar, G., & Cedeño, V. M. (2011). Adaptación de un Recomendador de Filtro Colaborativo Basado en el Usuario para la Creación de un Recomendador de Materias de Pregrado Basado en el Historial Académico de los Estudiantes. Revista Tecnológica ESPOL, Vol. 24, pp. 29–34.
Abstract: Los sistemas de recomendación son ampliamente utilizados hoy en día gracias a su capacidad de analizar las preferencias de usuarios y sugerir ítems. No obstante, el uso de los recomendadores está limitado a un modelo basado en el usuario y no en su historial de preferencias, discriminando así el campo de aplicación, por ejemplo, a sistemas académicos donde sea primordial el estudio de las decisiones del estudiante a lo largo de su carrera. El presente
trabajo presenta un esfuerzo por adaptar filtros colaborativos basados en el usuario a filtros colaborativos basados en el historial del usuario. Con un conjunto de pruebas mediremos su efectividad utilizando dos algoritmos distintos de similaridad para recomendar materias a un estudiante en el sexto semestre de la carrera de Ingeniería en Electrónica y Telecomunicaciones ofertada por la FIEC – ESPOL. Los resultados muestran que es factible adaptar un recomendador a un modelo basado en el historial del usuario
|
|
