2022 |
|
|
Rivadeneira R. E., S. A. D., Vintimilla B. X. and Hammoud R. (2022). A Novel Domain Transfer-Based Approach for Unsupervised Thermal Image Super- Resolution. In Sensors, Vol. 22(Issue 6), Article number 2254.
|
|
|
|
Rivadeneira, R. E., & Sappa, A. D. and V. B. X. (2022). Thermal Image Super-Resolution: A Novel Unsupervised Approach. In Communications in Computer and Information Science, 15th International Communications in Computer and Information Science Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Vol. 1474 CCIS, pp 495 – 506).
|
|
|
|
Roberto Jacome Galarza. (2022). Multimodal deep learning for crop yield prediction. In Doctoral Symposium on Information and Communication Technologies –DSICT 2022. Octubre 12-14..
|
|
|
|
Velesaca, H. O., Suárez, P. L., Sappa, A. D., Carpio, D., Rivadeneira, R. E., & Sanchez, A. (2022). Review on Common Techniques for Urban Environment Video Analytics. In In WORKSHOP BRASILEIRO DE CIDADES INTELIGENTES (WBCI 2022) (p. pp. 107–118.).
|
|
|
|
Velez R., P. A., Silva S., Paillacho D., and Paillacho J. (2022). Implementation of a UVC lights disinfection system for a diferential robot applying security methods in indoor. In Communications in Computer and Information Science, International Conference on Applied Technologies (ICAT 2021), octubre 27-29 (Vol. 1535, pp. 319–331).
|
|
|
|
Xavier Soria, G. P. - J. & A. S. (2022). LDC: Lightweight Dense CNN for Edge Detection. IEEE Access journal, Vol. 10, pp 68281 – 68290.
|
|
2021 |
|
|
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. (Vol. 110. Article number 104182), .
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.
|
|
|
|
Dennys Paillacho, Nayeth I. Solorzano Alcivar, & Jonathan S. Paillacho Corredores. (2021). LOLY 1.0: A Proposed Human-Robot-Game Platform Architecture for the Engagement of Children with Autism in the Learning Process. In The international Conference on Systems and Information Sciences (ICCIS 2020), julio 27-29. Advances in Intelligent Systems and Computing. (Vol. 1273, pp. 225–238).
|
|
|
|
Henry O. Velesaca, P. L. S., Dario Carpio, and Angel D. Sappa. (2021). Synthesized Image Datasets: Towards an Annotation-Free Instance Segmentation Strategy. In 16 International Symposium on Visual Computing. Octubre 4-6, 2021. Lecture Notes in Computer Science (Vol. 13018, pp. 178-190).
|
|
|
|
Jacome-Galarza L.-R. (2021). Crop yield prediction utilizing multimodal deep learning. In 16th Iberian Conference on Information Systems and Technologies, CISTI 2021, junio 23 – 26, 2021.
Abstract: La agricultura de precisión es una práctica vital para
mejorar la producción de cosechas. El presente trabajo tiene
como objetivo desarrollar un modelo multimodal de aprendizaje
profundo que es capaz de producir un mapa de salud de
cosechas. El modelo recibe como entradas imágenes multiespectrales
y datos de sensores de campo (humedad,
temperatura, estado del suelo, etc.) y crea un mapa de
rendimiento de la cosecha. La utilización de datos multimodales
tiene como finalidad extraer patrones ocultos del estado de salud
de las cosechas y de esta manera obtener mejores resultados que
los obtenidos mediante los índices de vegetación.
|
|
