| |
|
Teutsh M., H. R., Angel Sappa. (2021). Synthesis Lectures on Computer Vision. Infrared Computer Vision, .
|
|
Ronald Velez Burgos, A. P. R., Steven Silva Mendoza, Dennys Paillacho Chiluiza, Jonathan Paillacho Corredores. (2021). Implementation of a UVC lights disinfection system for a differential robot applying security methods in indoor. In Accepted in International Conference on Applied Technologies (ICAT 2021).
Abstract: Implementing methods that allow trajectory tracing for an
autonomous robotic system is a topic that covers several fields of study
since different parameters must be taken into account to locate obstacles
to ensure proper navigation in environments where there is a moderate
traffic of people. For this purpose, different methods of trajectory tracing
will be implemented, which take as a reference the distance at which peo-
ple are located. In addition, there are added human image recognition for
avoid exposing people to UVC light. As a result, it can be observed that
the methods implemented for the trajectory tracing give quite acceptable
”pathing” results, since the main criterion to determine the efficiency is
the SII, and thanks to the T265 and D435i sensors, it was possible to
determine the presence of people in terms of image processing.
|
|
Patricia L. Suárez, A. D. S., Boris X. Vintimilla. (2021). Cycle generative adversarial network: towards a low-cost vegetation index estimation. In In Accepted in IEEE International Conference on Image Processing (ICIP 2021).
Abstract: This paper presents a novel unsupervised approach to estimate the Normalized Difference Vegetation Index (NDVI).The NDVI is obtained as the ratio between information from the visible and near infrared spectral bands; in the current work, the NDVI is estimated just from an image of the visible spectrum through a Cyclic Generative Adversarial Network (CyclicGAN). This unsupervised architecture learns to estimate the NDVI index by means of an image translation between the red channel of a given RGB image and the NDVI unpaired index’s image. The translation is obtained by means of a ResNET architecture and a multiple loss function. Experimental results obtained with this unsupervised scheme show the validity of the implemented model. Additionally, comparisons with the state of the art approaches are provided showing improvements with the proposed approach.
|
|
|
Henry O. Velesaca, P. L. S., Dario Carpio, and Angel D. Sappa. (2021). Synthesized Image Datasets: Towards an Annotation-Free Instance Segmentation Strategy. In In Accepted in 16 International Symposium on Visual Computing. Octubre 4-6, 2021.
|
|
|
Patricia L. Suárez, D. C., and Angel Sappa. (2021). Non-Homogeneous Haze Removal through a Multiple Attention Module Architecture. In Accepted in 16 International Symposium on Visual Computing. Octubre 4-6, 2021.
|
|
|
