We present a methodology for high-resolution orthomosaic reconstruction using aerial images. Our proposal consists a neural network with two main stages, one to obtain the correspondences necessary to perform a LR-orthomosaic and another one that uses these results to generate an HR- orthomosaic, and a feedback connection. The CNN are based onwell known models and are trained to perform image stitching and obtain a high-resolution orthomosaic. The results obtained in this work show that our methodology provides similar results to those obtained by an expertin orthophotography, but in high-resolution.

In this paper, an approach through a Deep Learning architecture for the three-dimensional reconstruction of outdoor environments in challenging terrain conditions is presented. The architecture proposed is configured as an Autoencoder. However, instead of the typical convolutional layers, some differences are proposed. The Encoder stage is set as a residual net with four residual blocks, which have been provided with the necessary knowledge to extract the feature maps from aerial images of outdoor environments. On the other hand, the Decoder stage is set as a Generative Adversarial Network (GAN) and called a GAN-Decoder. The proposed network architecture uses a sequence of the 2D aerial image as input. The Encoder stage works for the extraction of the vector of features that describe the input image, while the GAN-Decoder generates a point cloud based on the information obtained in the previous stage. By supplying a sequence of frames that a percentage of overlap between them, it is possible to determine the spatial location of each generated point. The experiments show that with this proposal it is possible to perform a 3D representation of an area flown over by a drone using the point cloud generated with a deep architecture that has a sequence of aerial 2D images as input. In comparison with other works, our proposed system is capable of performing three-dimensional reconstructions in challenging urban landscapes. Compared with the results obtained using commercial software, our proposal was able to generate reconstructions in less processing time, with less overlapping percentage between 2D images and is invariant to the type of flight path.

Este escrito aborda el desarrollo de un robot móvil que pueda interaccionar con entornos dinámicos mediante la integración de visión por computadora y control de movimiento. Al respecto, se destaca la importancia de la detección y seguimiento de objetos en tiempo real para lograr una navegación segura en aplicaciones prácticas. Hoy en día, a pesar de los avances en visión por computadora y control robótico, persisten desafíos relacionados con la adaptación a entornos impredecibles. Por ende, la propuesta presentada consiste en un sistema que combina técnicas de procesamiento de imágenes y control robótico. El diseño del prototipo utiliza hardware y software libre, como lo son Python, Arduino, OpenCV y Numpy. La programación en Arduino se emplea para controlar un vehículo con cuatro motores mediante un módulo Bluetooth HC-05, mientras que el desarrollo de visión por computadora realiza el seguimiento de objetos de diferentes colores en tiempo real, enviando comandos a Arduino según el color detectado. El proyecto se considera un avance en robótica móvil, en tanto desarrolla un sistema integrado que permite a los robots navegar de manera segura en entornos dinámicos. En este caso, la combinación de visión por computadora y control de movimiento se presenta como una solución práctica respaldada por pruebas detalladas.