No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Development of aerial image transmitting sensor platform for disaster site surveillance
... Para esto, se han utilizado Can-Satellite, que pesa menos de 700 gramos y está equipado con una cámara RGB y con una cámara frontal de infrarrojo; también cuenta con sensores adicionales de vuelo e interfaces de redes, las cuales transmiten la información y coordinan el reconocimiento del sobreviviente detectado. Así mismo, tiene una profunda arquitectura en la red neuronal, cuya función es clasificar los objetos humanos en imágenes transmitidas (Kim, Hyun, & Myung, 2017). Así las cosas, se observa el creciente uso de los vehículos aéreos no tripulados para no solo reducir costos sino también para incrementar los niveles de acción, según la situación lo amerite; se pueden tomar acciones más acordes al problema, ya que las imágenes que transmite son en tiempo real. ...
Este artículo pretende evidenciar la necesidad del Ejército Nacional de Colombia de acceder y hacer uso de herramientas tecnológicas de vanguardia, como pueden ser los sensores IR-FLIR, en su afán de apoyar y complementar el desarrollo de diversas operaciones militares, además del control y la defensa de la seguridad nacional a lo largo del territorio colombiano. Los vehículos aéreos no tripulados (UAV por su sigla en inglés) han aportado en gran magnitud a la solución de diversas necesidades que a través del tiempo se han presentado en las tareas de la Inteligencia Militar (IMI) y a su vez de la defensa de los intereses nacionales para cualquier Estado. En la actualidad es fácil encontrar sobre el espacio aéreo diversos tipos de “Drones”, los cuales realizan misiones humanitarias por organismos estatales, acciones agropecuarias en el campo, como también otras actividades de entretenimiento realizadas por aficionados. En el Ejército Nacional de Colombia se presenta una situación particular, la utilización de vehículos “UAV” para apoyar el desarrollo de operaciones militares y actividades de inteligencia militar (Inteligencia, vigilancia y reconocimiento - ISR) no ha sido tenida en cuenta principalmente en operaciones militares nocturnas por la falta de credibilidad y confianza en la información suministrada por la Inteligencia Militar para el desarrollo de las misiones a nivel táctico, operacional y estratégico. Por tal razón se busca la pertinencia que tendría la adquisición de nuevos sensores para las FF.MM.
... Drones are unable to fly in adverse weather conditions such as rain or strong winds. This research suggests a new type of aircraft platform for airborne survivors' sensing at catastrophe sites, enabling for low-cost monitoring and operations even in bad weather [4]. The Can-Satellite (CanSat) is a satellite-inspired instructional kit. ...
This work presents the prototype design of an
advanced level Can Satellite (CanSat) with a view to developing
an experimental CanSat with meteorological and object detection
applications. Reduction of air pollution, the capability of imme�diate response in natural calamities, and the overall development
of complex aerospace projects are the main inspiration behind
the concept of designing the CanSat. A First Person View (FPV)
camera, flight sensors that provide information about tempera�ture, pressure, humidity, air quality, and network interfaces for
data transmission are used in this system. Detection of humans
and objects from the transmitted images has been achieved by
YOLO v3 and YOLO v4 model. An analysis and comparison
of meteorological aspects of important locations by processing
the signals of the sensors in the system has been presented. The
complete mission gives an overall error of 5-10%.
... The origin of unmanned aerial vehicles (UAVs), commonly known as "drones", can be placed chronologically at the beginning of the 20th century with mainly military purposes Dalamagkidis et al. [12], and many civilian uses have emerged in this decade. The use of UAVs has been extended to search and rescue missions Kim et al. [13], surveillance, transport systems Sánchez-Bou and López-Pujol [14], high-resolution map production, fire detection Wing et al. [15], crop monitoring or fumigation Faiçal et al. [16], forest inventory studies, and the propagation of trees by studying conifer tree cover Ivosevic et al. [17]. UAVs have also been applied in geothermal energy Harvey et al. [18], biodiversity and biology Bohmann et al. [19]. ...
The current computer technology facilitates the processing of large volumes of information in architectural design teams, in parallel with recent advances in-flight automation in unmanned aerial vehicles (UAVs) along with lower costs, facilitates their use to capture aerial photographs and obtain orthophotographs and 3D models of relief and terrain textures. With these technologies, 3D models can be produced that allow different geometric configurations of the distribution of construction elements on the ground to be analyzed. This article presents the process of implementation in a terrain integrated into the early stages of architectural design. A methodology is proposed that covers the detailed capture of terrain, the relationship with the architectural design environment, and its implementation on the plot. As a novelty, an inverse perspective to the remaining disciplines is presented, from the inside of the object to the outside. The proposed methodology for the use of UAVs integrates terrain capture, generation of the 3D mesh, superimposition of environmental realities and architectural design using building information modeling (BIM) technologies. In addition, it represents the beginning of a line of research on the implementation of the plot and the layout of foundations using UAVs. The results obtained in the study carried out in three different projects comparing traditional technologies with the integration of UAVs + BIM show a clear improvement in the second option. The use of new technologies applied to the execution and control of work not only improves accuracy but also reduces errors and saves time, which undoubtedly indicates significant savings in costs and deviations in the project.
We present YOLO, a unified pipeline for object detection. Prior work on
object detection repurposes classifiers to perform detection. Instead, we frame
object detection as a regression problem to spatially separated bounding boxes
and associated class probabilities. A single neural network predicts bounding
boxes and class probabilities directly from full images in one evaluation.
Since the whole detection pipeline is a single network, it can be optimized
end-to-end directly on detection performance. Our unified architecture is also
extremely fast; YOLO processes images in real-time at 45 frames per second,
hundreds to thousands of times faster than existing detection systems. Our
system uses global image context to detect and localize objects, making it less
prone to background errors than top detection systems like R-CNN. By itself,
YOLO detects objects at unprecedented speeds with moderate accuracy. When
combined with state-of-the-art detectors, YOLO boosts performance by 2-3%
points mAP.