TY - GEN
T1 - Low-cost system for on-board image processing in real time, applied to disaster mitigation
AU - Auccahuasi, Wilver
AU - Herrera, Lucas
AU - Rojas, Karin
AU - Urbano, Kitty
AU - Romero, Luis
AU - Lovera, Denny
AU - Díaz, Monica
AU - Pacheco, Orlando
AU - Perez, Ivan
AU - Santos, César
AU - Leva, Antenor
AU - Fuentes, Alfonso
AU - Sernaque, Fernando
N1 - Publisher Copyright:
© 2023 Author(s).
PY - 2023/4/4
Y1 - 2023/4/4
N2 - The climate change that affects our planet is constantly causing natural disasters, due to the increase in temperature, development of extreme rains, causing rivers to overflow; Thus, natural phenomena such as earthquakes that cause the destruction of bridges and can cause tsunamis, among other phenomena and disasters, can also occur. Current technology allows us to observe what is happening on the planet thanks to the use of terrestrial observation satellites, these satellite systems, as well as having advantages, also have disadvantages, among them we can mention that in the presence of clouds the registration of images It is carried out based on the clouds present, another of the drawbacks is the visiting time that the satellites have, which has the characteristic that the area that you want to record the image is not always available, therefore you have to wait for the day and the time in which the satellite orbit can pass through the area of interest that the image is to be recorded. Due to this characteristic, at the time of an emergency, either due to the effect of rain, earthquake or similar, when due to technical conditions the area of interest cannot be registered, other alternatives arise, such as drones, which solves a problem of satellites, on cloud cover, because the drone flies at low altitudes and does not have cloud problems, in the present work a methodology based on low-cost systems is proposed for on-board processing in drones of such In such a way that the effects of the natural disaster can be mitigated and decisions can be made in the shortest possible time, the methodology consists of processing the image in an embedded device, which is coupled to the drone and connected to the camera, in such a way that the information that is sent to the ground station, concentrates on the affected area, the methodology proposes an intelligent module capable of being able to process the newly acquired images on board and power to finalize them with a reference image bank of the area, in such a way as to be able to find any change in the land cover and to be able to send the result as an emergency message to its earth station, with this proposal it is possible to cut download times and Analysis of the images if it were to work in a conventional way because the drone must first be on the ground and then uncouple the camera, download the image and at the end just process them. As a result, it is presented by tests carried out on the detection of changes in land cover and its transmission to an earth station, using an embedded computer based on a Raspberry pi 3.
AB - The climate change that affects our planet is constantly causing natural disasters, due to the increase in temperature, development of extreme rains, causing rivers to overflow; Thus, natural phenomena such as earthquakes that cause the destruction of bridges and can cause tsunamis, among other phenomena and disasters, can also occur. Current technology allows us to observe what is happening on the planet thanks to the use of terrestrial observation satellites, these satellite systems, as well as having advantages, also have disadvantages, among them we can mention that in the presence of clouds the registration of images It is carried out based on the clouds present, another of the drawbacks is the visiting time that the satellites have, which has the characteristic that the area that you want to record the image is not always available, therefore you have to wait for the day and the time in which the satellite orbit can pass through the area of interest that the image is to be recorded. Due to this characteristic, at the time of an emergency, either due to the effect of rain, earthquake or similar, when due to technical conditions the area of interest cannot be registered, other alternatives arise, such as drones, which solves a problem of satellites, on cloud cover, because the drone flies at low altitudes and does not have cloud problems, in the present work a methodology based on low-cost systems is proposed for on-board processing in drones of such In such a way that the effects of the natural disaster can be mitigated and decisions can be made in the shortest possible time, the methodology consists of processing the image in an embedded device, which is coupled to the drone and connected to the camera, in such a way that the information that is sent to the ground station, concentrates on the affected area, the methodology proposes an intelligent module capable of being able to process the newly acquired images on board and power to finalize them with a reference image bank of the area, in such a way as to be able to find any change in the land cover and to be able to send the result as an emergency message to its earth station, with this proposal it is possible to cut download times and Analysis of the images if it were to work in a conventional way because the drone must first be on the ground and then uncouple the camera, download the image and at the end just process them. As a result, it is presented by tests carried out on the detection of changes in land cover and its transmission to an earth station, using an embedded computer based on a Raspberry pi 3.
UR - http://www.scopus.com/inward/record.url?scp=85152778116&partnerID=8YFLogxK
U2 - 10.1063/5.0125498
DO - 10.1063/5.0125498
M3 - Conference contribution
AN - SCOPUS:85152778116
T3 - AIP Conference Proceedings
BT - 2nd International Conference on Circuits, Signals, Systems and Securities, ICCSSS 2022
A2 - Harikumar, R.
A2 - Ganesh Babu, C.
A2 - Poongodi, C.
PB - American Institute of Physics Inc.
T2 - 2nd International Conference on Circuits, Signals, Systems and Securities, ICCSSS 2022
Y2 - 25 March 2022 through 26 March 2022
ER -