chromo-thermodynamics, thermochemical waves, Joule-Thomson expansion, dual quantum isomorphism, global warming, astrophysics
This paper presents a novel approach to address the challenge of self-localization of flying vehicles. It utilizes visual cues provided by the map imagery fed to a map-recognition convolution neural-network (CNN). This approach is invaluable during the navigation of flying vehicles in scenarios wher...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
National Institute for Aerospace Research “Elie Carafoli” - INCAS
2025-03-01
|
| Series: | INCAS Bulletin |
| Subjects: | |
| Online Access: | https://bulletin.incas.ro/files/kassem__hamdy__vol_17_iss_1.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850072183054794752 |
|---|---|
| author | Ayman Hamdy KASSEM Hamdy Ayman HAMDY |
| author_facet | Ayman Hamdy KASSEM Hamdy Ayman HAMDY |
| author_sort | Ayman Hamdy KASSEM |
| collection | DOAJ |
| description | This paper presents a novel approach to address the challenge of self-localization of flying vehicles. It utilizes visual cues provided by the map imagery fed to a map-recognition convolution neural-network (CNN). This approach is invaluable during the navigation of flying vehicles in scenarios where the Global Positioning System (GPS) signal is unavailable. The proposed approach leverages the power of convolutional neural networks (CNNs) to imitate the visual perception and navigation abilities of homing pigeons, enabling the vehicle to navigate using solely real- time visual data with limited or no GPS information. Two pre-trained CNN’s (SqueezeNet and GoogLeNet) are selected and re-trained with Google Maps imagery, enabling them to efficiently learn and generalize from the diverse visual attributes present in the map. Extensive experimentation and evaluation have demonstrated the efficacy and resilience of the vision-based GPS-free navigation system. The resulting system predicts position accurately achieving an accuracy of 89.9% and 96.4% for SqueezeNet and GoogLeNet, respectively, for images with a resolution of (one km x one km) and reaching an accuracy of 94.7 for GoogLeNet for images with a resolution of (374 m x 374 m). Results underscore the potential of this approach for overcoming the challenge of GPS unavailability in aerial navigation. |
| format | Article |
| id | doaj-art-a388f51a38d64e1d94cd470dddd441af |
| institution | DOAJ |
| issn | 2066-8201 2247-4528 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | National Institute for Aerospace Research “Elie Carafoli” - INCAS |
| record_format | Article |
| series | INCAS Bulletin |
| spelling | doaj-art-a388f51a38d64e1d94cd470dddd441af2025-08-20T02:47:07ZengNational Institute for Aerospace Research “Elie Carafoli” - INCASINCAS Bulletin2066-82012247-45282025-03-01171233210.13111/2066-8201.2025.17.1.2chromo-thermodynamics, thermochemical waves, Joule-Thomson expansion, dual quantum isomorphism, global warming, astrophysicsAyman Hamdy KASSEM0Hamdy Ayman HAMDY1Aerospace Engineering Department, Cairo City, Giza, Egypt, akassem@cu.edu.egFaculty of Urban and Regional Planning, Cairo University, Giza, Egypt, Ayman_222031@stud.furp.cu.edu.egThis paper presents a novel approach to address the challenge of self-localization of flying vehicles. It utilizes visual cues provided by the map imagery fed to a map-recognition convolution neural-network (CNN). This approach is invaluable during the navigation of flying vehicles in scenarios where the Global Positioning System (GPS) signal is unavailable. The proposed approach leverages the power of convolutional neural networks (CNNs) to imitate the visual perception and navigation abilities of homing pigeons, enabling the vehicle to navigate using solely real- time visual data with limited or no GPS information. Two pre-trained CNN’s (SqueezeNet and GoogLeNet) are selected and re-trained with Google Maps imagery, enabling them to efficiently learn and generalize from the diverse visual attributes present in the map. Extensive experimentation and evaluation have demonstrated the efficacy and resilience of the vision-based GPS-free navigation system. The resulting system predicts position accurately achieving an accuracy of 89.9% and 96.4% for SqueezeNet and GoogLeNet, respectively, for images with a resolution of (one km x one km) and reaching an accuracy of 94.7 for GoogLeNet for images with a resolution of (374 m x 374 m). Results underscore the potential of this approach for overcoming the challenge of GPS unavailability in aerial navigation.https://bulletin.incas.ro/files/kassem__hamdy__vol_17_iss_1.pdfconvolutional neural networkcnngps-free navigationvisual perceptionimage-based navigation |
| spellingShingle | Ayman Hamdy KASSEM Hamdy Ayman HAMDY chromo-thermodynamics, thermochemical waves, Joule-Thomson expansion, dual quantum isomorphism, global warming, astrophysics INCAS Bulletin convolutional neural network cnn gps-free navigation visual perception image-based navigation |
| title | chromo-thermodynamics, thermochemical waves, Joule-Thomson expansion, dual quantum isomorphism, global warming, astrophysics |
| title_full | chromo-thermodynamics, thermochemical waves, Joule-Thomson expansion, dual quantum isomorphism, global warming, astrophysics |
| title_fullStr | chromo-thermodynamics, thermochemical waves, Joule-Thomson expansion, dual quantum isomorphism, global warming, astrophysics |
| title_full_unstemmed | chromo-thermodynamics, thermochemical waves, Joule-Thomson expansion, dual quantum isomorphism, global warming, astrophysics |
| title_short | chromo-thermodynamics, thermochemical waves, Joule-Thomson expansion, dual quantum isomorphism, global warming, astrophysics |
| title_sort | chromo thermodynamics thermochemical waves joule thomson expansion dual quantum isomorphism global warming astrophysics |
| topic | convolutional neural network cnn gps-free navigation visual perception image-based navigation |
| url | https://bulletin.incas.ro/files/kassem__hamdy__vol_17_iss_1.pdf |
| work_keys_str_mv | AT aymanhamdykassem chromothermodynamicsthermochemicalwavesjoulethomsonexpansiondualquantumisomorphismglobalwarmingastrophysics AT hamdyaymanhamdy chromothermodynamicsthermochemicalwavesjoulethomsonexpansiondualquantumisomorphismglobalwarmingastrophysics |