Abstract
References
- Boone, J., Goodin, C., Dabbiru, L., Hudson, C., Cagle, L., & Carruth, D. (2023). Training artificial intelligence algorithms with automatically labelled uav data from physics-based simulation software. Applied Sciences, 13(1), 131. https://doi.org/10.3390/app13010131
- Boubeta-Puig, J., Moguel, E., Sánchez-Figueroa, F., Hernández, J., & Preciado, J. C. (2018). An autonomous UAV architecture for remote sensing and intelligent decision-making. IEEE Internet Computing, 22(3), 6–15.
- Casas, E., Ramos, L., Bendek, E. & Rivas-Echeverría, F. (2023). Assessing the effectiveness of YOLO architectures for smoke and wildfire detection. IEEE Access, 11, 96554-96583.
Abstract
An Unmanned Aerial Vehicle (UAV) is an autonomous airborne platform characterized by fundamental flight capabilities, including take-off and landing procedures, navigation, route tracking, and mission execution. UAVs serve civilian and military purposes across various domains, undertaking tasks that surpass human capabilities. These vehicles come in diverse hardware and software configurations, comprising essential components such as take-off and landing systems, navigation modules, emergency response mechanisms, sensory apparatus, imaging instrumentation, and energy supply systems. UAVs exhibit the capability for flight management, target identification, and mission analysis, drawing on data collected from preloaded datasets, control centers, and real-time environmental cues. Leveraging various artificial intelligence (AI) algorithms, UAVs autonomously process instantaneous data, incorporating methodologies such as artificial neural networks, image processing algorithms, learning algorithms, and optimization techniques. This paper analyses data analytics methodologies and AI technologies used by UAVs. Furthermore, an image processing application using a Convolutional Neural Network (CNN) algorithm is implemented to provide object recognition. The object recognition rate of the application developed in Python language was calculated with an accuracy of 0.7107. This finding shows that by using AI algorithms to analyze images acquired through onboard sensors, the UAV's capability to conduct critical operations such as target acquisition, obstacle avoidance and collision avoidance can be improved.
References
- Boone, J., Goodin, C., Dabbiru, L., Hudson, C., Cagle, L., & Carruth, D. (2023). Training artificial intelligence algorithms with automatically labelled uav data from physics-based simulation software. Applied Sciences, 13(1), 131. https://doi.org/10.3390/app13010131
- Boubeta-Puig, J., Moguel, E., Sánchez-Figueroa, F., Hernández, J., & Preciado, J. C. (2018). An autonomous UAV architecture for remote sensing and intelligent decision-making. IEEE Internet Computing, 22(3), 6–15.
- Casas, E., Ramos, L., Bendek, E. & Rivas-Echeverría, F. (2023). Assessing the effectiveness of YOLO architectures for smoke and wildfire detection. IEEE Access, 11, 96554-96583.
Details
| Primary Language | English |
|---|---|
| Subjects | Software Engineering (Other) |
| Journal Section | Articles |
| Authors | |
| Early Pub Date | December 24, 2023 |
| Publication Date | December 30, 2023 |
| Published in Issue | Year 2023Volume: 26 |
