Low-Cost Computer-Vision-Based Embedded Systems for Unmanned Aerial Vehicles: History
View Latest Version
Please note this is an old version of this entry, which may differ significantly from the current revision.
Contributor:
Luis D. Ortega
,
Erick S. Loyaga
,
Patricio J. Cruz
,
Henry P. Lema
,
Jackeline Abad
,
Esteban A. Valencia

Unmanned Aerial Vehicles (UAVs) are versatile, adapting hardware and software for research. They are vital for remote monitoring, especially in challenging settings such as volcano observation with limited access. In response, economical computer vision systems provide a remedy by processing data, boosting UAV autonomy, and assisting in maneuvering. Through the application of these technologies, researchers can effectively monitor remote areas, thus improving surveillance capabilities. Moreover, flight controllers employ onboard tools to gather data, further enhancing UAV navigation during surveillance tasks. 

  • unmanned aerial vehicles
  • autonomous landing

1. Introduction

In recent years, unmanned aerial vehicles (UAVs) have rapidly developed and can be used for academic, private, and commercial purposes [1][2]. Due to technological advances in computer hardware and navigation software, UAVs have grown considerably in agriculture, environment, and security, among others. Thus, by 2025, their value is expected to reach USD 42.8 billion, according to Dronell’s report [3]. These UAVs have proven to be capable of collecting large amounts of data in relatively short periods of time, allowing for more agile and precise analysis. Their advancements have facilitated studies in archaeology, geosciences, and spatial ecology [4][5][6][7][8].
The very purpose of this work was developed within research projects related to environmental monitoring (PIGR 21-01, PIM 21-01), with one of the main objectives being volcano surveillance. These are environments in which UAVs must integrate precise and low-energy-consumption onboard systems to maximize flight time; enhance mapping, characterization, interpretation, surveillance, and risk assessment; and stimulate new avenues of research [9]. Furthermore, in developing countries such as Ecuador, where environmental risk is high according to a report by the European Commission in 2020 [10], the use of UAVs for monitoring in environmental risk management plans represents a great option to reduce operational costs and achieve broader coverage.
Considering that a UAV is composed of components that enable its control and maneuverability [11], the autopilot stands out. It is an electronic device within the control subsystem that interprets signals from a remote control or a ground control station and emits the appropriate signals to guide the aircraft to its desired location and manner. One of the most well-known autopilots on the market is the Pixhawk [12], which currently features a set of position, orientation, and acceleration sensors that facilitate the handling and control of UAVs. However, its autonomous navigation system requires additional instrumentation to support maneuvers such as landing or obstacle avoidance, and can even perform tasks for specific applications. Although autopilots are capable of performing automatic takeoffs and landings, the majority of drone accidents occur during takeoff or landing maneuvers, resulting in material losses due to hardware or software damage, causing delays or mission aborts and, consequently, significant economic losses. Furthermore, nearly 80% of accidents and incidents occur while the aircraft is in flight or cruising, emphasizing the importance of addressing safety measures during these critical phases [13]. These issues can be attributed to the lack of sufficient environmental feedback that would enable the correction of differential changes from takeoff to landing points, highlighting the need for instrumentation to support the autopilot in specific maneuvers or tasks.

2. Low-Cost Computer-Vision-Based Embedded Systems for Unmanned Aerial Vehicles

Guo et al. in [14] propose a LOAS that allows a UAV to autonomously land on a moving Ground Vehicle (GV). The UAV follows the GV using an object tracker while avoiding unexpected obstacles through path planning until it lands on the target GV. In contrast, Singla et al. in [15] present a method to enable a multirotor, equipped with a monocular camera, to autonomously avoid obstacles in unstructured and unknown indoor environments. For this purpose, they propose a Deep Reinforcement Learning (DRL) method based on Recurrent Neural Network (RNN) architecture and temporal attention. The previous works show promising results in terms of data accuracy but demand high computational and energy costs due to the use of trajectory generators or DRL systems. This is inefficient for complex BVLOS applications as it leads to a loss of flight autonomy due to high energy consumption.
White et al. in [16] present an evasion algorithm based on concepts of differential geometry such as curvature and tangential velocity. However, this solution only yields good results on straight trajectories and non-dynamic objects. Similarly, Lai et al. in [17] propose an obstacle detection system based on morphological operations and temporal filters such as Hidden Markov Models (HMMs) and the Viterbi algorithm. The use of morphological operations for image processing does not require high computational power, but the cost increases when using temporal filters. Nonetheless, this can be addressed by implementing other types of filters that demand less processing, thereby making the proposed solution feasible for low-cost auxiliary platforms.
An additional study addressing the autonomous landing is the one conducted by Cocchioni et al. [18]. This work proposes a landing and battery recharging system based on a computer vision algorithm that detects helipads using the OpenCV library. This eliminates the need for a high-performance card to carry out the task.
Currently, there is a large number of studies describing the development of auxiliary platforms. This is because UAVs are increasingly being used in more challenging and dangerous applications for humans. An example of this is the monitoring of volcanic activity. This can be observed in the work conducted by Di Stefano et al. in [19][20], where a multirotor equipped with cameras is used to monitor and gather data on the Lusi mud crater in Indonesia. Additionally, Everaerts in [21] explains the usefulness of UAVs for remote sensing and scientific mapping due to their low cost and ease of access to the platforms. Another example is the one presented by Flores et al. in [22], where they use a fixed-wing UAV for volcano surveillance.

This entry is adapted from the peer-reviewed paper 10.3390/robotics12060145

References

  1. Melita, C.D.; Longo, D.; Muscato, G.; Giudice, G. Measurement and Exploration in Volcanic Environments. In Handbook of Unmanned Aerial Vehicles; Springer: Dordrecht, The Netherlands, 2014; pp. 2667–2692.
  2. Jordan, B.R. Collecting field data in volcanic landscapes using small UAS (sUAS)/drones. J. Volcanol. Geotherm. Res. 2019, 385, 231–241.
  3. Schroth, L. Drone Market Size 2020–2025; Technical Report; Drone Industry Insights: Hamburg, Germany, 2020.
  4. Campana, S. Drones in Archaeology. State-of-the-art and Future Perspectives. Archaeol. Prospect. 2017, 24, 275–296.
  5. Niedzielski, T. Applications of Unmanned Aerial Vehicles in Geosciences: Introduction. Pure Appl. Geophys. 2018, 175, 3141–3144.
  6. Moor, J.M.; Stix, J.; Avard, G.; Muller, C.; Corrales, E.; Diaz, J.A.; Alan, A.; Brenes, J.; Pacheco, J.; Aiuppa, A.; et al. Insights on Hydrothermal-Magmatic Interactions and Eruptive Processes at Poás Volcano (Costa Rica) From High-Frequency Gas Monitoring and Drone Measurements. Geophys. Res. Lett. 2019, 46, 1293–1302.
  7. Cruzan, M.B.; Weinstein, B.G.; Grasty, M.R.; Kohrn, B.F.; Hendrickson, E.C.; Arredondo, T.M.; Thompson, P.G. Small Unmanned Aerial Vehicles (Micro-Uavs, Drones) in Plant Ecology. Appl. Plant Sci. 2016, 4, 1600041.
  8. Marx, A.; McFarlane, D.; Alzahrani, A. UAV data for multi-temporal Landsat analysis of historic reforestation: A case study in Costa Rica. Int. J. Remote. Sens. 2017, 38, 2331–2348.
  9. Granados-Bolaños, S.; Quesada-Román, A.; Alvarado, G.E. Low-cost UAV applications in dynamic tropical volcanic landforms. J. Volcanol. Geotherm. Res. 2021, 410, 107143.
  10. Index for Risk Management for Latin America and The Caribbean. Technical Report. 2020. Available online: https://drmkc.jrc.ec.europa.eu/inform-index/Portals/0/InfoRM/2020/Subnational/LAC/LAC_INFORM_2020_v007_MainResults_Eng.pdf (accessed on 22 June 2023).
  11. Bi, Y.; Duan, H. Implementation of autonomous visual tracking and landing for a low-cost quadrotor. Optik-Int. J. Light Electron. Opt. 2013, 124, 3296–3300.
  12. Lorenz, M. The History of Pixhawk—Auterion. 2008. Available online: https://auterion.com/the-history-of-pixhawk/ (accessed on 8 April 2023).
  13. Ghasri, M.; Maghrebi, M. Factors affecting unmanned aerial vehicles’ safety: A post-occurrence exploratory data analysis of drones’ accidents and incidents in Australia. Saf. Sci. 2021, 139, 105273.
  14. Guo, J.; Dong, X.; Gao, Y.; Li, D.; Tu, Z. Simultaneous Obstacles Avoidance and Robust Autonomous Landing of a UAV on a Moving Vehicle. Electronics 2022, 11, 3110.
  15. Singla, A.; Padakandla, S.; Bhatnagar, S. Memory-Based Deep Reinforcement Learning for Obstacle Avoidance in UAV With Limited Environment Knowledge. IEEE Trans. Intell. Transp. Syst. 2021, 22, 107–118.
  16. White, B.A.; Shin, H.S.; Tsourdos, A. UAV Obstacle Avoidance using Differential Geometry Concepts. IFAC Proc. Vol. 2011, 44, 6325–6330.
  17. Lai, J.; Mejias, L.; Ford, J.J. Airborne vision-based collision-detection system. J. Field Robot. 2011, 28, 137–157.
  18. Cocchioni, F.; Mancini, A.; Longhi, S. Autonomous navigation, landing and recharge of a quadrotor using artificial vision. In Proceedings of the 2014 International Conference on Unmanned Aircraft Systems (ICUAS), Orlando, FL, USA, 27–30 May 2014.
  19. Stefano, G.D.; Romeo, G.; Mazzini, A.; Iarocci, A.; Hadi, S.; Pelphrey, S. The Lusi drone: A multidisciplinary tool to access extreme environments. Mar. Pet. Geol. 2018, 90, 26–37.
  20. Schellenberg, B.J. Long Range UAS Operations for Volcanic Monitoring. Ph.D. Dissertation, University of Bristol, Bristol, UK, 2020.
  21. Everaerts, J. The use of unmanned aerial vehicles (UAVs) for remote sensing and mapping. Int. Arch. Photogramm. Remote. Sens. Spat. Inf. Sci. 2008, 37, 1187–1192.
  22. Flores, A.; Scipion, D.; Saito, C.; Apaza, J.; Milla, M. Unmanned Aircraft System for Andean Volcano monitoring and surveillance. In Proceedings of the 2019 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), Würzburg, Germany, 2–4 September 2019.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.
This entry is offline, you can click here to edit this entry!
ScholarVision Creations
Feedback