A multiple-UAV architecture for autonomous media production

Mademlis, Ioannis; Torres-González, Arturo; Capitán, Jesús; Montagnuolo, Maurizio; Messina, Alberto; Negro, Fulvio; Barz, Cédric Le; Gonçalves, Tiago; Cunha, Rita; Guerreiro, Bruno J.; Zhang, Fan; Boyle, Stephen; Guerout, Gregoire; Tefas, Anastasios; Nikolaidis, Nikos; Bull, David; Pitas, Ioannis

doi:10.1007/s11042-022-13319-8

Cited by 14 publications

(4 citation statements)

References 41 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, the problem of real-time video stream synchronization from UAVs in the working environment of an apple orchard is a challenging research problem with significant implications for orchard management. Accurately synchronizing the video streams from multiple UAVs can enable more accurate tracking of the growth and condition of apple trees [16], leading to improved crop yield optimization. Additionally, the proposed methods for real-time video stream synchronization from UAVs have applications beyond apple orchards and can be applied in other dynamic environments where real-time video stream synchronization is essential.…”

Section: Related Workmentioning

confidence: 99%

Method of Real-Time Video Stream Synchronization in the Working Environment of an Apple Orchard

Мельниченко¹

2023

CSIT

View full text Add to dashboard Cite

Monitoring and analyzing the state of harvest in an apple orchard is essential for efficient horticulture. Unmanned aerial vehicles (UAVs) have been increasingly used for this purpose due to their ability to capture high-resolution images and videos of the orchard from different perspectives. However, synchronizing the video streams from multiple UAVs in real-time presents a significant challenge. The traditional controller-worker architecture used for video stream synchronization is prone to latency issues, which can negatively impact the accuracy of the monitoring system. To address this issue, the authors propose a decentralized method using a consensus algorithm that allows the group of UAVs to synchronize their video streams in real time without relying on a centralized controller device. The proposed method also addresses the challenges of limited network connectivity and environmental factors, such as wind and sunlight. The automated system that utilizes the proposed method was tested in an actual apple orchard. The experimental results show that the proposed approach achieves real-time video stream synchronization with minimal latency and high accuracy. As such, the SSIM index varies from 0.79 to 0.92, with an average value of 0.87, and the PSNR index – varies from 22 to 39, which indicates the decent quality of the received information from combined images. Meanwhile, the effectiveness of the developed system with the proposed approach was proven, which is confirmed by a high average value of 82.69% of the reliability indicator of detecting and calculating the number of fruit fruits and a low average level of type I (14.67%) and II (18.33%) errors. Overall, the proposed method provides a more reliable and efficient approach to real-time video stream synchronization in an apple orchard, which can significantly improve the monitoring and management of apple orchards.

show abstract

Section: Related Workmentioning

confidence: 99%

Method of Real-Time Video Stream Synchronization in the Working Environment of an Apple Orchard

Мельниченко¹

2023

CSIT

View full text Add to dashboard Cite

show abstract

“…By relying on Internet of Things technology, drones can not only establish airspace networks and air to ground networks, but also compensate for the shortcomings of ground networks in terms of longitudinal spatial scalability. The integration and optimization of data collection and transmission by UAV, and the guarantee of reliability and safety in information gathering, is addressed through task and channel allocation [7][8][9]. Therefore, from this point of view, this research takes bipartite graph technology as the optimization basis to optimize the continuous operation of UAV information collection and information transmission in an integrated way.…”

Section: Introductionmentioning

confidence: 99%

UAV Network Channel Allocation Method Based on Bipartite Graph Popular Matching Algorithm

Li,

Guo

2024

IEEE Access

View full text Add to dashboard Cite

To address the challenges of selecting task schemes and ensuring secure channels duringdata collection and transmission by unmanned aerial vehicles, the study divides the secure transmission model into physical domain and social domain based on graph theory to ensure the security of unmanned aerial vehicles during task execution. Secondly, the multi to one matching problem was optimized through matching theory, achieving maximum benefits between drones and ground to ground (D2D) users. This study designed a stable matching scheme for drone task allocation based on bipartite graphs and a popular matching strategy for drone security spectrum resource allocation based on bipartite graphs. By adapting the design of a series of coherent actions of drones from information collection to information transmission, the efficiency and security of drone information transmission can be improved. The experimental results show that the average revenue of the designed algorithm for unmanned aerial vehicles is between 21 and 40, while the average revenue range for a single task is between 173 and 210. Compared with other algorithms in terms of security performance for drones and D2D users, the algorithm designed in the study shows strong advantages. Specifically, in terms of drone safety performance, the design algorithm's performance improves as the spectrum sharing limit increases. The advantage becomes more obvious when the sharing limit value reaches 1; From the perspective of D2D users, the average worst-case safety rate of the design algorithm increases with the increase of flight cycle and average power. Compared tofixed-trajectory drones, the overall performance gain of the research and design algorithm reaches about 18.2%, and compared with fixed power drones, the overall performance gain reaches about 15.5%. In summary, the research has made significant progress in task allocation and channel security spectrum resource allocation. The design algorithm achieves the optimal effect between computational complexity and performance, and overall maximizes the benefits between drones and D2D users.

show abstract

“…Recent advances have led to an unprecedented popularization of Unmanned Aerial Vehicles (UAVs, or "drones") during the last decade. Drones have proven useful for many civilian and military applications, such as search and rescue operations, surveillance, inspection, mapping [1], wildlife monitoring, crowd monitoring/management, precision agriculture, or aerial media production [2] [3] [4] [5]. Gradual increases…”

Section: Introductionmentioning

confidence: 99%

Auth-Persons: A Dataset for Detecting Humans in Crowds from Aerial Views

Symeonidis

Mademlis

Pitas

et al. 2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Recent advances in artificial intelligence, control and sensing technologies have facilitated the development of autonomous Unmanned Aerial Vehicles (UAVs). Detecting humans from video input captured on-the-fly from UAVs is a critical task for ensuring flight safety, mostly handled with lightweight Deep Neural Networks (DNNs). However the detection of individual people in the case of dense crowds and/or distribution shifts (i.e., significant visual differences between the training and the test sets) is still very challenging. This paper presents AUTH-Persons, a new, annotated, publicly available video dataset, that consists of both real and synthetic footage, suitable for training and evaluating aerial-view person detection algorithms. The synthetic data were collected from 8 visually distinct photorealistic outdoor environments and they mostly contain scenes with crowded areas, where heavy occlusions and high person densities pose challenges to common detectors. This dataset is employed to evaluate the generalization performance of various stateof-the-art detection frameworks, by testing them on environments that are visually distinct from those they have been trained on. Finally, given that Non-Maximum Suppression (NMS) methods at the end of person detection pipelines typically suffer in crowded scenes, the performance of various NMS algorithms is also compared in AUTH-Persons.

show abstract

A multiple-UAV architecture for autonomous media production

Cited by 14 publications

References 41 publications

Method of Real-Time Video Stream Synchronization in the Working Environment of an Apple Orchard

Method of Real-Time Video Stream Synchronization in the Working Environment of an Apple Orchard

UAV Network Channel Allocation Method Based on Bipartite Graph Popular Matching Algorithm

Auth-Persons: A Dataset for Detecting Humans in Crowds from Aerial Views

Contact Info

Product

Resources

About