Multi-UAV System Architecture for Environmental Protection Area Monitoring

Santos, Vitor Gaboardi dos; Pereira, Diego da Silva; Alsina, Pablo Javier; Fernandes, Daniel H. S.; Nascimento, Luís; Leite, Deyvid L.; Morais, Mateus Rodrigues de; Silva, Maurício Rabello; Souza, Elitelma da Silva

doi:10.17648/sbai-2019-111424

Cited by 3 publications

(3 citation statements)

References 8 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Monitoring of the protected areas and surroundings at a regional and local level is critical given their exposure to anthropogenic pressures, including those associated with climatic change [1]. But an application for monitoring a region of protection is complicated, covers several areas and may have different purposes [2]. Although monitoring has commonly revolved around field data, remote sensing can play a crucial role in establishing baselines of habitats and associated diversity and quantifying failures, degradation or recovery related to specific events or processes.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Concept of the Mobile Monitoring System

Dolný¹,

Moravčíková²

2022

Acta Avionica

View full text Add to dashboard Cite

In connection with the spread of viral diseases caused by COVID-19, its high dynamics and the formation of infection outbreaks were observed. The experience from the first wave of the pandemic showed that, although state-wide measures are effective, they have a significant economic impact and more effective solutions are therefore necessary. In the activities aimed at combating the pandemic caused by COVID-19, one of the most effective means is the isolation of sick patients and the most vulnerable population groups, where the level of risk is the highest. No universally applicable technical solutions which are available on the commercial market would assist in population isolation, in case of protection and monitoring. Creating a mobile monitoring system to protect isolated and at-risk population groups against the spread of viral diseases is highly relevant within Slovakia and with great potential for applicability abroad. This article is focused on the project description that was approved in connection with the protection against the spread of COVID-19, the definition of its main goals, methodology, activities, and benefits.

show abstract

Section: Theoretical Backgroundmentioning

confidence: 99%

Concept of the Mobile Monitoring System

Dolný¹,

Moravčíková²

2022

Acta Avionica

View full text Add to dashboard Cite

show abstract

“…In our previous work (Santos et al, 2019), we used a SSD network to perform boat detection, where a recognition rate of up to 62,15 % was achieved with 10 FP. In this paper, we significantly improved this metric to 86,70 % while also decreasing the FP to 6.…”

Section: P Recision = T P T P + F Pmentioning

confidence: 99%

“…In this context, our previous work (Santos et al, 2019) presented a multi-UAV architecture for monitoring human activity in the APARC. The main contributions were establishing an UAV network to send images, a flight formation strategy to capture images using UAVs, and testing a pre-trained SSD Neural Network to detect boats in forbidden regions.…”

Section: Introductionmentioning

confidence: 99%

CNN-based Boat Detection for Environmental Protection Area Monitoring

Santos,

Pereira,

Nascimento

et al. 2022

Anais Do(a) XXIV Congresso Brasileiro De Automática

View full text Add to dashboard Cite

Boats and ships have always been used throughout history as one of the main types of transportation. In recent years, due to the fast evolution of deep learning techniques and online datasets available, convolutional neural networks (CNN) have been widely used for ship and boat detection applications, such as surveillance of marine resources, helping in maritime rescue, monitoring illegal marine activities, among others. In this paper, we present a robust and efficient CNN-based on state-of-the-art YOLO model to perform boat and other water vehicles detection. The training dataset was built considering boats of different sizes, located on the coast and sea and taken with drones and satellites. We also applied data augmentation techniques such as flipping, cropping and changing brightness to increase the number of samples and improve the model robustness. A case study is presented considering a multi Unmanned Aerial Vehicles (UAV) to detect boats in a Coral Reefs Environmental Protection Area (APARC), where human activity is limited. We evaluated the developed system considering a testing dataset with images of the case study, achieving a recognition rate of 87,2% and a mean average precision of 97,23%.

show abstract