Um Estudo Comparativo de Modelos de Autoencoders para Redução de Dados Visuais em Operações de Veículos Aéreos Não Tripulados (UAV) em Operações de Busca e Resgate (SAR)
Sustainable Business International Journal · 16.03.2026 · 1 (101)
DOI: 10.22409/4sw09a96 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sustainable Business International Journal, online erschienen am 16.03.2026. Verfasst von Samuel Cotta und 2 weiteren Autor:innen.
Abstract (Originalsprache)
This article evaluates the performance of different autoencoder architectures, conventional, variational, and redundancy-penalized, for image compression in autonomous aerial vehicles during search and rescue operations. The main hypothesis anticipated that penalized models would outperform others, balancing computational efficiency and reconstruction fidelity. Experiments were conducted using the SARD 2 dataset, and the analysis considered PSNR, SSIM, MS-SSIM, compression rate, and processing time. Results showed that the conventional autoencoder achieved higher reconstruction quality, while the penalized model excelled in computational efficiency. The variational autoencoder presented intermediate performance. Contrary to expectations, the hypothesis was not fully confirmed, highlighting the need to balance quality and efficiency according to operational constraints. Statistical analysis (Kruskal-Wallis test) indicated significant differences among models. It is important to note the limitation regarding end-to-end latency assessment, as only compression and reconstruction times were measured in the experimental environment. For future work, evaluation in real transmission scenarios and analysis of energy impact and adaptive approaches for different operational conditions are recommended.
Zitieren
APA
Cotta, S., Dantas, M. A. R., & Araújo, M. A. P. (2026). Um Estudo Comparativo de Modelos de Autoencoders para Redução de Dados Visuais em Operações de Veículos Aéreos Não Tripulados (UAV) em Operações de Busca e Resgate (SAR). Sustainable Business International Journal, 1(101). https://doi.org/10.22409/4sw09a96
Vancouver
Cotta S, Dantas MAR, Araújo MAP. Um Estudo Comparativo de Modelos de Autoencoders para Redução de Dados Visuais em Operações de Veículos Aéreos Não Tripulados (UAV) em Operações de Busca e Resgate (SAR). Sustainable Business International Journal. 2026;1(101). doi:10.22409/4sw09a96
BibTeX
@article{Cotta2026,
author = {Cotta, Samuel and Dantas, Mário Antônio Ribeiro and Araújo, Marco Antônio Pereira},
title = {Um Estudo Comparativo de Modelos de Autoencoders para Redução de Dados Visuais em Operações de Veículos Aéreos Não Tripulados (UAV) em Operações de Busca e Resgate (SAR)},
journal = {Sustainable Business International Journal},
year = {2026},
volume = {1},
number = {101},
doi = {10.22409/4sw09a96}
}
EUVIMED