Non-linear Distortion Recognition in UAVs’ Images using Deep Learning

Silva, Leandro H. F. P.; Dias, Jocival Dantas; Santos, Jean Fabrício Batista; Mari, Jean‐François; Escarpinati, Maurício Cunha; Backes, André Ricardo

doi:10.5220/0010309504470454

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to classify and consequently recognize the presence of deformations in an patch mentioned in sections 4.1.1 and 4.1.2, we consider 4 traditional CNN architectures: InceptionV3 (Szegedy et al, 2016), ResNet (He et al, 2016), SqueezeNet (IANDOLA et al, 2016) and VGG-16 (SIMONYAN;ZISSERMAN, 2014). We used these networks pre-trained in the 2012 dataset Imagenet and made the pertinent adjustments (e.g., input/output sizes) to our classification problem (SILVA et al, 2020a;SILVA et al, 2021).…”

Section: Methodsmentioning

confidence: 99%

Detection and correction of deformations in UAVs’ images using deep learning

Silva¹

Self Cite

View full text Add to dashboard Cite

To God, for the privilege of life. To my mother, Iris de Fátima Furtado Pinto, who has always provided me with love and support, and never having tried so hard to achieve my dreams.To my advisors, Professor Dr. André Ricardo Backes and Professor Dr. Mauricio Cunha Escarpinati, for the friendship, commitment, opportunities, and teachings of this journey.To Professor Dr. João Fernando Mari for his friendship and contribution to my training.To Professor MSc. Pedro Moisés de Sousa for all the advice and teachings. To Professors Dr. Bruno Augusto Nassif Travençolo and Dr. Dalcimar Casanova who kindly accepted to participate in the examination board of this work.To colleague Jocival Dantas Dias Júnior for the support provided.To the Federal University of Uberlândia and the Federal University of Viçosa, Institutions that I have provided me with academic and professional growth.To Coordenação de Aperfeiçoamento de Pessoal de Nível Superior -Brazil (CAPES) -for financial support. This study was financed by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior -Brazil (CAPES) -Finance Code 001. I would like to thank too the company Sensix Inovações em Drones Ltda for providing the images used in the experiments."We are just an advanced breed of monkeys on a minor planet of a very average star.But we can understand the Universe. That makes us something very special."

show abstract

Section: Methodsmentioning

confidence: 99%

Detection and correction of deformations in UAVs’ images using deep learning

Silva¹

Self Cite

View full text Add to dashboard Cite

show abstract

Directions of using technologies of machine training in the military sphere

Lytvyn¹,

Peleshchak²

2022

Stuc.intelekt

View full text Add to dashboard Cite

Abstract. Creating the Ukrainian Artificial Intelligence Strategy is undoubtedly a pivotal task, especially for reconnaissance and combat operations. Machine learning technologies are considered, including deep learning for detection, analysis, identification of landmines and multispectral images, missiles and other aircraft, hybrid models that use adaptive coding techniques and neural networks, recognition of spatial images in the spectral range.

show abstract

Non-linear Distortion Recognition in UAVs’ Images using Deep Learning

Cited by 2 publications

References 0 publications

Detection and correction of deformations in UAVs’ images using deep learning

Detection and correction of deformations in UAVs’ images using deep learning

Directions of using technologies of machine training in the military sphere

Contact Info

Product

Resources

About