Pretraga

Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1005210

Ensemble Transfer Learning Framework for Vessel Size Estimation from 2D Images

Miličević, Mario; Žubrinić, Krunoslav; Grbavac, Ivan; Kešelj, Ana
Ensemble Transfer Learning Framework for Vessel Size Estimation from 2D Images // Advances in Computational Intelligence. IWANN 2019. : Conference proceedings / Rojas, Ignacio ; Joya, Gonzalo ; Catala, Andreu (ur.).
Las Palmas de Gran Canaria, Španjolska: Springer, 2019. str. 258-269 doi:10.1007/978-3-030-20518-8_22 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)

CROSBI ID: 1005210 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Ensemble Transfer Learning Framework for Vessel Size Estimation from 2D Images

Autori
Miličević, Mario ; Žubrinić, Krunoslav ; Grbavac, Ivan ; Kešelj, Ana

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Advances in Computational Intelligence. IWANN 2019. : Conference proceedings / Rojas, Ignacio ; Joya, Gonzalo ; Catala, Andreu - : Springer, 2019, 258-269

ISBN
978-3-030-20521-8

Skup
15th International Work-Conference on Artificial Neural Networks

Mjesto i datum
Las Palmas de Gran Canaria, Španjolska, 12.06.2019. - 14.06.2019

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
deep learning ; convolutional neural networks ; transfer learning ; regression ; ensemble methods ; computer vision ; vessel size estimation

Sažetak
The term gross tonnage refers to the internal volume of a vessel and it has several legal, administrative and safety uses. Therefore, there is significant value in developing a mechanism for the automatic estimation of vessel size based on 2D images taken in uncontrolled conditions. However, this is a demanding task as vessels can be photographed from various angles and distances, a part of a vessel can be obstructed, or a vessel can blend with the background. We proposed an ensemble of fine-tuned transfer learning models, which we trained on 20, 000 images in a training dataset consisting of randomly downloaded images from the Shipspotting website. Multiple deep learning methods were applied and modified for regression problems, together with two classical machine learning algorithms. A detailed analysis of model performances was given, based on which it can be concluded that such an approach results in a vessel size evaluation of the same quality as with the best human experts from the corresponding field.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA

Ustanove:
Sveučilište u Dubrovniku

Profili:

Avatar Url Mario Miličević (autor)

Avatar Url Ana Kešelj (autor)

Avatar Url Krunoslav Žubrinić (autor)

Avatar Url Ivan Grbavac (autor)

Poveznice na cjeloviti tekst rada:

Pristup cjelovitom tekstu rada doi link.springer.com

Citiraj ovu publikaciju:

Miličević, Mario; Žubrinić, Krunoslav; Grbavac, Ivan; Kešelj, Ana
Ensemble Transfer Learning Framework for Vessel Size Estimation from 2D Images // Advances in Computational Intelligence. IWANN 2019. : Conference proceedings / Rojas, Ignacio ; Joya, Gonzalo ; Catala, Andreu (ur.).
Las Palmas de Gran Canaria, Španjolska: Springer, 2019. str. 258-269 doi:10.1007/978-3-030-20518-8_22 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Miličević, M., Žubrinić, K., Grbavac, I. & Kešelj, A. (2019) Ensemble Transfer Learning Framework for Vessel Size Estimation from 2D Images. U: Rojas, I., Joya, G. & Catala, A. (ur.)Advances in Computational Intelligence. IWANN 2019. : Conference proceedings doi:10.1007/978-3-030-20518-8_22.
@article{article, author = {Mili\v{c}evi\'{c}, Mario and \v{Z}ubrini\'{c}, Krunoslav and Grbavac, Ivan and Ke\v{s}elj, Ana}, year = {2019}, pages = {258-269}, DOI = {10.1007/978-3-030-20518-8\_22}, keywords = {deep learning, convolutional neural networks, transfer learning, regression, ensemble methods, computer vision, vessel size estimation}, doi = {10.1007/978-3-030-20518-8\_22}, isbn = {978-3-030-20521-8}, title = {Ensemble Transfer Learning Framework for Vessel Size Estimation from 2D Images}, keyword = {deep learning, convolutional neural networks, transfer learning, regression, ensemble methods, computer vision, vessel size estimation}, publisher = {Springer}, publisherplace = {Las Palmas de Gran Canaria, \v{S}panjolska} }
@article{article, author = {Mili\v{c}evi\'{c}, Mario and \v{Z}ubrini\'{c}, Krunoslav and Grbavac, Ivan and Ke\v{s}elj, Ana}, year = {2019}, pages = {258-269}, DOI = {10.1007/978-3-030-20518-8\_22}, keywords = {deep learning, convolutional neural networks, transfer learning, regression, ensemble methods, computer vision, vessel size estimation}, doi = {10.1007/978-3-030-20518-8\_22}, isbn = {978-3-030-20521-8}, title = {Ensemble Transfer Learning Framework for Vessel Size Estimation from 2D Images}, keyword = {deep learning, convolutional neural networks, transfer learning, regression, ensemble methods, computer vision, vessel size estimation}, publisher = {Springer}, publisherplace = {Las Palmas de Gran Canaria, \v{S}panjolska} }

Citati:

    Altmetrijski pokazatelji:


    Podijeli:





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font
    CROSBI koristi kolačiće (cookies) kako bi poboljšao funkcionalnost stranice.