Nalazite se na CroRIS probnoj okolini. Ovdje evidentirani podaci neće biti pohranjeni u Informacijskom sustavu znanosti RH. Ako je ovo greška, CroRIS produkcijskoj okolini moguće je pristupi putem poveznice www.croris.hr
izvor podataka: crosbi !

Comparison of two deep learning methods for ship target recognition with optical remotely sensed data (CROSBI ID 282825)

Prilog u časopisu | izvorni znanstveni rad | međunarodna recenzija

Dianjun Zhang ; Jie Zhan ; Lifeng Tan ; Yuhang Gao ; Robert Župan Comparison of two deep learning methods for ship target recognition with optical remotely sensed data // Neural computing and applications, 1 (2020), 1; 1-11. doi: 10.1007/s00521-020-05307-6

Podaci o odgovornosti

Dianjun Zhang ; Jie Zhan ; Lifeng Tan ; Yuhang Gao ; Robert Župan

engleski

Comparison of two deep learning methods for ship target recognition with optical remotely sensed data

As an important part of modern marine monitoring systems, ship target identification has important significance inmaintaining marine rights and monitoring maritime traffic. With the development of artificial intelligence technology, image detection and recognition based on deep learning methods have become the most popular and practical method. Inthis paper, two deep learning algorithms, the Mask R-CNN algorithm and the Faster R-CNN algorithm, are used to buildship target feature extraction and recognition models based on deep convolutional neural networks. The established modelswere compared and analyzed to verify the feasibility of target detection algorithms. In this study, 5748 remote sensingmaps were selected as the dataset for experiments, and two algorithms were used to classify and extract warships andcivilian ships. Experiments showed that for the accuracy of ship identification, Mask R-CNN and Faster R-CNN reached95.21% and 92.76%, respectively. These results demonstrated that the Mask R-CNN algorithm achieves pixel-levelsegmentation. Compared with the Faster R-CNN algorithm, the obtained target detection effect is more accurate, and theperformance in target detection and classification is better, which reflects the great advantage of pixel-level recognition.

Full convolutional network, Ship target recognition, Pixel level, Mask R-CNN, Faster R-CNN, Optical remote sensing images

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

Podaci o izdanju

1 (1)

2020.

1-11

objavljeno

0941-0643

1433-3058

10.1007/s00521-020-05307-6

Trošak objave rada u otvorenom pristupu

APC

Povezanost rada

Geodezija

Poveznice
Indeksiranost