Deep Learning Approach For Objects Detection in Underwater Pipeline Images

Gašparović, Boris; Lerga, Jonatan; Mauša, Goran; Ivašić-Kos, Marina

doi:10.1080/08839514.2022.2146853

Pregled bibliografske jedinice broj: 1232522

Deep Learning Approach For Objects Detection in Underwater Pipeline Images

Gašparović, Boris; Lerga, Jonatan; Mauša, Goran; Ivašić-Kos, Marina

Deep Learning Approach For Objects Detection in Underwater Pipeline Images // Applied artificial intelligence, 32 (2022), 1; 2146853, 21 doi:10.1080/08839514.2022.2146853 (međunarodna recenzija, članak, znanstveni)

CROSBI ID: 1232522 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Deep Learning Approach For Objects Detection in Underwater Pipeline Images

Autori
Gašparović, Boris ; Lerga, Jonatan ; Mauša, Goran ; Ivašić-Kos, Marina

Izvornik
Applied artificial intelligence (0883-9514) 32 (2022), 1; 2146853, 21

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Deep learning ; Object detection ; Underwater images

Sažetak
In this paper, we present automatic, deep-learning methods for pipeline detection in underwater environments. Seafloor pipelines are critical infrastructure for oil and gas transport. The inspection of those pipelines is required to verify their integrity and determine the need for maintenance. Underwater conditions present a harsh environment that is challenging for image recognition due to light refraction and absorption, poor visibility, scattering, and attenuation, often causing poor image quality. Modern machine-learning object detectors utilize Convolutional Neural Network (CNN), requiring a training dataset of sufficient quality. In the paper, six different deep-learning CNN detectors for underwater object detection were trained and tested: five are based on the You Only Look Once (YOLO) architectures (YOLOv4, YOLOv4-Tiny, CSP- YOLOv4, YOLOv4@Resnet, YOLOv4@DenseNet), and one on the Faster Region-based CNN (RCNN) architecture. The models’ performances were evaluated in terms of detection accuracy, mean average precision (mAP), and processing speed measured with the Frames Per Second (FPS) on a custom dataset containing underwater pipeline images. In the study, the YOLOv4 outperformed other models for underwater pipeline object detection resulting in an mAP of 94.21% with the ability to detect objects in real-time. Based on the literature review, this is one of the pioneering works in this field.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo

POVEZANOST RADA

Projekti:
IP-2018-01-3739 - Sustav potpore odlučivanju za zeleniju i sigurniju plovidbu brodova (DESSERT) (Prpić-Oršić, Jasna, HRZZ - 2018-01) ( CroRIS)
EK--951732 - Nacionalni centri kompetencija u okviru EuroHPC (EUROCC) (Štula, Maja; Kranjčević, Lado; Kovač, Mario; Skala, Karolj; Miletić, Vedran, EK ) ( CroRIS)
MINGO-ESIF-KK.01.2.1.02.0179 - ABsistemDCiCloud (ABsistemDCiCloud) (Lerga, Jonatan, MINGO - Fond: Europski fond za regionalni razvoj Program: OP Konkurentnost i kohezija 2014. - 2020. Jačanje gospodarstva primjenom istraživanja i inovacija Područje: IRI - Povećanje razvoja novih proizvoda i usluga koji proizlaze iz aktivnosti istraživanja i raz) ( CroRIS)
VLASTITA-SREDSTVA-uniri-tehnic-17 - Računalom potpomognuta digitalna analiza i klasifikacija signala (UNIRI-TEHNIC-18-17) (Lerga, Jonatan, VLASTITA-SREDSTVA - UNIRI2018) ( CroRIS)
NadSve-Sveučilište u Rijeci-uniri-tehnic-18-15 - Razvoj postupaka temeljenih na strojnom učenju za prepoznavanje bolesti i ozljeda iz medicinskih slika (Štajduhar, Ivan, NadSve ) ( CroRIS)
MZO-BI-HR/20-21-043 - Analiza hiperspektralnih slika korištenjem strojnog učenja i adaptivnog filtrianja prilagođenog podacima (Lerga, Jonatan, MZO ) ( CroRIS)
undefined