Vertaisarvioitu alkuperäisartikkeli tai data-artikkeli tieteellisessä aikakauslehdessä (A1)
ABOships-An Inshore and Offshore Maritime Vessel Detection Dataset with Precise Annotations
Julkaisun tekijät: Iancu B, Soloviev V, Zelioli L, Lilius J
Kustantaja: MDPI
Julkaisuvuosi: 2021
Tietokannassa oleva lehden nimi: REMOTE SENSING
Lehden akronyymi: REMOTE SENS-BASEL
Volyymi: 13
Sivujen määrä: 17
DOI: http://dx.doi.org/10.3390/rs13050988
Tiivistelmä
Availability of domain-specific datasets is an essential problem in object detection. Datasets of inshore and offshore maritime vessels are no exception, with a limited number of studies addressing maritime vessel detection on such datasets. For that reason, we collected a dataset consisting of images of maritime vessels taking into account different factors: background variation, atmospheric conditions, illumination, visible proportion, occlusion and scale variation. Vessel instances (including nine types of vessels), seamarks and miscellaneous floaters were precisely annotated: we employed a first round of labelling and we subsequently used the CSRT tracker to trace inconsistencies and relabel inadequate label instances. Moreover, we evaluated the out-of-the-box performance of four prevalent object detection algorithms (Faster R-CNN, R-FCN, SSD and EfficientDet). The algorithms were previously trained on the Microsoft COCO dataset. We compared their accuracy based on feature extractor and object size. Our experiments showed that Faster R-CNN with Inception-Resnet v2 outperforms the other algorithms, except in the large object category where EfficientDet surpasses the latter.
Availability of domain-specific datasets is an essential problem in object detection. Datasets of inshore and offshore maritime vessels are no exception, with a limited number of studies addressing maritime vessel detection on such datasets. For that reason, we collected a dataset consisting of images of maritime vessels taking into account different factors: background variation, atmospheric conditions, illumination, visible proportion, occlusion and scale variation. Vessel instances (including nine types of vessels), seamarks and miscellaneous floaters were precisely annotated: we employed a first round of labelling and we subsequently used the CSRT tracker to trace inconsistencies and relabel inadequate label instances. Moreover, we evaluated the out-of-the-box performance of four prevalent object detection algorithms (Faster R-CNN, R-FCN, SSD and EfficientDet). The algorithms were previously trained on the Microsoft COCO dataset. We compared their accuracy based on feature extractor and object size. Our experiments showed that Faster R-CNN with Inception-Resnet v2 outperforms the other algorithms, except in the large object category where EfficientDet surpasses the latter.
Turun yliopiston Tutkimustietojärjestelmän portaali