TY - JOUR
T1 - ABOships - An Inshore and Offshore Maritime Vessel Detection Dataset with Precise Annotations
AU - Iancu, Bogdan
AU - Soloviev, Valentin
AU - Zelioli, Luca
AU - Lilius, Johan
PY - 2021/2/5
Y1 - 2021/2/5
N2 - 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.
AB - 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.
KW - maritime vessel dataset
KW - ship detection
KW - object detection
KW - convolutional neural network
KW - deep learning
KW - autonomous marine navigation
U2 - https://doi.org/10.3390/rs13050988
DO - https://doi.org/10.3390/rs13050988
M3 - Article
SN - 2072-4292
VL - 13
SP - 1
EP - 17
JO - Remote Sensing
JF - Remote Sensing
IS - 5
M1 - 988
ER -