Abstract
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.
Original language | English |
---|---|
Article number | 988 |
Pages (from-to) | 1-17 |
Number of pages | 17 |
Journal | Remote Sensing |
Volume | 13 |
Issue number | 5 |
DOIs | |
Publication status | Published - 5 Feb 2021 |
MoE publication type | A1 Journal article-refereed |
Keywords
- maritime vessel dataset
- ship detection
- object detection
- convolutional neural network
- deep learning
- autonomous marine navigation