期刊
MACHINE VISION AND APPLICATIONS
卷 32, 期 3, 页码 -出版社
SPRINGER
DOI: 10.1007/s00138-021-01199-1
关键词
Maritime surveillance; Deep learning; CNNs; Image retrieval; Maritime vessel re-identification
类别
资金
- European H2020 Interreg PASSAnT Project
- Provincial Government of Noord-Brabant, The Netherlands
Maritime vessel re-identification is a computer vision task involving matching vessel identities across different camera views. This study introduces a new dataset and performs baseline analysis, comparing performances of 10 deep learning architectures to propose best practices. A novel multi-branch deep learning architecture, MVR-net, is proposed to address the challenging problem of vessel re-identification, outperforming existing networks in evaluation on the new dataset.
Maritime vessel re-identification (re-ID) is a computer vision task of vessel identity matching across disjoint camera views. Prominent applications of vessel re-ID exist in the fields of surveillance and maritime traffic flow analysis. However, the field suffers from the absence of a large-scale dataset that enables training of deep learning models. In this study, we present a new dataset that includes 4614 images of 729 vessels along with 5-bin orientation and 8-class vessel-type annotations to promote further research. A second contribution of this study is the baseline re-ID analysis of our new dataset. Performances of 10 recent deep learning architectures are quantitatively compared to reveal the best practices. Lastly, we propose a novel multi-branch deep learning architecture, Maritime Vessel Re-ID network (MVR-net), to address the challenging problem of vessel re-ID. Evaluation of our approach on the new dataset yields 74.5% mAP and 77.9% Rank-1 score, providing a performance increase of 5.7% mAP and 5.0% Rank-1 over the best-performing baseline. MVR-net also outperforms the PRN (a pioneering vehicle re-ID network), by 2.9% and 4.3% higher mAP and Rank-1, respectively.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据