Maritime vessel re-identification: novel VR-VCA dataset and a multi-branch architecture MVR-net
Authors:
Open Access
- 15 April 2021
- journal article
- research article
- Published by Springer Nature in Machine Vision and Applications
- Vol. 32 (3) , 1-14
Abstract
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.Keywords
This publication has 30 references indexed in Scilit:
- Toward robust multitype and orientation detection of vessels in maritime surveillanceJournal of Electronic Imaging, 2020
- Vessel-speed Enforcement System by Multi-camera Detection and Re-identification2020
- Towards Parameter-Optimized Vessel Re-identification Based on IORnet2019
- Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification2017
- Maritime transportation of illegal drugs from South AmericaInternational Journal of Drug Policy, 2017
- Deep Residual Learning for Image Recognition2016
- A survey of approaches and trends in person re-identificationImage and Vision Computing, 2014
- Symmetry-driven accumulation of local features for human characterization and re-identificationComputer Vision and Image Understanding, 2013
- Project Catch: A space based solution to combat illegal, unreported and unregulated fishingActa Astronautica, 2012
- Person Re-identification by Efficient Impostor-Based Metric Learning2012