指挥控制与仿真2024，Vol.46Issue(4)：88-96,9.DOI:10.3969/j.issn.1673-3819.2024.04.012
基于深度学习的舰船目标重识别技术
Vessel reidentification technology based on deep learning
莫倩倩 1刘俊 1管坚 1杨麒霖 1彭冬亮 1陈华杰 1谷雨1
作者信息
- 1. 杭州电子科技大学,浙江 杭州 310018
- 折叠
摘要
Abstract
Re-identification technology for pedestrians and vehicles has been successfully applied in the field of intelligence analysis.However,there is a lack of research on re-identification technology for ship targets.In this paper,we propose a double-feature fusion-based maritime defogging re-identification network for intelligence analysis and supervision of ship tar-gets.To reduce the impact of negative samples on features,we adopt a perspective-assisted adaptive query expansion method and a similarity-based feature fusion method.Furthermore,a defogging branch is embedded in the shallow layer of the re-i-dentification branch.This branch utilizes weight sharing technology to extract fog-free features.The defogged image is then reconstructed using upsampling technology and the pyramid model,enhancing the recognition ability of the re-identification network in low-visibility scenarios.Finally,a pseudo-IOU based non-maximum suppression method is proposed to enhance the detection accuracy of ship targets.This method modifies the confidence of the detection frame.Experimental results dem-onstrate that the proposed method outperforms existing methods,and each module contributes to the network's performance.关键词
船舶重识别/深度学习/卷积神经网络/视角辅助Key words
vessel recognition/deep learning/convolutional neural networks/perspective assistance分类
信息技术与安全科学引用本文复制引用
莫倩倩,刘俊,管坚,杨麒霖,彭冬亮,陈华杰,谷雨..基于深度学习的舰船目标重识别技术[J].指挥控制与仿真,2024,46(4):88-96,9.
