基于模态度量的多模态海上船舶识别方法

摘要：

现有的海上多模态识别方法在处理复杂非线性特征方面存在欠缺之处，无法充分利用不同模态的信息，而且融合过程采用的是固定融合策略、融合权重,基于此提出了一种基于模态度量的海上船舶识别网络，这个模型引进了特征过滤模块，能够抑制无关信息，减轻模态间的分布差异.增强多模态特征提取的鲁棒性.本文还设计了模态度量评估机制，依据各模态特征的贡献来动态分配融合权重，从而最大程度地减少低价值模态对最终融合性能的影响.此机制能够根据当前场景、环境的变化，自适应地调整融合权重，提高融合效果.本文提出的方法在公开的VAIS海上红外可见光多模态数据集上进行了基准测试，在准确性和计算效率方面都优于当前最先进的方法.

To address the shortcomings that current maritime multimodal recognition methods have in processing com-plex nonlinear features, effectively utilizing information from various modalities. and using fixed fusion strategies and weights.this paper puts forward a Modality Measurement-based Maritime Ship Recognition Network (MM-NET). The model has inside a Feature Filtering Module (FFM) which is used for effective suppression of useless information, reduction of distribution differences between different modalities, and improvement of the stability of multimodal feature picking work. In addition. this article devises a Modality Measurement(MM) mechanism which dynamically gives out fusion weights according to the contribu-tion of every modal feature, therefore reducing to the smallest extent the inlluence that low- value modalities have on the final fusion pertormance, This mechanism can promote fusion effet degree on current scenarios and enviroment changes, and on self-adaption fusion weight changes. The method we put forward has carried on the benchmark test on the public VAIS mari-time infrared-visible multimodal data set, thus it has shown that the accuracy and calculation efficiency outperform than the existing advanced methods.

作者：

徐政伟,黄沛基,何建樑,王世豪

Xu Zhengwei,Huang Peiji,He Jianliang,Wang Shihao

机构地区：

河南师范大学a.计算机与信息工程学院(人工智能学院)；b.河南省教育人工智能与个性化学习重点实验室；哈尔滨工程大学信息与通信工程学院

引用本文：

徐政伟，黄沛基，何建樑等。基于模态度量的多模态海上船舶识别方法[J].河南师范大学学报(自然科学版),2026,54(5):105-111.(Xu Zhengwei,Huang Peiji,He Jianliang,et al.Multimodal maritime ship recognition method based on modality metric[J].Journal of Henan Normal University(Natural Science Edition).2026,54(5):105-111.DOI:10.16366/j.cnki.1000-2367.2025.06.25.0001.)

基金：

国家自然科学基金；河南省科技攻关计划项目

关键词：

多模态融合;海上船舶识别;特征过滤;模态度量

multimodal fusion; maritime ship recognition; feature filtering; modality metric

分类号：

TP391

基于模态度量的多模态海上船舶识别方法.pdf