基于特征金字塔融合的水下目标识别方法研究  

Research on underwater target recognition method based on feature pyramid fusion

作　　者：刘梦然 连恒绪 聂磊[1] 简泽明 LIU Mengran;LIAN Hengxu;NIE Lei;JIAN Zeming(Hubei Key Laboratory of Modern Manufacturing Quantity Engineering,School of Mechanical Engineering,Hubei University of Technology,Wuhan 430068,China)

机构地区：[1]湖北工业大学机械工程学院现代制造质量工程湖北省重点实验室,湖北武汉430068

出　　处：《舰船科学技术》2025年第4期117-123,共7页Ship Science and Technology

基　　金：国家自然科学基金资助项目(51805154);湖北省自然科学基金资助项目(2022CFB473);湖北省教育厅科学研究计划项目(B2022049)。

摘　　要：复杂的海洋环境会加大水下目标识别的难度,为进一步提高水下目标识别准确率,本文提出基于特征金字塔融合的识别方法。提取了梅尔频率的倒谱系数(Mel Frequency Cepstrum Coefficient,MFCC)、线性预测倒谱系数(Linear Predictive Cepstral Coefficient,LPCC)、色度频谱和短时能量4种频率信息不同的特征,分别基于特征金字塔完成特征的深层信息与浅层信息之间的融合,并将融合特征分别输入迁移学习后的轻量化神经网络shufflenetV2,进行水下目标识别。在Deepship数据集和Shipsear数据集上进行测试,结果表明,本文中4种频率信息不同特征基于特征金字塔融合后水下目标识别准确率均大于98%,相比于原始特征,识别准确率更高。该方法可应用于海洋资源勘探、海洋防御与安全、海洋环境监测等场景,为水下目标识别领域的研究提供了新的思路。The complex marine environment increases the difficulty of underwater target recognition.In order to fur-ther improve the accuracy of underwater target recognition,this paper proposed a recognition method based on feature pyr-amid fusion.Four different frequency information features,namely Mel frequency cepstral coefficient(Mel Frequency Cep-strum Coefficient,MFCC),linear prediction cepstral coefficient(Linear Predictive Cepstral Coefficient,LPCC),chromati-city spectrum,and short-term energy,were extracted.Based on the feature pyramid,the deep and shallow information of the features were fused,and the fused features were separately input into the lightweight neural network shufflenetV2 after trans-fer learning for underwater target recognition.The test results on the deepship dataset and shipsear dataset showed that the underwater target recognition accuracy of the four different frequency information features fused based on feature pyramids in this article were all greater than 98%,and compared to the original features,the recognition accuracy was higher.This method can be applied to scenarios such as marine resource exploration,marine defense and safety,and marine environment-al monitoring,providing new ideas for research in the field of underwater target recognition.

关 键 词：水下目标识别 特征金字塔融合 深度学习 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]