删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

多特征融合的鸟类物种识别方法

本站小编 Free考研考试/2022-01-02
-->
谢将剑,杨俊,邢照亮,张卓,陈新.多特征融合的鸟类物种识别方法[J].,2020,39(2):207-215
多特征融合的鸟类物种识别方法
Bird species recognition method based on multi-feature fusion
投稿时间：2019-06-16修订日期：2020-02-25
中文摘要:
深度学习输入特征的选择直接影响其分类性能，为了进一步提高基于深度学习的鸟类物种识别模型的分类性能，该文提出一种多特征融合识别方法。该方法首先通过短时傅里叶变换、梅尔倒谱变换和线性调频小波变换分别计算得到鸣声信号的3种语图样本集，然后分别利用3种语图样本集训练3个基于VGG16迁移的单一特征模型，将3个模型的输出进行自适应加权求和实现融合，并修正了加权交叉熵函数以克服样本不平衡的问题，最后对语图进行分类实现鸟类物种的识别。以ICML4B鸣声库的35种鸟类为研究对象，对比了4种模型的平均识别准确率(MAP)，结果表明特征融合模型较单一特征模型的MAP最大提高了0.307；选择输入语图的持续时间分别为100 ms、300 ms以及500 ms，对比不同持续时间下4种模型的测试MAP值，结果表明持续时间为300ms时4种模型的MAP值均为最高；对比了不同信噪比下4种模型的识别效果，多特征融合模型的识别准确率随着信噪比的下降降低最少。说明在选择合适的语图持续时间后，该文提出的特征融合模型能得到更高的识别准确率，具有一定的抗噪能力，且训练参数少，更适合于少样本鸟类的识别。
英文摘要:
The choice of input feature directly affects the classification performance of the deep learning, a multi-feature fusion recognition method was proposed to improve the classification performance of the bird species recognition model. In this method, firstly three kinds of spectrogram samples of vocalization signals were calculated through short time Fourier transform, Mel-frequency cepstrum transform and chirplet transform respectively, then three single feature models which based on VGG16 transfer learning were trained using these three kinds of spectrogram samples accordingly, modified weighted cross entropy function was used to fix the problem of imbalanced data set, the outputs of three models were fused to classify the spectrograms and realize the recognition of bird species. Taken the 35 kinds of bird in ICML4B database for study subject, the MAPs were compared, results show that the mean average precision (MAP) of feature fusion model is highest increased by 0.307 contrast to the single feature model; Three spectrogram durations, 100 ms, 300 ms and 500 ms were chosen to compare the test MAP of four models, the results reveal that the 300 ms duration is the best; the precision of 4 models with different SNR were compared, the precision reduction of feature fusion model as the SNR decreased is the least. The proposed model can achieve better performance with suitable duration, have anti-noise ability in some degree, and the trainable parameters are less, which is more suitable for birds with little samples.
DOI：10.11684/j.issn.1000-310X.2020.02.005
中文关键词:鸟类物种识别,深度卷积神经网络,多特征融合
英文关键词:Birdspecies recognition, Deepconvolutional neuralnetworks, Multi-featurefusion
基金项目:国家自然科学基金项目（面上项目，重点项目，重大项目）,国家重点基础研究发展计划（973计划）
作者单位E-mail
谢将剑北京林业大学工学院shyneforce@bjfu.edu.cn
杨俊北京林业大学工学院2216334840@qq.com
邢照亮先进输电技术国家重点实验室（全球能源互联网研究院有限公司）344369028@qq.com
张卓先进输电技术国家重点实验室（全球能源互联网研究院有限公司）344369028@qq.com
陈新先进输电技术国家重点实验室（全球能源互联网研究院有限公司）344369028@qq.com
摘要点击次数:1003
全文下载次数:779
查看全文查看/发表评论下载PDF阅读器
相关附件：修改说明1修改说明1修改说明2修改说明3论文原图
关闭








PDF全文下载地址:

http://yysx.cnjournals.cn/ch/reader/create_pdf.aspx?file_no=19091&flag=1&journal_id=yysx&year_id=2020
相关话题/互联网 技术 实验室 能源 北京

Free考研考试FreeKaoYan.Com
欢迎来到Free考研考试，"为实现人生的Free而奋斗"

© 2020 FreeKaoYan! . All rights reserved.