首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于图像处理的回声定位信号检测方法
引用本文:段德鑫,姜莹,刘宗伟,杨春梅,吕连港.基于图像处理的回声定位信号检测方法[J].海洋科学进展,2022,40(1):145-153.
作者姓名:段德鑫  姜莹  刘宗伟  杨春梅  吕连港
作者单位:自然资源部第一海洋研究所;自然资源部海洋环境科学与数值模拟重点实验室;山东省海洋环境科学与数值模拟重点实验室;青岛海洋科学与技术试点国家实验室区域海洋动力学与数值模拟功能实验室
基金项目:国家自然科学基金项目——南极普里兹湾和麦克默多湾虎鲸声信号特征研究(41906170)。
摘    要:鲸豚类海洋哺乳动物发出的回声定位信号是一种频率较高的短时脉冲信号,研究回声定位信号检测方法有助于快速、准确地检测海洋哺乳动物发声,进而更好地保护海洋哺乳动物.本文提出了一种基于图像处理的鲸豚类动物回声定位信号检测方法.该方法首先对收集到的数据进行分帧,计算每帧信号的时频图;使用Frangi滤波器对时频图进行滤波,以降低...

关 键 词:图像处理  Frangi滤波  直线检测  随机森林分类器  回声定位信号

Detection Method for Echolocation Clicks Based on Image Processing
Institution:(First Institute of Oceanography, MNR, Qingdao 266061, China;Key Laboratory of Marine Science and Numerical Modeling, MNR, Qingdao 266061, China;Shandong Key Laboratory of Marine Science and Numerical Modeling, Qingdao 266061, China;Laboratory for Regional Oceanography and Numerical Modeling,Pilot National Laboratory for Marine Science and Technology(Qingdao),Qingdao 266237,China)
Abstract:Odontocetes echolocation click is a kind of short-time signal with high frequency.Research on the detection method of echolocation signal is helpful for the rapid and accurate detection of marine mammal vocalization,so as to better protection of marine mammals.A method based on image processing is proposed to detect odontocetes echolocation clicks.The collected data are divided into fixed-length frames and the time-frequency diagram of each frame is calculated.The spectrogram images of click signals are filtered to remove noise and enhance the line-shape signals.Considering that the echolocation signals are like lines in time-frequency domain,line detection is subsequently used to obtain the precise position of the signal,and then to acquire the feature of signals.Finally,a Random Forest Classifier was trained to obtain a detector to distinguish between click and non-click clips.Experiments were carried out using acoustic data of Mesoplodon densirostris,Globicephalamelas,Eubalaena japonica and Orcaella brevirostris.The performance of the proposed method was evaluated using real audio recordings.The experimental results indicate that comparing with the traditional energy detector method,the proposed algorithm shows higher recall and precise under low signal-to-noise ratio(SNR).The proposed method can provide technical support for marine bioacoustics study.
Keywords:image processing  Frangi filter  line detection  Random Forest Classifier  echolocation clicks
本文献已被 维普 等数据库收录!
点击此处可从《海洋科学进展》浏览原始摘要信息
点击此处可从《海洋科学进展》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号