Categorization of Ecosystems based on Soundscape Analysis: a perspective from Image Classification

被引:0
作者
Gaitan, Daniel [1 ]
Isaza, Claudia [1 ]
Gomez, William [1 ]
Daza, Juan [2 ]
机构
[1] Univ Antioquia UdeA, UdeA, Dept Engn, SISTEMIC, Calle 70 52-21, Medellin, Colombia
[2] Univ Antioquia UdeA, UdeA, Inst Biol, GHA, Calle 70 52-21, Medellin, Colombia
来源
2016 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE & COMPUTATIONAL INTELLIGENCE (CSCI) | 2016年
关键词
Soundscape; nPSD; DSIFT; ecosystems; classification; ACOUSTIC INDEXES; BIODIVERSITY;
D O I
10.1109/CSCI.2016.147
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This article presents a novel approach to analyze the soundscape in ecosystems, in order to categorize them in terms of their acoustic properties, focusing on the characterization of four ecosystems through an image classification system which contain information of daily acoustic activity in the frequency range (1kHz-11kHz), for five consecutive months. Emphasis is placed on pre-processing of acoustic recordings and their transformation into contour images of normalized power spectral density (nPSD), which acts as a distinctive acoustic metric for each ecosystem. Within the classification system where a support vector machine (SVM) is implemented, the description of the images using SIFT descriptors by dense sampling (DSIFT) and its representation following a BoW scheme is highlighted. The results of the proposed methodology show a high system performance, above 97% accuracy.
引用
收藏
页码:762 / 766
页数:5
相关论文
共 50 条
[31]   IMAGE PIXEL CLASSIFICATION BY CHROMATICITY ANALYSIS [J].
ANDREADIS, I ;
BROWNE, MA ;
SWIFT, JA .
PATTERN RECOGNITION LETTERS, 1990, 11 (01) :51-58
[32]   Classification based polynomial image interpolation [J].
Lenke, Sebastian ;
Schroeder, Hartmut .
IMAGE PROCESSING: ALGORITHMS AND SYSTEMS VI, 2008, 6812
[33]   Fundus Image Based Cataract Classification [J].
Zheng, Jin ;
Guo, Liye ;
Peng, Lihui ;
Yang, Jijiang ;
Li, Jianqiang ;
Liang, Qingfeng .
2014 IEEE INTERNATIONAL CONFERENCE ON IMAGING SYSTEMS & TECHNIQUES (IST), 2014, :90-94
[34]   Froth delineation based on image classification [J].
Wang, W ;
Bergholm, F ;
Yang, B .
MINERALS ENGINEERING, 2003, 16 (11) :1183-1192
[35]   Perception-based image classification [J].
Henry, Christopher ;
Peters, James F. .
INTERNATIONAL JOURNAL OF INTELLIGENT COMPUTING AND CYBERNETICS, 2010, 3 (03) :410-430
[36]   An Image Based Classification Method for Cataract [J].
Shen, Hualei ;
Hao, Hongwei ;
Wei, Lihong ;
Wang, Zhibin .
ISCSCT 2008: INTERNATIONAL SYMPOSIUM ON COMPUTER SCIENCE AND COMPUTATIONAL TECHNOLOGY, VOL 1, PROCEEDINGS, 2008, :583-586
[37]   TEXTURE BASED HYPERSPECTRAL IMAGE CLASSIFICATION [J].
Kumar, B. ;
Dikshit, O. .
ISPRS TECHNICAL COMMISSION VIII SYMPOSIUM, 2014, 40-8 :793-798
[38]   HYPERSPECTRAL IMAGE CLASSIFICATION BASED ON SPECTRAL MIXTURE ANALYSIS FOR CROP TYPE DETERMINATION [J].
Kim, Yeji ;
Kim, Yongil .
IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, :5304-5307
[39]   CLASSIFICATION OF CHRONIC MYELOID LEUKEMIA CELL SUBTYPES BASED ON MICROSCOPIC IMAGE ANALYSIS [J].
Ghane, Narjes ;
Vard, Alireza ;
Talebi, Ardeshir ;
Nematollahy, Pardis .
EXCLI JOURNAL, 2019, 18 :382-404
[40]   A COMPARATIVE ANALYSIS OF MUTUAL INFORMATION BASED FEATURE SELECTION FOR HYPERSPECTRAL IMAGE CLASSIFICATION [J].
Fu, Yuanyuan ;
Jia, Xiuping ;
Huang, Wenjiang ;
Wang, Jihua .
2014 IEEE CHINA SUMMIT & INTERNATIONAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (CHINASIP), 2014, :148-152