Mobile bird recognition method based on birdsong

A mobile, bird-based technology, applied in the field of bird voice recognition, can solve the problems of large amount of calculation, long recognition time, low recognition efficiency, etc., and achieve the effect of high recognition efficiency, small amount of eigenvalue data, and small amount of calculation

Inactive Publication Date: 2015-05-27
CHINA JILIANG UNIV
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] 3. The recognition efficiency is not high
Due to the large amount of calculation, the recognition takes a long time

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Mobile bird recognition method based on birdsong
  • Mobile bird recognition method based on birdsong
  • Mobile bird recognition method based on birdsong

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be further described below in conjunction with accompanying drawing.

[0024] like figure 1 As shown, the device used in the present invention includes a car, computer, CRIO (CompactRIO series modular instrument), camera, dynamic signal analyzer, IEPE integrated circuit piezoelectric microphone, LabVIEW and MATLAB software. Both the CRIO and the dynamic signal analyzer are connected to the first computer, which is equipped with LabVIEW and MATLAB software. The first computer realizes the intelligent control of the car through the CRIO, including forward, backward, turning and automatic speed control through the PID algorithm. Real-time monitoring of the voltage of the power supply battery, alarms for undervoltage, and other functions; the monitoring of the car is realized through the camera, and the collection of the bird's song signal is realized through the dynamic signal analyzer and the IEPE integrated circuit piezoelectric microphone. on...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a mobile bird recognition method based on birdsong. A birdsong signal acquired by a piece of LabVIEW software is preprocessed; the birdsong signal after preprocessing is processed by an AOK time-frequency analysis method programmed by the LabVIEW software and a piece of MATLAB software in a mixed way; and finally, an AOK time-frequency spectrogram is processed by the MATLAB software to realize feature value extraction. Model training is performed on feature values of birds of known bird species to generate training templates and data is stored, model training is performed on the feature value of a bird of a bird species to be recognized to generate a test template, and the bird is recognized by matching the test template with the training templates based on a DTW algorithm. The mobile bird recognition method based on birdsong of the invention well makes up for the shortcomings of the existing bird recognition method such as a large amount of computation and a large amount of data. A bird recognition method which has the advantages of a small amount of computation, a small amount of data, and high identification rate is provided.

Description

technical field [0001] The invention belongs to the technical field of bird voice recognition, and relates to a mobile bird recognition method based on bird voice. Background technique [0002] Bird voice recognition, like speaker recognition, is a type of biometric recognition, which is based on the differences between species and objects. Most of the existing bird voice recognition technologies use the short-term stationary characteristics of bird voices to process the bird voice into frames, and then extract Mel cepstral coefficients (MFCC) or linear predictive cepstral coefficients (LPCC) as bird voice The set of eigenvalue points of the acoustic signal. Then build a Gaussian Mixture Model (GMM) or Hidden Markov Model (HMM) for final identification. Although the existing technology can achieve a good recognition rate, it also has the following deficiencies: [0003] 1. The eigenvalue extraction process is complicated and the calculation amount is relatively large. ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G10L17/26
Inventor 孙斌万鹏威陶达赵玉晓陈飞
Owner CHINA JILIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap