A team of scientists at the College of Engineering (CoE) in Pune, India, is developing an efficient method for monitoring and recognizing bird species that will help in evaluating the avian biodiversity of a specific region.
A keel-billed toucan (Ramphastos sulfuratus) in Costa Rica. Image credit: T. Tschleuder / CC BY-SA 3.0.
Birds play an important role in a wide variety of ecosystems as both predator and prey.
As birds are high up in the food chain, they are good indicators of the general state of biodiversity health. When they start disappearing, it means that something is wrong with the environment.
From a scientific perspective it is therefore crucial to monitor bird populations.
“Bird songs and calls are made up of syllables and each call and song unique to a given species consists of a group of syllables which in turn are made up of elements,” said CoE researchers Arti Bang and Priti Rege.
“It is possible to carry out a spectrographic analysis of the sound, but this is laborious and requires experts with a good ear for the sounds birds make.”
“Ultimately, however, such an approach will be subjective when it comes to distinguishing between birds with very similar sounding calls and songs.”
“Automated bird recognition based on recordings of the sounds the birds make is a pattern recognition problem,” the scientists added.
They developed an automated system that circumvents the problems associated with previous attempts to automate the process and is based on extracting syllables with 10-millisecond audio frames.
The analysis builds on techniques that have been used to extract information, such as tempo, key signature, and genre from recordings of music.
The team tested the algorithm on samples of bird songs and calls from an online bird sound database called Xeno-Canto.
“We did preliminary testing of the system on ten bird species native to India,” the researchers said.
“The same approach could equally be applied to species found anywhere in the world.”
“Redundancy reduction within the system allows us to cut down the effects of background noise in any given audio recording and so improve accuracy still further,” they noted.
Their work is published in the International Journal of Computer Applications in Technology.
_____
Arti V. Bang & Priti P. Rege. 2017. Evaluation of various feature sets and feature selection towards automatic recognition of bird species. International Journal of Computer Applications in Technology 56 (3): 172-184; doi: 10.1504/IJCAT.2017.088197
