Low Resource Species Agnostic Bird Activity Detection
Abstract
This paper explores low resource classifiers and features for the detection of bird activity, suitable for embedded Automatic Recording Units which are typically deployed for long term remote monitoring of bird populations. Features include low-level spectral parameters, statistical moments on pitch samples, and features derived from amplitude modulation. Performance is evaluated on several lightweight classifiers using the NIPS4Bplus dataset. Our experiments show that random forest classifiers perform best on this task, achieving an accuracy of 0.721 and an F1-Score of 0.604. We compare the results of our system against both a Convolutional Neural Network based detector, and standard MFCC features. Our experiments show that we can achieve equal or better performance in most metrics using features and models with a smaller computational cost and which are suitable for edge deployment.
Keywords
Cite
@article{arxiv.2112.09042,
title = {Low Resource Species Agnostic Bird Activity Detection},
author = {Mark Anderson and John Kennedy and Naomi Harte},
journal= {arXiv preprint arXiv:2112.09042},
year = {2021}
}
Comments
This paper is accepted and presented at the IEEE Workshop on Signal Processing Systems (SiPS) October 2021, 3 Figures, 5 Tables