Birdsong Detection at the Edge with Deep Learning

Simone DIsabato, Giuseppe Canonaco, Paul G. Flikkema, Manuel Roveri, Cesare Alippi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Understanding the distribution of bird species and populations and learning how birds behave and communicate are of great importance in wildlife biology, animal ecology, conservation of ecosystems, and assessing the effects of climate change and urbanization. The temporal and spatial limitations of human observation have motivated significant efforts to develop technology for bird song and vocalization detection and classification. While solutions based on signal processing and machine learning are extant, they are limited in various combinations of speed, computational complexity, and memory use, as well as in detection/classification capability in real-world conditions. This paper introduces ToucaNet, a deep neural network for birdsong detection based on transfer-learning, a deep learning mechanism allowing us to exploit knowledge acquired on various tasks: this enables us to speed up training and shows improved detection accuracy. ToucaNet provides birdsong detection accuracy in line with the best solutions in the literature but with much less computational complexity and memory demand. We also introduce BarbNet, an approximated version of ToucaNet tailored for Internet-of-Things (IoT) units. We show the proposed solution's effectiveness and efficiency in terms of detection accuracy and the implementation feasibility in real-world IoT devices, with specific results for the STM32 Nucleo H7 board, which is based on an ARM Cortex-M7 processor. To our best knowledge, this is the first birdsong detection algorithm designed to take into account constraints on memory, computational speed, and power usage of embedded devices. Thus, this work points the way to cost-effective IoT technology for at-scale intelligent birdsong data collection and analysis in the field.

Original languageEnglish (US)
Title of host publicationProceedings - 2021 IEEE International Conference on Smart Computing, SMARTCOMP 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages9-16
Number of pages8
ISBN (Electronic)9781665412520
DOIs
StatePublished - Aug 2021
Event7th IEEE International Conference on Smart Computing, SMARTCOMP 2021 - Virtual, Irvine, United States
Duration: Aug 23 2021Aug 27 2021

Publication series

NameProceedings - 2021 IEEE International Conference on Smart Computing, SMARTCOMP 2021

Conference

Conference7th IEEE International Conference on Smart Computing, SMARTCOMP 2021
Country/TerritoryUnited States
CityVirtual, Irvine
Period8/23/218/27/21

Keywords

  • Bird Vocalization
  • Birdsong Detection
  • Deep Learning
  • Embedded Systems
  • Internet-of-Things

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Birdsong Detection at the Edge with Deep Learning'. Together they form a unique fingerprint.

Cite this