TU Darmstadt / ULB / TUbiblio

Bird@Edge: Bird Species Recognition at the Edge

Höchst, Jonas ; Bellafkir, Hicham ; Lampe, Patrick ; Vogelbacher, Markus ; Mühling, Markus ; Schneider, Daniel ; Lindner, Kim ; Rösner, Sascha ; Schabo, Dana G. ; Farwig, Nina ; Freisleben, Bernd (2022)
Bird@Edge: Bird Species Recognition at the Edge.
10th Edition of the International Conference on Networked Systems (NETYS 2022). virtual Conference (17.-19.05.2022)
doi: 10.1007/978-3-031-17436-0_6
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

We present Bird@Edge, an Edge AI system for recognizing bird species in audio recordings to support real-time biodiversity monitoring. Bird@Edge is based on embedded edge devices operating in a distributed system to enable efficient, continuous evaluation of soundscapes recorded in forests. Multiple ESP32-based microphones (called Bird@Edge Mics) stream audio to a local Bird@Edge Station, on which bird species recognition is performed. The results of several Bird@Edge Stations are transmitted to a backend cloud for further analysis, e.g., by biodiversity researchers. To recognize bird species in soundscapes, a deep neural network based on the EfficientNet-B3 architecture is trained and optimized for execution on embedded edge devices and deployed on a NVIDIA Jetson Nano board using the DeepStream SDK. Our experiments show that our deep neural network outperforms the state-of-the-art BirdNET neural network on several data sets and achieves a recognition quality of up to 95.2% mean average precision on soundscape recordings in the Marburg Open Forest, a research and teaching forest of the University of Marburg, Germany. Measurements of the power consumption of the Bird@Edge components highlight the real-world applicability of the approach. All software and firmware components of Bird@Edge are available under open source licenses.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2022
Autor(en): Höchst, Jonas ; Bellafkir, Hicham ; Lampe, Patrick ; Vogelbacher, Markus ; Mühling, Markus ; Schneider, Daniel ; Lindner, Kim ; Rösner, Sascha ; Schabo, Dana G. ; Farwig, Nina ; Freisleben, Bernd
Art des Eintrags: Bibliographie
Titel: Bird@Edge: Bird Species Recognition at the Edge
Sprache: Englisch
Publikationsjahr: 17 Mai 2022
Verlag: Springer
Reihe: Lecture Notes in Computer Science
Band einer Reihe: 13464
Veranstaltungstitel: 10th Edition of the International Conference on Networked Systems (NETYS 2022)
Veranstaltungsort: virtual Conference
Veranstaltungsdatum: 17.-19.05.2022
DOI: 10.1007/978-3-031-17436-0_6
URL / URN: https://link.springer.com/chapter/10.1007/978-3-031-17436-0_...
Kurzbeschreibung (Abstract):

We present Bird@Edge, an Edge AI system for recognizing bird species in audio recordings to support real-time biodiversity monitoring. Bird@Edge is based on embedded edge devices operating in a distributed system to enable efficient, continuous evaluation of soundscapes recorded in forests. Multiple ESP32-based microphones (called Bird@Edge Mics) stream audio to a local Bird@Edge Station, on which bird species recognition is performed. The results of several Bird@Edge Stations are transmitted to a backend cloud for further analysis, e.g., by biodiversity researchers. To recognize bird species in soundscapes, a deep neural network based on the EfficientNet-B3 architecture is trained and optimized for execution on embedded edge devices and deployed on a NVIDIA Jetson Nano board using the DeepStream SDK. Our experiments show that our deep neural network outperforms the state-of-the-art BirdNET neural network on several data sets and achieves a recognition quality of up to 95.2% mean average precision on soundscape recordings in the Marburg Open Forest, a research and teaching forest of the University of Marburg, Germany. Measurements of the power consumption of the Bird@Edge components highlight the real-world applicability of the approach. All software and firmware components of Bird@Edge are available under open source licenses.

Freie Schlagworte: Bird Species Recognition, Edge Computing, Passive Acoustic Monitoring, Biodiversity, emergenCITY, emergenCITY_KOM
Zusätzliche Informationen:

Presentation at the youtube-Channel of Netys-2022

Fachbereich(e)/-gebiet(e): DFG-Sonderforschungsbereiche (inkl. Transregio)
DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche
LOEWE
LOEWE > LOEWE-Zentren
LOEWE > LOEWE-Zentren > emergenCITY
DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1053: MAKI – Multi-Mechanismen-Adaption für das künftige Internet
DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1053: MAKI – Multi-Mechanismen-Adaption für das künftige Internet > A: Konstruktionsmethodik
DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1053: MAKI – Multi-Mechanismen-Adaption für das künftige Internet > A: Konstruktionsmethodik > Teilprojekt A3: Migration
Hinterlegungsdatum: 15 Aug 2022 07:47
Letzte Änderung: 12 Jan 2024 08:51
PPN: 502047429
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen