Bird@Edge Core is the software running on NVIDIA Jetson Nano devices for birdsong recognition in soundscape recordings.

Bird@Edge is 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. If you are interested in our research, read our paper or watch the talk recorded for Springer NETYS 2022 conference.

Separate repositories exist for the code running on Bird@Edge Mic and for the operating system image Bird@Edge OS created for running on the Bird@Edge Stations.

• Jetson Nano Developer Kit
• MicroSD Card
• Micro-USB Power Supply (5V⎓2A)

• Jetson Nano Developer Kit SD Card Image
• DeepStream SDK 6.0

Run the following command to compile the application:make -j4

• Download the inference model birdmodel_batchsize_10.trt and place it in the ./model directory.
• Set the environment variables:
  • LD_LIBRARY_PATH=/opt/nvidia/deepstream/deepstream-6.0/lib/gst-plugins/
  • LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libgomp.so.1
• Run the following command to start the pipeline:
  • ./birdedge -c configs/ds_audio_config.txt --gst-debug=1
• The output format is as follows:
  • {"frame_num": %d, "timestamp": %ld, "label": %s, "source_id": %d, "confidence": %f}

If you are using Bird@Edge in academia, we'd appreciate if you cited our scientific research paper. Please cite as "Höchst & Bellafkir et al."

J. Höchst, H. Bellafkir, P. Lampe, M. Vogelbacher, M. Mühling, D. Schneider, K. Lindner, S. Rösner, D. G. Schabo, N. Farwig, and B. Freisleben, "Bird@Edge: Bird Species Recognition at the Edge," in International Conference on Networked Systems (NETYS), 2022. DOI: 10.1007/978-3-031-17436-0_6

@inproceedings{hoechst2022birdedge,
  title = {{Bird@Edge: Bird Species Recognition at the Edge}},
  author = {H{\"o}chst, Jonas and Bellafkir, Hicham and Lampe, Patrick and Vogelbacher, Markus and M{\"u}hling, Markus and Schneider, Daniel and Lindner, Kim and R{\"o}sner, Sascha and Schabo, Dana G. and Farwig, Nina and Freisleben, Bernd},
  booktitle = {International Conference on Networked Systems (NETYS)},
  year = {2022},
  month = may,
  organization = {Springer},
  keywords = {Bird Species Recognition, Edge Computing, Passive Acoustic Monitoring, Biodiversity},
  doi = {10.1007/978-3-031-17436-0_6},
}