Towards real-time rainforest gunshot detection using efficient deep learning and acoustic sensor integration
The Journal of the Acoustical Society of America · 01.10.2025 · 158 (4_Supplement) · A205-A205
DOI: 10.1121/10.0040620 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, erschienen am 01.10.2025. Verfasst von Naveen Dhar und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Despite increased surveillance and global collaboration, wildlife poaching remains a major conservation concern. The technological advancement of Autonomous Recording Units (ARUs) has enabled acoustic monitoring over large spatial and temporal scales, creating the possibility of real-time alerting systems for poaching. However, high false-positive rates (FPRs) and large computational needs of existing models have rendered real-time detection of poaching impractical. I propose a lightweight rainforest gunshot detection model suitable for on-device processing and a sensor consensus function to minimize false-positives. The developed model, trained on augmented log-mel spectrograms from Belize, consisted of both 2-D and 1-D depthwise-separable convolutional layers and a Gated-Recurrent layer. High FPRs are a pervasive challenge for gunshot detection systems due to the acoustic similarity of commonplace sounds such as cracking branches. SAIL (Sensor Analysis and Integration Layer) was developed to reduce false-positives by leveraging gunshot propagation properties. Testing through acoustic propagation simulation on a spatially distinct dataset across 1000 iterations showed significant FPR reduction when comparing SAIL probabilities to simple inference. The developed model achieved 0.908 validation F1 at 11MB (964KB serialized), retaining 89% of existing literature performance while reducing model size by over 98%. Altogether, this approach presents a promising approach to cost-effective real-time poaching detection.
Zitieren
APA
Dhar, N., Verahrami, A. K., Malonga, P. J., Samba, O. J., & Tolkova, I. (2025). Towards real-time rainforest gunshot detection using efficient deep learning and acoustic sensor integration. The Journal of the Acoustical Society of America, 158(4_Supplement), A205-A205. https://doi.org/10.1121/10.0040620
Vancouver
Dhar N, Verahrami AK, Malonga PJ, Samba OJ, Tolkova I. Towards real-time rainforest gunshot detection using efficient deep learning and acoustic sensor integration. The Journal of the Acoustical Society of America. 2025;158(4_Supplement):A205-A205. doi:10.1121/10.0040620
BibTeX
@article{Dhar2025,
author = {Dhar, Naveen and Verahrami, Anahita K. and Malonga, Phael J. and Samba, Onesi J. and Tolkova, Irina},
title = {Towards real-time rainforest gunshot detection using efficient deep learning and acoustic sensor integration},
journal = {The Journal of the Acoustical Society of America},
year = {2025},
volume = {158},
number = {4_Supplement},
pages = {A205--A205},
doi = {10.1121/10.0040620}
}
EUVIMED