Abstract
Electronic shot counters allow armourers to perform preventive and predictive maintenance based on quantitative measurements, improving reliability, reducing the frequency of accidents, and reducing maintenance costs. To answer a market pressure for both low lead time to market and increased customisation, we aim to solve the shot detection and shot counting problem in a generic way through machine learning.
In this study, we describe a method allowing one to construct a dataset with minimal labelling effort by only requiring the total number of shots fired in a time series. To our knowledge, this is the first study to propose a technique, based on learning from label proportions, that is able to exploit these weak labels to derive an instance-level classifier able to solve the counting problem and the more general discrimination problem. We also show that this technique can be deployed in heavily constrained microcontrollers while still providing hard real-time (<100 ms) inference. We evaluate our technique against a state-of-the-art unsupervised algorithm and show a sizeable improvement, suggesting that the information from the weak labels is successfully leveraged. Finally, we evaluate our technique against human-generated state-of-the-art algorithms and show that it provides comparable performance and significantly outperforms them in some offline and real-world benchmarks.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Calhoun, R.B., Lamkin, S., Rodgers, D.: Systems and methods involving creation and/or utilization of image mosaic in classification of acoustic events (2019)
Dempster, A., Schmidt, D.F., Webb, G.I.: MINIROCKET: a very fast (almost) deterministic transform for time series classification. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp. 248–257 (2021). https://doi.org/10.1145/3447548.3467231
FN Herstal, S.A.: Small arms management: break free of paper chains with a smart, digital armory. White paper (2020)
Joannes, R., Delcourt, J.P., Heins, P.: Device for detecting and counting shots fired by an automatic or semi-automatic firearm, and firearm equipped with such a device (2010)
Lai, L., Suda, N., Chandra, V.: CMSIS-NN: efficient neural network kernels for arm cortex-m CPUs. arXiv:1801.06601 [cs] (2018). https://doi.org/10.48550/arXiv.1801.06601
Laine, S., Aila, T.: Temporal ensembling for semi-supervised learning. arXiv:1610.02242 [cs] (2017). https://doi.org/10.48550/arXiv.1610.02242
Loeffler, C.E.: Detecting gunshots using wearable accelerometers. PLoS ONE 9(9), 1–6 (2014). https://doi.org/10.1371/journal.pone.0106664
Madiraju, N.S., Sadat, S.M., Fisher, D., Karimabadi, H.: Deep temporal clustering : fully unsupervised learning of time-domain features. arXiv:1802.01059 [cs.LG] (2018). https://doi.org/10.48550/arXiv.1802.01059
Miyato, T., Maeda, S.I., Koyama, M., Ishii, S.: Virtual adversarial training: a regularization method for supervised and semi-supervised learning. arXiv:1704.03976 [cs, stat] (2018). https://doi.org/10.48550/arXiv.1704.03976
Putra, I.P.E.S., Brusey, J., Gaura, E., Vesilo, R.: An event-triggered machine learning approach for accelerometer-based fall detection. Sensors 18, 20 (2017). https://doi.org/10.3390/s18010020
Reese, K.A.: A situational-awareness system for networked infantry including an accelerometer-based shot-identification algorithm for direct-fire weapons. Master’s thesis, Naval Postgraduate School (2016)
Santos, G.L., Endo, P.T., de Carvalho Monteiro, K.H., da Silva Rocha, E., Silva, I., Lynn, T.: Accelerometer-based human fall detection using convolutional neural networks. Sensors 19, 1644 (2019). https://doi.org/10.3390/s19071644
Tsai, K.H., Lin, H.T.: Learning from label proportions with consistency regularization. CoRR abs/1910.13188 (2019). https://doi.org/10.48550/arXiv.1910.13188
Ufer, R., Brinkley, K.L.: Self calibrating weapon shot counter (2014)
Weiss, I., Hyden, I., Ami, M.: Device system and method for projectile launcher operation monitoring (2021)
Acknowledgements
I would like to thank my colleague Louis Huggenberger for his continuous help in data acquisition. I would like to thank my thesis supervisors Hugues Libotte and Louis Wehenkel for their precious advice and suggestions.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Morsa, N. (2023). EDGAR: Embedded Detection of Gunshots by AI in Real-time. In: Guyet, T., Ifrim, G., Malinowski, S., Bagnall, A., Shafer, P., Lemaire, V. (eds) Advanced Analytics and Learning on Temporal Data. AALTD 2022. Lecture Notes in Computer Science(), vol 13812. Springer, Cham. https://doi.org/10.1007/978-3-031-24378-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-24378-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-24377-6
Online ISBN: 978-3-031-24378-3
eBook Packages: Computer ScienceComputer Science (R0)
