Low-cost animal and pedestrian crossing detection in rural roads using WiFi sensing and deep learning
Resumo
Road traffic accidents involving animals cause great health, environmental, and monetary costs every year, specially on rural areas. Current animal detection systems suffer from either cost, scalability or accuracy issues, which prevent their effective use in a more extensive manner. In our research, we explore WiFi sensing to monitor events in rural roads, using low-cost IoT devices to collect WiFi data, publishing the first open CSI dataset of animal crossings and applying machine learning techniques to detect and classify them. Event detection runs on ESP32-S3 devices, while classification runs on Raspeberry Pi 4 devices, both with accuracy of at least 95%. Our system enables a scalable and cost-effective solution for monitoring multiple kilometers of roads.
Palavras-chave:
Wi-Fi Sensing, Internet of Things, Animal Detection, Road Monitoring, Integrated Sensing and Communications (ISAC), Coexistence Between IEEE 802.15.4 and IEEE 802.11
Referências
(2024). Omnet++ discrete event simulator. [link].
(2024). Openthread border router example. [link].
Abra, F. D., Huijser, M. P., Magioli, M., Bovo, A. A. A., and de Barros Ferraz, K. M. P. M. (2021). An estimate of wild mammal roadkill in são paulo state, brazil. Heliyon, 7.
Agafonovs, N., Skageris, A., Strazdins, G., and Mednis, A. (2014). Imilepost: Embedded solution for dangerous road situation warnings. In Proceedings - 1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013, Kota Kinabalu, Malaysia. IEEE.
Chen, J., Xu, H., Wu, J., Yue, R., Yuan, C., and Wang, L. (2019). Deer crossing road detection with roadside lidar sensor. IEEE Access, 7.
Ducca, S. V., Jordão, A., and Margi, C. B. (2023). Detection and classification of animal crossings on roads using iot-based wifi sensing. In 2023 IEEE Latin-American Conference on Communications (LATINCOM), pages 1–6, Panama City, Panama. IEEE.
Ducca, S. V. and Margi, C. B. (2022). Performance trade offs in iot-based traffic monitoring and incident detection systems. In 2022 Symposium on Internet of Things (SIoT), pages 1–4, São Paulo, Brazil. IEEE.
Ducca, S. V., Margi, C. B., and Correia, A. J. L. (2024). Low-cost animal and pedestrian crossing detection in rural roads using wifi sensing and deep learning. Master’s thesis, Universidade de São Paulo.
(FHWA), F. H. A. (2008). Wildlife-Vehicle Collision Reduction Study: Report To Congress. U.S. Department of Transportation (FHWA-HRT-08-034). Federal High-way Administration (FHWA).
Maus, G. and Brückmann, D. (2020). A non-intrusive, single-sided car traffic monitoring system based on low-cost ble devices. volume 2020-October. IEEE.
Sharma, N. and Garg, R. D. (2022). Real-time computer vision for transportation safety using deep learning and iot. In 8th International Conference on Engineering and Emerging Technologies, ICEET 2022, Kuala Lumpur, Malasya. IEEE.
Singh, P. K., Singh, K. N., Choudhury, M. K., Bharadwaj, J., Das, R. J., and Gogoi, D. (2022). Advanced warning mechanism to reduce man animal conflict on roads using renewable energy. In 2022 IEEE International Power and Renewable Energy Conference (IPRECON), pages 1–4, Kerala , India. IEEE.
Viani, F., Polo, A., Giarola, E., Robol, F., Benedetti, G., and Zanetti, S. (2016). Performance assessment of a smart road management system for the wireless detection of wildlife road-crossing. In IEEE 2nd International Smart Cities Conference: Improving the Citizens Quality of Life, ISC2 2016 - Proceedings, Trento, Italy. IEEE.
(WHO), W. H. O. (2018). Global status report on road safety 2018: summary. (WHO/NMH/NVI/18.20). World Health Organization, Geneva.
Won, M., Sahu, S., and Park, K. J. (2019). Deepwitraffic: Low cost wifi-based traffic monitoring system using deep learning. In Proceedings - 2019 IEEE 16th International Conference on Mobile Ad Hoc and Smart Systems, MASS 2019, Monterey, USA. IEEE.
Österlind, F., Dunkels, A., Eriksson, J., Finne, N., and Voigt, T. (2006). Cross-level sensor network simulation with cooja. In Proceedings - Conference on Local Computer Networks, LCN, Tampa, Florida. IEEE.
(2024). Openthread border router example. [link].
Abra, F. D., Huijser, M. P., Magioli, M., Bovo, A. A. A., and de Barros Ferraz, K. M. P. M. (2021). An estimate of wild mammal roadkill in são paulo state, brazil. Heliyon, 7.
Agafonovs, N., Skageris, A., Strazdins, G., and Mednis, A. (2014). Imilepost: Embedded solution for dangerous road situation warnings. In Proceedings - 1st International Conference on Artificial Intelligence, Modelling and Simulation, AIMS 2013, Kota Kinabalu, Malaysia. IEEE.
Chen, J., Xu, H., Wu, J., Yue, R., Yuan, C., and Wang, L. (2019). Deer crossing road detection with roadside lidar sensor. IEEE Access, 7.
Ducca, S. V., Jordão, A., and Margi, C. B. (2023). Detection and classification of animal crossings on roads using iot-based wifi sensing. In 2023 IEEE Latin-American Conference on Communications (LATINCOM), pages 1–6, Panama City, Panama. IEEE.
Ducca, S. V. and Margi, C. B. (2022). Performance trade offs in iot-based traffic monitoring and incident detection systems. In 2022 Symposium on Internet of Things (SIoT), pages 1–4, São Paulo, Brazil. IEEE.
Ducca, S. V., Margi, C. B., and Correia, A. J. L. (2024). Low-cost animal and pedestrian crossing detection in rural roads using wifi sensing and deep learning. Master’s thesis, Universidade de São Paulo.
(FHWA), F. H. A. (2008). Wildlife-Vehicle Collision Reduction Study: Report To Congress. U.S. Department of Transportation (FHWA-HRT-08-034). Federal High-way Administration (FHWA).
Maus, G. and Brückmann, D. (2020). A non-intrusive, single-sided car traffic monitoring system based on low-cost ble devices. volume 2020-October. IEEE.
Sharma, N. and Garg, R. D. (2022). Real-time computer vision for transportation safety using deep learning and iot. In 8th International Conference on Engineering and Emerging Technologies, ICEET 2022, Kuala Lumpur, Malasya. IEEE.
Singh, P. K., Singh, K. N., Choudhury, M. K., Bharadwaj, J., Das, R. J., and Gogoi, D. (2022). Advanced warning mechanism to reduce man animal conflict on roads using renewable energy. In 2022 IEEE International Power and Renewable Energy Conference (IPRECON), pages 1–4, Kerala , India. IEEE.
Viani, F., Polo, A., Giarola, E., Robol, F., Benedetti, G., and Zanetti, S. (2016). Performance assessment of a smart road management system for the wireless detection of wildlife road-crossing. In IEEE 2nd International Smart Cities Conference: Improving the Citizens Quality of Life, ISC2 2016 - Proceedings, Trento, Italy. IEEE.
(WHO), W. H. O. (2018). Global status report on road safety 2018: summary. (WHO/NMH/NVI/18.20). World Health Organization, Geneva.
Won, M., Sahu, S., and Park, K. J. (2019). Deepwitraffic: Low cost wifi-based traffic monitoring system using deep learning. In Proceedings - 2019 IEEE 16th International Conference on Mobile Ad Hoc and Smart Systems, MASS 2019, Monterey, USA. IEEE.
Österlind, F., Dunkels, A., Eriksson, J., Finne, N., and Voigt, T. (2006). Cross-level sensor network simulation with cooja. In Proceedings - Conference on Local Computer Networks, LCN, Tampa, Florida. IEEE.
Publicado
19/05/2025
Como Citar
DUCCA, Samuel Vieira; CORREIA, Artur Jordão Lima; MARGI, Cíntia Borges.
Low-cost animal and pedestrian crossing detection in rural roads using WiFi sensing and deep learning. In: CONCURSO DE TESES E DISSERTAÇÕES - SIMPÓSIO BRASILEIRO DE REDES DE COMPUTADORES E SISTEMAS DISTRIBUÍDOS (SBRC), 43. , 2025, Natal/RN.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 252-261.
ISSN 2177-9384.
DOI: https://doi.org/10.5753/sbrc_estendido.2025.7082.
