RSSi-Based Visitor Tracking in Museums via Cascaded AI Classifiers and Coloured Graph Representations




RSSi-based tracking, total-coloured graph analysis, pedestrian dynamics in museums, IoT, machine learning


Individual tracking of museum visitors based on portable radio beacons, an asset for behavioural analyses and comfort/performance improvements, is seeing increasing diffusion. Conceptually, this approach enables room-level localisation based on a network of small antennas (thus, without invasive modification of the existent structures). The antennas measure the intensity (RSSi) of self-advertising signals broadcasted by beacons individually assigned to the visitors. The signal intensity provides a proxy for the distance to the antennas and thus indicative positioning. However, RSSi signals are well-known to be noisy, even in ideal conditions (high antenna density, absence of obstacles, absence of crowd, ...). In this contribution, we present a method to perform accurate RSSi-based visitor tracking when the density of antennas is relatively low, e.g. due to technical constraints imposed by historic buildings. We combine an ensemble of "simple" localisers, trained based on ground-truth, with an encoding of the museum topology in terms of a total-coloured graph. This turns the localisation problem into a cascade process, from large to small scales, in space and in time. Our use case is visitors tracking in Galleria Borghese, Rome (Italy), for which our method manages >96% localisation accuracy, significantly improving on our previous work (J. Comput. Sci. 101357, 2021).


Robinson, E.S.: The behavior of the museum visitor. New Series, Number 5. Publications of the American Association of Museums, Washington, D. C. (1928). ERIC: ED044919

Feng, Y., Duives, D., Daamen, W., Hoogendoorn, S.: Data collection methods for studying pedestrian behaviour: A systematic review. Building and Environment 187, 107329 (2021). doi:10.1016/j.buildenv.2020.107329

Yoshimura, Y., Sobolevsky, S., Ratti, C., Girardin, F., Carrascal, J.P., Blat, J., Sinatra, R.: An analysis of visitors' behavior in the Louvre Museum: A study using Bluetooth data. Environment and Planning B: Planning and Design 41, 1113-1131 (2014). doi:10.1068/b130047p

Centorrino, P., Corbetta, A., Cristiani, E., Onofri, E.: Managing crowded museums: Visitors flow measurement, analysis, modeling, and optimization. Journal of Computational Science 53, 101357 (2021). doi:10.1016/j.jocs.2021.101357

Balzotti, C., Briani, M., Corbetta, A., Cristiani, E., Minozzi, M., Natalini, R., Suriano, S., Toschi, F.: Forecasting visitors behaviour in crowded museums. In: Proceedings of the 9th International Conference on Pedestrian and Evacuation Dynamics (PED2018), Lund, Sweden, August 22-24, 2018 (2018). doi:10.17815/CD.2020.82

Pluchino, A., Garofalo, C., Inturri, G., Rapisarda, A., Ignaccolo, M.: Agent-based simulation of pedestrian behaviour in closed spaces: A museum case study. Journal of Artificial Societies and Social Simulation 17(1), 16 (2014). doi:10.18564/jasss.2336

Falk, J.H.: Identity and the museum visitor experience. Routledge, Taylor & Francis Group, London and New York (2016). doi:10.4324/9781315427058

Yalowitz, S.S., Bronnenkant, K.: Timing and tracking: Unlocking visitor behavior. Visitor Studies 12(1), 47-64 (2009). doi:10.1080/10645570902769134

Chianese, A., Piccialli, F.: Designing a smart museum: When cultural heritage joins iot. In: 2014 Eighth International Conference on Next Generation Mobile Apps, Services and Technologies, pp. 300-306 (2014). doi:10.1109/NGMAST.2014.21

Pouw, C.A., Willems Joris Van Schadewijk, F., Thurau, J., Toschi, F., Corbetta, A.: Benchmarking high-fidelity pedestrian tracking systems for research, real-time monitoring and crowd control. In: submitted (2021). Arxiv-2108.11719

Deak, G., Curran, K., Condell, J.: A survey of active and passive indoor localisation systems. Computer Communications 35(16), 1939-1954 (2012). doi:10.1016/j.comcom.2012.06.004

Sadowski, S., Spachos, P.: Rssi-based indoor localization with the internet of things. IEEE Access 6, 30149-30161 (2018). doi:10.1109/ACCESS.2018.2843325

Iadanza, E.: Designing an indoor real-time location system for healthcare facilities. In: Mediterranean Forum-Data Science Conference: First International Conference, MeFDATA 2020, Sarajevo, Bosnia and Herzegovina, October 24, 2020, Revised Selected Papers, vol. 1343, p. 110. Springer Nature (2021). doi:10.1007/978-3-030-72805-2_8

Varma, P.S., Anand, V.: Random forest learning based indoor localization as an iot service for smart buildings. Wireless Personal Communications 117(4), 3209-3227 (2021). doi:10.1007/s11277-020-07977-w

Piccialli, F., Cuomo, S., Schiano di Cola, V., Casolla, G.: A machine learning approach for IoT cultural data. Journal of Ambient Intelligence and Humanized Computing (2019). doi:10.1007/s12652-019-01452-6

Wang, X., Bischoff, O., Laur, R., Paul, S.: Localization in wireless ad-hoc sensor networks using multilateration with rssi for logistic applications. Procedia Chemistry 1(1), 461-464 (2009). doi:10.1109/GLOCOM.2009.5425237

Xue, W., Qiu, W., Hua, X., Yu, K.: Improved wi-fi rssi measurement for indoor localization. IEEE Sensors Journal 17(7), 2224-2230 (2017). doi:10.1109/JSEN.2017.2660522

Yang, B., Guo, L., Guo, R., Zhao, M., Zhao, T.: A novel trilateration algorithm for rssi-based indoor localization. IEEE Sensors Journal 20(14), 8164-8172 (2020). doi:10.1109/JSEN.2020.2980966

Beder, C., Klepal, M.: Fingerprinting based localisation revisited. A rigorous approach for comparing RSSI measurements coping with missed access points and differing antenna attenuations. In: Proceedings of the International Conference on Indoor Positioning and Indoor Navigation (IPIN 2012), November 13-15, 2012 (2012). doi:10.1109/IPIN.2012.6418940

Mackey, A., Spachos, P., Song, L., Plataniotis, K.N.: Improving ble beacon proximity estimation accuracy through bayesian filtering. IEEE Internet of Things Journal 7(4), 3160-3169 (2020). doi:10.1109/JIOT.2020.2965583

Zhou, C., Yuan, J., Liu, H., Qiu, J.: Bluetooth indoor positioning based on rssi and kalman filter. Wireless Personal Communications 96(3), 4115-4130 (2017). doi:10.1007/s11277-017-4371-4

Centorrino, P., Corbetta, A., Cristiani, E., Onofri, E.: Measurement and analysis of visitors' trajectories in crowded museums. In: Proceedings of 2019 IMEKO TC-4 International Conference on Metrology for Archaeology and Cultural Heritage, Florence, Italy, December 4-6, 2019, pp. 423-428 (2019). ArXiv:1912.02744

Diestel, R.: Graph Theory, 5th edn. Springer Publishing Company, Incorporated (2017). ISBN: 978-3-662-53622-3

Mansour, N., Ponnusamy, R., Choudhary, A., Fox, G.C.: Graph contraction for physical optimization methods: a quality-cost tradeoff for mapping data on parallel computers. In: Proceedings of the 7th International Conference on Supercomputing, pp. 1-10 (1993). doi:10.1145/165939.165942

Lombardi, F., Onofri, E.: Graph contraction on attribute-based coloring. Procedia Computer Science (2022). The 13th International Conference on Ambient Systems, Networks and Technologies (ANT)

Ahuja, R.K., Mehlhorn, K., Orlin, J., Tarjan, R.E.: Faster algorithms for the shortest path problem. Journal of the ACM (JACM) 37(2), 213-223 (1990). doi:10.1145/77600.77615

Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms, 2nd edn. The MIT Press (2001). ISBN: 978-0-262-03293-3

Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016). URL

MacKay, D.J.C.: Information Theory, Inference & Learning Algorithms. Cambridge University Press, USA (2002). ISBN: 978-0-521-64298-9

Lara-Benítez, P., Carranza-García, M., Riquelme, J.: An experimental review on deep learning architectures for time series forecasting. International Journal of Neural Systems 31(3) (2021). doi:10.1142/S0129065721300011

Biau, G., Scornet, E.: A random forest guided tour. Test 25(2), 197-227 (2016). doi:10.1007/s11749-016-0481-7




How to Cite

Onofri, E., & Corbetta, A. (2022). RSSi-Based Visitor Tracking in Museums via Cascaded AI Classifiers and Coloured Graph Representations. Collective Dynamics, 6, 1–17.



Pedestrian and Evacuation Dynamics 2021