Enhancing Water Level Identification with a Barcode-Patterned Panel and Machine Learning

• Gabriel Montagni Domingues Filho Universidade de São Paulo
• Caetano Mazzoni Ranieri Universidade de São Paulo
• Douglas Queiroz Galucio Batista Universidade de São Paulo
• Jó Ueyama Universidade de São Paulo

DOI: https://doi.org/10.5753/eniac.2023.234311

Resumo

Floods cause significant material and human losses worldwide, leading to research in monitoring water levels in urban streams. Existing technologies, such as pressure and ultrasonic sensors, are accurate but costly to deploy. Although ground cameras offer a low-cost alternative, current approaches relying on weak visual markers are sensitive to environmental factors. We address this research gap by introducing a physical marker, called "barcode panel", which is a stainless steel plate with printed black stripes indicating water level. A deep learning algorithm was employed to accurately predict water levels based on this marker. We evaluated our approach using two datasets: one in a pool and another in an actual river. The model demonstrated precise water level predictions in the pool dataset and good results for the river dataset, despite training solely on the pool images. These promising results provide valuable insights for further studies and practical applications.

Palavras-chave: computer vision, deep learning, flood management, visual marker, water gauge

Referências

Aljohani, F.H., Abi Sen, A.A., Ramazan, M.S., Alzahrani, B., Bahbouh, N.M.: A smart framework for managing natural disasters based on the iot and ml. Applied Sciences 13(6), 3888 (2023)

Bioresita, F., Puissant, A., Stumpf, A., Malet, J.P.: A method for automatic and rapid mapping of water surfaces from sentinel-1 imagery. Remote Sensing 10(2), 217 (2018)

Bolanos, S., Stiff, D., Brisco, B., Pietroniro, A.: Operational surface water detection and monitoring using radarsat 2. Remote Sensing 8(4), 285 (2016)

Brazilian National Water and Basic Sanitation Agency - ANA: Conjuntura dos recursos hídricos no Brasil 2022: informe anual (2023)

Brito, L.A., Meneguette, R.I., De Grande, R.E., Ranieri, C.M., Ueyama, J.: Floras: urban flash-flood prediction using a multivariate model. Applied Intelligence pp. 1–19 (2022)

Ding, Y., Zhu, Y., Feng, J., Zhang, P., Cheng, Z.: Interpretable spatio-temporal attention lstm model for flood forecasting. Neurocomputing 403, 348–359 (2020)

Do, H.N., Vo, M.T., Tran, V.S., Tan, P.V., Trinh, C.V.: An early flood detection system using mobile networks. In: 2015 international conference on advanced technologies for communications (ATC). pp. 599–603. IEEE (2015)

Fernandes Jr, F.E., Nonato, L.G., Ueyama, J.: A river flooding detection system based on deep learning and computer vision. Multimedia Tools and Applications 81(28), 40231–40251 (2022)

Fernandes Junior, F.E., Nonato, L.G., Ranieri, C.M., Ueyama, J.: Memory-based pruning of deep neural networks for iot devices applied to flood detection. Sensors 21(22), 7506 (2021)

Furquim, G., Neto, F., Pessin, G., Ueyama, J., de Albuquerque, J.P., Clara, M., Mendiondo, E.M., de Souza, V.C., de Souza, P., Dimitrova, D., et al.: Combining wireless sensor networks and machine learning for flash flood nowcasting. In: 2014 28th International Conference on Advanced Information Networking and Applications Workshops. pp. 67–72. IEEE (2014)

He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14. pp. 630–645. Springer (2016)

Iqbal, U., Perez, P., Li, W., Barthelemy, J.: How computer vision can facilitate flood management: A systematic review. International Journal of Disaster Risk Reduction 53, 102030 (2021)

Koyama, N., Sakai, M., Yamada, T.: Study on a water-level-forecast method based on a time series analysis of urban river basins—a case study of shibuya river basin in tokyo. Water 15(1), 161 (2023)

Lei, X., Chen, W., Panahi, M., Falah, F., Rahmati, O., Uuemaa, E., Kalantari, Z., Ferreira, C.S.S., Rezaie, F., Tiefenbacher, J.P., et al.: Urban flood modeling using deep-learning approaches in seoul, south korea. Journal of Hydrology 601, 126684 (2021)

Lin, Y.T., Lin, Y.C., Han, J.Y.: Automatic water-level detection using single-camera images with varied poses. Measurement 127, 167–174 (2018)

Marengo,J.,Alcantara,E.,Cunha,A.,Seluchi,M.,Nobre,C.,Dolif,G.,Goncalves, D., Dias, M.A., Cuartas, L., Bender, F., et al.: Flash floods and landslides in the city of recife, northeast brazil after heavy rain on may 25–28, 2022: Causes, impacts, and disaster preparedness. Weather and Climate Extremes p. 100545 (2023)

Marengo, J.A., Seluchi, M.E., Cunha, A.P., Cuartas, L.A., Goncalves, D., Sperling, V.B., Ramos, A.M., Dolif, G., Saito, S., Bender, F., et al.: Heavy rainfall associated with floods in southeastern brazil in november–december 2021. Natural Hazards pp. 1–28 (2023)

Natividad, J., Mendez, J.: Flood monitoring and early warning system using ultrasonic sensor. In: IOP conference series: materials science and engineering. vol. 325, p. 012020. IOP Publishing (2018)

Pan, J., Yin, Y., Xiong, J., Luo, W., Gui, G., Sari, H.: Deep learning-based unmanned surveillance systems for observing water levels. Ieee Access 6, 73561–73571 (2018)

Park, J.C., Kim, D.G., Yang, J.R., Kang, K.S.: Transformer-based flood detection using multiclass segmentation. In: 2023 IEEE International Conference on Big Data and Smart Computing (BigComp). pp. 291–292. IEEE (2023)

Patro, S., Chatterjee, C., Mohanty, S., Singh, R., Raghuwanshi, N.: Flood inundation modeling using mike flood and remote sensing data. Journal of the Indian Society of Remote Sensing 37, 107–118 (2009)

Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al.: Imagenet large scale visual recognition challenge. International journal of computer vision 115, 211–252 (2015)

Sabbatini, L., Palma, L., Belli, A., Sini, F., Pierleoni, P.: A computer vision system for staff gauge in river flood monitoring. Inventions 6(4), 79 (2021)

Strobl, B., Etter, S., van Meerveld, I., Seibert, J.: Accuracy of crowdsourced streamflow and stream level class estimates. Hydrological Sciences Journal 65(5), 823–841 (2020)

Vandaele, R., Dance, S.L., Ojha, V.: Deep learning for automated river-level monitoring through river-camera images: an approach based on water segmentation and transfer learning. Hydrology and Earth System Sciences 25(8), 4435–4453 (2021)

Wilfried, D.P., Rai, N., Singla, K.: Automatic flood detection by leveraging deep convolutional neural networks. In: 2023 11th International Conference on Internet of Everything, Microwave Engineering, Communication and Networks (IEME-CON). pp. 1–6. IEEE (2023)

Wu, X., Zhang, Z., Xiong, S., Zhang, W., Tang, J., Li, Z., An, B., Li, R.: A near-real-time flood detection method based on deep learning and sar images. Remote Sensing 15(8), 2046 (2023)

Yang, P., Ng, T.L.: Gauging through the crowd: A crowd-sourcing approach to urban rainfall measurement and storm water modeling implications. Water Resources Research 53(11), 9462–9478 (2017)

Zhang, Z., Zhou, Y., Liu, H., Zhang, L., Wang, H.: Visual measurement of water level under complex illumination conditions. Sensors 19(19), 4141 (2019)