Deep Learning and object detection for water level measurement using patterned visual markers

Authors

  • Gabriel M. Domingues Filho Sao Carlos School of Engineering (EESC), University of Sao Paulo (USP) https://orcid.org/0000-0003-1443-8436
  • Caetano M. Ranieri Institute of Geosciences and Exact Sciences (IGCE), Sao Paulo State University (UNESP)
  • Saulo Neves Matos Institute of Mathematical and Computer Sciences (ICMC), University of Sao Paulo (USP) https://orcid.org/0009-0005-7931-3767
  • Rodolfo Ipolito Meneguette Institute of Mathematical and Computer Sciences (ICMC), University of Sao Paulo (USP) https://orcid.org/0000-0003-2982-4006
  • Jó Ueyama Institute of Mathematical and Computer Sciences (ICMC), University of Sao Paulo (USP) https://orcid.org/0000-0002-5591-3750

Keywords:

Deep learning, computer vision, flood management, visual marker

Abstract

Flooding is one of the most impactful natural disasters, causing significant losses and prompting extensive research into monitoring water levels in urban streams. Current technologies rely on pressure and ultrasonic sensors, which, while accurate, can be susceptible to damage from floods and are often costly. As an alternative, ground camera approaches offer a low-cost solution; however, most of these methods use raw images from the water stream and are sensitive to environmental factors. We address this gap with a dataset comprising a visual marker with black bars indicating the water level, which we refer to as "barcode panel".  We employed various deep learning algorithms to predict the water level and compared their performance. The proposed approach was evaluated using classic classification and error metrics. The models demonstrated accuracy in detecting the water level. These promising results provide important insights for practical applications and future studies.

Downloads

Download data is not yet available.

Author Biographies

Gabriel M. Domingues Filho, Sao Carlos School of Engineering (EESC), University of Sao Paulo (USP)

Gabriel M. Domingues Filho is an undergraduate student in Electrical Engineering with an emphasis on electronics at the Sao Carlos School of Engineering, University of Sao Paulo. His research interests lie in Artificial Intelligence, particularly in Deep Learning and Computer Vision. Gabriel has participated in various research projects, primarily focused on water level detection for flood events. His career goals include advancing the field of AI and contributing to innovative technological solutions.

Caetano M. Ranieri, Institute of Geosciences and Exact Sciences (IGCE), Sao Paulo State University (UNESP)

Caetano M. Ranieri is an Assistant Professor at the Institute of Geosciences and Exact Scientes of the Sao Paulo State University (IGCE-UNESP). He was a postdoctoral research fellow at the University of Sao Paulo (USP), with research focused on Artificial Intelligence in the context of the Internet of Things. He graduated in Computer Science at UNESP (2013) and did his Master's degree (2016) and Ph.D. (2021) at USP. During his Ph.D., he worked as a visiting scholar at Heriot-Watt University, Scotland (2020).

Saulo Neves Matos, Institute of Mathematical and Computer Sciences (ICMC), University of Sao Paulo (USP)

Saulo N. Matos is a Ph.D. student at the University of Sao Paulo (USP), with research focused on Machine Learning, Instrumentation, and Internet of Things. He holds a master's degree in Instrumentation, Control, and Automation of Mining Processes from the University of Ouro Preto and the Vale Technological Institute (2022). He graduated in Control and Automation Engineering from the Federal University of Ouro Preto (2020). He has published papers and patents on instrumentation, embedded systems, machine learning, and control theory.

Rodolfo Ipolito Meneguette, Institute of Mathematical and Computer Sciences (ICMC), University of Sao Paulo (USP)

Rodolfo I. Meneguette is a professor at University of Sao Paulo (USP). He received his Bachelor’s degree in Computer Science from the Paulista University (UNIP) in 2006. He received his master’s degree in 2009 from the Federal University of Sao Carlos (UFSCar). He received his doctorate from the University of Campinas (Unicamp) in 2013. In 2017, he did his post-doctorate at the PARADISE Research Laboratory, University of Ottawa, Canada. His research interests are in vehicular networks, resources management, flow of mobility, and vehicular clouds.

Jó Ueyama, Institute of Mathematical and Computer Sciences (ICMC), University of Sao Paulo (USP)

Jo Ueyama is a Full Professor at the Institute of Mathematical and Computer Sciences (ICMC) of the University of Sao Paulo (USP). He has been a Brazilian Research Council (CNPq) fellow since 2014. He received his Ph.D. in computer science from the University of Lancaster in 2006 and was a research fellow at the University of Kent at Canterbury before joining USP. Jo has a publication record with 72 journal articles and over 100 conference papers. His research interests are focused on Computer Networks, Security, and Blockchain.

References

I. Melekhov, J. Kannala, and E. Rahtu, “Siamese network features for image matching,” in 2016 23rd international conference on pattern recognition (ICPR), 2016, pp. 378–383. doi: 10.1109/ICPR.2016.7899663.

C. M. Ranieri, T. L. D. e Souza, M. Nishijima, B. Krishnamachari, and J. Ueyama, “A deep learning workflow enhanced with optical flow fields for flood risk estimation,” Applied Intelligence, pp. 1–22, 2024, doi: 0.1007/s10489-024-05466-2.

R. Hadsell, S. Chopra, and Y. LeCun, “Dimensionality reduction by learning an invariant mapping,” in 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR’06), 2006, vol. 2, pp. 1735–1742. doi: 10.1109/CVPR.2006.100.

K. He, X. Zhang, S. Ren, and J. Sun, “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, 2016, pp. 630–645. doi: 10.1007/978-3-319-46493-0_38.

O. Russakovsky et al., “Imagenet large scale visual recognition challenge,” International journal of computer vision, vol. 115, pp. 211–252, 2015, doi: 10.1007/s11263-015-0816-y.

T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980–2988. doi: 10.1109/ICCV.2017.324.

S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” Advances in neural information processing systems, vol. 28, 2015, doi: 10.1109/TPAMI.2016.2577031.

T.-Y. Lin et al., “Microsoft coco: Common objects in context,” in Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, 2014, pp. 740–755. doi: 10.1007/978-3-319-10602-1_48.

G. M. Domingues Filho, C. M. Ranieri, D. Q. G. Batista, and J. Ueyama, “Enhancing Water Level Identification with a Barcode-Patterned Panel and Machine Learning,” in Anais do XX Encontro Nacional de Inteligência Artificial e Computacional, 2023, pp. 668–682. doi: 10.5753/eniac.2023.234311.

C. K. Seigerman, N. S. Leite, E. S. P. Martins, and D. R. Nelson, “At the extremes: Assessing interrelations among the impacts of and responses to extreme hydroclimatic events in Ceará, Northeast Brazil,” Journal of Hydrology, p. 130850, 2024, doi: 10.1016/j.jhydrol.2024.130850.

M. H. K. Valentini, S. Beskow, T. L. C. Beskow, C. R. de Mello, F. Cassalho, and M. E. S. da Silva, “At-site flood frequency analysis in Brazil,” Natural Hazards, vol. 120, no. 1, pp. 601–618, 2024, doi: 10.1007/s11069-023-06231-3.

M. P. de Oliveira Roza, R. A. Cecı́lio, S. S. Zanetti, M. C. Abreu, G. B. Lyra, and G. B. Reis, “Natural disasters related to rainfall trends in Espı́rito Santo, southeastern Brazil,” Theoretical and Applied Climatology, vol. 155, no. 2, pp. 1451–1466, 2024, doi: 10.1007/s00704-023-04703-x.

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

Brazilian National Water and Basic Sanitation Agency - ANA, Conjuntura dos recursos hídricos no Brasil 2023: informe anual. 2024.

H. N. Do, M.-T. Vo, V.-S. Tran, P. V. Tan, and C. V. Trinh, “An early flood detection system using mobile networks,” in 2015 international conference on advanced technologies for communications (ATC), 2015, pp. 599–603. doi: 10.1109/ATC.2015.7388400.

A. Gold et al., “Data from the drain: a sensor framework that captures multiple drivers of chronic coastal floods,” Water Resources Research, vol. 59, no. 4, p. e2022WR032392, 2023, doi: 10.1029/2022WR032392.

P. Yang and T. L. Ng, “Gauging through the crowd: A crowd-sourcing approach to urban rainfall measurement and storm water modeling implications,” Water Resources Research, vol. 53, no. 11, pp. 9462–9478, 2017, doi: 10.1002/2017WR020682.

J. Natividad and J. Mendez, “Flood monitoring and early warning system using ultrasonic sensor,” in IOP conference series: materials science and engineering, 2018, vol. 325, no. 1, p. 012020. doi: 10.1088/1757-899X/325/1/012020.

C. M. Ranieri et al., “Water level identification with laser sensors, inertial units, and machine learning,” Engineering Applications of Artificial Intelligence, vol. 127, p. 107235, 2024, doi: 10.1016/j.engappai.2023.107235.

C. Moreno et al., “RiverCore: IoT device for river water level monitoring over cellular communications,” Sensors, vol. 19, no. 1, p. 127, 2019, doi: 10.3390/s19010127.

F. E. Fernandes Junior, L. G. Nonato, C. M. Ranieri, and J. Ueyama, “Memory-based pruning of deep neural networks for IoT devices applied to flood detection,” Sensors, vol. 21, no. 22, p. 7506, 2021, doi: doi.org/10.3390/s21227506.

S.-W. Lo, J.-H. Wu, F.-P. Lin, and C.-H. Hsu, “Cyber surveillance for flood disasters,” Sensors, vol. 15, no. 2, pp. 2369–2387, 2015, doi: 10.3390/s150202369.

J. Pan, Y. Yin, J. Xiong, W. Luo, G. Gui, and H. Sari, “Deep learning-based unmanned surveillance systems for observing water levels,” Ieee Access, vol. 6, pp. 73561–73571, 2018, doi: 10.1109/ACCESS.2018.2883702.

J.-C. Park, D.-G. Kim, J.-R. Yang, and K.-S. Kang, “Transformer-based flood detection using multiclass segmentation,” in 2023 IEEE International Conference on Big Data and Smart Computing (BigComp), 2023, pp. 291–292. doi: 10.1109/BigComp57234.2023.00056.

Y.-T. Lin, Y.-C. Lin, and J.-Y. Han, “Automatic water-level detection using single-camera images with varied poses,” Measurement, vol. 127, pp. 167–174, 2018, doi: 10.1016/j.measurement.2018.05.100.

X. Wu et al., “A Near-Real-Time Flood Detection Method Based on Deep Learning and SAR Images,” Remote Sensing, vol. 15, no. 8, p. 2046, 2023, doi: 10.3390/rs15082046.

C. Chen et al., “An integrated method for river water level recognition from surveillance images using convolution neural networks,” Remote Sensing, vol. 14, no. 23, p. 6023, 2022, doi: 10.3390/rs14236023.

Z. Zhang, Y. Zhou, H. Liu, L. Zhang, and H. Wang, “Visual measurement of water level under complex illumination conditions,” Sensors, vol. 19, no. 19, p. 4141, 2019, doi: 10.3390/s19194141.

L. Sabbatini, L. Palma, A. Belli, F. Sini, and P. Pierleoni, “A computer vision system for staff gauge in river flood monitoring,” Inventions, vol. 6, no. 4, p. 79, 2021, doi: 10.3390/inventions6040079.

R. Vandaele, S. L. Dance, and V. Ojha, “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, vol. 25, no. 8, pp. 4435–4453, 2021, doi: 10.5194/hess-25-4435-2021.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778. doi: 10.1109/CVPR.2016.90.

Downloads

Published

2024-10-22

How to Cite

M. Domingues Filho, G., M. Ranieri, C., Neves Matos, S., Ipolito Meneguette, R., & Ueyama, J. . (2024). Deep Learning and object detection for water level measurement using patterned visual markers. IEEE Latin America Transactions, 22(11), 892–898. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/9046

Issue

Vol. 22 No. 11 (2024): Ordinary Issue

Section

Computing