Skip to main content
SpringerLink
Log in

A river flooding detection system based on deep learning and computer vision

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Although floods cause millions of dollars in economic and social losses each year, many people living in developing countries, such as Brazil, do not have access to a flooding alert system because of its cost. To address this issue, we propose a cheap and robust River Flooding Detection System, which can be easily deployed in any river with a flat surface at its bedside. The novelty of our system is the use of raw images from off-the-shelf cameras with no preprocessing required. Hence, our methodology can be deployed using existing surveillance cameras in urban environments. The proposed system measures the river level by first performing a semantic segmentation of the river water blade using Deep Neural Networks (DNNs). Then, it uses Computer Vision (CV) to estimate the water level. If the water level is near or above a dangerous threshold, it sends alerts automatically without human intervention. Moreover, our system can successfully measure a river’s water level with a Mean Absolute Error (MAE) of 3.32 cm, which is enough to detect when a river is about to overflow. The system is also reliable in measuring a river’s water level from different camera viewpoints and lighting conditions. We show our approach’s viability and evaluate our prototype’s performance and overhead by deploying it to monitor two urban rivers in the city of São Carlos, SP, Brazil.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Code Availability

The code will be made available at the following https://github.com/feferna/river-flooding-detection

Notes

  1. https://g1.globo.com/sp/sao-carlos-regiao/noticia/2020/12/01/prejuizos-causados-pela-enchente-ultrapassam-r-43-milhoes-diz-defesa-civil-de-sao-carlos.ghtml

  2. https://github.com/feferna/river-flooding-detection

  3. The proposed flooding detection system can be accessed through the http://agora.icmc.usp.br:5001

  4. https://g1.globo.com/sp/sao-carlos-regiao/noticia/2020/12/17/inteligencia-artificial-que-monitora-e-alerta-sobre-enchentes-e-criada-pela-usp-de-sao-carlos.ghtml

References

  1. ImageNet Benchmark (Image Classification) (2021). https://paperswithcode.com/sota/image-classification-on-imagenet

  2. Al Qundus J, Dabbour K, Gupta S, Meissonier R, Paschke A (2020) Wireless sensor network for AI-based flood disaster detection. Ann Oper Res. https://doi.org/10.1007/s10479-020-03754-x

  3. Alderman K, Turner L R, Tong S (2012) Floods and human health: a systematic review. Environ Int 47:37–47. https://doi.org/10.1016/j.envint.2012.06.003, https://linkinghub.elsevier.com/retrieve/pii/S0160412012001237

    Article  Google Scholar 

  4. Ali A, Zhu Y, Zakarya M (2021) A data aggregation based approach to exploit dynamic spatio-temporal correlations for citywide crowd flows prediction in fog computing. Multimed Tools Appl 80(20):31401–31433. https://doi.org/10.1007/s11042-020-10486-4

    Article  Google Scholar 

  5. Ali A, Zhu Y, Zakarya M (2021) Exploiting dynamic spatio-temporal correlations for citywide traffic flow prediction using attention based neural networks. Inf Sci 577:852–870. https://doi.org/10.1016/j.ins.2021.08.042https://doi.org/10.1016/j.ins.2021.08.042, https://linkinghub.elsevier.com/retrieve/pii/S0020025521008483

    Article  MathSciNet  Google Scholar 

  6. Ali A, Zhu Y, Zakarya M (2022) Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction. Neural Netw 145:233–247. https://doi.org/10.1016/j.neunet.2021.10.021https://doi.org/10.1016/j.neunet.2021.10.021, https://linkinghub.elsevier.com/retrieve/pii/S0893608021004123

    Article  Google Scholar 

  7. Arshad B, Ogie R, Barthelemy J, Pradhan B, Verstaevel N, Perez P (2019) Computer vision and IoT-based sensors in flood monitoring and mapping: a systematic review. Sensors 19(22):5012. https://doi.org/10.3390/s19225012, https://www.mdpi.com/1424-8220/19/22/5012

    Article  Google Scholar 

  8. Barratt J, Pan C (July 2019) Playing go without game tree search using convolutional neural networks. arXiv:1907.04658

  9. Barros M T L, Conde F (2017) Urban flood warning system social benefits. In: world environmental and water resources congress 2017. https://doi.org/10.1061/9780784480601.054. American society of civil engineers, Sacramento, pp 642–653

  10. Ba̧czyk A, Piwiński J, Kłoda R, Grygoruk M (2017) Survey on river water level measuring technologies: case study for flood management purposes of the C2-SENSE project. In: Szewczyk R, Kaliczyńska M (eds) recent advances in systems, control and information Technology. http://link.springer.com/10.1007/978-3-319-48923-0_65. Series Title: advances in intelligent systems and computing, vol 543. Springer International Publishing, Cham, pp 610–623

  11. Chen L-C, Papandreou G, Schroff F, Adam H (2017) Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587

  12. Deng J, Dong W, Socher R, Li L-J, Kai Li, Li Fei-Fei (June 2009) ImageNet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. http://ieeexplore.ieee.org/document/5206848/. IEEE, Miami, pp 248–255

  13. Du W, FitzGerald G J, Clark M, Hou X-Y (2010) Health impacts of floods. Prehospital Disaster Med 25(3):265–272. https://doi.org/10.1017/S1049023X00008141

    Article  Google Scholar 

  14. Fernandes F E, Yen G G (2020) Automatic searching and pruning of deep neural networks for medical imaging diagnostic. IEEE Trans Neural Netw Learn Syst:1–11. https://doi.org/10.1109/TNNLS.2020.3027308, https://ieeexplore.ieee.org/document/9222548/

  15. Fernandes F E, Yen G G (2021) Pruning of generative adversarial neural networks for medical imaging diagnostics with evolution strategy. Inf Sci 558:91–102. https://doi.org/10.1016/j.ins.2020.12.086, https://linkinghub.elsevier.com/retrieve/pii/S0020025521000189

    Article  MathSciNet  Google Scholar 

  16. Furquim G, Filho G, Jalali R, Pessin G, Pazzi R, Ueyama J (2018) How to improve fault tolerance in disaster predictions: a case study about flash floods using IoT, ML and real data. Sensors 18(3):907. https://doi.org/10.3390/s18030907

    Article  Google Scholar 

  17. Furquim G, Pessin G, Gomes P H, Mendiondo E M, Ueyama J (2015) A distributed approach to flood prediction using a WSN and ML: a comparative study of ML techniques in a WSN deployed in Brazil. In: Jackowski K, Burduk R, Walkowiak K, Wozniak M, Yin H (eds) Intelligent Data Engineering and Automated Learning IDEAL 2015. Series Title: Lecture Notes in Computer Science, vol 9375. Springer International Publishing, Cham, pp 485–492

  18. Geirhos R, Temme C R M, Rauber J, Schtt H H, Bethge M, Wichmann F A (2018) Generalisation in humans and deep neural networks. In: Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R (eds) Advances in Neural Information Processing Systems. https://proceedings.neurips.cc/paper/2018/file/0937fb5864ed06ffb59ae5f9b5ed67a9-Paper.pdf, vol 31. Curran Associates, Inc.

  19. Guo Z, Leitao J P, Simoes N E, Moosavi V (2020) Data-driven flood emulation: speeding up urban flood predictions by deep convolutional neural networks. arXiv:2004.08340

  20. Haddad E A, Teixeira E (2015) Economic impacts of natural disasters in megacities: The case of floods in So Paulo, Brazil. Habitat Int 45:106–113. https://doi.org/10.1016/j.habitatint.2014.06.023, https://linkinghub.elsevier.com/retrieve/pii/S019739751400099X

    Article  Google Scholar 

  21. Hagan M T, Demuth H B, Beale M H, De Jesus O (2014) Neural network design, 2nd edn. Amazon Fulfillment Poland Sp. z o.o, Wrocław

    Google Scholar 

  22. Hapuarachchi H A P, Wang Q J, Pagano T C (2011) A review of advances in flash flood forecasting. Hydrol Process 25(18):2771–2784. https://doi.org/10.1002/hyp.8040

    Article  Google Scholar 

  23. Hughes D, Ueyama J, Mendiondo E, Matthys N, Horré W, Michiels S, Huygens C, Joosen W, Man K L, Guan S-U (2011) A middleware platform to support river monitoring using wireless sensor networks. J Brazil Comput Soc 17(2):85–102. https://doi.org/10.1007/s13173-011-0029-3

    Article  Google Scholar 

  24. Kafli N, Isa K (2017) Internet of things (IoT) for measuring and monitoring sensors data of water surface platform. In: 2017 IEEE 7th international conference on underwater system technology: theory and applications (USYS). http://ieeexplore.ieee.org/document/8309441/. IEEE, Kuala Lumpur, pp 1–6

  25. Kamilaris A, Prenafeta-Boldú F X (2018) Disaster monitoring using unmanned aerial vehicles and deep learning. arXiv:1807.11805

  26. Kang W, Xiang Y, Wang F, Wan L, You H (2018) Flood detection in Gaofen-3 SAR images via fully convolutional networks. Sensors 18(9):2915. https://doi.org/10.3390/s18092915, http://www.mdpi.com/1424-8220/18/9/2915

    Article  Google Scholar 

  27. Khan T A, Alam M, Kadir K, Shahid Z, Mazliham MS (2018) A novel approach for the investigation of flash floods using soil flux and CO 2: an implementation of MLP with less false alarm Rate. In: 2018 2nd international conference on smart sensors and application (ICSSA). https://ieeexplore.ieee.org/document/8535606/. IEEE, Kuching, pp 130–134

  28. Kim K, Lee N-K, Han Y, Hahn H (2007) Remote detection and monitoring of a water level using narrow band channel. In: Proceedings of the 6th WSEAS international conference on signal processing, robotics and automation, ISPRA’07. event-place: Corfu Island, Greece. World Scientific and Engineering Academy and Society (WSEAS), Stevens Point, pp 25–30

  29. Krzhizhanovskaya VV, Shirshov GS, Melnikova NB, Belleman RG, Rusadi FI, Broekhuijsen BJ, Gouldby BP, Lhomme J, Balis B, Bubak M, Pyayt AL, Mokhov II, Ozhigin AV, Lang B, Meijer RJ (2011) Flood early warning system: design, implementation and computational modules. Procedia Comput Sci 4:106–115. https://doi.org/10.1016/j.procs.2011.04.012, https://linkinghub.elsevier.com/retrieve/pii/S1877050911000706

    Article  Google Scholar 

  30. Levine S, Pastor P, Krizhevsky A, Ibarz J, Quillen D (2018) Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. Int J Robot Res 37(4-5):421–436. https://doi.org/10.1177/0278364917710318

    Article  Google Scholar 

  31. Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick C L (2014) Microsoft COCO: Common Objects in Context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer Vision - ECCV 2014. https://doi.org/10.1007/978-3-319-10602-1_48. Series Title: Lecture Notes in Computer Science, vol 8693. Springer International Publishing, Cham, pp 740–755

  32. Liu Y, Wu L (2016) Geological disaster recognition on optical remote sensing images using deep learning. Procedia Comput Sci 91:566–575. https://doi.org/10.1016/j.procs.2016.07.144, https://linkinghub.elsevier.com/retrieve/pii/S1877050916313370

    Article  Google Scholar 

  33. Liu Y, Wu L (2018) High performance geological disaster recognition using deep learning. Procedia Comput Sci 139:529–536. https://doi.org/10.1016/j.procs.2018.10.237, https://linkinghub.elsevier.com/retrieve/pii/S1877050918319069

    Article  Google Scholar 

  34. Lopez-Fuentes L, Rossi C, Skinnemoen H (2017) River segmentation for flood monitoring. In: 2017 IEEE International Conference on Big Data (Big Data). http://ieeexplore.ieee.org/document/8258373/. IEEE, Boston, pp 3746–3749

  35. Mahdianpari M, Salehi B, Rezaee M, Mohammadimanesh F, Zhang Y (2018) Very deep convolutional neural networks for complex land cover mapping using multispectral remote sensing imagery. Remote Sens 10(7):1119. http://www.mdpi.com/2072-4292/10/7/1119

    Article  Google Scholar 

  36. Noar N A Z M, Kamal M M (2017) The development of smart flood monitoring system using ultrasonic sensor with blynk applications. In: 2017 IEEE 4th international conference on smart instrumentation, measurement and application (ICSIMA). http://ieeexplore.ieee.org/document/8312009/. IEEE, Putrajaya, pp 1–6

  37. Ortigossa E S, Dias F, Ueyama J, Nonato L G (2015) Using digital image processing to estimate the depth of urban streams. In: Workshop of undergraduate works in conjunction with conference on graphics, patterns and images (SIBGRAPI), Salvador

  38. Pan J, Yin Y, Xiong J, Luo W, Gui G, Sari H (2018) Deep Learning-Based Unmanned Surveillance Systems for Observing Water Levels. IEEE Access 6:73561–73571. https://doi.org/10.1109/ACCESS.2018.2883702, https://ieeexplore.ieee.org/document/8550626/

    Article  Google Scholar 

  39. Paterson D L, Wright H, Harris P N A (2018) Health risks of flood disasters. Clin Infect Dis 67(9):1450–1454. https://doi.org/10.1093/cid/ciy227, https://academic.oup.com/cid/article/67/9/1450/4945455

    Article  Google Scholar 

  40. Polydoros A S, Nalpantidis L, Kruger V (2015) Real-time deep learning of robotic manipulator inverse dynamics. In: 2015 IEEE/RSJ International conference on intelligent robots and systems (IROS). http://ieeexplore.ieee.org/document/7353857/. IEEE, Hamburg, pp 3442–3448

  41. Popescu D, Ichim L, Caramihale T (2015) Flood areas detection based on UAV surveillance system. In: 2015 19th International conference on system theory, control and computing (ICSTCC). http://ieeexplore.ieee.org/document/7321384/. IEEE, Cheile Gradistei, pp 753–758

  42. Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). http://ieeexplore.ieee.org/document/7780460/. IEEE, Las Vegas, pp 779–788

  43. Roccetti M, Casini L, Delnevo G, Orr V, Marchetti N (2020) Potential and limitations of designing a deep learning model for discovering new archaeological sites: a case with the mesopotamian floodplain. In: Proceedings of the 6th EAI international conference on smart objects and technologies for social good. https://doi.org/10.1145/3411170.3411254. ACM, Antwerp Belgium, pp 216–221

  44. Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W M, Frangi A F (eds) Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015. https://doi.org/10.1007/978-3-319-24574-4_28. Series Title: Lecture Notes in Computer Science, vol 9351. Springer International Publishing, Cham, pp 234–241

  45. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556

  46. Singh S P, Kumar A, Darbari H, Singh L, Rastogi A, Jain S (2017) Machine translation using deep learning: An overview. In: 2017 International Conference on Computer, Communications and Electronics (Comptelix). http://ieeexplore.ieee.org/document/8003957/. IEEE, Jaipur, pp 162–167

  47. Subeesh A, Kumar P, Chauhan N (2019) Flood Early Detection System Using Internet of Things and Artificial Neural Networks. In: Bhattacharyya S, Hassanien A E, Gupta D, Khanna A, Pan I (eds) International Conference on Innovative Computing and Communications. https://doi.org/10.1007/978-981-13-2324-9_30. Series Title: Lecture Notes in Networks and Systems, vol 55. Springer Singapore, Singapore, pp 297–305

  48. Sylvain J-D, Drolet G, Brown N (2019) Mapping dead forest cover using a deep convolutional neural network and digital aerial photography. ISPRS J Photogramm Remote Sens 156:14–26. https://doi.org/10.1016/j.isprsjprs.2019.07.010, https://linkinghub.elsevier.com/retrieve/pii/S0924271619301777

    Article  Google Scholar 

  49. Wirawan W, Rachman S, Pratomo I, Mita N (2008) Design of low cost wireless sensor networks-based environmental monitoring system for developing country. In: 2008 14th Asia-Pacific Conference on Communications. IEEE, Tokyo, pp 1–5

  50. Yang S-N, Chang L-C (2020) Regional Inundation Forecasting Using Machine Learning Techniques with the Internet of Things. Water 12(6):1578. https://doi.org/10.3390/w12061578, https://www.mdpi.com/2073-4441/12/6/1578

    Article  Google Scholar 

  51. Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks?. In: Ghahramani Z, Welling M, Cortes C, Lawrence N, Weinberger K Q (eds) Advances in Neural Information Processing Systems. https://proceedings.neurips.cc/paper/2014/file/375c71349b295fbe2dcdca9206f20a06-Paper.pdf, vol 27. Curran Associates, Inc., pp 3320–3328

Download references

Acknowledgments

The authors would like to thank the São Paulo Research Foundation (FAPESP), grant 2020/05426-0, for the financial support used to complete this work. The views expressed are those of the authors and do not reflect the official policy or position of the São Paulo Research Foundation.

Funding

The authors would like to thank the São Paulo Research Foundation (FAPESP), grant 2020/05426-0, for the financial support used to complete this work. The views expressed are those of the authors and do not reflect the official policy or position of the São Paulo Research Foundation.

Author information

Authors and Affiliations

  1. Institute of Mathematical and Computer Sciences, University of São Paulo, São Carlos, SP, Brazil

    Francisco E. Fernandes Jr., Luis Gustavo Nonato & Jó Ueyama

Authors
  1. Francisco E. Fernandes Jr.
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Luis Gustavo Nonato
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jó Ueyama
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Francisco E. Fernandes Jr. is responsible for the proposed method investigation and methodology, and experimental comparison and validation.

Luis Gustavo Nonato is responsible for structuring part of the experiments and comparisons, while reviewing the manuscript to ensure the work is reproducible.

Jo Ueyama is responsible for the project’s supervision and administration, and ensuring that the descriptions are accurate and agreed by all authors.

Corresponding author

Correspondence to Francisco E. Fernandes Jr..

Ethics declarations

Conflict of Interests

The authors declare that there is no conflict of interest.

Additional information

Availability of data and material

Data will be made available upon request.

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Fernandes, F.E., Nonato, L.G. & Ueyama, J. A river flooding detection system based on deep learning and computer vision. Multimed Tools Appl 81, 40231–40251 (2022). https://doi.org/10.1007/s11042-022-12813-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12813-3

Keywords

Search

Navigation