A Deep Learning Approach to Early Drowning Detection for Child Safety using ResNet and Flower Pollination Algorithm
DOI:
https://doi.org/10.71426/jcdt.v1.i2.pp104-114Keywords:
Drowning detection, Deep learning, Computer vision, ResNet, Feature fusion, Flower pollination algorithm, Child safety.Abstract
Drowning is one of the top five worldwide causes of mortality for kids between the ages of four to fourteen. According to World Health Organization statistics, drowning is the third most common cause of unintentional fatalities. The need to create a drowning detection system to save swimmers especially children is growing. There are several drowning detection systems incorporating distinct technological systems such as wearable sensors, vision based monitoring and AI driven surveillance. Wearable sensors such as heart rate monitoring and accelerometers offer continuous monitoring but these existing systems have their own limitations like intrusiveness and poor visibility. To address these challenges this study offers a deep learning and computer vision-based early drowning detection technique. An overall accuracy of 99.4% has been achieved on our dataset by using pre-trained models including CNN-ResNet50, ResNet18, and Flower Pollination Algorithm. The study contributes to the advancement of intelligent drowning surveillance systems thus abridging the gap in the attainment of more efficient and reliable drowning detection systems.
References
[1] Shatnawi M, Albreiki F, Alkhoori A, Alhebshi M. Deep learning and vision-based early drowning detection. Information. 2023;14(1):52. Available from: https://doi.org/10.3390/info14010052
[2] Handalage U, Nikapotha N, Subasinghe C, Prasanga T, Thilakarthna T, Kasthurirathna D. Computer vision enabled drowning detection system. In: 2021 International Conference on Advancements in Computing (ICAC); 2021 Dec 9; pp. 240–245. Available from: https://ieeexplore.ieee.org/document/9671126
[3] Hasan S, Joy J, Ahsan F, Khambaty H, Agarwal M, Mounsef J. A water behavior dataset for an image-based drowning solution. In: 2021 IEEE Green Energy and Smart Systems Conference (IGESSC); 2021 Nov 1; pp. 1–5. Available from: https://ieeexplore.ieee.org/document/9618700
[4] He X, Yuan F, Liu T, Zhu Y. A video system based on convolutional autoencoder for drowning detection. Neural Computing and Applications. 2023;35(21):15791–15803. Available from: https://doi.org/10.1007/s00521-023-08526-9
[5] Chan YT, Hou TW, Huang YL, Lan WH, Wang PC, Lai CT. Implementation of deep-learning-based edge computing for preventing drowning. Computing. 2020;8:13. Available from: https://doi.org/10.12792/iciae2020.041
[6] Bhargavi KN, Suma G. Identifying drowning objects in flood water and classifying using deep convolution neural networks. I-Manager’s Journal on Image Processing. 2021;8(3). Available from: https://doi.org/10.26634/jip.8.3.18451
[7] Rashid AH, Razzak I, Tanveer M, Hobbs M. Reducing rip current drowning: An improved residual based lightweight deep architecture for rip detection. ISA Transactions. 2023;132:199–207. Available from: https://doi.org/10.1016/j.isatra.2022.05.015
[8] Zhang J, Zhou Y, Vieira DN, Cao Y, Deng K, Cheng Q, Zhu Y, Zhang J, Qin Z, Ma K, Chen Y. An efficient method for building a database of diatom populations for drowning site inference using a deep learning algorithm. International Journal of Legal Medicine. 2021;135(3):817–827. Available from: https://doi.org/10.1007/s00414-020-02497-5
[9] Ramos JO, Flores HV, Villena JR, Gonzales JZ, Joseph GM. Development of a detection system for people drowning through aerial images and convolutional neural networks. Przegląd Elektrotechniczny. 2023;99(2):109–113. Available from: https://pe.org.pl/articles/2023/2/18.pdf
[10] Qureshi AH, Zhang X, Ichiji K, Kawasumi Y, Usui A, Funayama M, Homma N. Deep CNN-based computer-aided diagnosis for drowning detection using post-mortem lungs CT images. In: IEEE International Conference on Bioinformatics and Biomedicine (BIBM); 2021 Dec 9; pp. 2309–2313. Available from: https://ieeexplore.ieee.org/document/9669644
[11] Eng H, Toh KA, Kam AH, Wang J, Yau WY. An automatic drowning detection surveillance system for challenging outdoor pool environments. In: Ninth IEEE International Conference on Computer Vision; 2003 Oct 13; pp. 532–539. Available from: https://ieeexplore.ieee.org/document/1238393
[12] Cepeda-Pacheco JC, Domingo MC. Deep learning and 5G and beyond for child drowning prevention in swimming pools. Sensors. 2022;22(19):7684. Available from: https://doi.org/10.3390/s22197684
[13] Zeng Y, Zhang X, Kawasumi Y, Usui A, Ichiji K, Funayama M, Homma N. Deep learning-based interpretable computer-aided diagnosis of drowning for forensic radiology. In: 60th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE); 2021 Sep 8; pp. 820–824. Available from: https://ieeexplore.ieee.org/document/9555359
[14] Urruchi C, Cervantes-Chauca D, Huamanchahua D. Proposal of a swimming pool drowning detection system using cameras and Raspberry Pi based on machine learning. In: 2nd International Conference on Robotics, Automation and Artificial Intelligence (RAAI); 2022 Dec 9; pp. 178–181. Available from: https://doi.org/10.1109/RAAI56146.2022.10092956
[15] Kam AH, Lu W, Yau WY. A video-based drowning detection system. In: European Conference on Computer Vision; 2002 Apr 29; pp. 297–311. Berlin: Springer. Available from: https://doi.org/10.1007/3-540-47979-1_20
[16] Zhang FY, Wang LL, Dong WW, Zhang M, Tash D, Li XJ, Du SK, Yuan HM, Zhao R, Guan DW. A preliminary study on early postmortem submersion interval (PMSI) estimation and cause-of-death discrimination based on nontargeted metabolomics and machine learning algorithms. International Journal of Legal Medicine. 2022;136(3):941–954. Available from: https://doi.org/10.1007/s00414-022-02783-4
[17] Birk A. A survey of underwater human-robot interaction (U-HRI). Current Robotics Reports. 2022;3(4):199–211. Available from: https://doi.org/10.1007/s43154-022-00092-7
[18] Durairaj M, Subudhi S, Rao VV, Jayanthi J, Suganthi D. AI-driven drowned-detection system for rapid coastal rescue operations. Spatial Information Research. 2024;32(2):143–150. Available from: https://doi.org/10.1007/s41324-023-00549-7
[19] Kulhandjian H, Ramachandran N, Kulhandjian M, D’Amours C. Human activity classification in underwater using sonar and deep learning. In: 14th International Conference on Underwater Networks & Systems; 2019 Oct 23; pp. 1–5. Available from: https://doi.org/10.1145/3366486.3366509
[20] Yu W, Xue Y, Knoops R, Yu D, Balmashnova E, Kang X, Falgari P, Zheng D, Liu P, Chen H, Shi H. Automated diatom searching in digital scanning electron microscopy images of drowning cases using deep neural networks. International Journal of Legal Medicine. 2021;135(2):497–508. Available from: https://doi.org/10.1007/s00414-020-02392-z
[21] Bai B, Chen L, Li X. Improved YOLOv7 fusion detection line for swimming pool drowning detection. In: IEEE 16th International Conference on Electronic Measurement & Instruments (ICEMI); 2023 Aug 9; pp. 129–134. Available from: https://ieeexplore.ieee.org/document/10270676
[22] He L, Hou H, Yan Z, Xing G. Demo abstract: An underwater sonar-based drowning detection system. In: 21st ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN); 2022 May 4; pp. 493–494. Available from: https://ieeexplore.ieee.org/document/9825955
[23] Carballo-Fazanes A, Bierens JJLM, The International Expert Group to Study Drowning Behaviour. The visible behaviour of drowning persons: A pilot observational study using analytic software and a nominal group technique. International Journal of Environmental Research and Public Health. 2020;17(18):6930. Available from: https://doi.org/10.3390/ijerph17186930
[24] Wang F, Ai Y, Zhang W. Detection of early dangerous state in deep water of indoor swimming pool based on surveillance video. Signal, Image and Video Processing. 2022;16(1):29–37. Available from: https://doi.org/10.1007/s11760-021-01953-y
[25] Zemblys R, Niehorster DC, Komogortsev O, Holmqvist K. Using machine learning to detect events in eye-tracking data. Behavior Research Methods. 2017;50(1):160–181. Available from: https://doi.org/10.3758/s13428-017-0860-3
[26] Batislaong JP, Leonin JC, Utto AK, Dadula DP, Banal RG, Dadula CP. Acoustic-based classifier for detecting abnormal events in a university setting. In: 6th International Conference on Applied Computational Intelligence in Information Systems (ACIIS); 2023 Oct 23; pp. 1–6. Available from: https://ieeexplore.ieee.org/document/10367396
[27] Shoka AA, Dessouky MM, El-Sherbeny AS, El-Sayed A. Fast seizure detection from EEG using machine learning. In: 7th International Japan-Africa Conference on Electronics, Communications, and Computations (JAC-ECC); 2020; pp. 7448. Available from: https://ieeexplore.ieee.org/document/9051070
[28] Harras MS, Saleh S, Battseren B, Hardt W. Vision-based propeller damage inspection using machine learning. Embedded Selforganising Systems. 2023;10(7):43–47. Available from: https://doi.org/10.14464/ess.v10i7.604
[29] Soma AK. Hybrid RNN-GRU-LSTM model for accurate detection of DDoS attacks on IDS dataset. Journal of Modern Technology. 2024;2(1):283–291. Available from: https://doi.org/10.71426/jmt.v2.i1.pp283-291
[30] Tao X, Zhang D, Hou W, Ma W, Xu D. Industrial weak scratches inspection based on multifeature fusion network. IEEE Transactions on Instrumentation and Measurement. 2020;70:1–4. Available from: https://doi.org/10.1109/TIM.2020.3025642
[31] Alshbatat AI, Alhameli S, Almazrouei S, Alhameli S, Almarar W. Automated vision-based surveillance system to detect drowning incidents in swimming pools. In: Advances in Science and Engineering Technology International Conferences (ASET); 2020 Feb 4; pp. 1–5. Available from: https://doi.org/10.1109/ASET48392.2020.9118248
[32] Zhang C, Li X, Lei F. A novel camera-based drowning detection algorithm. In: Chinese Conference on Image and Graphics Technologies; 2015 Jun 17; pp. 224–233. Berlin: Springer. Available from: https://doi.org/10.1007/978-3-662-47791-5_26
[33] Zhang C, Li X, Lei F. A novel camera-based drowning detection algorithm. In: Communications in Computer and Information Science; 2015; pp. 224–233. Available from: https://doi.org/10.1007/978-3-662-47791-5_26
[34] Wong WK, Hui JH, Loo CK, Lim WS. Off-time swimming pool surveillance using thermal imaging system. In: International Conference on Signal and Image Processing Applications (ICSIPA); 2011 Nov 16; pp. 366–371. Available from: https://ieeexplore.ieee.org/document/6144091
[35] Li D, Yu L, Jin W, Zhang R, Feng J, Fu N. An improved detection method of human target at sea based on YOLOv3. In: IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE); 2021 Jan 15; pp. 100–103. Available from: https://ieeexplore.ieee.org/document/9342056
[36] Rostami-Moez M, Kangavari M, Teimori G, Afshari M, Khah ME. Cultural adaptation for country diversity: A systematic review of injury prevention interventions caused by domestic accidents in children under five years old. Medical Journal of the Islamic Republic of Iran. 2019;33:124. Available from: https://pmc.ncbi.nlm.nih.gov/articles/PMC7137865/
[37] Chen Y, Zhu X, Gong S. Person re-identification by deep learning multi-scale representations. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) Workshops; 2017 Oct. Available from: https://openaccess.thecvf.com/content_ICCV_2017_workshops/html/Chen_Person_Re-Identification_by_ICCV_2017_paper.html
[38] Chen H, Yuan H, Qin H, Mu X. Underwater drowning people detection based on bottleneck transformer and feature pyramid network. In: IEEE International Conference on Unmanned Systems (ICUS); 2022 Oct 28; pp. 1145–1150. Available from: https://ieeexplore.ieee.org/document/9986998
[39] Hu X, Liu Y, Zhao Z, Liu J, Yang X, Sun C, Chen S, Li B, Zhou C. Real-time detection of uneaten feed pellets in underwater images for aquaculture using an improved YOLOv4 network. Computers and Electronics in Agriculture. 2021;185:106135. Available from: https://doi.org/10.1016/j.compag.2021.106135
[40] Cha YJ, Choi W, Büyüköztürk O. Deep learning-based crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering. 2017;32(5):361–378. Available from: https://doi.org/10.1111/mice.12263
[41] Xu W, Matzner S. Underwater fish detection using deep learning for water power applications. In: International Conference on Computational Science and Computational Intelligence (CSCI); 2018 Dec 12; pp. 313–318. Available from: https://ieeexplore.ieee.org/document/8947884
[42] Chen J, Tam D, Raffel C, Bansal M, Yang D. An empirical survey of data augmentation for limited data learning in NLP. Transactions of the Association for Computational Linguistics. 2023;11:191–211. Available from: https://doi.org/10.1162/tacl_a_00542
[43] Alomar K, Aysel HI, Cai X. Data augmentation in classification and segmentation: A survey and new strategies. Journal of Imaging. 2023;9(2):46. Available from: https://doi.org/10.3390/jimaging9020046
[44] Huang H, Feng Y, Shi C, Xu L, Yu J, Yang S. Free-bloom: Zero-shot text-to-video generator with LLM director and LDM animator. In: Advances in Neural Information Processing Systems; 2023; Vol. 36; pp. 26135–26158. Available from: https://proceedings.neurips.cc/paper_files/paper/2023/file/52f050499cf82fa8efb588e263f6f3a7-Paper-Conference.pdf
[45] Fang J, Xu Y, Zhao Y, Yan Y, Liu J, Liu J. Weighing features of lung and heart regions for thoracic disease classification. BMC Medical Imaging. 2021;21(1):99. Available from: https://doi.org/10.1186/s12880-021-00627-y
[46] Han M, Du S, Ge Y, Zhang D, Chi Y, Long H, Yang J, Yang Y, Xin J, Chen T, Zheng N. With or without human interference for precise age estimation based on machine learning? International Journal of Legal Medicine. 2022;136(3):821–831. Available from: https://doi.org/10.1007/s00414-022-02796-z
[47] Cohen J, Rosenfeld E, Kolter Z. Certified adversarial robustness via randomized smoothing. In: International Conference on Machine Learning (ICML); 2019 May 24; pp. 1310–1320. Available from: https://proceedings.mlr.press/v97/cohen19c.html
[48] Shi Z, Liao Z, Tabata H. Enhancing performance of convolutional neural network-based epileptic electroencephalogram diagnosis by asymmetric stochastic resonance. IEEE Journal of Biomedical and Health Informatics. 2023;27(9):4228–4239. Available from: https://doi.org/10.1109/JBHI.2023.3282251
[49] Huo G, Wu Z, Li J. Underwater object classification in sidescan sonar images using deep transfer learning and semisynthetic training data. IEEE Access. 2020;8:47407–47418. Available from: https://doi.org/10.1109/ACCESS.2020.2978880
[50] Shoeibi A, Khodatars M, Jafari M, Ghassemi N, Sadeghi D, Moridian P, Khadem A, Alizadehsani R, Hussain S, Zare A, Sani ZA. Automated detection and forecasting of COVID-19 using deep learning techniques: A review. Neurocomputing. 2024;577:127317. Available from: https://doi.org/10.1016/j.neucom.2024.127317
[51] Alqahtani A, Alsubai S, Sha M, Peter V, Almadhor AS, Abbas S. Falling and drowning detection framework using smartphone sensors. Computational Intelligence and Neuroscience. 2022;2022:1–12. Available from: https://doi.org/10.1155/2022/6468870
[52] Liu T, He X, He L, Yuan F. A video drowning detection device based on underwater computer vision. IET Image Processing. 2023;17(6):1905–1918. Available from: https://doi.org/10.1049/ipr2.12765
[53] Pandiyan N, Narayan S. A survey on deep learning models embedding bio-inspired algorithms in cardiac disease classification. The Open Biomedical Engineering Journal. 2022;17(1). Available from: https://doi.org/10.2174/18741207-v16-e221227-2022-ht27-3589-14
[54] Kiliç Ş, Askerzade I, Kaya Y. Using ResNet transfer deep learning methods in person identification according to physical actions. IEEE Access. 2020;8:220364–220373. Available from: https://doi.org/10.1109/ACCESS.2020.3040649
[55] Dhal P, Azad C. Hybrid momentum accelerated bat algorithm with GWO-based optimization approach for spam classification. Multimedia Tools and Applications. 2024;83(9):26929–26969. Available from: https://doi.org/10.1007/s11042-023-16448-w
[56] Drowning detection classification dataset. Available from: https://universe.roboflow.com/team-burraq/drowning-detect-wiqs0/dataset/3/download
[57] Drowning detection dataset repository. Available from: https://universe.roboflow.com/team-burraq/drowning-detect-wiqs0/dataset/3/
[58] World Health Organization. Drowning. Available from: https://www.who.int/news-room/fact-sheets/detail/drowning
[59] Kara RV. SmartBio: An AI-enabled smart medical device for early cancer detection using variational autoencoders and multimodal sensor integration. Journal of Modern Technology. 2025;2(1):292–301. Available from: https://doi.org/10.71426/jmt.v2.i1.pp292-301
[60] Elango PFM, Dhanabalan SS, Robel MR, Elango SP, Walia S, Sriram S, et al. Dry electrode geometry optimization for wearable ECG devices. Applied Physics Reviews. 2023;10(4). Available from: https://doi.org/10.1063/5.0152554
[61] Yang M, Dhanabalan SS, Robel MR, Thekkekara LV, Mahasivam S, Rahman MA, et al. Miniaturized optical glucose sensor using 1600–1700 nm near-infrared light. Advanced Sensor Research. 2024;4(3). Available from: https://doi.org/10.1002/adsr.202300160
Downloads
Issue
Section
License
Copyright (c) 2025 Muhammad Aftab Hayat, Yang Guotian, Shams ur Rehman (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
