Enhancing Drowning Detection Efficiency: A YOLOv11 Approach with Lightweight Improvements

Benbo Cao

doi:10.47297/taposatWSP2633-456945.20250610

PDF
导出
分享
收藏
专辑

Enhancing Drowning Detection Efficiency: A YOLOv11 Approach with Lightweight Improvements

6卷第10期

浏览量: 0 Downloads: 0

Enhancing Drowning Detection Efficiency: A YOLOv11 Approach with Lightweight Improvements
Enhancing Drowning Detection Efficiency: A YOLOv11 Approach with Lightweight Improvements
Nanjing University of Information Science & Technology, Nanjing, Jiangsu, 210044, China
2025年6卷第10期页码：229-233
纸质出版：2025-10-30
DOI：10.47297/taposatWSP2633-456945.20250610
Accepted：

Scan QR Code

Benbo Cao. (2025). Enhancing Drowning Detection Efficiency: A YOLOv11 Approach with Lightweight Improvements. 科技理论与实践（英文版）, 6(10), 229-233.

Cao Benbo.Enhancing Drowning Detection Efficiency: A YOLOv11 Approach with Lightweight Improvements[J].Theory and Practice of Science and Technology,2025,06(10):229-233.
Benbo Cao. (2025). Enhancing Drowning Detection Efficiency: A YOLOv11 Approach with Lightweight Improvements. 科技理论与实践（英文版）, 6(10), 229-233. DOI： 10.47297/taposatWSP2633-456945.20250610.

Cao Benbo.Enhancing Drowning Detection Efficiency: A YOLOv11 Approach with Lightweight Improvements[J].Theory and Practice of Science and Technology,2025,06(10):229-233. DOI： 10.47297/taposatWSP2633-456945.20250610.

摘要

Abstract

Swimming

while a popular activity worldwide

poses significant safety risks

with drowning being a leading cause of accidental death

particularly among youth. Traditional surveillance methods

such as lifeguard monitoring

are prone to fatigue and high costs

highlighting the urgent need for automated drowning detection systems. This study explores the application of the YOLOv11 model

a state-of-the-art one stage object detector

for real-time drowning detection. To enhance its suitability for edge devices

this paper introduces a lightweight C3K2 module through structural improvements and incorporates a BiFPN architecture into the neck network. These modifications reduce the number of parameters and enhance the inference speed of the model. Experimental results demonstrate that the pruned YOLOv11 model achieves a high mean average precision (mAP) on a custom dataset containing three critical categories (drowning

swimming

and floating). The study validates the feasibility of the proposed approach

which effectively balances performance and efficiency

and provides a practical

scalable solution for enhancing water safety through intelligent surveillance.

关键词

Keywords

references

Massey H, Gorczynski P, Harper C M, et al. Perceived impact of outdoor swimming on health: web-based survey[J]. Interactive Journal of Medical Research, 2022, 11(1): e25589.

World Health Organization (WHO). Global Drowning statistics reports[R/OL]. (2024) [2025-09-11]. https://www.who.int/ne ws-room/fact-sheets/detail/drowning.

People's Online Public Opinion Data Center. 2022 China Youth Drowning Prevention Big Data Report[R/OL]. (2022) [2025-09- 11]. https://fcy.618cloud.com.cn/news/info?data=48844efbadb 140acb17aca7c33c3cb85&active=1.

PREVENTION P. Prevention of drowning[J]. Pediatrics, 2019, 143(5).

Jalalifar S, Belford A, Erfani E, et al. Enhancing water safety: exploring recent technological approaches for drowning detec- tion[J]. Sensors, 2024, 24(2): 331.

Eng H L, Toh K A, Yau W Y, et al. DEWS: A live visual surveillance system for early drowning detection at pool[J]. IEEE transactions on circuits and systems for video technology, 2008, 18(2): 196-210.

Zhang Y, Li X, Wang F, et al. A comprehensive review of one-stage networks for object detection[C]//2021 IEEE Inter- national Conference on Signal Processing, Communications and Computing (ICSPCC). IEEE, 2021: 1-6.

Ren S, He K, Girshick R, et al. Faster R-CNN: Towards real- time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2016, 39(6): 1137-1149.

Vijayakumar A, Vairavasundaram S. Yolo-based object detec- tion models: A review and its applications[J]. Multimedia Tools and Applications, 2024, 83(35): 83535-83574.

Song Q, Yao B, Xue Y, et al. MS-YOLO: A lightweight and high-precision YOLO model for drowning detection[J]. Sensors, 2024, 24(21): 6955.

Jiang X, Tang D, Xu W, et al. Swimming-YOLO: a drowning de- tection method in multi-swimming scenarios based on improved YOLO algorithm[J]. Signal, Image and Video Processing, 2025, 19(1): 161.

Yuan J K, Liu F, Jiang L, et al. GEF-YOLO: an enhanced model for detecting drowning risks at sea[J]. Journal of Real- Time Image Processing, 2025, 22(4): 1-19.

Khanam R, Hussain M. Yolov11: An overview of the key ar- chitectural enhancements[J ] . arXiv preprint arXiv: 2410.17725 , 2024.

Wang X, Deng H, Gao L, et al. Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Models[J ] . arXiv preprint arXiv: 2503.08201 , 2025.

Ma X, Dai X, Bai Y, et al. Rewrite the stars[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2024: 5694-5703.

Wang H, Ju X, Zhu H, et al. SEFormer: A Lightweight CNN- Transformer Based on Separable Multiscale Depthwise Convo- lution and Eﬀicient Self-Attention for Rotating Machinery Fault Diagnosis[J]. Computers, Materials & Continua, 2025, 82(1).

Doherty J, Gardiner B, Kerr E, et al. Bifpn-yolo: One-stage object detection integrating bi-directional feature pyramid net- works[J]. Pattern Recognition, 2025, 160: 111209.

Chen J, Mai H S, Luo L, et al. Effective feature fusion network in BIFPN for small object detection[C]//2021 IEEE international conference on image processing (ICIP). IEEE, 2021: 699-703.

文章被引用时，请邮件提醒。

Submit

A Lightweight Real-time Detection System for Power Line Defects Based on DartNet-YOLO

Related Author

Zitong Xu Jinan Xinhang Experimental Foreign Language School

Related Institution

Jinan Xinhang Experimental Foreign Language School

⁰