| 39 | 0 | 41 |
| Downloads | Citas | Reads |
随着游泳池溺水事故的增多，人们对人工智能溺水检测方法的精度和速度要求也越来越高。该文提出一种基于改进的YOLO游泳池溺水检测方法，命名为DrownACB-YOLO。现有方法都只关注溺水状态，该文在原始数据集中添加了一个过渡标签，以提供及时警报。在此基础上，对YOLOv5算法进行了两点改进。首先，将YOLOv5的空间金字塔池化模块和默认的上采样算子分别替换为空洞空间金字塔池化模块和内容感知特征重组模块。其次，将YOLOv5的主干部分末尾的C3模块替换为bottleneck transformer模块。对比实验的结果表明，DrownACB-YOLO性能优于其他模型。
Abstract：With the rise in drowning accidents in swimming pools, the demand for the precision and speed in artificial intelligence(AI) drowning detection methods has become increasingly crucial. Here, an improved YOLO-based method, named DrownACB-YOLO, for drowning detection in swimming pools is proposed. Since existing methods focus on the drowned state, a transition label is added to the original dataset to provide timely alerts. Following this expanded dataset, two improvements are implemented in the original YOLOv5. Firstly, the spatial pyramid pooling(SPP) module and the default upsampling operator are replaced by the atrous spatial pyramid pooling(ASPP) module and the content-aware reassembly of feature(CARAFE) module, respectively. Secondly, the cross stage partial bottleneck with three convolutions(C3) module at the end of the backbone is replaced with the bottleneck transformer(BotNet) module. The results of comparison experiments demonstrate that DrownACB-YOLO performs better than other models.
[1] World Health Organization.Global report on drowning:preventing a leading killer[R].World Health Organization,2014.
[2] HE X Y,YUAN F,LIU T Z,et al.A video system based on convolutional autoencoder for drowning detection[J].Neural Computing and Applications,2023,35(21):15791-15803.
[3] URRUCHI C,CERVANTES-CHAUCA D,HUAMANCHAHUA D.Proposal of a swimming pool drowning detection system using cameras and raspberry Pi based on machine learning[C]//2022 2nd International Conference on Robotics,Automation and Artificial Intelligence (RAAI).New York:IEEE,2022:178-181.
[4] HE Q N,ZHANG H S,MEI Z Q,et al.High accuracy intelligent real-time framework for detecting infant drowning based on deep learning[J].Expert Systems with Applications,2023,228:120204.
[5] VENKATA M,NISHANT S.Detecting and tracking of humans in an underwater environment using deep learning algorithms[D].Karlskrona:Blekinge Institute of Technology,2019.
[6] HAYAT M A,YANG G T,IQBAL A.Mask R-CNN based real time near drowning person detection system in swimming pools[C]//2022 Mohammad Ali Jinnah University International Conference on Computing (MAJICC).New York:IEEE,2022:1-6.
[7] HANDALAGE U,NIKAPOTHA N,SUBASINGHE C,et al.Computer vision enabled drowning detection system[C]//2021 3rd International Conference on Advancements in Computing (ICAC).New York:IEEE,2021:240-245.
[8] ZHANG X N.Research on swimming pools drowning warning based on pose estimation and edge computing[D].Shanghai:Donghua University,2023.(in Chinese)
[9] HUANG C,ZHU Y,WANG J Y,et al.Water surface target detection algorithm for unmanned cleaning ship based on improved YOLO V5[C]//2022 International Conference on Cyber-Physical Social Intelligence (ICCSI).New York:IEEE,2022:386-391.
[10] XIE R L,ZHU Y J,LUO J,et al.Detection algorithm for bearing roller end surface defects based on improved YOLOv5n and image fusion[J].Measurement Science and Technology,2023,34(4):045402.
[11] HUANG Y,WANG Q Q,JIA W J,et al.See more than once:kernel-sharing atrous convolution for semantic segmentation[J].Neurocomputing,2021,443:26-34.
[12] WANG J H,GAO X H,LIU Z,et al.GSC-YOLOv5:an algorithm based on improved attention mechanism for road creak detection[C]//2023 IEEE 12th Data Driven Control and Learning Systems Conference (DDCLS).New York:IEEE,2023:1664-1671.
[13] HUANGFU X Y,QIAN H M,HUANG M.A review of deep neural networks combined with attention mechanism[J].Computer and Modernization,2023,2:40.
[14] SRINIVAS A,LIN T Y,PARMAR N,et al.Bottleneck transformers for visual recognition[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).New York:IEEE,2021:16519-16529.
[15] LI Y,LI R,XU Y.Design of online vision detection system for stator winding coil[J].Journal of Donghua University (English Edition),2023,40(6):639-648.
Basic Information:
DOI：10.19884/j.1672-5220.202406015
China Classification Code:TP18;TP391.41
Citation Information:
[1]ZENG Xiaoya,XU Wujun,ZHANG Xiunian.DrownACB-YOLO:an Improved YOLO for Drowning Detection in Swimming Pools[J].Journal of Donghua University (English Edition),2025,42(04):417-424.DOI:10.19884/j.1672-5220.202406015.
Fund Information: