Worker Abnormal Behavior Recognition Based on Spatio-Temporal Graph Convolution and Attention Model

被引:2
|
作者
Li, Zhiwei [1 ]
Zhang, Anyu [1 ]
Han, Fangfang [1 ]
Zhu, Junchao [1 ]
Wang, Yawen [1 ]
机构
[1] Tianjin Univ Technol, Sch Elect Engn & Automat, Tianjin 300384, Peoples R China
关键词
smart site; behavior recognition; spatio-temporal graph convolutional network; attention mechanism; Alphapose;
D O I
10.3390/electronics12132915
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In response to the problem where many existing research models only consider acquiring the temporal information between sequences of continuous skeletons and in response to the lack of the ability to model spatial information, this study proposes a model for recognizing worker falls and lays out abnormal behaviors based on human skeletal key points and a spatio-temporal graph convolutional network (ST-GCN). Skeleton extraction of the human body in video sequences was performed using Alphapose. To resolve the problem of graph convolutional networks not being effective enough for skeletal key points feature aggregation, we propose an NAM-STGCN model that incorporates a normalized attention mechanism. By using the activation function PReLU to optimize the model structure, the improved ST-GCN model can more effectively extract skeletal key points action features in the spatio-temporal dimension for the purposes of abnormal behavior recognition. The experimental results show that our optimized model achieves a 96.72% accuracy for recognition on the self-built dataset, which is 4.92% better than the original model; the model loss value converges below 0.2. Tests were performed on the KTH and Le2i datasets, which are both better than typical classification recognition networks. The model can precisely identify abnormal human behaviors, facilitating the detection of abnormalities and rescue in a timely manner and offering novel ideas for smart site construction.
引用
收藏
页数:24
相关论文
共 50 条
  • [1] Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition
    Li, Chaolong
    Cui, Zhen
    Zheng, Wenming
    Xu, Chunyan
    Yang, Jian
    THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 3482 - 3489
  • [2] Abnormal Behavior Recognition Based on Spatio-temporal Context
    Yang, Yuanfeng
    Li, Lin
    Liu, Zhaobin
    Liu, Gang
    JOURNAL OF INFORMATION PROCESSING SYSTEMS, 2020, 16 (03): : 612 - 628
  • [3] Spatio-Temporal Attention-based Graph Convolution Networks for Traffic Prediction
    Chongqing University, College of Computer Science, Chongqing, China
    Conf. Proc. IEEE Int. Conf. Syst. Man Cybern., 2022, (642-649): : 642 - 649
  • [4] STCA: an action recognition network with spatio-temporal convolution and attention
    Tian, Qiuhong
    Miao, Weilun
    Zhang, Lizao
    Yang, Ziyu
    Yu, Yang
    Zhao, Yanying
    Yao, Lan
    INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL, 2025, 14 (01)
  • [5] SPATIO-TEMPORAL ATTENTION GRAPH CONVOLUTION NETWORK FOR FUNCTIONAL CONNECTOME CLASSIFICATION
    Wang, Wenhan
    Kong, Youyong
    Hou, Zhenghua
    Yang, Chunfeng
    Yuan, Yonggui
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 1486 - 1490
  • [6] Spatio-Temporal Graph Attention Convolution Network for Traffic Flow Forecasting
    Liu, Kun
    Zhu, Yifan
    Wang, Xiao
    Ji, Hongya
    Huang, Chengfei
    TRANSPORTATION RESEARCH RECORD, 2024, 2678 (09) : 136 - 149
  • [7] RETRACTED: Based on spatio-temporal graph convolution networks with residual connection for intelligence behavior recognition (Retracted Article)
    Zhang, Yinong
    Guan, Shanshan
    Xu, Cheng
    Liu, Hongzhe
    INTERNATIONAL JOURNAL OF ELECTRICAL ENGINEERING EDUCATION, 2021, 60 (1_suppl) : 3784 - 3796
  • [8] Spatio-Temporal Sparse Graph Convolution Network for Hand Gesture Recognition
    Ikne, Omar
    Slama, Rim
    Saoudi, Hichem
    Wannous, Hazem
    2024 IEEE 18TH INTERNATIONAL CONFERENCE ON AUTOMATIC FACE AND GESTURE RECOGNITION, FG 2024, 2024,
  • [9] Traffic Prediction Model Based on Spatio-temporal Graph Attention Network
    Chen, Jing
    Wang, Linkai
    Wang, Wei
    Song, Ruizhuo
    2022 4TH INTERNATIONAL CONFERENCE ON CONTROL AND ROBOTICS, ICCR, 2022, : 428 - 432
  • [10] Traffic Flow Prediction Model Based on Spatio-Temporal Dilated Graph Convolution
    Sun, Xiufang
    Li, Jianbo
    Lv, Zhiqiang
    Dong, Chuanhao
    KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2020, 14 (09): : 3598 - 3614