An Approach for Human Posture Recognition Based on the Fusion PSE-CNN-BiGRU Model

作     者：Xianghong Cao Xinyu Wang Xin Geng Donghui Wu Houru An 

作者机构：School of Building and Environment EngineeringZhengzhou University of Light IndustryZhengzhou450000China 

出 版 物：《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模（英文）)

年 卷 期：2024年第140卷第7期

页      面：385-408页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：funded by the Henan Provincial Science and Technology Research Project(222102210086) the Starry Sky Creative Space Innovation Space Innovation Incubation Project of Zhengzhou University of Light Industry(2023ZCKJ211) 

主　　题：Posture recognition mediapipe BiGRU CNN ELU attention 

摘      要：This study proposes a pose estimation-convolutional neural network-bidirectional gated recurrent unit(PSECNN-BiGRU)fusion model for human posture recognition to address low accuracy issues in abnormal posture recognition due to the loss of some feature information and the deterioration of comprehensive performance in model detection in complex home ***,the deep convolutional network is integrated with the Mediapipe framework to extract high-precision,multi-dimensional information from the key points of the human skeleton,thereby obtaining a human posture feature ***,a double-layer BiGRU algorithm is utilized to extract multi-layer,bidirectional temporal features from the human posture feature set,and a CNN network with an exponential linear unit(ELU)activation function is adopted to perform deep convolution of the feature map to extract the spatial feature of the human ***,a squeeze and excitation networks(SENet)module is introduced to adaptively learn the importance weights of each channel,enhancing the network’s focus on important ***,comparative experiments are performed on available datasets,including the public human activity recognition using smartphone dataset(UCIHAR),the public human activity recognition 70 plus dataset(HAR70PLUS),and the independently developed home abnormal behavior recognition dataset(HABRD)created by the authors’*** results show that the average accuracy of the proposed PSE-CNN-BiGRU fusion model for human posture recognition is 99.56%,89.42%,and 98.90%,respectively,which are 5.24%,5.83%,and 3.19%higher than the average accuracy of the five models proposed in the comparative literature,including CNN,GRU,and *** F1-score for abnormal posture recognition reaches 98.84%(heartache),97.18%(fall),99.6%(bellyache),and 98.27%(climbing)on the self-builtHABRDdataset,thus verifying the effectiveness,generalization,and robustness of the proposed model in enhancing human posture rec