SlowFast Based Real-Time Human Motion Recognition with Action Localization

作     者：Gyu-Il Kim Hyun Yoo Kyungyong Chung 

作者机构：Department of Computer ScienceKyonggi UniversitySuwon16227Korea Contents Convergence Software Research InstituteKyonggi UniversitySuwon16227Korea Division of AI Computer Science and EngineeringKyonggi UniversitySuwon16227Korea 

出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)

年 卷 期：2023年第47卷第11期

页      面：2135-2152页

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2020R1A6A1A03040583) supported by Kyonggi University’s Graduate Research Assistantship 2023 

主　　题：Artificial intelligence convolutional neural network video analysis human action recognition skeleton extraction 

摘      要：Artificial intelligence is increasingly being applied in the field of video analysis,particularly in the area of public safety where video surveillance equipment such as closed-circuit television(CCTV)is used and automated analysis of video information is ***,various issues such as data size limitations and low processing speeds make real-time extraction of video data *** analysis technology applies object classification,detection,and relationship analysis to continuous 2D frame data,and the various meanings within the video are thus analyzed based on the extracted basic *** recognition is key in this *** recognition is a challenging field that analyzes human body movements,requiring the interpretation of complex movements of human joints and the relationships between various *** deep learning-based human skeleton detection algorithm is a representative motion recognition ***,motion analysis models such as the SlowFast network algorithm,have also been developed with excellent ***,these models do not operate properly in most wide-angle video environments outdoors,displaying low response speed,as expected from motion classification extraction in environments associated with high-resolution *** proposed method achieves high level of extraction and accuracy by improving SlowFast’s input data preprocessing and data structure *** input data are preprocessed through object tracking and background removal using YOLO and DeepSORT.A higher performance than that of a single model is achieved by improving the existing SlowFast’s data structure into a frame unit *** on the confusion matrix,accuracies of 70.16%and 70.74%were obtained for the existing SlowFast and proposed model,respectively,indicating a 0.58%increase in *** detection,based on behavioral classification,the existing SlowFast detected 2,341,164 cases,whereas the proposed model detected 3,11