Two-Stream Deep Learning Architecture-Based Human Action Recognition  

作　　者：Faheem Shehzad Muhammad Attique Khan Muhammad Asfand E.Yar Muhammad Sharif Majed Alhaisoni Usman Tariq Arnab Majumdar Orawit Thinnukool 

机构地区：[1]Department of Computer Science,COMSATS University Islamabad,Wah Campus,Pakistan [2]Department of Computer Science,HITEC University,Taxila,Pakistan [3]Department of Computer Science,Bahria University,Islamabad,Pakistan [4]Computer Sciences Department,College of Computer and Information Sciences,Princess Nourah bint Abdulrahman University,Riyadh,11671,Saudi Arabia [5]College of Computer Engineering and Science,Prince Sattam Bin Abdulaziz University,Al-Kharaj,11942,Saudi Arabia [6]Faculty of Engineering,Imperial College London,London,SW72AZ,UK [7]College of Arts,Media,and Technology,Chiang Mai University,Chiang Mai,50200,Thailand

出　　处：《Computers, Materials & Continua》2023年第3期5931-5949,共19页计算机、材料和连续体（英文）

基　　金：This research work is supported in part by Chiang Mai University and HITEC University.

摘　　要：Human action recognition(HAR)based on Artificial intelligence reasoning is the most important research area in computer vision.Big breakthroughs in this field have been observed in the last few years;additionally,the interest in research in this field is evolving,such as understanding of actions and scenes,studying human joints,and human posture recognition.Many HAR techniques are introduced in the literature.Nonetheless,the challenge of redundant and irrelevant features reduces recognition accuracy.They also faced a few other challenges,such as differing perspectives,environmental conditions,and temporal variations,among others.In this work,a deep learning and improved whale optimization algorithm based framework is proposed for HAR.The proposed framework consists of a few core stages i.e.,frames initial preprocessing,fine-tuned pre-trained deep learning models through transfer learning(TL),features fusion using modified serial based approach,and improved whale optimization based best features selection for final classification.Two pre-trained deep learning models such as InceptionV3 and Resnet101 are fine-tuned and TL is employed to train on action recognition datasets.The fusion process increases the length of feature vectors;therefore,improved whale optimization algorithm is proposed and selects the best features.The best selected features are finally classified usingmachine learning(ML)classifiers.Four publicly accessible datasets such as Ut-interaction,Hollywood,Free Viewpoint Action Recognition usingMotion History Volumes(IXMAS),and centre of computer vision(UCF)Sports,are employed and achieved the testing accuracy of 100%,99.9%,99.1%,and 100%respectively.Comparison with state of the art techniques(SOTA),the proposed method showed the improved accuracy.

关 键 词：Human action recognition deep learning transfer learning fusion of multiple features features optimization 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]