Squirrel Search Optimization with Deep Convolutional Neural Network for Human Pose Estimation

Human pose estimation (HPE) is a procedure for determining the structure of body and it considered challenging issue in computer vision (CV) communities. HPE finds its applications several fields namely activity recognition human-computer interface. Despite benefits HPE, still process due to variations visual appearances, lighting, occlusions, dimensionality, etc. To resolve these issues, this paper presents squirrel search optimization with deep convolutional neural network (SSDCNN-HPE) technique. The major intention SSDCNN-HPE technique identify human accurately efficiently. Primarily, video frame conversion performed pre-processing takes place via bilateral filtering-based noise removal process. Then, EfficientNet model applied points person no problem constraints. Besides, hyperparameter tuning by use algorithm (SSA). In final stage, multiclass support vector machine (M-SVM) was utilized identification classification poses. design filtering followed SSA based depicts novelty work. demonstrate enhanced outcomes approach, series simulations are executed. experimental results reported betterment system over recent existing techniques terms different measures.