Human Behavior Classification using 2D – Convolutional Neural Network, VGG16 and ResNet50
M Sowmya, M Balasubramanian, K. Vaidehi · Indian Journal of Science and Technology · 2023
Objective: To develop a real-time application for human behavior classification using 2- Dimensional Convolution Neural Network, VGG16 and ResNet50. Methods: This study provides a novel system which considers sitting, standing and walking as normal human behaviors. It consists of three major steps: dataset collection, training, and testing. In this work real time images are used. In human behavior classification dataset there are 2271 trained images and 539 testing images. Findings: The Convolution Neural Network (CNN), VGG16 and ResNet50 are trained using human normal behavior images. Novelty: The dataset namely human behavior classification dataset is used in this work and the experimental results has shown that on human behavior classification ResNet50 has outperformed with accuracy of 99.72% compared to VGG16 and 2D-CNN. This work can detect the three normal behaviors of humans in an unconstrained laboratory environment. Keywords: Deep Learning; 2D Convolution Neural Network (CNN); Human Behavior Classification; ADAM Optimizer; VGG16; ResNet50