Human Action Recognition Using ConvBiLSTM-GRU In Indoor Environment
Manoj Kumar Sain, Joyeeta Singha, Sandeep Saini, Vijay Bhaskar Semwal
Abstract
Human Activity Recognition (HAR) is a significant challenge in research. Traditional pattern recognition methods have faced limitations in terms of classification efficiency. In this paper, a novel deep learning architecture, Convolutional-Bidirectional Long Short-Term Memory and Gated Recurrent Unit (ConvBiLSTM-GRU) has been proposed. The model comprises a Convolutional Neural Network (CNN), a Bidirectional Long Short-Term Memory Unit, a Gated Recurrent Unit, and a fully connected layer. We have created and compared our dataset with available datasets, i.e., NTU-RGBD, UP-FALL, UR-Fall, WISDM, and UCI HAR. The proposed dataset consists of seven activities: eating, exercise, handshake, situps, vomiting, headache, and walking. The activities were collected from fifty-four subjects between the ages of 25 and 40 using a Kinect v2 sensor at 30FPS. TThe suggested model builds unique guided features using the preprocessed skeleton coordinates and their distinctive geometrical and kinematic aspects. Results from the experiment are contrasted with the performance of standalone CNNs, LSTMs, and ConvLSTM. The proposed model’s accuracy of 99.5% surpasses that of CNN, LSTM, and ConvLSTM, which have accuracy rates of 95.76%, 97%, and 98.89%, respectively. Our Proposed technique is invariant of stance, speed, individual, clothes, etc. The proposed dataset sample is accessible to the general public.