| Abstrakt: |
This research builds a human action recognition system based on a single image or video capture snapshot. The TensorFlow Deep Learning models are developed using human keypoints generated by OpenPose. Four classifiers are considered: Neural Network, Random Forest, K-Nearest Neighbor (KNN), and Support Vector Machine (SVM) Classifiers. The models’ input layer are 50 points from x and y coordinate of 25 keypoints from OpenPose, and the output layer is the numerical representation of 11 human action labels which are 'hand-wave', 'jump', 'leg-cross', 'plank', 'ride', 'run', 'sit', 'lay-down', 'squat', 'stand', 'walk’. A total of 2132 images dataset was used for model training and testing. The results show the two best classifier models: Neural Network Classifier with 512 hidden nodes with an accuracy of 0.7733, and Random Forest Classifier with 60 estimators with an accuracy of 0.7752. Both models are then used as inference engines to recognize human action from images and real-time video. [ABSTRACT FROM AUTHOR] |
