Categorization of Human Movement Based on Rule-Based Classifier

Human activity recognition is an active research field in computer vision and image processing. This paper has been concentrated on the recognition between different cyclic motion activities such as running and walking. The proposed system consists of three major steps. Initially by using a single camera, in a variety of angles, the movement of the object is detected, and object silhouette is generated in each frame. Then, our proposed method for generating a skeleton of silhouette is presented. The skeleton is used to determine human activities such as running and walking. In the last stage, a rule-based classifier is used to classify the action.