Human Action Recognition Using STIP Evaluation Techniques

The activities of human can be classified into human actions, interactions, object–human interactions and group actions. The recognition of actions in the input video is very much useful in computer vision technology. This system gives application to develop a model that can detect and recognize the actions. The variety of HAR applications are surveillance environment systems, healthcare systems, military, patient monitoring system (PMS), etc., that involve interactions between electronic devices such as human–computer interfaces with persons. Initially, collecting the videos containing actions or interactions was performed by the humans. The given input videos were converted into number of frames, and then these frames were undergone preprocessing stage using by applying median filter. The noise of the given input frame is reduced by applying the median filter of the neighboring pixels. Through frames, desired features were extracted. The actions of the person which is recognised from the system is going to extract further. There are three spatial–temporal interest point (STIP) techniques such as Harris SPIT, Gabor SPIT and HOG SPIT used for feature extraction from video frames. SVM algorithm is applied for classifying the extracted feature. The action recognition is based on the colored label identified by classifier. The system performance is measured by calculating the classifier performance which is the accuracy, sensitivity and specificity. The accuracy represents the classifier reliability. The specificity and sensitivity represent how exactly the classifier categorizes its features to each correct category and how the classifier rejects the features that are not belonging to the particular correct category.