Abstract
In this article, we present an algorithm to identify actions by processing videos obtained from everyday human activities. The algorithm based on the movement characteristics of people consists of two main steps, namely taking the features in the video and collecting the characteristics of these actions and making conclusions for each frame in the video processing image. The algorithm aims to improve the accuracy and enhance the user's experience in identifying human actions in different contexts. The video from the collection has been performed by the algorithm. The results presented at the end of this article show that the proposal algorithm not only improve the accuracy of algorithm but also speed of processor.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have