Performance analysis of object recognition and tracking for the use of surveillance system

Recent research on large data processing have been actively carried out in the name of cloud computing. Video surveillance system must handle larger amounts of data in real time. Video surveillance systems in a cloud computing environment constantly need to handle larger amounts of data in order to recognize and track an object. The system requires a technique which can handle larger amounts of data in order to recognize and track an object by extracting the feature of the object. However, most object tracking approaches based on feature matching have a problem, showing high computational complexity and/or weak robustness in various environments. This paper proposes a robust object recognition and tracking method, which uses an advanced feature matching for use on real time environment. Our algorithm recognizes an object using invariant features, and reduces the dimension of a feature descriptor to deal with the problems. The experimental result shows that our method is faster and more robust than the traditional methods, as well as the proposed method that can detect and track a moving object accurately in various environments.