Objects tracking in video: a object-oriented approach using Unified Modeling Language

• DOI: 10.1504/ijcvr.2015.068800
• Publication Date: 2015-04-14T07:30:17Z
• Authors: Nilesh J. Uke; Ravindra C. Thool
• Keywords: 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

So far, little research has been conducted into developing a computer vision application using object oriented approach. These applications contain numerical calculations and complex data structures. Mathematical models are generally used for such numeric calculation. Unified Modeling Language UML is a powerful modelling tool to represent any research problems visually. This paper demonstrates the usage of UML diagrams for effective solution to modelling object tracking in video. Object detection and tracking is an inevitable step in many computer vision applications. Important steps like shot segmentation, feature extraction, and object tracking are seemingly combined for detecting moving objects; is modelled using UML diagram. We analysed the system by use case, sequence, class, activity, and component diagram of UML. We briefly examine the issues in adopting UML for such complex problems of computer vision. Modelling such problems using UML helps application developer to visualise the system effectively.