Date of Award
Dr. Qiuming Zhu
Dr. Haifeng Guo
Dr. William Mahoney
Video surveillance systems play an important role in many civilian and military applications, for the purposes of security and surveillance. Object detection is an important component in a video surveillance system, used to identify possible objects of interest and to generate data for tracking and analysis purposes. Not much exploration has been done to track the moving parts of the object which is being tracked. Some of the promising techniques like Kalman Filter, Mean-shift algorithm, Matching Eigen Space, Discrete Wavelet Transform, Curvelet Transform, Distance Metric Learning have shown good performance for keeping track of moving object.
Most of this work is focused on studying and analyzing various object tracking techniques which are available. Most of the techniques which are available for object tracking have heavy computation requirements. The intention of this research is to design a technique, which is not computationally intensive and to be able to track relative movements of object parts in real time. The research applies a technique called foreground detection (also known as background subtraction) for tracking the object as it is not computationally intensive. For tracking the relative movement of object parts, a skeletonization technique is used. During implementation, it is found that using skeletonization technique, it is harder to extract the objects parts.
Talluri, Praneeth, "Modeling and tracking relative movement of object parts" (2014). Student Work. 2898.
Files over 3MB may be slow to open. For best results, right-click and select "save as..."