Paper Title
A Critical Appraisal On Engineering Kalman-Filters For Real-Time Object Tracking & Motion Detection Systems

Object tracking in video sequences has long been a challenging area in the field of computer vision and has many real world applications like surveillance system, robotics, missile defense system, public security system and visual information processing. A lot of research has been undergoing ranging from applications to noble algorithms. However, most works are focused on a specific application, such as tracking human, car, or pre-learned objects. The work described in this paper is focused on tracking a randomly moving object chosen by a user using Kalman filter. For simplicity, a video sequence with just one object within has been selected. The Kalman filter predicts the most probable location of a detected object in the subsequent video frame and tracks an object by assuming the initial state and noise covariance. After sufficient information about the objects is accumulated, we can exploit the learning to successfully track objects.Extended the same concept for tracking the virtual objects such as stock prices which vary randomly and non-linear in nature. Extended Kalman Filter (EKF) is used to track or predict such objects movement, by modeling its non-linear process.The Kalman filter also helps to smooth out the irregularities due to the measurement error. An experimental result from different moving object video samples shows a very good result. This filter is intended to be robust without being programmed with any environment specific rules.