Window-matching techniques with Kalman filtering for an improved object visual tracking

This paper describes the development and application of an algorithm for object visual tracking from a sequence of images. The algorithm is based on window-matching techniques using the sum of squared differences (SSD) as a distance-similarity measure, but adding stochastic filtering. The algorithm is then applied for tracking: a vehicle on an urban environment; two people meeting and walking together; a ball on a ping-pong game. It is concluded that incorporating the Kalman filtering greatly improves the tracking performance.