Abstract
In this paper, we describe a strongly improved tracking method using combination of CAMshift and Kalman filter algorithm. CAMshift algorithm doesn`t consider the object`s moving direction and velocity information when it set the search windows for tracking. However if Kalman filter is combined with CAMshift for setting the search window, it can accurately predict the object`s location with the object`s present location and velocity information. By using this prediction before CAMshift algorithm, we can track fast moving objects successfully. Also in this research, we show better tracking results than conventional approaches which make use of single color information by using both color information of HSV and YCrCb simultaneously. This modified approach obtains more robust color segmentation than others using single color information.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
