Academic Journals Database
Disseminating quality controlled scientific knowledge

Research for the Technology of Motion Image Fast Tracking

ADD TO MY LIST
 
Author(s): QU Ju-bao | LIN Hong-ji | LIANG Hong-tao | LIU Sheng

Journal: Journal of Chongqing Normal University
ISSN 1672-6693

Volume: 28;
Issue: 1;
Start page: 44;
Date: 2011;
Original page

Keywords: image | track | adaptability | MeanShift | detection

ABSTRACT
According to some problems, such as requiring the manual intervention for montion image target detection , tracking the core window to be fixed, the goal easy to lose and so on, the paper proposes a method that changes the background frame difference based on background difference, frame difference and threshold value, and combines with the grayscale centroid location and auto-adapted core window with, then improved the MeanShift tracking algorithm. This method can detecte all variety of moving targets in a complex environment, and carry on real-time tracking, even when the target makes big changes in the scale, rotation, and disorder large displacement situation, it also can carry on the fast and accurate detection and tracking. A large number of simulation experiments show that this algorithm has the high detection rate, fewer iteration numbers, strong real-time, good adaptability and robustness.
Affiliate Program      Why do you need a reservation system?