Mean shift based object tracking supported with adaptive Kalman filter

2015 ◽  
Author(s):  
Mehmet Murat Turhan ◽  
Davut Hanbay
Keyword(s):  
Kalman Filter ◽  
Object Tracking ◽  
Mean Shift ◽  
Adaptive Kalman Filter

Applied-Information Technology in Adaptive Kalman Filter with Model Error and Noise Error

2014 ◽  
Vol 1046 ◽  
pp. 380-383
Author(s):  
Juan Wang ◽  
Wei Wei Tao ◽  
Chun Ying Wu
Keyword(s):  
Kalman Filter ◽  
Target Location ◽  
Mean Shift ◽  
Model Error ◽  
Adaptive Kalman Filter ◽  
Current Frame ◽  
Mean Shift Algorithm ◽  
System Equation ◽  
Previous Frame ◽  
Noise Error

Kalman filter is successfully used to predict the object position under occlusion in this paper. Firstly, according to the target location in the previous frame, Kalman filter predicts target location in the current frame adaptively.Secondly, find the real target location in the neighborhood by mean shift algorithm. Finally, update the filter parameters. Because the adaptive Kalman filter predicts target location through system equation, it can improve the tracking effect in occlusion in a certain degree.

Object Tracking Based on Corrected Background-Weighted Histogram Mean Shift and Kalman Filter

2013 ◽  
Vol 765-767 ◽  
pp. 720-725 ◽  
Author(s):  
Yu Yang ◽  
Yong Xing Jia ◽  
Chuan Zhen Rong ◽  
Ying Zhu ◽  
Yuan Wang ◽  
...  
Keyword(s):  
Kalman Filter ◽  
Object Tracking ◽  
Mean Shift ◽  
Tracking Algorithm ◽  
Experimental Results ◽  
Complex Environments ◽  
The Real ◽  
Real Environment ◽  
Background Clutter ◽  
Weighted Histogram

The classical mean shift (MS) algorithm is the best color-based method for object tracking. However, in the real environment it presents some limitations, especially under the presence of noise, objects with partial and full occlusions in complex environments. In order to deal with these problems, this paper proposes a reliable object tracking algorithm using corrected background-weighted histogram (CBWH) and the Kalman filter (KF) based on the MS method. The experimental results show that the proposed method is superior to the traditional MS tracking in the following aspects: 1) it provides consistent object tracking throughout the video; 2) it is not influenced by the objects with partial and full occlusions; 3) it is less prone to the background clutter.

Sign in / Sign up

Export Citation Format

Share Document