Multiple Objects Tracking Based on Linear Fitting
2014 ◽
Vol 602-605
◽
pp. 1438-1441
Keyword(s):
For multiple objects tracking in complex scenes, a new tracking algorithm based on linear fitting for multiple moving objects is proposed. DG_CENTRIST feature and color feature are combined to describe the object, and the overlapping ratio of the tracking object is calculated. The object in the current frame is measured by using coincidence degree. If there is occlusion, we predict the path of each object by linear fitting and adjust the results of tracking in order to get correct results. The experiment results show that this method can effectively improve the accuracy of the multiple target tracking.
2014 ◽
Vol 945-949
◽
pp. 1869-1874
2016 ◽
Vol 11
(4)
◽
pp. 324
Keyword(s):
Keyword(s):