Object tracking systems and methods

Abstract

An object tracking method may include: receiving frames of data containing image information of an object; performing an object segmentation to obtain an object motion result; and using the object motion result to conduct an object tracking. In particular, the object segmentation may include: extracting motion vectors from the frames of data; estimating a global motion using the motion vectors; and subtracting the global motion from the motion vectors to generate an object motion result.

1 . An object tracking method comprising:
 receiving frames of data containing compressed-domain information of an object;   performing an object segmentation based on motion vectors of the series of frames of data in a compressed domain to generate an object segmentation result with the effect of an estimated global motion removed from the object segmentation result; and   conducting a similarity analysis of the object segmentation result and an initial object model.   
   
   
       2 . The method of  claim 1 , further comprising refining the object segmentation result by applying particle filtering. 
   
   
       3 . The method of  claim 1 , wherein performing the object segmentation comprises:
 extracting the motion vectors from the frames of data;   estimating the global motion using the motion vectors;   subtracting the global motion from the motion vectors to generate the object segmentation result.   
   
   
       4 . The method of  claim 3 , further comprises performing a label set process after generating the object segmentation result, wherein the label set process comprises distinguishing the object from a second object for conducting multiple-object tracking. 
   
   
       5 . The method of  claim 3 , wherein the frames of data belong to a portion of a compressed video stream and performing the object segmentation comprises performing the object segmentation in the compressed domain.