We propose a novel method for object tracking using prototype-based deformable template models. To track an object in an image sequence, we use a criterion which combines two terms: the deviation of the object shape from its shape in the previous frame, and the fidelity of the detected shape to the input image. Shape and gradient information are used to track the object. We have also used the consistency between corresponding object regions throughout the sequence to help in trading the object of interest. Inter-frame motion is also used to track the boundary of moving objects. We have applied the algorithm to a number of image sequences from different sources. The inherent structure in the deformable template, together with region, motion, and image gradient cues, make the algorithm relatively insensitive to the adverse effects of weak image features and moderate partial occlusion.
Object tracking using deformable templates
1998-01-01
864802 byte
Conference paper
Electronic Resource
English
Object Tracking using Deformable Templates
British Library Conference Proceedings | 1998
|Motion detection and tracking using deformable templates
IEEE | 1994
|Motion Detection and Tracking using Deformable Templates
British Library Conference Proceedings | 1994
|Tracking Deformable Templates Using a Shortest Path Algorithm
British Library Online Contents | 2001
|Vehicle Segmentation Using Deformable Templates
British Library Conference Proceedings | 1995
|