Visual tracking of objects using multiresolution

Presents a methodology for multiple object tracking in image sequences at a high video rate using a multi-resolution technique based on the Haar basis of the wavelet transform. The main objective of visual tracking is to closely follow objects in each frame of a video stream such that the object position and other geometric information are always known. The idea is to locate and accompany an object based on previously identified features, such as salient geometric properties. The methodology was implemented and experiments were conducted where single and multiple objects were successfully tracked at high video rates. Important applications of this system include real-time tracking of single or multiple targets.