We present a new paradigm for tracking objects in video in the presence of other similar objects. This branch-and-track paradigm is also useful in the absence of motion, for the discovery of repetitive patterns in images. The object of interest is the lead object and the distracters are extras. The lead tracker branches out trackers for extras when they are detected, and all trackers share a common set of features. Sometimes, extras are tracked because they are of interest in their own right. In other cases, and perhaps more importantly, tracking extras makes tracking the lead nimbler and more robust, both because shared features provide a richer object model, and because tracking extras accounts for sources of confusion explicitly. Sharing features also makes joint tracking less expensive, and coordinating tracking across lead and extras allows optimizing window positions jointly rather than separately, for better results. The joint tracking of both lead and extras can be solved optimally by dynamic programming and branching is quickly determined by efficient subwindow search. Matlab experiments show near real time performance at 5-30 frames per second on a single-core laptop for 240 by 320 images.
We present an efficient computational scheme for tracking similar objcects in both spatial and temporal domain. The branching process utilizes the efficient subwindow search to localize similar targets in a recursive fashion. The tracking process is equivalent to tracking a set of windows in the form of a pictorial sturcture. Note that the topology of the pictorial structure is incrementally changed frame by frame due to the branching process. Here are the MATLAB/C++ [Code] and the [Paper].
