Abstract

Data association is an essential component of any human tracking system. The ma jority of current methods, such as bipartite matching, incorporate a limited-temporal-locality of the sequence into the data association problem, which makes them inherently prone to ID- switches and difficulties caused by long-term occlusion, cluttered back- ground, and crowded scenes. We propose an approach to data association which incorporates both motion and appearance in a global manner. Un- like limited-temporal-locality methods which incorporate a few frames into the data association problem, we incorporate the whole temporal span and solve the data association problem for one ob ject at a time, while implicitly incorporating the rest of the ob jects. In order to achieve this, we utilize Generalized Minimum Clique Graphs to solve the opti- mization problem of our data association method. Our proposed method yields a better formulated approach to data association which is sup- ported by our superior results. Experiments show the proposed method makes significant improvements in tracking in the diverse sequences of Town Center [1], TUD-crossing [2], TUD-Stadtmitte [2], PETS2009 [3], and a new sequence called Parking Lot compared to the state of the art methods.