Improving Global Multi-Target Tracking with Local Updates

Abstract

We propose a scheme to explicitly detect and resolve ambiguous situations in multiple target tracking. During periods of uncertainty, our method applies multiple local single target trackers to hypothesise short term tracks. These tracks are combined with the tracks obtained by a global multi-target tracker, if they result in a reduction in the global cost function. Since tracking failures typically arise when targets become occluded, we propose a local data association scheme to maintain the target identities in these situations. We demonstrate a reduction of up to $50\,\%$ in the global cost function, which in turn leads to superior performance on several challenging benchmark sequences. Additionally, we show tracking results in sports videos where poor video quality and frequent and severe occlusions between multiple players pose difficulties for state-of-the-art trackers.