Feature-Based Multi-Object Tracking With Maximally One Object per Class

This paper deals with the problem of tracking multiple objects, in which each object is known to belong to a unique class. We follow the tracking by detection paradigm and assume that the object detector provides scores in addition to each detection. The problem is tackled as simultaneous classification and tracking using random finite sets. Inspired by the multi-Bernoulli mixture (MBM) filter, we propose a solution to the problem by modifying the target birth process. To simplify the implementation and to mitigate the computational costs, we develop tractable solutions with linear complexity. The algorithms are subsequently used for visual tracking of surgical instruments. As a by-product, we derive the prediction step of the Bernoulli filter using the probability generating functionals (PGFLs).