Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths
This work addresses the problem of scaling multiple object tracking to long and crowded sequences for computer vision researchers, representing an incremental improvement by making an existing model more efficient.
The authors tackled the scalability of the lifted disjoint paths problem for multiple object tracking by developing an efficient approximate message passing solver, achieving performance comparable or better than state-of-the-art methods on MOT15/16/17/20 benchmarks.
We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT). Our tracker scales to very large instances that come from long and crowded MOT sequences. Our approximate solver enables us to process the MOT15/16/17 benchmarks without sacrificing solution quality and allows for solving MOT20, which has been out of reach up to now for LDP solvers due to its size and complexity. On all these four standard MOT benchmarks we achieve performance comparable or better than current state-of-the-art methods including a tracker based on an optimal LDP solver.