FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation

TL;DR

This paper introduces an efficient online min-cost flow tracking algorithm that operates with bounded memory and computation, enabling real-time multi-target tracking on long video sequences with state-of-the-art accuracy.

Contribution

It presents a novel dynamic shortest-path algorithm for optimal data association and an approximate online method that handles streaming data with limited resources.

Findings

Significantly faster inference than standard solvers.

Achieves real-time tracking on long videos.

State-of-the-art performance on KITTI and PETS2009 benchmarks.

Abstract

One of the most popular approaches to multi-target tracking is tracking-by-detection. Current min-cost flow algorithms which solve the data association problem optimally have three main drawbacks: they are computationally expensive, they assume that the whole video is given as a batch, and they scale badly in memory and computation with the length of the video sequence. In this paper, we address each of these issues, resulting in a computationally and memory-bounded solution. First, we introduce a dynamic version of the successive shortest-path algorithm which solves the data association problem optimally while reusing computation, resulting in significantly faster inference than standard solvers. Second, we address the optimal solution to the data association problem when dealing with an incoming stream of data (i.e., online setting). Finally, we present our main contribution which is an approximate online solution with bounded memory and computation which is capable of handling videos of arbitrarily length while performing tracking in real time. We demonstrate the effectiveness of our algorithms on the KITTI and PETS2009 benchmarks and show state-of-the-art performance, while being significantly faster than existing solvers.