FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation
This work addresses the problem of real-time, scalable multi-target tracking for applications like autonomous driving and surveillance, though it is incremental as it builds on existing min-cost flow methods.
The paper tackles the computational and memory inefficiencies of min-cost flow algorithms for multi-target tracking in videos by introducing an approximate online solution with bounded memory and computation, achieving state-of-the-art performance on benchmarks like KITTI and PETS2009 while being significantly faster.
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.