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

07/23/2014
by   Philip Lenz, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/31/2017

A Hybrid Data Association Framework for Robust Online Multi-Object Tracking

Global optimization algorithms have shown impressive performance in data...
research
11/08/2020

Faster object tracking pipeline for real time tracking

Multi-object tracking (MOT) is a challenging practical problem for visio...
research
04/11/2022

Constrained Shortest Path and Hierarchical Structures

The Constraint Shortest Path (CSP) problem is as follows. An n-vertex gr...
research
03/30/2022

Learning of Global Objective for Network Flow in Multi-Object Tracking

This paper concerns the problem of multi-object tracking based on the mi...
research
08/20/2019

An End-to-end Video Text Detector with Online Tracking

Video text detection is considered as one of the most difficult tasks in...
research
11/02/2019

Efficient Global Multi-object Tracking Under Minimum-cost Circulation Framework

We developed a minimum-cost circulation framework for solving the global...
research
11/30/2022

I Will Survive: An Online Conformance Checking Algorithm Using Decay Time

Process executions in organizations generate a large variety of data. Pr...

Please sign up or login with your details

Forgot password? Click here to reset