Simple online and realtime tracking with a deep association metric

TLDR

Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking that emphasizes simple, effective algorithms. The paper integrates appearance information to improve the performance of SORT. We train a deep association metric offline on a large‑scale person re‑identification dataset and then use nearest‑neighbor queries in visual appearance space during online tracking. This extension reduces identity switches by 45%, enables tracking through longer occlusions, and achieves competitive performance at high frame rates.

Abstract

Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms. In this paper, we integrate appearance information to improve the performance of SORT. Due to this extension we are able to track objects through longer periods of occlusions, effectively reducing the number of identity switches. In spirit of the original framework we place much of the computational complexity into an offline pre-training stage where we learn a deep association metric on a largescale person re-identification dataset. During online application, we establish measurement-to-track associations using nearest neighbor queries in visual appearance space. Experimental evaluation shows that our extensions reduce the number of identity switches by 45%, achieving overall competitive performance at high frame rates.